\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: United States v. Thrower\\nCourt: U.S. Court of Appeals for the Second Circuit\\nDate decided: 2019-01-31\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n17‐445‐pr \\nUnited States v. Thrower \\n \\n UNITED STATES COURT OF APPEALS \\n FOR THE SECOND CIRCUIT \\n ______________ \\n \\n August Term, 2017 \\n \\n (Submitted: April 19, 2018 Decided: January 31, 2019) \\n \\n Docket No. 17‐445‐pr \\n ____________ \\n \\n UNITED STATES OF AMERICA, \\n \\n Petitioner‐Appellee, \\n \\n –v.– \\n \\n WILLIAM THROWER, \\n \\n Respondent‐Appellant. *\\n \\n ______________ \\n \\n \\n ON APPEAL FROM THE UNITED STATES DISTRICT COURT FOR THE \\n EASTERN DISTRICT OF NEW YORK \\n \\nBefore: \\n WESLEY and CHIN, Circuit Judges, and COTE, District Judge.† \\n\\n\\n* The Clerk of the Court is directed to amend the caption as set forth above. \\n Judge Denise Cote, of the United States District Court for the Southern District of New \\n†\\n\\nYork, sitting by designation. \\n\\f The Government appeals from a judgment of the United States District \\nCourt for the Eastern District of New York (Ross, J.) reducing the defendant’s \\nsentence from 180 months to 120 months and ordering his immediate release on \\ntime served. The Government argues that the district court erred in concluding \\nthat the defendant’s prior convictions for the New York offenses of robbery in the \\nthird degree and attempted robbery in the third degree do not qualify as predicate \\n“violent felonies” under the Armed Career Criminal Act, 18 U.S.C. § 924(e)(1). \\n We agree with the Government. Accordingly, we REVERSE the district \\ncourt’s grant of Thrower’s § 2255 petition, VACATE the amended judgment, and \\nREMAND for the district court to reinstate Thrower’s original sentence. \\n ______________ \\n \\n Amy Busa, Alexander Mindlin, Assistant United States \\n Attorneys, for Richard P. Donoghue, United States \\n Attorney for the Eastern District of New York, for \\n Appellant. \\n \\n Jane Simkin Smith, Millbrook, NY, for Defendant‐\\n Appellee. \\n \\n ______________ \\n \\nPER CURIAM: \\n\\n The Government appeals from a February 13, 2017 judgment of the United \\n\\nStates District Court for the Eastern District of New York (Ross, J.) reducing \\n\\ndefendant William Thrower’s sentence from 180 months to 120 months and \\n\\nordering Thrower’s immediate release on time served. The Government argues \\n\\nthat the district court erred in concluding that Thrower’s prior convictions for the \\n\\nNew York offenses of robbery in the third degree and attempted robbery in the \\n\\n\\n 2 \\n\\fthird degree do not qualify as predicate “violent felonies” under the Armed Career \\n\\nCriminal Act (“ACCA”), 18 U.S.C. § 924(e)(1), an enhancement that mandates a \\n\\nminimum sentence of 180 months. \\n\\n We agree with the Government. Accordingly, we REVERSE the district \\n\\ncourt’s grant of Thrower’s § 2255 petition, VACATE the amended judgment, and \\n\\nREMAND for the district court to reinstate Thrower’s original sentence. \\n\\n\\n BACKGROUND \\n\\n In 2005, William Thrower was convicted of possessing a firearm while \\n\\npreviously having been convicted of a “violent felony,” in violation of 18 U.S.C. \\n\\n§ 922(g)(1). A conviction under § 922(g)(1) carries a mandatory‐minimum sentence \\n\\nof 120 months. During sentencing in 2008, the district court additionally found that \\n\\nThrower qualified as an “armed career criminal” under ACCA, 18 U.S.C. \\n\\n§ 924(e)(1), which mandates a minimum sentence of 180 months for anyone \\n\\nconvicted of § 922(g)(1) who also has three prior “violent felony” convictions. The \\n\\ndistrict court noted that Thrower’s criminal history included the following felony \\n\\noffenses: (1) a 1981 conviction for first‐degree robbery, N.Y. Penal Law § 160.15; \\n\\n(2) a 1981 conviction for third‐degree burglary, N.Y. Penal Law § 140.20; (3) a 1993 \\n\\nconviction for fourth‐degree larceny, N.Y. Penal Law § 155.30; (4) a 1994 conviction \\n\\n 3 \\n\\ffor attempted third‐degree robbery, N.Y. Penal Law §§ 160.05 and 110.00; and (5) \\n\\na 2000 conviction for third‐degree robbery, N.Y. Penal Law § 160.05. Without \\n\\nspecifying which of Thrower’s prior convictions constituted the three predicate \\n\\n“violent felonies” or which ACCA clause(s)—the force clause, the enumerated‐\\n\\noffenses clause, or the residual clause—it relied upon in determining that the \\n\\nconvictions so qualified, the district court found Thrower subject to the ACCA \\n\\nenhancement and consequently sentenced him to 180 months’ incarceration. \\n\\n The Supreme Court subsequently struck down ACCA’s residual clause as \\n\\nunconstitutionally vague, Johnson v. United States, 135 S. Ct. 2551, 2557 (2015) \\n\\n(“Johnson II”); see also Welch v. United States, 136 S. Ct. 1257, 1265 (2016) (holding \\n\\nthat Johnson II applies retroactively), calling into question Thrower’s sentence. \\n\\nConsequently, Thrower challenged the ACCA enhancement in a 28 U.S.C. § 2255 \\n\\npetition for a writ of habeas corpus, which the district court granted.1 The district \\n\\ncourt agreed with Thrower that neither New York robbery in the third degree nor \\n\\nNew York attempted robbery in the third degree qualifies as a “violent felony” \\n\\n\\n1 In adjudicating Thrower’s petition under § 2255, the district court concluded that when \\nsentencing Thrower in 2008, it had relied, at least in part, on the now‐unconstitutional \\nresidual clause to determine that ACCA’s mandatory sentencing provision applied. It \\ntherefore analyzed anew whether at least three of Thrower’s prior convictions qualified \\nunder the two remaining ACCA clauses. Because they did not, the district court found \\nthat the prior error was prejudicial. \\n 4 \\n\\funder ACCA’s force clause.2 Because the Government no longer claimed that \\n\\nfourth‐degree larceny qualified without the residual clause, only two of Thrower’s \\n\\nprior convictions remained as potential ACCA predicates—a number insufficient \\n\\nto subject him to the ACCA enhancement. Seeing, therefore, no need to determine \\n\\nwhether first‐degree robbery or third‐degree burglary qualifies as a “violent \\n\\nfelony,” the district court ordered Thrower immediately released on time served. \\n\\n The Government timely appealed, arguing that because robbery in the first \\n\\nand third degrees and attempted robbery in the third degree qualify as ACCA \\n\\npredicates, the district court erred in granting Thrower’s § 2255 petition. \\n\\n\\n DISCUSSION \\n\\n We review de novo whether the offenses of New York robbery in the first and \\n\\nthird degrees and attempted robbery in the third degree qualify as ACCA “violent \\n\\nfelonies.” See United States v. Brown, 629 F.3d 290, 293 (2d Cir. 2011) (per curiam). \\n\\nThey do. \\n\\n \\n\\n \\n\\n\\n\\n2 The Government did not contend that either offense satisfies the requirements of the \\nenumerated‐offenses clause. \\n 5 \\n\\f 1. Armed Career Criminal Act \\n\\n ACCA mandates a minimum 180‐month term of imprisonment for any \\n\\nperson convicted of possessing a firearm in violation of 18 U.S.C. § 922(g)(1) who \\n\\nalso has three prior “violent felony” convictions. Id. § 924(e)(1). Under the force \\n\\nclause, a “violent felony” is “any crime punishable by imprisonment for a term \\n\\nexceeding one year, . . . that . . . has as an element the use, attempted use, or \\n\\nthreatened use of physical force against the person of another.” Id. § 924(e)(2)(B)(i). \\n\\nAs the Supreme Court has explained, “‘physical force’ means violent force—that \\n\\nis, force capable of causing physical pain or injury to another person.” Johnson v. \\n\\nUnited States, 559 U.S. 133, 140 (2010) (“Johnson I”) (emphasis in original); see also \\n\\nStokeling v. United States, 139 S. Ct. 544, 554 (2019) (explaining that “Johnson [I] . . . \\n\\ndoes not require any particular degree of likelihood or probability that the force \\n\\nused will cause physical pain or injury; only potentiality”). \\n\\n Courts apply a “categorical approach” to determine whether a prior \\n\\nconviction qualifies as a “violent felony.” See, e.g., United States v. Hill, 890 F.3d 51, \\n\\n55–56 (2d Cir. 2018). Under the categorical approach, “courts identify ‘the \\n\\nminimum criminal conduct necessary for conviction under a particular statute.’” \\n\\n \\n\\n\\n 6 \\n\\fId. at 55 (quoting United States v. Acosta, 470 F.3d 132, 135 (2d Cir. 2006) (per \\n\\ncuriam)). In so doing, they “look only to the statutory definitions—i.e., the \\n\\nelements—of the offense, and not to the particular underlying facts.” Id. (quoting \\n\\nDescamps v. United States, 570 U.S. 254, 261 (2013) (alterations omitted)). If the state‐\\n\\nlaw offense categorically requires the elements listed in § 924(e)(2)(B)(i), it may \\n\\nserve as a predicate “violent felony.” \\n\\n 2. New York Robbery in the First and Third Degrees \\n\\n Thrower argues that the New York offense of robbery in the third degree \\n\\ndoes not qualify as a “violent felony” because the requisite force for the offense \\n\\n“can be something less than ‘force capable of causing physical pain or injury.’” \\n\\nAppellee Br. 17 (quoting Johnson I, 599 U.S. at 140). We disagree. \\n\\n The New York offense of robbery in the third degree occurs when a person \\n\\n“forcibly steals property.” N.Y. Penal Law § 160.05. Forcible stealing—common to \\n\\nevery degree of robbery in New York State3—is defined as: \\n\\n when, in the course of committing a larceny, [a person] uses or \\n threatens the immediate use of physical force upon another person \\n for the purpose of: 1. Preventing or overcoming resistance to the \\n taking of the property or to the retention thereof immediately after \\n the taking; or 2. Compelling the owner of such property or another \\n\\n\\n3 See N.Y. Penal Law § 160.05; id. § 160.10; id. § 160.15; see also People v. Miller, 87 N.Y.2d \\n211, 214 (1995) (“The essence of the [New York] crime of robbery is forcible stealing.”). \\n 7 \\n\\f person to deliver up the property or to engage in other conduct which \\n aids in the commission of the larceny. \\n \\nId. § 160.00. \\n\\n By its plain language, the New York robbery statute matches the ACCA \\n\\ndefinition of a “violent felony.” Predicate offenses under ACCA include those that \\n\\nhave as an element “the use . . . or threatened use of physical force.” 18 U.S.C. § \\n\\n924(e)(2)(B)(i). New York requires the “use[] or threaten[ed] . . . immediate use of \\n\\nphysical force.” Additionally, the New York robbery statute, like ACCA’s force \\n\\nclause, is modeled on the common law definition of robbery. As the Supreme \\n\\nCourt recently explained in Stokeling, “the term ‘physical force’ in ACCA \\n\\nencompasses the degree of force necessary to commit common‐law robbery,” \\n\\ndefined as “the amount of force necessary to overcome a victim’s resistance.” \\n\\nStokeling, 139 S. Ct. at 555. Like the Florida robbery statute at issue in Stokeling, the \\n\\nNew York robbery statute uses the term “physical force.” The New York Court of \\n\\nAppeals has explained that “if a statute uses a word which has a definite and well‐\\n\\nknown meaning at common law, it will be construed with the aid of common‐law \\n\\ndefinitions, unless it clearly appears that it was not so intended.” People v. King, 61 \\n\\nN.Y.2d 550, 554–55 (1984). Far from evincing a clear intent to stray from the \\n\\ncommon law understanding of robbery, the robbery statute explicitly incorporates \\n\\n 8 \\n\\fthe common law definition by explaining that “physical force” means enough \\n\\nforce to “[p]revent[] or overcom[e] resistance to the taking . . . or . . . [to c]ompel[] \\n\\nthe owner . . . to deliver up the property.” N.Y. Penal Law § 160.00; see also People \\n\\nv. Jurgins, 26 N.Y.3d 607, 614 (2015). \\n\\n None of the cases to which Thrower cites convince us that New York courts \\n\\ninterpret the force required for New York robbery as less than that required under \\n\\nACCA. In People v. Lee, 197 A.D.2d 378 (1st Dep’t 1993), a New York intermediate \\n\\ncourt of appeals found the force element of § 160.05 satisfied where the defendant \\n\\n“bumped his unidentified victim, took money, and fled while another forcibly \\n\\nblocked the victim’s pursuit,” because the act of blocking was a form of \\n\\novercoming the victim’s resistance, id. at 378 (citing People v. Patton, 184 A.D.2d \\n\\n483, 483 (1st Dep’t 1992) (“[A]ct[ing] as a blocker [is a form of] overcoming the \\n\\nvictim’s resistance to the robbery within the meaning of Penal Law § 160.00(1).” \\n\\n(emphasis added))).4 Similarly, in People v. Safon, 166 A.D.2d 892 (4th Dep’t 1990), \\n\\n\\n\\n4 See also United States v. Pereira‐Gomez, 903 F.3d 155, 166 (2d Cir. 2018) (explaining that a \\n“’human wall’ [is] no mere obstacle to the victim’s pursuit of the robber; it constitute[s] a \\nthreat that pursuit would lead to a violent confrontation” and therefore holding that New \\nYork attempted robbery in the second degree qualifies as a “crime of violence” under the \\nidentically worded force clause of application note 1(B)(iii) to Section 2L1.2 of the 2014 \\nSentencing Guidelines); see also U.S.S.G. § 2L1.2 cmt. 1(B)(iii) (2014) (defining a “crime of \\nviolence” as having “as an element the use, attempted use, or threatened use of physical \\nforce against the person of another”). \\n 9 \\n\\fa New York intermediate appellate court affirmed a third‐degree robbery \\n\\nconviction where the evidence showed that the defendant and the victim “tugged \\n\\nat each other until defendant’s hand slipped out of the glove holding the money” \\n\\nbecause this “was sufficient to prove that defendant used physical force for the \\n\\npurpose of overcoming the victimʹs resistance to the taking,” id. at 893 (emphasis \\n\\nadded). \\n\\n We therefore conclude that the New York offense of robbery in the third \\n\\ndegree, which like every degree of robbery in New York requires the common law \\n\\nelement of “forcible stealing,” is a “violent felony” under ACCA. By extension, \\n\\nNew York robbery in the first degree is also a “violent felony” under ACCA.5 \\n\\n 3. New York Attempted Robbery in the Third Degree \\n\\n Thrower next argues that the New York offense of attempted robbery in the \\n\\nthird degree does not qualify as a “violent felony” because a person may be \\n\\nconvicted of attempted robbery by merely attempting to threaten to use physical \\n\\n\\n\\n5 Thrower argues that his conviction for first‐degree robbery does not qualify as an ACCA \\npredicate because he received a Certificate of Relief from Civil Disabilities from the State \\nof New York that restored his civil rights. Although Thrower is correct that a conviction \\nwith respect to which civil rights have been restored cannot serve as an ACCA predicate, \\nthis exception applies only where the Certificate does not prohibit the possession of \\nfirearms. See 18 U.S.C. § 921(a)(20). Thrower has not shown that his Certificate lacks such \\na prohibition. See United States v. Bullock, 550 F.3d 247, 250 (2d Cir. 2008). \\n 10 \\n\\fforce, falling short of the requirement of attempting to use physical force. We again \\n\\ndisagree. \\n\\n As above, the New York attempted robbery statute, by its own terms, \\n\\nmatches the ACCA definition of a “violent felony.” Predicate offenses under \\n\\nACCA include those that have as an element the “attempted use . . . of physical \\n\\nforce.” 18 U.S.C. § 924(e)(2)(B)(i). Under federal law, “[a] person is guilty of an \\n\\nattempt to commit a crime if he or she (1) had the intent to commit the crime, and \\n\\n(2) engaged in conduct amounting to a ‘substantial step’ towards the commission \\n\\nof the crime.” United States v. Martinez, 775 F.2d 31, 35 (2d Cir. 1985). \\n\\n New York requires that, “with intent to commit a crime . . . [a person] \\n\\nengage[] in conduct which tends to effect the commission of such crime.” N.Y. \\n\\nPenal Law § 110.00. The New York Court of Appeals has clarified that an attempt \\n\\nrequires that the action taken by an accused be “so near to its accomplishment that \\n\\nin all reasonable probability the crime itself would have been committed but for \\n\\ntimely interference.” People v. Rizzo, 246 N.Y. 334, 337 (1927); see also People v. \\n\\nDenson, 26 N.Y.3d 179, 189 (2015) (“[F]or a defendant to be guilty of an attempted \\n\\ncrime, the defendant must have engaged in conduct that came dangerously near \\n\\ncommission of the completed crime.” (quotation marks and citation omitted)). \\n\\n\\n 11 \\n\\fWhere a statute requires that a person be so “dangerously near” forcibly stealing \\n\\nproperty “that in all reasonable probability” she would have completed the \\n\\nrobbery but for interference, the statute categorically requires that a person take a \\n\\n“substantial step” toward the use of physical force. See People v. Acosta, 80 N.Y.2d \\n\\n665, 670 (1993) (explaining that New York’s attempt statute is “more stringent” \\n\\nthan the “‘substantial step’ test . . . adopted by [the Second Circuit]”); United States \\n\\nv. Farhane, 634 F.3d 127, 146 (2d Cir. 2011) (noting that the federal “substantial \\n\\nstep” test “ushered in a broader view of attempt” than that employed at common \\n\\nlaw). \\n\\n Nothing from New York’s courts leads us to conclude otherwise. Though \\n\\nThrower posits that a defendant might be convicted of attempted robbery in New \\n\\nYork for an attempt to threaten to use physical force—as distinct from an attempt \\n\\nto use physical force or a threat to use physical force—he fails to “at least point to \\n\\nhis own case or other cases in which the state courts in fact did apply the statute \\n\\nin the . . . manner for which he argues.”6 See Gonzales v. Duenas–Alvarez, 549 U.S. \\n\\n\\n\\n\\n6 Even if Thrower could cite to such an example, we would not come out differently on \\nthis issue. An attempt to threaten to use force by, for example, attempting to use a \\nthreatening note, itself constitutes a “threatened use of physical force.” \\n 12 \\n\\f183, 193 (2007). As such, we are left with the text of the New York attempted \\n\\nrobbery statute, which plainly matches ACCA’s definition of a “violent felony.” \\n\\n We therefore conclude that the New York offense of attempted robbery in \\n\\nthe third degree is a “violent felony” under ACCA. \\n\\n\\n CONCLUSION \\n\\n Robbery in the first and third degrees and attempted robbery in the third \\n\\ndegree, in violation of N.Y. Penal Law §§ 110.00, 160.05, 160.15, are “violent \\n\\nfelonies” under the force clause of ACCA. Because Thrower therefore has three \\n\\nqualifying “violent felony” convictions under ACCA, the district court erred by \\n\\nnot sentencing him to the applicable 180‐month mandatory minimum term of \\n\\nincarceration. \\n\\n We REVERSE the district court’s grant of Thrower’s § 2255 petition, \\n\\nVACATE the amended judgment, and REMAND for the district court to reinstate \\n\\nThrower’s original sentence. \\n\\n\\n\\n\\n 13\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":57,"cells":{"id":{"kind":"number","value":8443861,"string":"8,443,861"},"name":{"kind":"string","value":"United States v. William THROWER"},"name_abbreviation":{"kind":"string","value":"United States v. Thrower"},"decision_date":{"kind":"string","value":"2019-01-31"},"docket_number":{"kind":"string","value":"Docket No. 17-445-pr; August Term, 2017"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Second Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Chin, Cote, Wesley\", \"parties\": \"\", \"opinions\": [{\"author\": \"PER CURIAM\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/8415288/\", \"author_raw\": \"PER CURIAM\"}]}"},"judge1":{"kind":"string","value":"CHIN"},"judge2":{"kind":"string","value":"COTE"},"judge3":{"kind":"string","value":"WESLEY"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/8443861/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":0,"string":"0"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: United States v. William THROWER\nCourt: U.S. Court of Appeals for the Second Circuit\nDate decided: 2019-01-31\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: United States v. William THROWER\\nCourt: U.S. Court of Appeals for the Second Circuit\\nDate decided: 2019-01-31\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":58,"cells":{"id":{"kind":"number","value":4578607,"string":"4,578,607"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Kevin Culley v. Cumberland Valley School Dist"},"decision_date":{"kind":"string","value":"2019-01-03"},"docket_number":{"kind":"string","value":"17-3800"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before: AMBRO, SCIRICA, and RENDELL, Circuit Judges (Opinion\", \"parties\": \"\", \"opinions\": [{\"author\": \"AMBRO, Circuit Judge\", \"type\": \"010combined\", \"text\": \"NOT PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n ________________\\n\\n No. 17-3800\\n ________________\\n\\n KEVIN CULLEY, and; DENISE CULLEY, on behalf of; J.C.\\n\\n v.\\n\\n CUMBERLAND VALLEY SCHOOL DISTRICT,\\n\\n Appellant\\n ________________\\n\\n Appeal from the United States District Court\\n for the Middle District of Pennsylvania\\n (D.C. Civil Action No. 1-15-cv-00857)\\n District Judge: Honorable John E. Jones, III\\n ________________\\n\\n Argued November 6, 2018\\n\\n Before: AMBRO, SCIRICA, and RENDELL, Circuit Judges\\n\\n (Opinion filed: December 20, 2018)\\n\\n\\nMark W. Cheramie Walz [Argued]\\nSweet, Stevens, Katz & Williams LLP\\n331 East Butler Avenue\\nP.O. Box 5069\\nNew Britain, PA 18901\\n Counsel for Appellant\\n\\nJudith A. Gran [Argued]\\nReisman Carolla & Gran LLP\\n19 Chestnut Street\\nHaddonfield, NJ 08033\\n\\fPhillip A. Drumheiser\\nP.O. Box 890\\nCarlisle, PA 17013\\n Counsel for Appellees\\n\\n ________________\\n\\n OPINION*\\n ________________\\n\\nAMBRO, Circuit Judge\\n\\n J.C., son of plaintiffs Kevin and Denise Culley, was diagnosed with Crohn’s\\n\\ndisease at age six. It is a painful, even debilitating, disease that affects the digestive tract\\n\\nand can cause abdominal pain, diarrhea, fatigue, weight loss, and malnutrition. It can\\n\\neven be life-threatening. See Mayo Clinic, Crohn’s Disease (Mar. 8, 2018), available at\\n\\nhttps://www.mayoclinic.org/diseases-conditions/crohns-disease/symptoms-causes/syc-\\n\\n20353304. After a disciplinary dispute with J.C.’s school, part of the Cumberland Valley\\n\\nSchool District system, that resulted in his expulsion, J.C.’s parents filed suit claiming\\n\\nthat Cumberland had violated J.C.’s rights under the Individuals with Disabilities\\n\\nEducation Act (IDEA), 20 U.S.C. § 1400 et seq., and under Section 504 of the\\n\\nRehabilitation Act. 29 U.S.C. § 701 et seq. The District Court agreed, and we now\\n\\naffirm.\\n\\n Born in 1998, J.C. was diagnosed with Crohn’s disease in 2004. Cumberland was\\n\\ninformed of the diagnosis in 2007. App. at 53. J.C.’s performance in school was\\n\\ngenerally strong through his sixth grade year, in 2009–2010, and he did not have\\n\\n\\n\\n*\\n This disposition is not an opinion of the full Court and pursuant to I.O.P. 5.7 does not\\nconstitute binding precedent.\\n 2\\n\\fsignificant behavioral or social difficulties through that time. Id. at 130–131. But from\\n\\nseventh grade onward, both J.C.’s academic performance and his disciplinary record took\\n\\nsignificant turns for the worse. From seventh through tenth grade, when the incident\\n\\ngiving rise to this lawsuit occurred and he was expelled, J.C. maintained a grade point\\n\\naverage just above a failing mark of 70, had numerous disciplinary incidents, and was\\n\\nincreasingly absent from school. Id. at 128, 131, 169–170. By tenth grade J.C. was\\n\\nabsent 43 times, or over 30% of the time.\\n\\n In April 2013, while in ninth grade, J.C. was admitted to Hershey Medical Center\\n\\nfor surgery. Shortly thereafter in May, the school received a letter from his physician\\n\\nstating that J.C. should be allowed to cease activities during his physical education\\n\\nclasses if he experienced pain. Id. at 170. In July 2013 the school received another letter\\n\\nfrom J.C.’s doctor stating that he should be allowed to leave class to use the bathroom on\\n\\na liberal basis. Id. It appears Cumberland agreed to these accommodations.\\n\\n On January 17, 2014, J.C. had a disciplinary incident where he, apparently along\\n\\nwith several friends, attempted to leave the school grounds during the day. The other\\n\\nstudents fled, while J.C. was apprehended and had disciplinary proceedings brought\\n\\nagainst him, with an eye toward expulsion. After J.C.’s doctor wrote a letter to the school\\n\\non January 27, 2014, giving a fuller account of J.C.’s diagnosis and the accommodations\\n\\nhe required, his parents filed a due process complaint under the IDEA on January 29.\\n\\nCumberland adopted a Section 504 Service Plan for J.C. in March 2014, which provided\\n\\nfor a number of accommodations, including an “any time pass” to go to the nurse or the\\n\\nbathroom, extra time to complete assignments, and the provision of class notes in case of\\n\\n 3\\n\\ffrequent absences. Id. at 92–94. After receiving a letter from J.C.’s doctor stating that he\\n\\nshould receive homebound instruction for half of each school day, Cumberland tried to\\n\\nimplement this accommodation as well, but things did not go well. J.C. was rarely\\n\\npresent when the instructor arrived at his house, and even when present was not\\n\\nmotivated or cooperative. Id. at 107–116.\\n\\n The school board voted to expel J.C. on April 7, 2014, with the expulsion taking\\n\\neffect on May 8, 2014. At the same time, Cumberland released its Evaluation Report\\n\\nfrom its psychologist’s evaluation of J.C. Id. at 123. The report concluded that he did\\n\\nnot have a “qualifying disability” and thus was not eligible for special education under\\n\\nthe IDEA. Id. at 152. It also stated that there was insufficient evidence that J.C.’s\\n\\nCrohn’s disease was responsible for his difficulties in school, and that his condition\\n\\ncalled for Section 504 accommodations, not IDEA specialized instruction. J.C.’s parents\\n\\nthen requested an independent educational evaluation (IEE), which reached the opposite\\n\\nconclusion. Id. at 162–192. Noting the pervasive effect of Crohn’s on J.C.’s life, the IEE\\n\\nfound that he was eligible for special education under the IDEA and gave numerous\\n\\n“recommendations for specially designed instruction” to help tailor J.C.’s education to\\n\\nhis benefit. Id. at 189–191. It also found that J.C. had ADHD and specific learning\\n\\ndisabilities as to math and listening comprehension. Id. at 189. After J.C. moved to a\\n\\nneighboring school district, East Pennsboro, for the 2014–'15 school year, that district\\n\\nadopted an individualized education program (IEP) for J.C. to provide special education\\n\\nunder the IDEA. Id. at 249–279.\\n\\n\\n\\n 4\\n\\f Meanwhile, the Hearing Officer on J.C.’s due process complaint held a hearing\\n\\nand issued his decision in February 2015. He found that J.C. was not eligible for special\\n\\neducation under the IDEA because, even though Crohn’s disease was a qualifying\\n\\ndisability, it did not require specialized instruction. Id. at 48. The Hearing Officer\\n\\nendorsed Cumberland’s Evaluation Report and largely dismissed the findings from the\\n\\nIEE. He noted that while J.C.’s frequent absences doubtless caused much of his\\n\\nacademic decline, it was not clear that most or all of these absences were caused by\\n\\nCrohn’s. Id. The Hearing Officer also concluded that, while J.C. was unambiguously\\n\\ncovered by Section 504, Cumberland had met all of its obligations under that statute by\\n\\nproviding every accommodation requested by his family. Id. at 50–51.\\n\\n J.C.’s parents then timely filed a civil action on his behalf in the Middle District of\\n\\nPennsylvania challenging the Hearing Officer’s decision. See Culley et al. v.\\n\\nCumberland Valley School District, No. 1:15-cv-00857-JEJ (M.D. Pa. 2015). Ruling on\\n\\nthe parties’ cross-motions for judgment on the record, the District Court reversed the\\n\\nHearing Officer, finding that J.C. was eligible under the IDEA, that Cumberland had\\n\\nviolated its “Child Find” duty to identify students with disabilities, and that it violated\\n\\nSection 504 by failing to evaluate J.C. prior to March 2014. Op. at 26 (App. at 28).\\n\\nCumberland now appeals, arguing that the District Court erred by (1) reversing the\\n\\nHearing Officer’s determination that Cumberland’s Evaluation Report was appropriate,\\n\\n(2) finding that J.C. was eligible for special education under the IDEA, and (3) finding\\n\\nthat Cumberland breached its “Child Find” duty.\\n\\n\\n\\n 5\\n\\f The District Court had original jurisdiction under 28 U.S.C. § 1331 and 20 U.S.C.\\n\\n§ 1415(i)(2). We have appellate jurisdiction under 28 U.S.C. § 1291. We review afresh\\n\\nthe District Court’s conclusions of law, including whether it applied the correct legal\\n\\nstandards under the IDEA, and we review its findings of fact for clear error. Ridley\\n\\nSchool District v. M.R., 680 F.3d 260, 268 (3d Cir. 2012). As to the merits, we review\\n\\nthe state administrative decision under the so-called “modified de novo” standard, under\\n\\nwhich the hearing officer’s findings of fact are given “due weight” and treated as “prima\\n\\nfacie correct,” which means that, if the Court disagrees with those findings, it must\\n\\nexplain the basis for its disagreement. Id. This is not substantively different from de\\n\\nnovo review, though courts are cautioned not to substitute their view of sound educational\\n\\npolicy for that of local school authorities. Id.\\n\\n Cumberland’s first argument on appeal, concerning the “appropriateness” of the\\n\\nEvaluation Report, seems to involve a category error on its part. Neither the District\\n\\nCourt’s decision nor the Hearing Officer used the word “appropriate” in connection with\\n\\nthe Evaluation Report. Nor do the statutory and regulatory provisions governing IDEA\\n\\nevaluations. See 20 U.S.C. § 1414(b), 34 C.F.R. § 300.304. The cases Cumberland cites\\n\\nconcern whether an IEP adopted under the IDEA is appropriate. See, e.g., Board of\\n\\nEducation of Hendrick Hudson Central School District, Westchester Co. v. Rowley, 458\\n\\nU.S. 176 (1982). The deference commended by Rowley and the other cases Cumberland\\n\\ncites, therefore, goes not to the threshold question of eligibility under the IDEA but how\\n\\nbest to tailor the education of children to their unique needs once they are found eligible.\\n\\n\\n\\n 6\\n\\fThat is of no relevance to this case, where Cumberland found J.C. ineligible for IDEA\\n\\nspecial education.\\n\\n The question of the weight to be given to the Evaluation Report, and to the IEE, is\\n\\nundoubtedly key to the main issue in this case, namely whether J.C. is in fact qualified\\n\\nfor special education under the IDEA. Cumberland does identify one problem in the\\n\\nDistrict Court’s analysis: it misquoted the Report as stating that there was “insufficient\\n\\nevidence to determine eligibility based on the category of Other Health Impairment,”\\n\\nwhen in fact the Report said that there was “insufficient information that [J.C.] has\\n\\nlimited alertness due to a medical condition.” Compare Op. at 11 (App. at 13), App. at\\n\\n152. Hence the Report was not incomplete.\\n\\n The rest of Cumberland’s arguments misread the record. The District Court did\\n\\nnot neglect the second prong of IDEA eligibility—that a student need not only have an\\n\\neligible disability but must also require specially designed instruction due to that\\n\\ndisability. Rather, its opinion explicitly referred to the correct set of criteria. Op. at 9.\\n\\nAnd while the Court did not discuss in detail J.C.’s need for specially designed\\n\\ninstruction, it did give reasons why the Hearing Officer was wrong to discount the IEE,\\n\\nwhich contained detailed instructions for ways J.C.’s instruction should be modified to\\n\\nsuit his needs. If credited, then, the IEE provides ample support for finding that J.C. was\\n\\nIDEA eligible. And we agree that the IEE paints a fuller and more accurate picture of\\n\\nJ.C.’s conditions than the Evaluation Report.\\n\\n The Hearing Officer’s principal ground for discounting the independent report was\\n\\nits finding of a specific learning disability as to mathematics, but the District Court was\\n\\n 7\\n\\fcorrect that J.C.’s performance in math was anything but strong. In ninth grade, for\\n\\ninstance, J.C. failed the first three periods of his basic algebra course, only passing the\\n\\nentire course (with a D grade) due to a strong final period. App. at 69. Arguably this\\n\\npattern—strong performance for many years followed by a sharp decline—indicates a\\n\\n“discrepancy between intellectual ability and academic achievement.” See 22 Pa. Code\\n\\n§ 14.125. Cumberland cites no evidence for its claim that a specific learning disability\\n\\ncould not manifest progressively over time, aside from a conclusory citation to the\\n\\ndefinition of specific learning disabilities as “a disorder in one or more of the basic\\n\\npsychological processes involved” in various tasks. There is nothing illogical about the\\n\\nidea that a learning disability might only impair a student’s ability to do the tasks\\n\\ninvolved in higher and more complex forms of mathematics.\\n\\n Even aside from this specific dispute, the Hearing Officer was wrong to\\n\\ncharacterize the independent report as “conclusory;” it is plainly more detailed in its\\n\\nanalysis than the school’s own Evaluation Report, showing J.C.’s life and the misery his\\n\\ndisease inflicts on him in far richer context. Compare App. at 151–152, 188–189.\\n\\nPerhaps if the Hearing Officer’s factual conclusions were entitled to increased deference,\\n\\nsuch as clear error review, the District Court’s reversal as to the weight of the\\n\\nindependent evaluation would be more of a problem. But the “modified de novo”\\n\\nstandard does not actually restrict the Court’s power to reach its own conclusions as to\\n\\neligibility based on the preponderance of the evidence. This merely requires it to explain\\n\\nits disagreements with the Hearing Officer, which it did.\\n\\n\\n\\n 8\\n\\f Cumberland also misstates that the school’s Report concluded that J.C. was not\\n\\nIDEA eligible because of the second criterion, the need for specially designed instruction.\\n\\nIn fact the Report checked the box indicating that J.C. does not have a qualifying\\n\\ndisability at all. App. at 152. The Hearing Officer concluded to the contrary that Crohn’s\\n\\ndisease was a qualifying disability, and Cumberland does not argue otherwise. Nor is\\n\\nCumberland correct in stating that the East Pennsboro IEP is “actually just an\\n\\naccommodations plan, but contained on an IEP form instead of on a Section 504 form.”\\n\\nAppellant’s Br. at 18. Although the IEP does include many of the same accommodations\\n\\nas the Cumberland Section 504 plan, and states that J.C. must participate in the general\\n\\neducation curriculum for all classes, it also concludes that he requires itinerant\\n\\nlearning/emotional support and “specially designed instructional strategies within his\\n\\nmainstream courses of study.” App. at 262. And while Cumberland argues that there had\\n\\nnot been sufficient time to see whether the newly enacted Section 504 plan and its\\n\\naccommodation of homebound instruction would be sufficient to address J.C.’s needs, it\\n\\nwas already apparent that homebound instruction was, to put it mildly, not going well.\\n\\n Ultimately the basis for Cumberland’s conviction that J.C. does not require\\n\\nspecially designed instruction is not the Evaluation Report but rather a disbelief that “a\\n\\ndisease of the digestive system required adapting the content, methodology, or delivery of\\n\\nthe academic curriculum.” Appellant’s Br. at 17. But the independent evaluation\\n\\nexplains the connection well: J.C.’s life has been pervasively shaped in all facets by his\\n\\ndisease, and his numerous behavioral, emotional, social, and academic problems are, to\\n\\nsome degree, related to it. App. at 188. It may even, as the Evaluation Report itself\\n\\n 9\\n\\fsuggested, App. at 124, contribute to his ADHD—something neither the Report nor the\\n\\nHearing Officer considered in their analysis of J.C.’s IDEA eligibility. In seeing Crohn’s\\n\\nas something requiring only a Section 504 accommodation, not IDEA special education,\\n\\nCumberland and the Hearing Officer both treated the disease as something discrete and\\n\\nisolated rather than the defining condition of J.C.’s life. The District Court did not err in\\n\\nfinding to the contrary.\\n\\n Finally, Cumberland claims the District Court erred in finding that the school\\n\\nbreached its so-called “Child Find” duty. This refers to a school’s obligation, under\\n\\nrelevant federal law, to identify students with disabilities who require accommodations or\\n\\nspecial education services proactively rather than waiting around for a child’s parents to\\n\\nconfront them with evidence of this need. Both the IDEA and Section 504 impose such a\\n\\nduty, see 20 U.S.C. § 1412(a)(3); 34 C.F.R. § 104.32. And there appears to be some\\n\\nconfusion in this case about which “Child Find” duty is actually at issue. The Hearing\\n\\nOfficer’s decision made no finding as to Child Find under the IDEA because he\\n\\nconcluded that J.C. was not IDEA-eligible, and then ruled that Cumberland had not\\n\\nviolated Section 504 by failing to provide accommodations earlier. This analysis did not\\n\\ndiscuss the 504 Child Find obligation, and reasoned principally that the school had no\\n\\nnotice that J.C. required accommodations prior to receiving the physician’s notes in 2014.\\n\\nThe District Court, meanwhile, found a violation of the Child Find duty under the IDEA;\\n\\nit also found that Cumberland should have provided Section 504 services well before\\n\\nwhen it started providing those services, but did not discuss the 504 claims in terms of a\\n\\n\\n\\n 10\\n\\fChild Find duty. On appeal, however, both parties’ briefs discuss the Child Find issue as\\n\\nthough it were a Section 504 question.\\n\\n Because both the IDEA Child Find and the Section 504 claims involve what\\n\\nCumberland knew or should have known at what point in time, we will analyze them\\n\\ntogether. Cumberland knew of J.C.’s diagnosis as early as 2007. This seems sufficient to\\n\\ntrigger its Section 504 obligations to ensure that J.C. received whatever accommodations\\n\\nhe might require for his Crohn’s disease, as no one disputes that Crohn’s is sufficient to\\n\\ntrigger Section 504 coverage. Although it appears Cumberland was willing to make ad\\n\\nhoc accommodations to J.C.’s needs due to Crohn’s, see App. at 22, this was entirely\\n\\nreactive. It would be bad enough had J.C.’s performance in school been exemplary. But\\n\\nfrom seventh grade on he experienced severe academic decline and numerous\\n\\ndisciplinary issues. The District Court is correct that Cumberland at least should have\\n\\ninvestigated the question of whether J.C.’s numerous issues stemmed from his\\n\\ndebilitating, life-threatening disease in a way that would be helped by accommodations.\\n\\nIt did not do so. The same applies under the IDEA, given that J.C. is IDEA-eligible and\\n\\nthat among the warning signs was his declining academic performance.\\n\\n Cumberland contends that the Hearing Officer correctly rejected the Section 504\\n\\nclaim because J.C. and his parents failed to prove that the “warning signs” they cite were\\n\\ncaused by Crohn’s. Appellant’s Br. at 26–27. There are two problems here. First, the\\n\\ndiscussion they cite in the Hearing Officer’s decision was not about Section 504 or the\\n\\nChild Find obligation at all; instead it concerned whether J.C.’s Crohn’s disease qualified\\n\\nhim for special education under the IDEA. In that context the Hearing Officer held that\\n\\n 11\\n\\fJ.C. had not sufficiently proven that his absences from school were caused by Crohn’s,\\n\\nsuch that he had not proven his disease adversely affected his education.\\n\\n Second, Cumberland’s argument is illogical and inconsistent with the basic\\n\\nconcept of a Child Find obligation. The School knew that J.C. had Crohn’s, and it\\n\\nobserved the warning signs. There cannot have been a burden on J.C. or his parents to\\n\\ncome forward, at that time, with evidence the disease was the cause of his problems; that\\n\\nwould be placing the burden on J.C. and his family for identifying him as a student with a\\n\\ndisability, precisely what the Child Find duty forbids. If there was no burden at that time,\\n\\nif the school was obliged to investigate J.C.’s needs under the IDEA and Section 504\\n\\neven before he had proven that his poor conduct and performance were a result of his\\n\\ndisease, there can be no requirement for that proof now during litigation. That obligation\\n\\nwas in play even were his disease not behind his declining performance in school. The\\n\\nDistrict Court did not err, therefore, in concluding that Cumberland violated its Child\\n\\nFind obligations under the IDEA and that it violated its obligations under Section 504 by\\n\\nfailing to adopt a service plan for J.C. until March 2014.\\n\\n * * * * *\\n\\n Thus we affirm.\\n\\n\\n\\n\\n 12\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4355860/\", \"author_raw\": \"AMBRO, Circuit Judge\"}]}"},"judge1":{"kind":"string","value":"AMBRO"},"judge2":{"kind":"string","value":"SCIRICA"},"judge3":{"kind":"string","value":"RENDELL"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"AMBRO\": \", Circuit\", \"SCIRICA\": \", Circuit\", \"RENDELL\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4578607/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Kevin Culley v. Cumberland Valley School Dist\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-03\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nNOT PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n ________________\n\n No. 17-3800\n ________________\n\n KEVIN CULLEY, and; DENISE CULLEY, on behalf of; J.C.\n\n v.\n\n CUMBERLAND VALLEY SCHOOL DISTRICT,\n\n Appellant\n ________________\n\n Appeal from the United States District Court\n for the Middle District of Pennsylvania\n (D.C. Civil Action No. 1-15-cv-00857)\n District Judge: Honorable John E. Jones, III\n ________________\n\n Argued November 6, 2018\n\n Before: AMBRO, SCIRICA, and RENDELL, Circuit Judges\n\n (Opinion filed: December 20, 2018)\n\n\nMark W. Cheramie Walz [Argued]\nSweet, Stevens, Katz & Williams LLP\n331 East Butler Avenue\nP.O. Box 5069\nNew Britain, PA 18901\n Counsel for Appellant\n\nJudith A. Gran [Argued]\nReisman Carolla & Gran LLP\n19 Chestnut Street\nHaddonfield, NJ 08033\n\fPhillip A. Drumheiser\nP.O. Box 890\nCarlisle, PA 17013\n Counsel for Appellees\n\n ________________\n\n OPINION*\n ________________\n\nAMBRO, Circuit Judge\n\n J.C., son of plaintiffs Kevin and Denise Culley, was diagnosed with Crohn’s\n\ndisease at age six. It is a painful, even debilitating, disease that affects the digestive tract\n\nand can cause abdominal pain, diarrhea, fatigue, weight loss, and malnutrition. It can\n\neven be life-threatening. See Mayo Clinic, Crohn’s Disease (Mar. 8, 2018), available at\n\nhttps://www.mayoclinic.org/diseases-conditions/crohns-disease/symptoms-causes/syc-\n\n20353304. After a disciplinary dispute with J.C.’s school, part of the Cumberland Valley\n\nSchool District system, that resulted in his expulsion, J.C.’s parents filed suit claiming\n\nthat Cumberland had violated J.C.’s rights under the Individuals with Disabilities\n\nEducation Act (IDEA), 20 U.S.C. § 1400 et seq., and under Section 504 of the\n\nRehabilitation Act. 29 U.S.C. § 701 et seq. The District Court agreed, and we now\n\naffirm.\n\n Born in 1998, J.C. was diagnosed with Crohn’s disease in 2004. Cumberland was\n\ninformed of the diagnosis in 2007. App. at 53. J.C.’s performance in school was\n\ngenerally strong through his sixth grade year, in 2009–2010, and he did not have\n\n\n\n*\n This disposition is not an opinion of the full Court and pursuant to I.O.P. 5.7 does not\nconstitute binding precedent.\n 2\n\fsignificant behavioral or social difficulties through that time. Id. at 130–131. But from\n\nseventh grade onward, both J.C.’s academic performance and his disciplinary record took\n\nsignificant turns for the worse. From seventh through tenth grade, when the incident\n\ngiving rise to this lawsuit occurred and he was expelled, J.C. maintained a grade point\n\naverage just above a failing mark of 70, had numerous disciplinary incidents, and was\n\nincreasingly absent from school. Id. at 128, 131, 169–170. By tenth grade J.C. was\n\nabsent 43 times, or over 30% of the time.\n\n In April 2013, while in ninth grade, J.C. was admitted to Hershey Medical Center\n\nfor surgery. Shortly thereafter in May, the school received a letter from his physician\n\nstating that J.C. should be allowed to cease activities during his physical education\n\nclasses if he experienced pain. Id. at 170. In July 2013 the school received another letter\n\nfrom J.C.’s doctor stating that he should be allowed to leave class to use the bathroom on\n\na liberal basis. Id. It appears Cumberland agreed to these accommodations.\n\n On January 17, 2014, J.C. had a disciplinary incident where he, apparently along\n\nwith several friends, attempted to leave the school grounds during the day. The other\n\nstudents fled, while J.C. was apprehended and had disciplinary proceedings brought\n\nagainst him, with an eye toward expulsion. After J.C.’s doctor wrote a letter to the school\n\non January 27, 2014, giving a fuller account of J.C.’s diagnosis and the accommodations\n\nhe required, his parents filed a due process complaint under the IDEA on January 29.\n\nCumberland adopted a Section 504 Service Plan for J.C. in March 2014, which provided\n\nfor a number of accommodations, including an “any time pass” to go to the nurse or the\n\nbathroom, extra time to complete assignments, and the provision of class notes in case of\n\n 3\n\ffrequent absences. Id. at 92–94. After receiving a letter from J.C.’s doctor stating that he\n\nshould receive homebound instruction for half of each school day, Cumberland tried to\n\nimplement this accommodation as well, but things did not go well. J.C. was rarely\n\npresent when the instructor arrived at his house, and even when present was not\n\nmotivated or cooperative. Id. at 107–116.\n\n The school board voted to expel J.C. on April 7, 2014, with the expulsion taking\n\neffect on May 8, 2014. At the same time, Cumberland released its Evaluation Report\n\nfrom its psychologist’s evaluation of J.C. Id. at 123. The report concluded that he did\n\nnot have a “qualifying disability” and thus was not eligible for special education under\n\nthe IDEA. Id. at 152. It also stated that there was insufficient evidence that J.C.’s\n\nCrohn’s disease was responsible for his difficulties in school, and that his condition\n\ncalled for Section 504 accommodations, not IDEA specialized instruction. J.C.’s parents\n\nthen requested an independent educational evaluation (IEE), which reached the opposite\n\nconclusion. Id. at 162–192. Noting the pervasive effect of Crohn’s on J.C.’s life, the IEE\n\nfound that he was eligible for special education under the IDEA and gave numerous\n\n“recommendations for specially designed instruction” to help tailor J.C.’s education to\n\nhis benefit. Id. at 189–191. It also found that J.C. had ADHD and specific learning\n\ndisabilities as to math and listening comprehension. Id. at 189. After J.C. moved to a\n\nneighboring school district, East Pennsboro, for the 2014–'15 school year, that district\n\nadopted an individualized education program (IEP) for J.C. to provide special education\n\nunder the IDEA. Id. at 249–279.\n\n\n\n 4\n\f Meanwhile, the Hearing Officer on J.C.’s due process complaint held a hearing\n\nand issued his decision in February 2015. He found that J.C. was not eligible for special\n\neducation under the IDEA because, even though Crohn’s disease was a qualifying\n\ndisability, it did not require specialized instruction. Id. at 48. The Hearing Officer\n\nendorsed Cumberland’s Evaluation Report and largely dismissed the findings from the\n\nIEE. He noted that while J.C.’s frequent absences doubtless caused much of his\n\nacademic decline, it was not clear that most or all of these absences were caused by\n\nCrohn’s. Id. The Hearing Officer also concluded that, while J.C. was unambiguously\n\ncovered by Section 504, Cumberland had met all of its obligations under that statute by\n\nproviding every accommodation requested by his family. Id. at 50–51.\n\n J.C.’s parents then timely filed a civil action on his behalf in the Middle District of\n\nPennsylvania challenging the Hearing Officer’s decision. See Culley et al. v.\n\nCumberland Valley School District, No. 1:15-cv-00857-JEJ (M.D. Pa. 2015). Ruling on\n\nthe parties’ cross-motions for judgment on the record, the District Court reversed the\n\nHearing Officer, finding that J.C. was eligible under the IDEA, that Cumberland had\n\nviolated its “Child Find” duty to identify students with disabilities, and that it violated\n\nSection 504 by failing to evaluate J.C. prior to March 2014. Op. at 26 (App. at 28).\n\nCumberland now appeals, arguing that the District Court erred by (1) reversing the\n\nHearing Officer’s determination that Cumberland’s Evaluation Report was appropriate,\n\n(2) finding that J.C. was eligible for special education under the IDEA, and (3) finding\n\nthat Cumberland breached its “Child Find” duty.\n\n\n\n 5\n\f The District Court had original jurisdiction under 28 U.S.C. § 1331 and 20 U.S.C.\n\n§ 1415(i)(2). We have appellate jurisdiction under 28 U.S.C. § 1291. We review afresh\n\nthe District Court’s conclusions of law, including whether it applied the correct legal\n\nstandards under the IDEA, and we review its findings of fact for clear error. Ridley\n\nSchool District v. M.R., 680 F.3d 260, 268 (3d Cir. 2012). As to the merits, we review\n\nthe state administrative decision under the so-called “modified de novo” standard, under\n\nwhich the hearing officer’s findings of fact are given “due weight” and treated as “prima\n\nfacie correct,” which means that, if the Court disagrees with those findings, it must\n\nexplain the basis for its disagreement. Id. This is not substantively different from de\n\nnovo review, though courts are cautioned not to substitute their view of sound educational\n\npolicy for that of local school authorities. Id.\n\n Cumberland’s first argument on appeal, concerning the “appropriateness” of the\n\nEvaluation Report, seems to involve a category error on its part. Neither the District\n\nCourt’s decision nor the Hearing Officer used the word “appropriate” in connection with\n\nthe Evaluation Report. Nor do the statutory and regulatory provisions governing IDEA\n\nevaluations. See 20 U.S.C. § 1414(b), 34 C.F.R. § 300.304. The cases Cumberland cites\n\nconcern whether an IEP adopted under the IDEA is appropriate. See, e.g., Board of\n\nEducation of Hendrick Hudson Central School District, Westchester Co. v. Rowley, 458\n\nU.S. 176 (1982). The deference commended by Rowley and the other cases Cumberland\n\ncites, therefore, goes not to the threshold question of eligibility under the IDEA but how\n\nbest to tailor the education of children to their unique needs once they are found eligible.\n\n\n\n 6\n\fThat is of no relevance to this case, where Cumberland found J.C. ineligible for IDEA\n\nspecial education.\n\n The question of the weight to be given to the Evaluation Report, and to the IEE, is\n\nundoubtedly key to the main issue in this case, namely whether J.C. is in fact qualified\n\nfor special education under the IDEA. Cumberland does identify one problem in the\n\nDistrict Court’s analysis: it misquoted the Report as stating that there was “insufficient\n\nevidence to determine eligibility based on the category of Other Health Impairment,”\n\nwhen in fact the Report said that there was “insufficient information that [J.C.] has\n\nlimited alertness due to a medical condition.” Compare Op. at 11 (App. at 13), App. at\n\n152. Hence the Report was not incomplete.\n\n The rest of Cumberland’s arguments misread the record. The District Court did\n\nnot neglect the second prong of IDEA eligibility—that a student need not only have an\n\neligible disability but must also require specially designed instruction due to that\n\ndisability. Rather, its opinion explicitly referred to the correct set of criteria. Op. at 9.\n\nAnd while the Court did not discuss in detail J.C.’s need for specially designed\n\ninstruction, it did give reasons why the Hearing Officer was wrong to discount the IEE,\n\nwhich contained detailed instructions for ways J.C.’s instruction should be modified to\n\nsuit his needs. If credited, then, the IEE provides ample support for finding that J.C. was\n\nIDEA eligible. And we agree that the IEE paints a fuller and more accurate picture of\n\nJ.C.’s conditions than the Evaluation Report.\n\n The Hearing Officer’s principal ground for discounting the independent report was\n\nits finding of a specific learning disability as to mathematics, but the District Court was\n\n 7\n\fcorrect that J.C.’s performance in math was anything but strong. In ninth grade, for\n\ninstance, J.C. failed the first three periods of his basic algebra course, only passing the\n\nentire course (with a D grade) due to a strong final period. App. at 69. Arguably this\n\npattern—strong performance for many years followed by a sharp decline—indicates a\n\n“discrepancy between intellectual ability and academic achievement.” See 22 Pa. Code\n\n§ 14.125. Cumberland cites no evidence for its claim that a specific learning disability\n\ncould not manifest progressively over time, aside from a conclusory citation to the\n\ndefinition of specific learning disabilities as “a disorder in one or more of the basic\n\npsychological processes involved” in various tasks. There is nothing illogical about the\n\nidea that a learning disability might only impair a student’s ability to do the tasks\n\ninvolved in higher and more complex forms of mathematics.\n\n Even aside from this specific dispute, the Hearing Officer was wrong to\n\ncharacterize the independent report as “conclusory;” it is plainly more detailed in its\n\nanalysis than the school’s own Evaluation Report, showing J.C.’s life and the misery his\n\ndisease inflicts on him in far richer context. Compare App. at 151–152, 188–189.\n\nPerhaps if the Hearing Officer’s factual conclusions were entitled to increased deference,\n\nsuch as clear error review, the District Court’s reversal as to the weight of the\n\nindependent evaluation would be more of a problem. But the “modified de novo”\n\nstandard does not actually restrict the Court’s power to reach its own conclusions as to\n\neligibility based on the preponderance of the evidence. This merely requires it to explain\n\nits disagreements with the Hearing Officer, which it did.\n\n\n\n 8\n\f Cumberland also misstates that the school’s Report concluded that J.C. was not\n\nIDEA eligible because of the second criterion, the need for specially designed instruction.\n\nIn fact the Report checked the box indicating that J.C. does not have a qualifying\n\ndisability at all. App. at 152. The Hearing Officer concluded to the contrary that Crohn’s\n\ndisease was a qualifying disability, and Cumberland does not argue otherwise. Nor is\n\nCumberland correct in stating that the East Pennsboro IEP is “actually just an\n\naccommodations plan, but contained on an IEP form instead of on a Section 504 form.”\n\nAppellant’s Br. at 18. Although the IEP does include many of the same accommodations\n\nas the Cumberland Section 504 plan, and states that J.C. must participate in the general\n\neducation curriculum for all classes, it also concludes that he requires itinerant\n\nlearning/emotional support and “specially designed instructional strategies within his\n\nmainstream courses of study.” App. at 262. And while Cumberland argues that there had\n\nnot been sufficient time to see whether the newly enacted Section 504 plan and its\n\naccommodation of homebound instruction would be sufficient to address J.C.’s needs, it\n\nwas already apparent that homebound instruction was, to put it mildly, not going well.\n\n Ultimately the basis for Cumberland’s conviction that J.C. does not require\n\nspecially designed instruction is not the Evaluation Report but rather a disbelief that “a\n\ndisease of the digestive system required adapting the content, methodology, or delivery of\n\nthe academic curriculum.” Appellant’s Br. at 17. But the independent evaluation\n\nexplains the connection well: J.C.’s life has been pervasively shaped in all facets by his\n\ndisease, and his numerous behavioral, emotional, social, and academic problems are, to\n\nsome degree, related to it. App. at 188. It may even, as the Evaluation Report itself\n\n 9\n\fsuggested, App. at 124, contribute to his ADHD—something neither the Report nor the\n\nHearing Officer considered in their analysis of J.C.’s IDEA eligibility. In seeing Crohn’s\n\nas something requiring only a Section 504 accommodation, not IDEA special education,\n\nCumberland and the Hearing Officer both treated the disease as something discrete and\n\nisolated rather than the defining condition of J.C.’s life. The District Court did not err in\n\nfinding to the contrary.\n\n Finally, Cumberland claims the District Court erred in finding that the school\n\nbreached its so-called “Child Find” duty. This refers to a school’s obligation, under\n\nrelevant federal law, to identify students with disabilities who require accommodations or\n\nspecial education services proactively rather than waiting around for a child’s parents to\n\nconfront them with evidence of this need. Both the IDEA and Section 504 impose such a\n\nduty, see 20 U.S.C. § 1412(a)(3); 34 C.F.R. § 104.32. And there appears to be some\n\nconfusion in this case about which “Child Find” duty is actually at issue. The Hearing\n\nOfficer’s decision made no finding as to Child Find under the IDEA because he\n\nconcluded that J.C. was not IDEA-eligible, and then ruled that Cumberland had not\n\nviolated Section 504 by failing to provide accommodations earlier. This analysis did not\n\ndiscuss the 504 Child Find obligation, and reasoned principally that the school had no\n\nnotice that J.C. required accommodations prior to receiving the physician’s notes in 2014.\n\nThe District Court, meanwhile, found a violation of the Child Find duty under the IDEA;\n\nit also found that Cumberland should have provided Section 504 services well before\n\nwhen it started providing those services, but did not discuss the 504 claims in terms of a\n\n\n\n 10\n\fChild Find duty. On appeal, however, both parties’ briefs discuss the Child Find issue as\n\nthough it were a Section 504 question.\n\n Because both the IDEA Child Find and the Section 504 claims involve what\n\nCumberland knew or should have known at what point in time, we will analyze them\n\ntogether. Cumberland knew of J.C.’s diagnosis as early as 2007. This seems sufficient to\n\ntrigger its Section 504 obligations to ensure that J.C. received whatever accommodations\n\nhe might require for his Crohn’s disease, as no one disputes that Crohn’s is sufficient to\n\ntrigger Section 504 coverage. Although it appears Cumberland was willing to make ad\n\nhoc accommodations to J.C.’s needs due to Crohn’s, see App. at 22, this was entirely\n\nreactive. It would be bad enough had J.C.’s performance in school been exemplary. But\n\nfrom seventh grade on he experienced severe academic decline and numerous\n\ndisciplinary issues. The District Court is correct that Cumberland at least should have\n\ninvestigated the question of whether J.C.’s numerous issues stemmed from his\n\ndebilitating, life-threatening disease in a way that would be helped by accommodations.\n\nIt did not do so. The same applies under the IDEA, given that J.C. is IDEA-eligible and\n\nthat among the warning signs was his declining academic performance.\n\n Cumberland contends that the Hearing Officer correctly rejected the Section 504\n\nclaim because J.C. and his parents failed to prove that the “warning signs” they cite were\n\ncaused by Crohn’s. Appellant’s Br. at 26–27. There are two problems here. First, the\n\ndiscussion they cite in the Hearing Officer’s decision was not about Section 504 or the\n\nChild Find obligation at all; instead it concerned whether J.C.’s Crohn’s disease qualified\n\nhim for special education under the IDEA. In that context the Hearing Officer held that\n\n 11\n\fJ.C. had not sufficiently proven that his absences from school were caused by Crohn’s,\n\nsuch that he had not proven his disease adversely affected his education.\n\n Second, Cumberland’s argument is illogical and inconsistent with the basic\n\nconcept of a Child Find obligation. The School knew that J.C. had Crohn’s, and it\n\nobserved the warning signs. There cannot have been a burden on J.C. or his parents to\n\ncome forward, at that time, with evidence the disease was the cause of his problems; that\n\nwould be placing the burden on J.C. and his family for identifying him as a student with a\n\ndisability, precisely what the Child Find duty forbids. If there was no burden at that time,\n\nif the school was obliged to investigate J.C.’s needs under the IDEA and Section 504\n\neven before he had proven that his poor conduct and performance were a result of his\n\ndisease, there can be no requirement for that proof now during litigation. That obligation\n\nwas in play even were his disease not behind his declining performance in school. The\n\nDistrict Court did not err, therefore, in concluding that Cumberland violated its Child\n\nFind obligations under the IDEA and that it violated its obligations under Section 504 by\n\nfailing to adopt a service plan for J.C. until March 2014.\n\n * * * * *\n\n Thus we affirm.\n\n\n\n\n 12\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Kevin Culley v. Cumberland Valley School Dist\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-03\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nNOT PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n ________________\\n\\n No. 17-3800\\n ________________\\n\\n KEVIN CULLEY, and; DENISE CULLEY, on behalf of; J.C.\\n\\n v.\\n\\n CUMBERLAND VALLEY SCHOOL DISTRICT,\\n\\n Appellant\\n ________________\\n\\n Appeal from the United States District Court\\n for the Middle District of Pennsylvania\\n (D.C. Civil Action No. 1-15-cv-00857)\\n District Judge: Honorable John E. Jones, III\\n ________________\\n\\n Argued November 6, 2018\\n\\n Before: AMBRO, SCIRICA, and RENDELL, Circuit Judges\\n\\n (Opinion filed: December 20, 2018)\\n\\n\\nMark W. Cheramie Walz [Argued]\\nSweet, Stevens, Katz & Williams LLP\\n331 East Butler Avenue\\nP.O. Box 5069\\nNew Britain, PA 18901\\n Counsel for Appellant\\n\\nJudith A. Gran [Argued]\\nReisman Carolla & Gran LLP\\n19 Chestnut Street\\nHaddonfield, NJ 08033\\n\\fPhillip A. Drumheiser\\nP.O. Box 890\\nCarlisle, PA 17013\\n Counsel for Appellees\\n\\n ________________\\n\\n OPINION*\\n ________________\\n\\nAMBRO, Circuit Judge\\n\\n J.C., son of plaintiffs Kevin and Denise Culley, was diagnosed with Crohn’s\\n\\ndisease at age six. It is a painful, even debilitating, disease that affects the digestive tract\\n\\nand can cause abdominal pain, diarrhea, fatigue, weight loss, and malnutrition. It can\\n\\neven be life-threatening. See Mayo Clinic, Crohn’s Disease (Mar. 8, 2018), available at\\n\\nhttps://www.mayoclinic.org/diseases-conditions/crohns-disease/symptoms-causes/syc-\\n\\n20353304. After a disciplinary dispute with J.C.’s school, part of the Cumberland Valley\\n\\nSchool District system, that resulted in his expulsion, J.C.’s parents filed suit claiming\\n\\nthat Cumberland had violated J.C.’s rights under the Individuals with Disabilities\\n\\nEducation Act (IDEA), 20 U.S.C. § 1400 et seq., and under Section 504 of the\\n\\nRehabilitation Act. 29 U.S.C. § 701 et seq. The District Court agreed, and we now\\n\\naffirm.\\n\\n Born in 1998, J.C. was diagnosed with Crohn’s disease in 2004. Cumberland was\\n\\ninformed of the diagnosis in 2007. App. at 53. J.C.’s performance in school was\\n\\ngenerally strong through his sixth grade year, in 2009–2010, and he did not have\\n\\n\\n\\n*\\n This disposition is not an opinion of the full Court and pursuant to I.O.P. 5.7 does not\\nconstitute binding precedent.\\n 2\\n\\fsignificant behavioral or social difficulties through that time. Id. at 130–131. But from\\n\\nseventh grade onward, both J.C.’s academic performance and his disciplinary record took\\n\\nsignificant turns for the worse. From seventh through tenth grade, when the incident\\n\\ngiving rise to this lawsuit occurred and he was expelled, J.C. maintained a grade point\\n\\naverage just above a failing mark of 70, had numerous disciplinary incidents, and was\\n\\nincreasingly absent from school. Id. at 128, 131, 169–170. By tenth grade J.C. was\\n\\nabsent 43 times, or over 30% of the time.\\n\\n In April 2013, while in ninth grade, J.C. was admitted to Hershey Medical Center\\n\\nfor surgery. Shortly thereafter in May, the school received a letter from his physician\\n\\nstating that J.C. should be allowed to cease activities during his physical education\\n\\nclasses if he experienced pain. Id. at 170. In July 2013 the school received another letter\\n\\nfrom J.C.’s doctor stating that he should be allowed to leave class to use the bathroom on\\n\\na liberal basis. Id. It appears Cumberland agreed to these accommodations.\\n\\n On January 17, 2014, J.C. had a disciplinary incident where he, apparently along\\n\\nwith several friends, attempted to leave the school grounds during the day. The other\\n\\nstudents fled, while J.C. was apprehended and had disciplinary proceedings brought\\n\\nagainst him, with an eye toward expulsion. After J.C.’s doctor wrote a letter to the school\\n\\non January 27, 2014, giving a fuller account of J.C.’s diagnosis and the accommodations\\n\\nhe required, his parents filed a due process complaint under the IDEA on January 29.\\n\\nCumberland adopted a Section 504 Service Plan for J.C. in March 2014, which provided\\n\\nfor a number of accommodations, including an “any time pass” to go to the nurse or the\\n\\nbathroom, extra time to complete assignments, and the provision of class notes in case of\\n\\n 3\\n\\ffrequent absences. Id. at 92–94. After receiving a letter from J.C.’s doctor stating that he\\n\\nshould receive homebound instruction for half of each school day, Cumberland tried to\\n\\nimplement this accommodation as well, but things did not go well. J.C. was rarely\\n\\npresent when the instructor arrived at his house, and even when present was not\\n\\nmotivated or cooperative. Id. at 107–116.\\n\\n The school board voted to expel J.C. on April 7, 2014, with the expulsion taking\\n\\neffect on May 8, 2014. At the same time, Cumberland released its Evaluation Report\\n\\nfrom its psychologist’s evaluation of J.C. Id. at 123. The report concluded that he did\\n\\nnot have a “qualifying disability” and thus was not eligible for special education under\\n\\nthe IDEA. Id. at 152. It also stated that there was insufficient evidence that J.C.’s\\n\\nCrohn’s disease was responsible for his difficulties in school, and that his condition\\n\\ncalled for Section 504 accommodations, not IDEA specialized instruction. J.C.’s parents\\n\\nthen requested an independent educational evaluation (IEE), which reached the opposite\\n\\nconclusion. Id. at 162–192. Noting the pervasive effect of Crohn’s on J.C.’s life, the IEE\\n\\nfound that he was eligible for special education under the IDEA and gave numerous\\n\\n“recommendations for specially designed instruction” to help tailor J.C.’s education to\\n\\nhis benefit. Id. at 189–191. It also found that J.C. had ADHD and specific learning\\n\\ndisabilities as to math and listening comprehension. Id. at 189. After J.C. moved to a\\n\\nneighboring school district, East Pennsboro, for the 2014–'15 school year, that district\\n\\nadopted an individualized education program (IEP) for J.C. to provide special education\\n\\nunder the IDEA. Id. at 249–279.\\n\\n\\n\\n 4\\n\\f Meanwhile, the Hearing Officer on J.C.’s due process complaint held a hearing\\n\\nand issued his decision in February 2015. He found that J.C. was not eligible for special\\n\\neducation under the IDEA because, even though Crohn’s disease was a qualifying\\n\\ndisability, it did not require specialized instruction. Id. at 48. The Hearing Officer\\n\\nendorsed Cumberland’s Evaluation Report and largely dismissed the findings from the\\n\\nIEE. He noted that while J.C.’s frequent absences doubtless caused much of his\\n\\nacademic decline, it was not clear that most or all of these absences were caused by\\n\\nCrohn’s. Id. The Hearing Officer also concluded that, while J.C. was unambiguously\\n\\ncovered by Section 504, Cumberland had met all of its obligations under that statute by\\n\\nproviding every accommodation requested by his family. Id. at 50–51.\\n\\n J.C.’s parents then timely filed a civil action on his behalf in the Middle District of\\n\\nPennsylvania challenging the Hearing Officer’s decision. See Culley et al. v.\\n\\nCumberland Valley School District, No. 1:15-cv-00857-JEJ (M.D. Pa. 2015). Ruling on\\n\\nthe parties’ cross-motions for judgment on the record, the District Court reversed the\\n\\nHearing Officer, finding that J.C. was eligible under the IDEA, that Cumberland had\\n\\nviolated its “Child Find” duty to identify students with disabilities, and that it violated\\n\\nSection 504 by failing to evaluate J.C. prior to March 2014. Op. at 26 (App. at 28).\\n\\nCumberland now appeals, arguing that the District Court erred by (1) reversing the\\n\\nHearing Officer’s determination that Cumberland’s Evaluation Report was appropriate,\\n\\n(2) finding that J.C. was eligible for special education under the IDEA, and (3) finding\\n\\nthat Cumberland breached its “Child Find” duty.\\n\\n\\n\\n 5\\n\\f The District Court had original jurisdiction under 28 U.S.C. § 1331 and 20 U.S.C.\\n\\n§ 1415(i)(2). We have appellate jurisdiction under 28 U.S.C. § 1291. We review afresh\\n\\nthe District Court’s conclusions of law, including whether it applied the correct legal\\n\\nstandards under the IDEA, and we review its findings of fact for clear error. Ridley\\n\\nSchool District v. M.R., 680 F.3d 260, 268 (3d Cir. 2012). As to the merits, we review\\n\\nthe state administrative decision under the so-called “modified de novo” standard, under\\n\\nwhich the hearing officer’s findings of fact are given “due weight” and treated as “prima\\n\\nfacie correct,” which means that, if the Court disagrees with those findings, it must\\n\\nexplain the basis for its disagreement. Id. This is not substantively different from de\\n\\nnovo review, though courts are cautioned not to substitute their view of sound educational\\n\\npolicy for that of local school authorities. Id.\\n\\n Cumberland’s first argument on appeal, concerning the “appropriateness” of the\\n\\nEvaluation Report, seems to involve a category error on its part. Neither the District\\n\\nCourt’s decision nor the Hearing Officer used the word “appropriate” in connection with\\n\\nthe Evaluation Report. Nor do the statutory and regulatory provisions governing IDEA\\n\\nevaluations. See 20 U.S.C. § 1414(b), 34 C.F.R. § 300.304. The cases Cumberland cites\\n\\nconcern whether an IEP adopted under the IDEA is appropriate. See, e.g., Board of\\n\\nEducation of Hendrick Hudson Central School District, Westchester Co. v. Rowley, 458\\n\\nU.S. 176 (1982). The deference commended by Rowley and the other cases Cumberland\\n\\ncites, therefore, goes not to the threshold question of eligibility under the IDEA but how\\n\\nbest to tailor the education of children to their unique needs once they are found eligible.\\n\\n\\n\\n 6\\n\\fThat is of no relevance to this case, where Cumberland found J.C. ineligible for IDEA\\n\\nspecial education.\\n\\n The question of the weight to be given to the Evaluation Report, and to the IEE, is\\n\\nundoubtedly key to the main issue in this case, namely whether J.C. is in fact qualified\\n\\nfor special education under the IDEA. Cumberland does identify one problem in the\\n\\nDistrict Court’s analysis: it misquoted the Report as stating that there was “insufficient\\n\\nevidence to determine eligibility based on the category of Other Health Impairment,”\\n\\nwhen in fact the Report said that there was “insufficient information that [J.C.] has\\n\\nlimited alertness due to a medical condition.” Compare Op. at 11 (App. at 13), App. at\\n\\n152. Hence the Report was not incomplete.\\n\\n The rest of Cumberland’s arguments misread the record. The District Court did\\n\\nnot neglect the second prong of IDEA eligibility—that a student need not only have an\\n\\neligible disability but must also require specially designed instruction due to that\\n\\ndisability. Rather, its opinion explicitly referred to the correct set of criteria. Op. at 9.\\n\\nAnd while the Court did not discuss in detail J.C.’s need for specially designed\\n\\ninstruction, it did give reasons why the Hearing Officer was wrong to discount the IEE,\\n\\nwhich contained detailed instructions for ways J.C.’s instruction should be modified to\\n\\nsuit his needs. If credited, then, the IEE provides ample support for finding that J.C. was\\n\\nIDEA eligible. And we agree that the IEE paints a fuller and more accurate picture of\\n\\nJ.C.’s conditions than the Evaluation Report.\\n\\n The Hearing Officer’s principal ground for discounting the independent report was\\n\\nits finding of a specific learning disability as to mathematics, but the District Court was\\n\\n 7\\n\\fcorrect that J.C.’s performance in math was anything but strong. In ninth grade, for\\n\\ninstance, J.C. failed the first three periods of his basic algebra course, only passing the\\n\\nentire course (with a D grade) due to a strong final period. App. at 69. Arguably this\\n\\npattern—strong performance for many years followed by a sharp decline—indicates a\\n\\n“discrepancy between intellectual ability and academic achievement.” See 22 Pa. Code\\n\\n§ 14.125. Cumberland cites no evidence for its claim that a specific learning disability\\n\\ncould not manifest progressively over time, aside from a conclusory citation to the\\n\\ndefinition of specific learning disabilities as “a disorder in one or more of the basic\\n\\npsychological processes involved” in various tasks. There is nothing illogical about the\\n\\nidea that a learning disability might only impair a student’s ability to do the tasks\\n\\ninvolved in higher and more complex forms of mathematics.\\n\\n Even aside from this specific dispute, the Hearing Officer was wrong to\\n\\ncharacterize the independent report as “conclusory;” it is plainly more detailed in its\\n\\nanalysis than the school’s own Evaluation Report, showing J.C.’s life and the misery his\\n\\ndisease inflicts on him in far richer context. Compare App. at 151–152, 188–189.\\n\\nPerhaps if the Hearing Officer’s factual conclusions were entitled to increased deference,\\n\\nsuch as clear error review, the District Court’s reversal as to the weight of the\\n\\nindependent evaluation would be more of a problem. But the “modified de novo”\\n\\nstandard does not actually restrict the Court’s power to reach its own conclusions as to\\n\\neligibility based on the preponderance of the evidence. This merely requires it to explain\\n\\nits disagreements with the Hearing Officer, which it did.\\n\\n\\n\\n 8\\n\\f Cumberland also misstates that the school’s Report concluded that J.C. was not\\n\\nIDEA eligible because of the second criterion, the need for specially designed instruction.\\n\\nIn fact the Report checked the box indicating that J.C. does not have a qualifying\\n\\ndisability at all. App. at 152. The Hearing Officer concluded to the contrary that Crohn’s\\n\\ndisease was a qualifying disability, and Cumberland does not argue otherwise. Nor is\\n\\nCumberland correct in stating that the East Pennsboro IEP is “actually just an\\n\\naccommodations plan, but contained on an IEP form instead of on a Section 504 form.”\\n\\nAppellant’s Br. at 18. Although the IEP does include many of the same accommodations\\n\\nas the Cumberland Section 504 plan, and states that J.C. must participate in the general\\n\\neducation curriculum for all classes, it also concludes that he requires itinerant\\n\\nlearning/emotional support and “specially designed instructional strategies within his\\n\\nmainstream courses of study.” App. at 262. And while Cumberland argues that there had\\n\\nnot been sufficient time to see whether the newly enacted Section 504 plan and its\\n\\naccommodation of homebound instruction would be sufficient to address J.C.’s needs, it\\n\\nwas already apparent that homebound instruction was, to put it mildly, not going well.\\n\\n Ultimately the basis for Cumberland’s conviction that J.C. does not require\\n\\nspecially designed instruction is not the Evaluation Report but rather a disbelief that “a\\n\\ndisease of the digestive system required adapting the content, methodology, or delivery of\\n\\nthe academic curriculum.” Appellant’s Br. at 17. But the independent evaluation\\n\\nexplains the connection well: J.C.’s life has been pervasively shaped in all facets by his\\n\\ndisease, and his numerous behavioral, emotional, social, and academic problems are, to\\n\\nsome degree, related to it. App. at 188. It may even, as the Evaluation Report itself\\n\\n 9\\n\\fsuggested, App. at 124, contribute to his ADHD—something neither the Report nor the\\n\\nHearing Officer considered in their analysis of J.C.’s IDEA eligibility. In seeing Crohn’s\\n\\nas something requiring only a Section 504 accommodation, not IDEA special education,\\n\\nCumberland and the Hearing Officer both treated the disease as something discrete and\\n\\nisolated rather than the defining condition of J.C.’s life. The District Court did not err in\\n\\nfinding to the contrary.\\n\\n Finally, Cumberland claims the District Court erred in finding that the school\\n\\nbreached its so-called “Child Find” duty. This refers to a school’s obligation, under\\n\\nrelevant federal law, to identify students with disabilities who require accommodations or\\n\\nspecial education services proactively rather than waiting around for a child’s parents to\\n\\nconfront them with evidence of this need. Both the IDEA and Section 504 impose such a\\n\\nduty, see 20 U.S.C. § 1412(a)(3); 34 C.F.R. § 104.32. And there appears to be some\\n\\nconfusion in this case about which “Child Find” duty is actually at issue. The Hearing\\n\\nOfficer’s decision made no finding as to Child Find under the IDEA because he\\n\\nconcluded that J.C. was not IDEA-eligible, and then ruled that Cumberland had not\\n\\nviolated Section 504 by failing to provide accommodations earlier. This analysis did not\\n\\ndiscuss the 504 Child Find obligation, and reasoned principally that the school had no\\n\\nnotice that J.C. required accommodations prior to receiving the physician’s notes in 2014.\\n\\nThe District Court, meanwhile, found a violation of the Child Find duty under the IDEA;\\n\\nit also found that Cumberland should have provided Section 504 services well before\\n\\nwhen it started providing those services, but did not discuss the 504 claims in terms of a\\n\\n\\n\\n 10\\n\\fChild Find duty. On appeal, however, both parties’ briefs discuss the Child Find issue as\\n\\nthough it were a Section 504 question.\\n\\n Because both the IDEA Child Find and the Section 504 claims involve what\\n\\nCumberland knew or should have known at what point in time, we will analyze them\\n\\ntogether. Cumberland knew of J.C.’s diagnosis as early as 2007. This seems sufficient to\\n\\ntrigger its Section 504 obligations to ensure that J.C. received whatever accommodations\\n\\nhe might require for his Crohn’s disease, as no one disputes that Crohn’s is sufficient to\\n\\ntrigger Section 504 coverage. Although it appears Cumberland was willing to make ad\\n\\nhoc accommodations to J.C.’s needs due to Crohn’s, see App. at 22, this was entirely\\n\\nreactive. It would be bad enough had J.C.’s performance in school been exemplary. But\\n\\nfrom seventh grade on he experienced severe academic decline and numerous\\n\\ndisciplinary issues. The District Court is correct that Cumberland at least should have\\n\\ninvestigated the question of whether J.C.’s numerous issues stemmed from his\\n\\ndebilitating, life-threatening disease in a way that would be helped by accommodations.\\n\\nIt did not do so. The same applies under the IDEA, given that J.C. is IDEA-eligible and\\n\\nthat among the warning signs was his declining academic performance.\\n\\n Cumberland contends that the Hearing Officer correctly rejected the Section 504\\n\\nclaim because J.C. and his parents failed to prove that the “warning signs” they cite were\\n\\ncaused by Crohn’s. Appellant’s Br. at 26–27. There are two problems here. First, the\\n\\ndiscussion they cite in the Hearing Officer’s decision was not about Section 504 or the\\n\\nChild Find obligation at all; instead it concerned whether J.C.’s Crohn’s disease qualified\\n\\nhim for special education under the IDEA. In that context the Hearing Officer held that\\n\\n 11\\n\\fJ.C. had not sufficiently proven that his absences from school were caused by Crohn’s,\\n\\nsuch that he had not proven his disease adversely affected his education.\\n\\n Second, Cumberland’s argument is illogical and inconsistent with the basic\\n\\nconcept of a Child Find obligation. The School knew that J.C. had Crohn’s, and it\\n\\nobserved the warning signs. There cannot have been a burden on J.C. or his parents to\\n\\ncome forward, at that time, with evidence the disease was the cause of his problems; that\\n\\nwould be placing the burden on J.C. and his family for identifying him as a student with a\\n\\ndisability, precisely what the Child Find duty forbids. If there was no burden at that time,\\n\\nif the school was obliged to investigate J.C.’s needs under the IDEA and Section 504\\n\\neven before he had proven that his poor conduct and performance were a result of his\\n\\ndisease, there can be no requirement for that proof now during litigation. That obligation\\n\\nwas in play even were his disease not behind his declining performance in school. The\\n\\nDistrict Court did not err, therefore, in concluding that Cumberland violated its Child\\n\\nFind obligations under the IDEA and that it violated its obligations under Section 504 by\\n\\nfailing to adopt a service plan for J.C. until March 2014.\\n\\n * * * * *\\n\\n Thus we affirm.\\n\\n\\n\\n\\n 12\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":59,"cells":{"id":{"kind":"number","value":4578608,"string":"4,578,608"},"name":{"kind":"string","value":"John F. SIMPSON, T/A Warrior Ridge Trading; T/A LCT Pro Shop v. ATTORNEY GENERAL UNITED STATES OF AMERICA; Director, Bureau of Alcohol, Tobacco, Firearms & Explosives; Director of Industry Operations, Bureau of Alcohol, Tobacco, Firearms & Explosives; United States of America John F. Simpson, Appellant"},"name_abbreviation":{"kind":"string","value":"John Simpson v. Attorney General United States"},"decision_date":{"kind":"string","value":"2019-01-03"},"docket_number":{"kind":"string","value":"17-3718"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Chagares, Jordan, Vanaskie\", \"parties\": \"\", \"opinions\": [{\"author\": \"VANASKIE, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-3718\\n _____________\\n\\nJOHN F. SIMPSON, t/a Warrior Ridge Trading; t/a LCT Pro Shop\\n\\n v.\\n\\n ATTORNEY GENERAL UNITED STATES OF AMERICA;\\nDIRECTOR, BUREAU OF ALCOHOL, TOBACCO, FIREARMS\\n & EXPLOSIVES; DIRECTOR OF INDUSTRY OPERATIONS,\\n BUREAU OF ALCOHOL, TOBACCO, FIREARMS &\\n EXPLOSIVES; UNITED STATES OF AMERICA\\n\\n John F. Simpson,\\n Appellant\\n\\n _____________\\n\\n On Appeal from the United States District Court\\n for the Middle District of Pennsylvania\\n District Judge: Honorable John E. Jones, III\\n (D.C. Civil No. 1-15-mc-00297)\\n ______________\\n\\n Argued October 30, 2018\\n ______________\\n\\f Before: CHAGARES, JORDAN, and VANASKIE, Circuit\\n Judges\\n\\n (Opinion Filed: January 3, 2019)\\n\\nAdam J. Kraut\\nJoshua Prince [ARGUED]\\nPrince Law Offices\\n646 Lenape Road\\nBechtelsville, PA 19505\\n Counsel for Appellant\\n\\nDavid J. Freed\\nUnited States Attorney\\nCarlo D. Marchioli [ARGUED]\\nKate L. Mershimer\\nOffice of United States Attorney\\n228 Walnut Street, P.O. Box 11754\\n220 Federal Building and Courthouse\\nHarrisburg, PA 17108\\n\\nJeffrey A. Cohen\\nATF Associate Chief Counsel\\nJohn Kevin White\\nATF Division Counsel\\n601 Walnut Street, Suite 1000E\\nPhiladelphia, PA 19106\\n Counsel for Appellees\\n\\n\\n\\n The Honorable Judge Vanaskie transmitted the opinion to the\\nClerk for filing prior to retiring from the bench on January 1, 2019.\\nDue to the intervening holiday, the opinion has been entered on the\\ndocket by the Clerk this day.\\n\\n\\n\\n\\n 2\\n\\f ________________\\n\\n OPINION\\n ________________\\n\\nVANASKIE, Circuit Judge.\\n\\n Appellant John Simpson appeals the District Court’s\\norder granting summary judgment for Appellees and affirming\\nthe Bureau of Alcohol, Tobacco, Firearms & Explosives’\\n(“ATF”) revocation of his federal firearms licenses (“FFLs”).\\nAfter an annual compliance investigation, the ATF determined\\nthat Simpson had committed over 400 willful violations of the\\nGun Control Act of 1968, 18 U.S.C. § 921 et seq. (“GCA”),\\nand therefore revoked his FFLs pursuant to 18 U.S.C. § 923(e)\\nand 27 C.F.R. § 478.73. After an administrative hearing, the\\nATF affirmed its revocation decision and Simpson filed a\\npetition for judicial review under 18 U.S.C. § 923(f)(3). The\\nDistrict Court, adopting a Magistrate Judge’s report and\\nrecommendation, granted summary judgment in favor of the\\nATF. For the following reasons, we will affirm.\\n\\n Simpson’s appeal presents us with the question of what\\nstandard to apply to determine whether a violation of the GCA\\nwas willful, an issue we have not yet addressed in a\\nprecedential opinion. In a non-precedential opinion, we found\\npersuasive the willfulness standard used by seven other\\ncircuits: knowledge of a legal obligation and purposeful\\ndisregard or plain indifference to it. Taylor v. Hughes, 548 F.\\nApp’x 822, 824 (3d Cir. 2013) (citing Borchardt Rifle Corp. v.\\nCook, 684 F.3d 1037, 1042 n.9 (10th Cir. 2012) (listing cases)).\\nAgreeing with the unanimous view of all the Courts of Appeals\\nto have addressed this issue, we now hold in this precedential\\n\\n\\n\\n\\n 3\\n\\fopinion that this willfulness standard applies to violations of\\nthe GCA. Because it is clear that Simpson knew of and was\\nplainly indifferent to his obligations by committing hundreds\\nof GCA violations, we will affirm the District Court’s ruling.\\n\\n I.\\n\\n Simpson applied for a dealer’s FFL in 2010, which\\nprompted an ATF interview. During the interview, ATF\\nrepresentatives discussed Simpson’s legal responsibilities and\\nobligations as a firearms dealer, covering topics such as\\nacquisition and disposition (“A&D”) recordkeeping, sales to\\nlaw enforcement, out-of-state gun sales, prohibited sales,\\nconsignment of firearms, and personal firearms. At the end of\\nthe meeting, Simpson signed an Acknowledgement of Federal\\nFirearms Regulations, certifying that he understood his\\nresponsibility to learn and follow all laws and regulations\\ngoverning his FFL. Simpson subsequently received an FFL\\nand opened a firearms store, Warrior Ridge Trading\\n\\n In 2011, Simpson attended a seminar for FFL holders,\\nwhere ATF officials discussed federal firearms regulations and\\nshowed sample Firearms Transaction Records. In 2012, after\\nconsulting with the ATF about his desire to assemble AR-15\\nrifles, Simpson applied for an additional FFL to manufacture\\nfirearms. ATF officials met with him and discussed the legal\\nresponsibilities associated with a manufacturer’s license,\\nincluding the duty to mark all manufactured firearms and to\\nkeep a separate manufacturing A&D book. Simpson again\\nsigned an acknowledgement form certifying that he understood\\nhis legal obligations under his additional FFL.\\n\\n In February 2014, Simpson applied to relocate his FFLs\\nbecause he planned to move his firearms store to another\\n\\n\\n\\n\\n 4\\n\\flocation. An ATF Industry Operations Inspector (“IOI”) met\\nwith him and discussed his application. Simpson once again\\nsigned a form acknowledging that he understood his\\nresponsibilities and obligations under the GCA.\\n\\n In April 2014, ATF conducted a compliance inspection\\nof Simpson’s FFLs pursuant to 18 U.S.C. § 923(g)(1)(C). ]\\nAccording to IOI Susan Whitman, this inspection “was the\\nworst [she] ever conducted,” and, based upon her report, the\\nATF decided to revoke Simpson’s FFLs. (App. I 7). Simpson\\nrequested a review of the revocation decision pursuant to 18\\nU.S.C. § 923(f)(2) and 27 C.F.R. § 478.74. After a hearing,\\nATF Director of Industry Operations (“DIO”) Juan Orellana\\nfound that Simpson had committed over 400 willful violations\\nof the GCA. As summarized by the Magistrate Judge, these\\nviolations include:\\n\\n [S]elling or delivering multiple\\n firearms without having completed\\n Firearm Transaction Records,\\n ATF Forms 4473, and without\\n Simpson making the required\\n entries in his [A&D] Book;\\n transferring firearms without\\n conducting background checks;\\n dealing firearms at the Alexandria\\n Sportsman’s Club and in West\\n Virginia without obtaining a\\n license to do so; selling or\\n delivering firearms, firearm\\n frames, or firearm receivers in\\n seven instances to individuals who\\n did not live in Pennsylvania;\\n incorrectly identifying in multiple\\n\\n\\n\\n\\n 5\\n\\f instances the firearms that had\\n been transferred; failing to identify\\n and mark 14 firearms that he\\n manufactured, and failing to make\\n the required records for those\\n manufactured firearms; failing to\\n record the disposition of five\\n firearms to other licensees; failing\\n to record the record of disposition\\n of 30 firearms to non-licensees;\\n failing on over 70 occasions to\\n record required information in his\\n A&D Book; failing in\\n approximately 200 instances to\\n record information on ATF Forms\\n 4473; failing to appropriately sign\\n and date ATF Form 4473 in dozens\\n of cases to indicate that he did not\\n have reasonable cause to believe\\n that a transferee was disqualified\\n from receiving a firearm; and\\n failing to submit an Annual\\n Firearms Manufacturing and\\n Exportation Report (ATF Form\\n 5300.11) in 2012 and 2013.\\n\\n(App. I 7-8; see also App. II 137-98). As such, the ATF issued\\nfinal revocation notices to Simpson.\\n\\n Simpson then filed a petition for judicial review and\\nmoved for an emergency stay of the revocation of his FFLs.\\nThe District Court denied his motion, finding that Simpson was\\nunlikely to “succe[ed] on the merits, given the numerosity and\\ntypes of violations,” and because the court was not “persuaded\\n\\n\\n\\n\\n 6\\n\\fby [Simpson’s] contention that he was inadequately trained by\\n[the ATF].” (App. 9). The case was then referred to a\\nMagistrate Judge for pretrial management. Upon completion\\nof discovery, the parties filed cross-motions for summary\\njudgment.\\n\\n Addressing the cross-motions in a Report and\\nRecommendation, the Magistrate Judge concluded that the\\nATF was authorized to revoke Simpson’s FFLs because he had\\nwillfully committed over 400 violations of the GCA. (App. I\\n33-34). The District Court adopted the report and\\nrecommendation in its entirety, and thus granted summary\\njudgment for the ATF and affirmed its revocation of Simpson’s\\nFFLs. Simpson’s timely appeal followed.\\n\\n\\n\\n II.\\n\\n The District Court had jurisdiction to review the ATF’s\\nrevocation decision under 18 U.S.C. § 923(f), 5 U.S.C. § 702,\\nand 28 U.S.C. § 1331. We have appellate jurisdiction pursuant\\nto 28 U.S.C. § 1291. We exercise de novo review over the\\nDistrict Court’s grant of summary judgment. See, e.g., Kelly\\nv. Borough of Carlisle, 622 F.3d 248, 253 (3d Cir. 2010). A\\ngrant of summary judgment is warranted “if the movant shows\\nthat there is no genuine dispute as to any material fact and the\\nmovant is entitled to judgment as a matter of law.” Fed. R.\\nCiv. P. 56(a). Further, an administrative record “enjoys a\\npresumption of veracity” at summary judgment. Am. Arms\\nInt’l v. Herbert, 563 F.3d 78, 86 n.12 (4th Cir. 2009) (citation\\nomitted).\\n\\n\\n\\n\\n 7\\n\\f III.\\n\\n Under the GCA, the ATF may revoke an FFL if the\\nlicense holder willfully violated any provision of the GCA or\\nany rule or regulation prescribed under the GCA. 18 U.S.C.\\n§ 923(e); see also 27 C.F.R. § 478.73. “A single willful\\nviolation [of the GCA] authorizes the ATF to revoke the\\nviolator’s FFL, regardless of how severe . . . .” Fairmont Cash\\nMgmt., L.L.C. v. James, 858 F.3d 356, 362 (5th Cir. 2017).\\nThus, in the GCA context, our review of the District Court’s\\ngrant of summary judgment requires us to determine whether\\nthere was no genuine dispute as to any material fact\\nestablishing even one willful violation of the GCA. See Am.\\nArms, 563 F.3d at 86 (noting that “a single uncontested\\nviolation suffices to uphold” summary judgment for the ATF\\n(citing Armalite, Inc. v. Lambert, 544 F.3d 644, 649 (6th Cir.\\n2008))).\\n\\n Eight other Courts of Appeals have held that a violation\\nof the GCA is willful where the licensee knew of his legal\\nobligation and purposefully disregarded or was plainly\\nindifferent to the requirements. See Borchardt Rifle, 684 F.3d\\nat 1042; Fairmont Cash Mgmt., 858 F.3d at 362; Armalite, 544\\nF.3d at 647; RSM, Inc. v. Herbert, 466 F.3d 316, 317 (4th Cir.\\n2006); Article II Gun Shop, Inc. v. Gonzales, 441 F.3d 492, 497\\n(7th Cir. 2006); Willingham Sports, Inc. v. ATF, 415 F.3d 1274,\\n1277 (11th Cir. 2005); Perri v. ATF, 637 F.2d 1332, 1336 (9th\\nCir. 1981); Lewin v. Blumenthal, 590 F.2d 268, 269 (8th Cir.\\n1979). We find this definition of willfulness to be appropriate.\\nIndeed, this standard mirrors the willfulness standard we have\\napplied in the parallel context of ATF revocations of fireworks\\nand explosives licenses for violations of federal explosives\\nlaws. See Vineland Fireworks Co. v. ATF, 544 F.3d 509, 517–\\n19 (upholding the ATF’s interpretation of willful because it\\n\\n\\n\\n\\n 8\\n\\fwas reasonable).1 In Vineland, we upheld that willfulness\\n“do[es] not require a bad purpose,” or an intent to disobey the\\nlaw, but rather willfulness can be established by a mere\\n“violation of the regulations with knowledge of their\\nrequirements.” Id. Moreover, both parties in this case agree\\nwith this willfulness standard. Accordingly, we now join our\\nsister circuits in holding that a violation of the GCA is willful\\nwhere the licensee: (1) knew of his legal obligation under the\\nGCA, and (2) either purposefully disregarded or was plainly\\nindifferent to GCA requirements.\\n\\n Here, Simpson has been charged with willfully\\nviolating the GCA over 400 times. He contends that he did not\\nfully understand his obligations and that any violations he\\ncommitted were not willful, but due to mistake or ignorance.\\nWe disagree, as the record indicates that Simpson was well\\napprised of his duties under the GCA but continually violated\\nGCA recordkeeping, manufacturing, and sales requirements.\\n\\n\\n\\n 1\\n In Vineland, we deferred to the ATF’s interpretation\\nof willfulness under federal explosives law because we found\\nit reasonable. See Vineland, 544 F.3d at 518 n.17. Our review\\nof explosives licensing decisions is governed only by 5 U.S.C.\\n§ 706, so we apply Chevron deference to reasonable agency\\ndecisions. See 18 U.S.C. § 843(e)(2); see also Chevron,\\nU.S.A., Inc. v. Nat. Res. Def. Council, Inc., 467 U.S. 837\\n(1984). In contrast, the GCA explicitly tasks courts with\\nconducting de novo review of ATF licensing denials or\\nrevocations. See 18 U.S.C. § 923(f)(3). As such, we review\\ndistrict court decisions regarding ATF firearms licensing de\\nnovo. See, e.g., Willingham Sports, 415 F.3d at 1275-76.\\n\\n\\n\\n\\n 9\\n\\f A.\\n\\n The record shows that Simpson was informed of his\\nobligations as an FFL licensee. For example, Simpson met\\nwith ATF officials three times about his FFLs and, at the\\nconclusion of each meeting, he signed a form acknowledging\\nthat he discussed various regulatory topics with the ATF. In\\naddition, Simpson attended an ATF seminar for FFL holders\\nwhere he learned more about his obligations under the GCA.\\n\\n The record also demonstrates that Simpson often\\ncomplied with GCA requirements. On numerous occasions,\\nSimpson lawfully sold firearms and fully completed the A&D\\nrecordkeeping required under the GCA. Also, he applied to\\nrelocate his FFL, demonstrating that he knew that he was only\\nallowed to sell firearms from his approved FFL location. His\\nfull compliance with GCA requirements in some instances\\nbelies his assertion that he did not understand those\\nrequirements.\\n\\n Further, some of Simpson’s actions illustrate that he\\nunderstood the GCA regulatory scheme quite well. For\\nexample, he sometimes transferred firearms from his FFL\\ninventory to his personal collection, thereby taking advantage\\nof a statutory loophole that allowed him to later sell the\\nfirearms at gun shows without conducting background checks.\\nSuch action is inconsistent with that of a person who does not\\nunderstand the GCA regulatory scheme. Accordingly, we find\\nthat no reasonable fact-finder could disagree that Simpson\\nknew and understood his GCA obligations as an FFL licensee.\\n\\n\\n\\n\\n 10\\n\\f B.\\n\\n In this case, the ATF has alleged that Simpson was\\nplainly indifferent to the GCA’s requirements. We must\\ntherefore determine what constitutes plain indifference under\\nthe willfulness standard we have adopted.\\n\\n Plain indifference is demonstrated by “a lack of concern\\nfor [GCA] regulations. . . .” Am. Arms Int’l, 563 F.3d at 87. A\\nlack of concern may be shown by circumstantial evidence—\\nsuch as repeated violations or a large quantity of violations.\\nSee, e.g., Borchardt Rifle, 684 F.3d at 1043–44; Am. Arms\\nInt’l, 563 F.3d at 87; On Target Sporting Goods, Inc. v. Att’y\\nGen., 472 F.3d 572, 575 (8th Cir. 2007); RSM, Inc., 466 F.3d\\nat 322; Willingham Sports, 415 F.3d at 1277.\\n\\n The ATF charged Simpson with willfully violating a\\nlong list of separate provisions of the GCA under his\\nmanufacturer’s FFL, including, inter alia:\\n\\n (a) selling firearms without completing Form 4473s;\\n (b) selling or delivering firearms without recording the\\n disposition in his A&D book;\\n (c) transferring firearms without conducting\\n background checks;\\n (d) dealing firearms outside of his FFL premises;\\n (e) selling or delivering firearms to non-Pennsylvania\\n residents;\\n (f) transferring firearms and misidentifying\\n corresponding A&D entries;\\n (g) failing to identify and mark manufactured firearms;\\n (h) failing to record the manufacture of firearms in his\\n A&D book;\\n\\n\\n\\n\\n 11\\n\\f (i) failing to record dispositions of firearms to FFL\\n holders and non-licensees;\\n (j) failing to complete all fields of Form 4473s; and\\n (k) failing to sign and date Form 4473s.\\n\\n(See App. I 8). Additionally, the ATF charged Simpson with\\nwillfully violating another series of provisions of the GCA\\nunder his dealer’s FFL. These include, inter alia:\\n\\n (a) selling firearms without completing Form 4473s;\\n (b) selling or delivering firearms without recording the\\n disposition in his A&D book;\\n (c) transferring firearms without conducting\\n background checks;\\n (d) selling firearms in West Virginia;\\n (e) selling or delivering firearms to non-Pennsylvania\\n residents\\n (f) purchasing firearms without recording the purchases\\n in his A&D book;\\n (g) failing to complete all fields of Form 4473s; and\\n (h) failing to sign and date Form 4473s.\\n\\nId.\\n\\n Simpson contends that all of these violations either were\\nmere mistakes or were due to his “fundamental\\nmisunderstanding as to the importance” of GCA recordkeeping\\nrequirements. (Appellant’s Br. 35). However, in view of the\\nfact that Simpson received training on his obligations and\\nexplicitly acknowledged that he understood his GCA\\nobligations, the sheer number and continuing nature of the\\nviolations clearly demonstrate Simpson’s plain indifference to\\nthe GCA’s requirements.\\n\\n\\n\\n\\n 12\\n\\f While there is no dispute that Simpson violated the\\nGCA on numerous occasions, there is also evidence of other\\nfirearms transactions in which Simpson fully complied with\\nGCA requirements by completing, signing, and dating Form\\n4473s, recording the dispositions in his A&D book, and\\nconducting background checks. This inconsistent conduct\\nsuggests both that Simpson knew of his obligations and was\\nindifferent to complying with them. Moreover, there is\\nevidence of blatant GCA violations. For example, Simpson\\nroutinely transferred receivers to out-of-state residents—in\\nclear violation of the GCA—but falsely recorded the transfers\\nas rifle sales in his A&D book, making these transactions\\nappear lawful. Such behavior is indicative of Simpson’s lack\\nof concern for his GCA obligations as an FFL holder.\\n\\n In sum, the record sufficiently shows that Simpson had\\nknowledge of his FFL obligations, yet acted plainly\\nindifferently to them, thus willfully violating the GCA.\\nAccordingly, we find that the ATF was authorized to revoke\\nSimpson’s FFLs.\\n\\n\\n\\n IV.\\n\\n For the foregoing reasons we will affirm the District\\nCourt’s grant of summary judgment in favor of the ATF,\\naffirming its revocation of Simpson’s FFLs.\\n\\n\\n\\n\\n 13\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4355861/\", \"author_raw\": \"VANASKIE, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"CHAGARES"},"judge2":{"kind":"string","value":"JORDAN"},"judge3":{"kind":"string","value":"VANASKIE"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4578608/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: John F. SIMPSON, T/A Warrior Ridge Trading; T/A LCT Pro Shop v. ATTORNEY GENERAL UNITED STATES OF AMERICA; Director, Bureau of Alcohol, Tobacco, Firearms & Explosives; Director of Industry Operations, Bureau of Alcohol, Tobacco, Firearms & Explosives; United States of America John F. Simpson, Appellant\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-03\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-3718\n _____________\n\nJOHN F. SIMPSON, t/a Warrior Ridge Trading; t/a LCT Pro Shop\n\n v.\n\n ATTORNEY GENERAL UNITED STATES OF AMERICA;\nDIRECTOR, BUREAU OF ALCOHOL, TOBACCO, FIREARMS\n & EXPLOSIVES; DIRECTOR OF INDUSTRY OPERATIONS,\n BUREAU OF ALCOHOL, TOBACCO, FIREARMS &\n EXPLOSIVES; UNITED STATES OF AMERICA\n\n John F. Simpson,\n Appellant\n\n _____________\n\n On Appeal from the United States District Court\n for the Middle District of Pennsylvania\n District Judge: Honorable John E. Jones, III\n (D.C. Civil No. 1-15-mc-00297)\n ______________\n\n Argued October 30, 2018\n ______________\n\f Before: CHAGARES, JORDAN, and VANASKIE, Circuit\n Judges\n\n (Opinion Filed: January 3, 2019)\n\nAdam J. Kraut\nJoshua Prince [ARGUED]\nPrince Law Offices\n646 Lenape Road\nBechtelsville, PA 19505\n Counsel for Appellant\n\nDavid J. Freed\nUnited States Attorney\nCarlo D. Marchioli [ARGUED]\nKate L. Mershimer\nOffice of United States Attorney\n228 Walnut Street, P.O. Box 11754\n220 Federal Building and Courthouse\nHarrisburg, PA 17108\n\nJeffrey A. Cohen\nATF Associate Chief Counsel\nJohn Kevin White\nATF Division Counsel\n601 Walnut Street, Suite 1000E\nPhiladelphia, PA 19106\n Counsel for Appellees\n\n\n\n The Honorable Judge Vanaskie transmitted the opinion to the\nClerk for filing prior to retiring from the bench on January 1, 2019.\nDue to the intervening holiday, the opinion has been entered on the\ndocket by the Clerk this day.\n\n\n\n\n 2\n\f ________________\n\n OPINION\n ________________\n\nVANASKIE, Circuit Judge.\n\n Appellant John Simpson appeals the District Court’s\norder granting summary judgment for Appellees and affirming\nthe Bureau of Alcohol, Tobacco, Firearms & Explosives’\n(“ATF”) revocation of his federal firearms licenses (“FFLs”).\nAfter an annual compliance investigation, the ATF determined\nthat Simpson had committed over 400 willful violations of the\nGun Control Act of 1968, 18 U.S.C. § 921 et seq. (“GCA”),\nand therefore revoked his FFLs pursuant to 18 U.S.C. § 923(e)\nand 27 C.F.R. § 478.73. After an administrative hearing, the\nATF affirmed its revocation decision and Simpson filed a\npetition for judicial review under 18 U.S.C. § 923(f)(3). The\nDistrict Court, adopting a Magistrate Judge’s report and\nrecommendation, granted summary judgment in favor of the\nATF. For the following reasons, we will affirm.\n\n Simpson’s appeal presents us with the question of what\nstandard to apply to determine whether a violation of the GCA\nwas willful, an issue we have not yet addressed in a\nprecedential opinion. In a non-precedential opinion, we found\npersuasive the willfulness standard used by seven other\ncircuits: knowledge of a legal obligation and purposeful\ndisregard or plain indifference to it. Taylor v. Hughes, 548 F.\nApp’x 822, 824 (3d Cir. 2013) (citing Borchardt Rifle Corp. v.\nCook, 684 F.3d 1037, 1042 n.9 (10th Cir. 2012) (listing cases)).\nAgreeing with the unanimous view of all the Courts of Appeals\nto have addressed this issue, we now hold in this precedential\n\n\n\n\n 3\n\fopinion that this willfulness standard applies to violations of\nthe GCA. Because it is clear that Simpson knew of and was\nplainly indifferent to his obligations by committing hundreds\nof GCA violations, we will affirm the District Court’s ruling.\n\n I.\n\n Simpson applied for a dealer’s FFL in 2010, which\nprompted an ATF interview. During the interview, ATF\nrepresentatives discussed Simpson’s legal responsibilities and\nobligations as a firearms dealer, covering topics such as\nacquisition and disposition (“A&D”) recordkeeping, sales to\nlaw enforcement, out-of-state gun sales, prohibited sales,\nconsignment of firearms, and personal firearms. At the end of\nthe meeting, Simpson signed an Acknowledgement of Federal\nFirearms Regulations, certifying that he understood his\nresponsibility to learn and follow all laws and regulations\ngoverning his FFL. Simpson subsequently received an FFL\nand opened a firearms store, Warrior Ridge Trading\n\n In 2011, Simpson attended a seminar for FFL holders,\nwhere ATF officials discussed federal firearms regulations and\nshowed sample Firearms Transaction Records. In 2012, after\nconsulting with the ATF about his desire to assemble AR-15\nrifles, Simpson applied for an additional FFL to manufacture\nfirearms. ATF officials met with him and discussed the legal\nresponsibilities associated with a manufacturer’s license,\nincluding the duty to mark all manufactured firearms and to\nkeep a separate manufacturing A&D book. Simpson again\nsigned an acknowledgement form certifying that he understood\nhis legal obligations under his additional FFL.\n\n In February 2014, Simpson applied to relocate his FFLs\nbecause he planned to move his firearms store to another\n\n\n\n\n 4\n\flocation. An ATF Industry Operations Inspector (“IOI”) met\nwith him and discussed his application. Simpson once again\nsigned a form acknowledging that he understood his\nresponsibilities and obligations under the GCA.\n\n In April 2014, ATF conducted a compliance inspection\nof Simpson’s FFLs pursuant to 18 U.S.C. § 923(g)(1)(C). ]\nAccording to IOI Susan Whitman, this inspection “was the\nworst [she] ever conducted,” and, based upon her report, the\nATF decided to revoke Simpson’s FFLs. (App. I 7). Simpson\nrequested a review of the revocation decision pursuant to 18\nU.S.C. § 923(f)(2) and 27 C.F.R. § 478.74. After a hearing,\nATF Director of Industry Operations (“DIO”) Juan Orellana\nfound that Simpson had committed over 400 willful violations\nof the GCA. As summarized by the Magistrate Judge, these\nviolations include:\n\n [S]elling or delivering multiple\n firearms without having completed\n Firearm Transaction Records,\n ATF Forms 4473, and without\n Simpson making the required\n entries in his [A&D] Book;\n transferring firearms without\n conducting background checks;\n dealing firearms at the Alexandria\n Sportsman’s Club and in West\n Virginia without obtaining a\n license to do so; selling or\n delivering firearms, firearm\n frames, or firearm receivers in\n seven instances to individuals who\n did not live in Pennsylvania;\n incorrectly identifying in multiple\n\n\n\n\n 5\n\f instances the firearms that had\n been transferred; failing to identify\n and mark 14 firearms that he\n manufactured, and failing to make\n the required records for those\n manufactured firearms; failing to\n record the disposition of five\n firearms to other licensees; failing\n to record the record of disposition\n of 30 firearms to non-licensees;\n failing on over 70 occasions to\n record required information in his\n A&D Book; failing in\n approximately 200 instances to\n record information on ATF Forms\n 4473; failing to appropriately sign\n and date ATF Form 4473 in dozens\n of cases to indicate that he did not\n have reasonable cause to believe\n that a transferee was disqualified\n from receiving a firearm; and\n failing to submit an Annual\n Firearms Manufacturing and\n Exportation Report (ATF Form\n 5300.11) in 2012 and 2013.\n\n(App. I 7-8; see also App. II 137-98). As such, the ATF issued\nfinal revocation notices to Simpson.\n\n Simpson then filed a petition for judicial review and\nmoved for an emergency stay of the revocation of his FFLs.\nThe District Court denied his motion, finding that Simpson was\nunlikely to “succe[ed] on the merits, given the numerosity and\ntypes of violations,” and because the court was not “persuaded\n\n\n\n\n 6\n\fby [Simpson’s] contention that he was inadequately trained by\n[the ATF].” (App. 9). The case was then referred to a\nMagistrate Judge for pretrial management. Upon completion\nof discovery, the parties filed cross-motions for summary\njudgment.\n\n Addressing the cross-motions in a Report and\nRecommendation, the Magistrate Judge concluded that the\nATF was authorized to revoke Simpson’s FFLs because he had\nwillfully committed over 400 violations of the GCA. (App. I\n33-34). The District Court adopted the report and\nrecommendation in its entirety, and thus granted summary\njudgment for the ATF and affirmed its revocation of Simpson’s\nFFLs. Simpson’s timely appeal followed.\n\n\n\n II.\n\n The District Court had jurisdiction to review the ATF’s\nrevocation decision under 18 U.S.C. § 923(f), 5 U.S.C. § 702,\nand 28 U.S.C. § 1331. We have appellate jurisdiction pursuant\nto 28 U.S.C. § 1291. We exercise de novo review over the\nDistrict Court’s grant of summary judgment. See, e.g., Kelly\nv. Borough of Carlisle, 622 F.3d 248, 253 (3d Cir. 2010). A\ngrant of summary judgment is warranted “if the movant shows\nthat there is no genuine dispute as to any material fact and the\nmovant is entitled to judgment as a matter of law.” Fed. R.\nCiv. P. 56(a). Further, an administrative record “enjoys a\npresumption of veracity” at summary judgment. Am. Arms\nInt’l v. Herbert, 563 F.3d 78, 86 n.12 (4th Cir. 2009) (citation\nomitted).\n\n\n\n\n 7\n\f III.\n\n Under the GCA, the ATF may revoke an FFL if the\nlicense holder willfully violated any provision of the GCA or\nany rule or regulation prescribed under the GCA. 18 U.S.C.\n§ 923(e); see also 27 C.F.R. § 478.73. “A single willful\nviolation [of the GCA] authorizes the ATF to revoke the\nviolator’s FFL, regardless of how severe . . . .” Fairmont Cash\nMgmt., L.L.C. v. James, 858 F.3d 356, 362 (5th Cir. 2017).\nThus, in the GCA context, our review of the District Court’s\ngrant of summary judgment requires us to determine whether\nthere was no genuine dispute as to any material fact\nestablishing even one willful violation of the GCA. See Am.\nArms, 563 F.3d at 86 (noting that “a single uncontested\nviolation suffices to uphold” summary judgment for the ATF\n(citing Armalite, Inc. v. Lambert, 544 F.3d 644, 649 (6th Cir.\n2008))).\n\n Eight other Courts of Appeals have held that a violation\nof the GCA is willful where the licensee knew of his legal\nobligation and purposefully disregarded or was plainly\nindifferent to the requirements. See Borchardt Rifle, 684 F.3d\nat 1042; Fairmont Cash Mgmt., 858 F.3d at 362; Armalite, 544\nF.3d at 647; RSM, Inc. v. Herbert, 466 F.3d 316, 317 (4th Cir.\n2006); Article II Gun Shop, Inc. v. Gonzales, 441 F.3d 492, 497\n(7th Cir. 2006); Willingham Sports, Inc. v. ATF, 415 F.3d 1274,\n1277 (11th Cir. 2005); Perri v. ATF, 637 F.2d 1332, 1336 (9th\nCir. 1981); Lewin v. Blumenthal, 590 F.2d 268, 269 (8th Cir.\n1979). We find this definition of willfulness to be appropriate.\nIndeed, this standard mirrors the willfulness standard we have\napplied in the parallel context of ATF revocations of fireworks\nand explosives licenses for violations of federal explosives\nlaws. See Vineland Fireworks Co. v. ATF, 544 F.3d 509, 517–\n19 (upholding the ATF’s interpretation of willful because it\n\n\n\n\n 8\n\fwas reasonable).1 In Vineland, we upheld that willfulness\n“do[es] not require a bad purpose,” or an intent to disobey the\nlaw, but rather willfulness can be established by a mere\n“violation of the regulations with knowledge of their\nrequirements.” Id. Moreover, both parties in this case agree\nwith this willfulness standard. Accordingly, we now join our\nsister circuits in holding that a violation of the GCA is willful\nwhere the licensee: (1) knew of his legal obligation under the\nGCA, and (2) either purposefully disregarded or was plainly\nindifferent to GCA requirements.\n\n Here, Simpson has been charged with willfully\nviolating the GCA over 400 times. He contends that he did not\nfully understand his obligations and that any violations he\ncommitted were not willful, but due to mistake or ignorance.\nWe disagree, as the record indicates that Simpson was well\napprised of his duties under the GCA but continually violated\nGCA recordkeeping, manufacturing, and sales requirements.\n\n\n\n 1\n In Vineland, we deferred to the ATF’s interpretation\nof willfulness under federal explosives law because we found\nit reasonable. See Vineland, 544 F.3d at 518 n.17. Our review\nof explosives licensing decisions is governed only by 5 U.S.C.\n§ 706, so we apply Chevron deference to reasonable agency\ndecisions. See 18 U.S.C. § 843(e)(2); see also Chevron,\nU.S.A., Inc. v. Nat. Res. Def. Council, Inc., 467 U.S. 837\n(1984). In contrast, the GCA explicitly tasks courts with\nconducting de novo review of ATF licensing denials or\nrevocations. See 18 U.S.C. § 923(f)(3). As such, we review\ndistrict court decisions regarding ATF firearms licensing de\nnovo. See, e.g., Willingham Sports, 415 F.3d at 1275-76.\n\n\n\n\n 9\n\f A.\n\n The record shows that Simpson was informed of his\nobligations as an FFL licensee. For example, Simpson met\nwith ATF officials three times about his FFLs and, at the\nconclusion of each meeting, he signed a form acknowledging\nthat he discussed various regulatory topics with the ATF. In\naddition, Simpson attended an ATF seminar for FFL holders\nwhere he learned more about his obligations under the GCA.\n\n The record also demonstrates that Simpson often\ncomplied with GCA requirements. On numerous occasions,\nSimpson lawfully sold firearms and fully completed the A&D\nrecordkeeping required under the GCA. Also, he applied to\nrelocate his FFL, demonstrating that he knew that he was only\nallowed to sell firearms from his approved FFL location. His\nfull compliance with GCA requirements in some instances\nbelies his assertion that he did not understand those\nrequirements.\n\n Further, some of Simpson’s actions illustrate that he\nunderstood the GCA regulatory scheme quite well. For\nexample, he sometimes transferred firearms from his FFL\ninventory to his personal collection, thereby taking advantage\nof a statutory loophole that allowed him to later sell the\nfirearms at gun shows without conducting background checks.\nSuch action is inconsistent with that of a person who does not\nunderstand the GCA regulatory scheme. Accordingly, we find\nthat no reasonable fact-finder could disagree that Simpson\nknew and understood his GCA obligations as an FFL licensee.\n\n\n\n\n 10\n\f B.\n\n In this case, the ATF has alleged that Simpson was\nplainly indifferent to the GCA’s requirements. We must\ntherefore determine what constitutes plain indifference under\nthe willfulness standard we have adopted.\n\n Plain indifference is demonstrated by “a lack of concern\nfor [GCA] regulations. . . .” Am. Arms Int’l, 563 F.3d at 87. A\nlack of concern may be shown by circumstantial evidence—\nsuch as repeated violations or a large quantity of violations.\nSee, e.g., Borchardt Rifle, 684 F.3d at 1043–44; Am. Arms\nInt’l, 563 F.3d at 87; On Target Sporting Goods, Inc. v. Att’y\nGen., 472 F.3d 572, 575 (8th Cir. 2007); RSM, Inc., 466 F.3d\nat 322; Willingham Sports, 415 F.3d at 1277.\n\n The ATF charged Simpson with willfully violating a\nlong list of separate provisions of the GCA under his\nmanufacturer’s FFL, including, inter alia:\n\n (a) selling firearms without completing Form 4473s;\n (b) selling or delivering firearms without recording the\n disposition in his A&D book;\n (c) transferring firearms without conducting\n background checks;\n (d) dealing firearms outside of his FFL premises;\n (e) selling or delivering firearms to non-Pennsylvania\n residents;\n (f) transferring firearms and misidentifying\n corresponding A&D entries;\n (g) failing to identify and mark manufactured firearms;\n (h) failing to record the manufacture of firearms in his\n A&D book;\n\n\n\n\n 11\n\f (i) failing to record dispositions of firearms to FFL\n holders and non-licensees;\n (j) failing to complete all fields of Form 4473s; and\n (k) failing to sign and date Form 4473s.\n\n(See App. I 8). Additionally, the ATF charged Simpson with\nwillfully violating another series of provisions of the GCA\nunder his dealer’s FFL. These include, inter alia:\n\n (a) selling firearms without completing Form 4473s;\n (b) selling or delivering firearms without recording the\n disposition in his A&D book;\n (c) transferring firearms without conducting\n background checks;\n (d) selling firearms in West Virginia;\n (e) selling or delivering firearms to non-Pennsylvania\n residents\n (f) purchasing firearms without recording the purchases\n in his A&D book;\n (g) failing to complete all fields of Form 4473s; and\n (h) failing to sign and date Form 4473s.\n\nId.\n\n Simpson contends that all of these violations either were\nmere mistakes or were due to his “fundamental\nmisunderstanding as to the importance” of GCA recordkeeping\nrequirements. (Appellant’s Br. 35). However, in view of the\nfact that Simpson received training on his obligations and\nexplicitly acknowledged that he understood his GCA\nobligations, the sheer number and continuing nature of the\nviolations clearly demonstrate Simpson’s plain indifference to\nthe GCA’s requirements.\n\n\n\n\n 12\n\f While there is no dispute that Simpson violated the\nGCA on numerous occasions, there is also evidence of other\nfirearms transactions in which Simpson fully complied with\nGCA requirements by completing, signing, and dating Form\n4473s, recording the dispositions in his A&D book, and\nconducting background checks. This inconsistent conduct\nsuggests both that Simpson knew of his obligations and was\nindifferent to complying with them. Moreover, there is\nevidence of blatant GCA violations. For example, Simpson\nroutinely transferred receivers to out-of-state residents—in\nclear violation of the GCA—but falsely recorded the transfers\nas rifle sales in his A&D book, making these transactions\nappear lawful. Such behavior is indicative of Simpson’s lack\nof concern for his GCA obligations as an FFL holder.\n\n In sum, the record sufficiently shows that Simpson had\nknowledge of his FFL obligations, yet acted plainly\nindifferently to them, thus willfully violating the GCA.\nAccordingly, we find that the ATF was authorized to revoke\nSimpson’s FFLs.\n\n\n\n IV.\n\n For the foregoing reasons we will affirm the District\nCourt’s grant of summary judgment in favor of the ATF,\naffirming its revocation of Simpson’s FFLs.\n\n\n\n\n 13\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: John F. SIMPSON, T/A Warrior Ridge Trading; T/A LCT Pro Shop v. ATTORNEY GENERAL UNITED STATES OF AMERICA; Director, Bureau of Alcohol, Tobacco, Firearms & Explosives; Director of Industry Operations, Bureau of Alcohol, Tobacco, Firearms & Explosives; United States of America John F. Simpson, Appellant\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-03\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-3718\\n _____________\\n\\nJOHN F. SIMPSON, t/a Warrior Ridge Trading; t/a LCT Pro Shop\\n\\n v.\\n\\n ATTORNEY GENERAL UNITED STATES OF AMERICA;\\nDIRECTOR, BUREAU OF ALCOHOL, TOBACCO, FIREARMS\\n & EXPLOSIVES; DIRECTOR OF INDUSTRY OPERATIONS,\\n BUREAU OF ALCOHOL, TOBACCO, FIREARMS &\\n EXPLOSIVES; UNITED STATES OF AMERICA\\n\\n John F. Simpson,\\n Appellant\\n\\n _____________\\n\\n On Appeal from the United States District Court\\n for the Middle District of Pennsylvania\\n District Judge: Honorable John E. Jones, III\\n (D.C. Civil No. 1-15-mc-00297)\\n ______________\\n\\n Argued October 30, 2018\\n ______________\\n\\f Before: CHAGARES, JORDAN, and VANASKIE, Circuit\\n Judges\\n\\n (Opinion Filed: January 3, 2019)\\n\\nAdam J. Kraut\\nJoshua Prince [ARGUED]\\nPrince Law Offices\\n646 Lenape Road\\nBechtelsville, PA 19505\\n Counsel for Appellant\\n\\nDavid J. Freed\\nUnited States Attorney\\nCarlo D. Marchioli [ARGUED]\\nKate L. Mershimer\\nOffice of United States Attorney\\n228 Walnut Street, P.O. Box 11754\\n220 Federal Building and Courthouse\\nHarrisburg, PA 17108\\n\\nJeffrey A. Cohen\\nATF Associate Chief Counsel\\nJohn Kevin White\\nATF Division Counsel\\n601 Walnut Street, Suite 1000E\\nPhiladelphia, PA 19106\\n Counsel for Appellees\\n\\n\\n\\n The Honorable Judge Vanaskie transmitted the opinion to the\\nClerk for filing prior to retiring from the bench on January 1, 2019.\\nDue to the intervening holiday, the opinion has been entered on the\\ndocket by the Clerk this day.\\n\\n\\n\\n\\n 2\\n\\f ________________\\n\\n OPINION\\n ________________\\n\\nVANASKIE, Circuit Judge.\\n\\n Appellant John Simpson appeals the District Court’s\\norder granting summary judgment for Appellees and affirming\\nthe Bureau of Alcohol, Tobacco, Firearms & Explosives’\\n(“ATF”) revocation of his federal firearms licenses (“FFLs”).\\nAfter an annual compliance investigation, the ATF determined\\nthat Simpson had committed over 400 willful violations of the\\nGun Control Act of 1968, 18 U.S.C. § 921 et seq. (“GCA”),\\nand therefore revoked his FFLs pursuant to 18 U.S.C. § 923(e)\\nand 27 C.F.R. § 478.73. After an administrative hearing, the\\nATF affirmed its revocation decision and Simpson filed a\\npetition for judicial review under 18 U.S.C. § 923(f)(3). The\\nDistrict Court, adopting a Magistrate Judge’s report and\\nrecommendation, granted summary judgment in favor of the\\nATF. For the following reasons, we will affirm.\\n\\n Simpson’s appeal presents us with the question of what\\nstandard to apply to determine whether a violation of the GCA\\nwas willful, an issue we have not yet addressed in a\\nprecedential opinion. In a non-precedential opinion, we found\\npersuasive the willfulness standard used by seven other\\ncircuits: knowledge of a legal obligation and purposeful\\ndisregard or plain indifference to it. Taylor v. Hughes, 548 F.\\nApp’x 822, 824 (3d Cir. 2013) (citing Borchardt Rifle Corp. v.\\nCook, 684 F.3d 1037, 1042 n.9 (10th Cir. 2012) (listing cases)).\\nAgreeing with the unanimous view of all the Courts of Appeals\\nto have addressed this issue, we now hold in this precedential\\n\\n\\n\\n\\n 3\\n\\fopinion that this willfulness standard applies to violations of\\nthe GCA. Because it is clear that Simpson knew of and was\\nplainly indifferent to his obligations by committing hundreds\\nof GCA violations, we will affirm the District Court’s ruling.\\n\\n I.\\n\\n Simpson applied for a dealer’s FFL in 2010, which\\nprompted an ATF interview. During the interview, ATF\\nrepresentatives discussed Simpson’s legal responsibilities and\\nobligations as a firearms dealer, covering topics such as\\nacquisition and disposition (“A&D”) recordkeeping, sales to\\nlaw enforcement, out-of-state gun sales, prohibited sales,\\nconsignment of firearms, and personal firearms. At the end of\\nthe meeting, Simpson signed an Acknowledgement of Federal\\nFirearms Regulations, certifying that he understood his\\nresponsibility to learn and follow all laws and regulations\\ngoverning his FFL. Simpson subsequently received an FFL\\nand opened a firearms store, Warrior Ridge Trading\\n\\n In 2011, Simpson attended a seminar for FFL holders,\\nwhere ATF officials discussed federal firearms regulations and\\nshowed sample Firearms Transaction Records. In 2012, after\\nconsulting with the ATF about his desire to assemble AR-15\\nrifles, Simpson applied for an additional FFL to manufacture\\nfirearms. ATF officials met with him and discussed the legal\\nresponsibilities associated with a manufacturer’s license,\\nincluding the duty to mark all manufactured firearms and to\\nkeep a separate manufacturing A&D book. Simpson again\\nsigned an acknowledgement form certifying that he understood\\nhis legal obligations under his additional FFL.\\n\\n In February 2014, Simpson applied to relocate his FFLs\\nbecause he planned to move his firearms store to another\\n\\n\\n\\n\\n 4\\n\\flocation. An ATF Industry Operations Inspector (“IOI”) met\\nwith him and discussed his application. Simpson once again\\nsigned a form acknowledging that he understood his\\nresponsibilities and obligations under the GCA.\\n\\n In April 2014, ATF conducted a compliance inspection\\nof Simpson’s FFLs pursuant to 18 U.S.C. § 923(g)(1)(C). ]\\nAccording to IOI Susan Whitman, this inspection “was the\\nworst [she] ever conducted,” and, based upon her report, the\\nATF decided to revoke Simpson’s FFLs. (App. I 7). Simpson\\nrequested a review of the revocation decision pursuant to 18\\nU.S.C. § 923(f)(2) and 27 C.F.R. § 478.74. After a hearing,\\nATF Director of Industry Operations (“DIO”) Juan Orellana\\nfound that Simpson had committed over 400 willful violations\\nof the GCA. As summarized by the Magistrate Judge, these\\nviolations include:\\n\\n [S]elling or delivering multiple\\n firearms without having completed\\n Firearm Transaction Records,\\n ATF Forms 4473, and without\\n Simpson making the required\\n entries in his [A&D] Book;\\n transferring firearms without\\n conducting background checks;\\n dealing firearms at the Alexandria\\n Sportsman’s Club and in West\\n Virginia without obtaining a\\n license to do so; selling or\\n delivering firearms, firearm\\n frames, or firearm receivers in\\n seven instances to individuals who\\n did not live in Pennsylvania;\\n incorrectly identifying in multiple\\n\\n\\n\\n\\n 5\\n\\f instances the firearms that had\\n been transferred; failing to identify\\n and mark 14 firearms that he\\n manufactured, and failing to make\\n the required records for those\\n manufactured firearms; failing to\\n record the disposition of five\\n firearms to other licensees; failing\\n to record the record of disposition\\n of 30 firearms to non-licensees;\\n failing on over 70 occasions to\\n record required information in his\\n A&D Book; failing in\\n approximately 200 instances to\\n record information on ATF Forms\\n 4473; failing to appropriately sign\\n and date ATF Form 4473 in dozens\\n of cases to indicate that he did not\\n have reasonable cause to believe\\n that a transferee was disqualified\\n from receiving a firearm; and\\n failing to submit an Annual\\n Firearms Manufacturing and\\n Exportation Report (ATF Form\\n 5300.11) in 2012 and 2013.\\n\\n(App. I 7-8; see also App. II 137-98). As such, the ATF issued\\nfinal revocation notices to Simpson.\\n\\n Simpson then filed a petition for judicial review and\\nmoved for an emergency stay of the revocation of his FFLs.\\nThe District Court denied his motion, finding that Simpson was\\nunlikely to “succe[ed] on the merits, given the numerosity and\\ntypes of violations,” and because the court was not “persuaded\\n\\n\\n\\n\\n 6\\n\\fby [Simpson’s] contention that he was inadequately trained by\\n[the ATF].” (App. 9). The case was then referred to a\\nMagistrate Judge for pretrial management. Upon completion\\nof discovery, the parties filed cross-motions for summary\\njudgment.\\n\\n Addressing the cross-motions in a Report and\\nRecommendation, the Magistrate Judge concluded that the\\nATF was authorized to revoke Simpson’s FFLs because he had\\nwillfully committed over 400 violations of the GCA. (App. I\\n33-34). The District Court adopted the report and\\nrecommendation in its entirety, and thus granted summary\\njudgment for the ATF and affirmed its revocation of Simpson’s\\nFFLs. Simpson’s timely appeal followed.\\n\\n\\n\\n II.\\n\\n The District Court had jurisdiction to review the ATF’s\\nrevocation decision under 18 U.S.C. § 923(f), 5 U.S.C. § 702,\\nand 28 U.S.C. § 1331. We have appellate jurisdiction pursuant\\nto 28 U.S.C. § 1291. We exercise de novo review over the\\nDistrict Court’s grant of summary judgment. See, e.g., Kelly\\nv. Borough of Carlisle, 622 F.3d 248, 253 (3d Cir. 2010). A\\ngrant of summary judgment is warranted “if the movant shows\\nthat there is no genuine dispute as to any material fact and the\\nmovant is entitled to judgment as a matter of law.” Fed. R.\\nCiv. P. 56(a). Further, an administrative record “enjoys a\\npresumption of veracity” at summary judgment. Am. Arms\\nInt’l v. Herbert, 563 F.3d 78, 86 n.12 (4th Cir. 2009) (citation\\nomitted).\\n\\n\\n\\n\\n 7\\n\\f III.\\n\\n Under the GCA, the ATF may revoke an FFL if the\\nlicense holder willfully violated any provision of the GCA or\\nany rule or regulation prescribed under the GCA. 18 U.S.C.\\n§ 923(e); see also 27 C.F.R. § 478.73. “A single willful\\nviolation [of the GCA] authorizes the ATF to revoke the\\nviolator’s FFL, regardless of how severe . . . .” Fairmont Cash\\nMgmt., L.L.C. v. James, 858 F.3d 356, 362 (5th Cir. 2017).\\nThus, in the GCA context, our review of the District Court’s\\ngrant of summary judgment requires us to determine whether\\nthere was no genuine dispute as to any material fact\\nestablishing even one willful violation of the GCA. See Am.\\nArms, 563 F.3d at 86 (noting that “a single uncontested\\nviolation suffices to uphold” summary judgment for the ATF\\n(citing Armalite, Inc. v. Lambert, 544 F.3d 644, 649 (6th Cir.\\n2008))).\\n\\n Eight other Courts of Appeals have held that a violation\\nof the GCA is willful where the licensee knew of his legal\\nobligation and purposefully disregarded or was plainly\\nindifferent to the requirements. See Borchardt Rifle, 684 F.3d\\nat 1042; Fairmont Cash Mgmt., 858 F.3d at 362; Armalite, 544\\nF.3d at 647; RSM, Inc. v. Herbert, 466 F.3d 316, 317 (4th Cir.\\n2006); Article II Gun Shop, Inc. v. Gonzales, 441 F.3d 492, 497\\n(7th Cir. 2006); Willingham Sports, Inc. v. ATF, 415 F.3d 1274,\\n1277 (11th Cir. 2005); Perri v. ATF, 637 F.2d 1332, 1336 (9th\\nCir. 1981); Lewin v. Blumenthal, 590 F.2d 268, 269 (8th Cir.\\n1979). We find this definition of willfulness to be appropriate.\\nIndeed, this standard mirrors the willfulness standard we have\\napplied in the parallel context of ATF revocations of fireworks\\nand explosives licenses for violations of federal explosives\\nlaws. See Vineland Fireworks Co. v. ATF, 544 F.3d 509, 517–\\n19 (upholding the ATF’s interpretation of willful because it\\n\\n\\n\\n\\n 8\\n\\fwas reasonable).1 In Vineland, we upheld that willfulness\\n“do[es] not require a bad purpose,” or an intent to disobey the\\nlaw, but rather willfulness can be established by a mere\\n“violation of the regulations with knowledge of their\\nrequirements.” Id. Moreover, both parties in this case agree\\nwith this willfulness standard. Accordingly, we now join our\\nsister circuits in holding that a violation of the GCA is willful\\nwhere the licensee: (1) knew of his legal obligation under the\\nGCA, and (2) either purposefully disregarded or was plainly\\nindifferent to GCA requirements.\\n\\n Here, Simpson has been charged with willfully\\nviolating the GCA over 400 times. He contends that he did not\\nfully understand his obligations and that any violations he\\ncommitted were not willful, but due to mistake or ignorance.\\nWe disagree, as the record indicates that Simpson was well\\napprised of his duties under the GCA but continually violated\\nGCA recordkeeping, manufacturing, and sales requirements.\\n\\n\\n\\n 1\\n In Vineland, we deferred to the ATF’s interpretation\\nof willfulness under federal explosives law because we found\\nit reasonable. See Vineland, 544 F.3d at 518 n.17. Our review\\nof explosives licensing decisions is governed only by 5 U.S.C.\\n§ 706, so we apply Chevron deference to reasonable agency\\ndecisions. See 18 U.S.C. § 843(e)(2); see also Chevron,\\nU.S.A., Inc. v. Nat. Res. Def. Council, Inc., 467 U.S. 837\\n(1984). In contrast, the GCA explicitly tasks courts with\\nconducting de novo review of ATF licensing denials or\\nrevocations. See 18 U.S.C. § 923(f)(3). As such, we review\\ndistrict court decisions regarding ATF firearms licensing de\\nnovo. See, e.g., Willingham Sports, 415 F.3d at 1275-76.\\n\\n\\n\\n\\n 9\\n\\f A.\\n\\n The record shows that Simpson was informed of his\\nobligations as an FFL licensee. For example, Simpson met\\nwith ATF officials three times about his FFLs and, at the\\nconclusion of each meeting, he signed a form acknowledging\\nthat he discussed various regulatory topics with the ATF. In\\naddition, Simpson attended an ATF seminar for FFL holders\\nwhere he learned more about his obligations under the GCA.\\n\\n The record also demonstrates that Simpson often\\ncomplied with GCA requirements. On numerous occasions,\\nSimpson lawfully sold firearms and fully completed the A&D\\nrecordkeeping required under the GCA. Also, he applied to\\nrelocate his FFL, demonstrating that he knew that he was only\\nallowed to sell firearms from his approved FFL location. His\\nfull compliance with GCA requirements in some instances\\nbelies his assertion that he did not understand those\\nrequirements.\\n\\n Further, some of Simpson’s actions illustrate that he\\nunderstood the GCA regulatory scheme quite well. For\\nexample, he sometimes transferred firearms from his FFL\\ninventory to his personal collection, thereby taking advantage\\nof a statutory loophole that allowed him to later sell the\\nfirearms at gun shows without conducting background checks.\\nSuch action is inconsistent with that of a person who does not\\nunderstand the GCA regulatory scheme. Accordingly, we find\\nthat no reasonable fact-finder could disagree that Simpson\\nknew and understood his GCA obligations as an FFL licensee.\\n\\n\\n\\n\\n 10\\n\\f B.\\n\\n In this case, the ATF has alleged that Simpson was\\nplainly indifferent to the GCA’s requirements. We must\\ntherefore determine what constitutes plain indifference under\\nthe willfulness standard we have adopted.\\n\\n Plain indifference is demonstrated by “a lack of concern\\nfor [GCA] regulations. . . .” Am. Arms Int’l, 563 F.3d at 87. A\\nlack of concern may be shown by circumstantial evidence—\\nsuch as repeated violations or a large quantity of violations.\\nSee, e.g., Borchardt Rifle, 684 F.3d at 1043–44; Am. Arms\\nInt’l, 563 F.3d at 87; On Target Sporting Goods, Inc. v. Att’y\\nGen., 472 F.3d 572, 575 (8th Cir. 2007); RSM, Inc., 466 F.3d\\nat 322; Willingham Sports, 415 F.3d at 1277.\\n\\n The ATF charged Simpson with willfully violating a\\nlong list of separate provisions of the GCA under his\\nmanufacturer’s FFL, including, inter alia:\\n\\n (a) selling firearms without completing Form 4473s;\\n (b) selling or delivering firearms without recording the\\n disposition in his A&D book;\\n (c) transferring firearms without conducting\\n background checks;\\n (d) dealing firearms outside of his FFL premises;\\n (e) selling or delivering firearms to non-Pennsylvania\\n residents;\\n (f) transferring firearms and misidentifying\\n corresponding A&D entries;\\n (g) failing to identify and mark manufactured firearms;\\n (h) failing to record the manufacture of firearms in his\\n A&D book;\\n\\n\\n\\n\\n 11\\n\\f (i) failing to record dispositions of firearms to FFL\\n holders and non-licensees;\\n (j) failing to complete all fields of Form 4473s; and\\n (k) failing to sign and date Form 4473s.\\n\\n(See App. I 8). Additionally, the ATF charged Simpson with\\nwillfully violating another series of provisions of the GCA\\nunder his dealer’s FFL. These include, inter alia:\\n\\n (a) selling firearms without completing Form 4473s;\\n (b) selling or delivering firearms without recording the\\n disposition in his A&D book;\\n (c) transferring firearms without conducting\\n background checks;\\n (d) selling firearms in West Virginia;\\n (e) selling or delivering firearms to non-Pennsylvania\\n residents\\n (f) purchasing firearms without recording the purchases\\n in his A&D book;\\n (g) failing to complete all fields of Form 4473s; and\\n (h) failing to sign and date Form 4473s.\\n\\nId.\\n\\n Simpson contends that all of these violations either were\\nmere mistakes or were due to his “fundamental\\nmisunderstanding as to the importance” of GCA recordkeeping\\nrequirements. (Appellant’s Br. 35). However, in view of the\\nfact that Simpson received training on his obligations and\\nexplicitly acknowledged that he understood his GCA\\nobligations, the sheer number and continuing nature of the\\nviolations clearly demonstrate Simpson’s plain indifference to\\nthe GCA’s requirements.\\n\\n\\n\\n\\n 12\\n\\f While there is no dispute that Simpson violated the\\nGCA on numerous occasions, there is also evidence of other\\nfirearms transactions in which Simpson fully complied with\\nGCA requirements by completing, signing, and dating Form\\n4473s, recording the dispositions in his A&D book, and\\nconducting background checks. This inconsistent conduct\\nsuggests both that Simpson knew of his obligations and was\\nindifferent to complying with them. Moreover, there is\\nevidence of blatant GCA violations. For example, Simpson\\nroutinely transferred receivers to out-of-state residents—in\\nclear violation of the GCA—but falsely recorded the transfers\\nas rifle sales in his A&D book, making these transactions\\nappear lawful. Such behavior is indicative of Simpson’s lack\\nof concern for his GCA obligations as an FFL holder.\\n\\n In sum, the record sufficiently shows that Simpson had\\nknowledge of his FFL obligations, yet acted plainly\\nindifferently to them, thus willfully violating the GCA.\\nAccordingly, we find that the ATF was authorized to revoke\\nSimpson’s FFLs.\\n\\n\\n\\n IV.\\n\\n For the foregoing reasons we will affirm the District\\nCourt’s grant of summary judgment in favor of the ATF,\\naffirming its revocation of Simpson’s FFLs.\\n\\n\\n\\n\\n 13\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":60,"cells":{"id":{"kind":"number","value":4578609,"string":"4,578,609"},"name":{"kind":"string","value":"CHIAO FANG KU, AKA Chiao Fang Ronan, AKA Anna Ronan, Petitioner v. ATTORNEY GENERAL UNITED STATES OF AMERICA, Respondent"},"name_abbreviation":{"kind":"string","value":"Chiao Ku v. Attorney General United States"},"decision_date":{"kind":"string","value":"2019-01-03"},"docket_number":{"kind":"string","value":"17-3001"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Jordan, Vanaskie, Nygaard\", \"parties\": \"\", \"opinions\": [{\"author\": \"VANASKIE, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-3001\\n _____________\\n\\n CHIAO FANG KU,\\n AKA Chiao Fang Ronan, AKA Anna Ronan,\\n Petitioner\\n v.\\n\\nATTORNEY GENERAL UNITED STATES OF AMERICA,\\n Respondent\\n _____________\\n\\n On Petition for Review of an Order of the\\n Board of Immigration Appeals\\n (Agency No. A077-160-352)\\n Immigration Judge: Walter A. Durling\\n ______________\\n\\n Argued September 12, 2018\\n ______________\\n\\n Before: JORDAN, VANASKIE, and NYGAARD, Circuit\\n Judges\\n\\n\\n The Honorable Judge Vanaskie transmitted the opinion to the Clerk for\\nfiling prior to retiring from the bench on January 1, 2019. Due to the\\nintervening holiday, the opinion has been entered on the docket by the\\nClerk this day.\\n\\f (Opinion Filed: January 3, 2019)\\n\\n\\nThomas M. Griffin [Argued]\\nSurin & Griffin\\n718 Arch Street\\nSuite 701N\\nPhiladelphia, PA 19106\\n Counsel for Petitioner\\n\\nChad A. Readler, Acting Assistant Attorney General\\nNancy E. Friedman, Senior Litigation Counsel\\nJustin R. Markel, Senior Litigation Counsel\\nGregory A. Pennington, Jr. [Argued]\\nUnited States Department of Justice\\nOffice of Immigration Litigation\\nCivil Division\\nP.O. Box 878\\nBen Franklin Station\\nWashington, DC 20044\\n Counsel for Respondent\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\n\\nVANASKIE, Circuit Judge.\\n\\n Seeking to remain in this country, Chiao Fang Ku\\npetitions for review of a final order of removal issued by the\\nBoard of Immigration Appeals (“BIA” or “Board”). The\\nBoard determined that Ku had committed an aggravated felony\\n\\n\\n\\n\\n 2\\n\\funder 8 U.S.C. § 1101(a)(43)(M)(i) because her prior\\nconviction for wire fraud constituted an offense involving\\nfraud or deceit in which the loss to the victims exceeded\\n$10,000. The Board also found that Ku’s wire fraud conviction\\nconstituted a “crime involving moral turpitude” under 8 U.S.C.\\n§ 1182(a)(2)(A)(i)(I) such that, without a waiver, she is\\nineligible for an adjustment of status. Although the\\nImmigration Judge (“IJ”) granted Ku a waiver of\\ninadmissibility under 8 U.S.C. § 1182(h)(1)(B) based on the\\nextreme hardship that her deportation would cause her U.S.\\nCitizen children, the Board reversed that decision. Ku\\nchallenges each of the Board’s decisions.\\n\\n In Nijhawan v. Holder, 557 U.S. 29 (2009), the Court\\nheld that determination of whether a fraud offense involved\\nloss to the victims of $10,000 or more requires a circumstance-\\nspecific approach, allowing the immigration court to review\\nboth the charging document and sentencing-related materials\\nto determine the loss amount attributable to the offense. On\\nthe facts of this case, we find that the undisputed loss to the\\nvictims of well over $10,000 was sufficiently tethered to Ku’s\\nwire fraud conviction such that the conviction qualifies as an\\naggravated felony. Furthermore, we find no error in the\\nBoard’s determination that wire fraud constitutes a crime of\\nmoral turpitude. Lastly, regarding the waiver of admissibility,\\nwe do not have jurisdiction to review the discretionary denial\\nof a waiver under § 212(h) of the INA. Accordingly, we will\\ndeny in part and dismiss in part Ku’s petition for review.\\n\\n I.\\n\\n Ku is a native and citizen of Taiwan. She was admitted\\nto the United States in 1997 and gained status as a lawful\\npermanent resident in 2002. In 2014, Ku was charged with a\\n\\n\\n\\n\\n 3\\n\\fsingle count of wire fraud, in violation of 18 U.S.C. § 1343.\\nKu waived her right to an indictment and was charged by\\ninformation only. The Information alleged that Ku was tasked\\nwith managing the finances of her in-laws, E.R. and M.R, and\\nthat she was provided access to her in-laws’ bank accounts in\\nconnection with this role. The Information further alleged that,\\nbetween May 2008 and July 2013, Ku defrauded her in-laws\\nby using her access to their accounts to take money from them\\nfor her personal use. In particular, it alleged that Ku: (1)\\ntransferred funds from her in-laws’ accounts to her own\\naccounts; (2) withdrew funds from her in-laws’ accounts as\\ncash; (3) made payments from her in-laws’ accounts to pay off\\nher personal credit cards; (4) wrote and cashed checks payable\\nto herself by forging her mother-in-law’s signature; and (5)\\nfraudulently applied for and obtained credit cards in her\\nmother-in-law’s name and used them for her own purposes.\\nThe Information alleged that, in total, Ku stole more than\\n$950,000 from her in-laws.\\n\\n These allegations were incorporated by reference into\\nthe sole count of the Information, which alleged that, on or\\nabout November 7, 2011, Ku,\\n\\n having devised and intending to devise a\\n scheme and artifice to defraud and to obtain\\n money and property by means of materially\\n false and fraudulent pretenses,\\n representations, and promises, did cause\\n writings, signs, signals, pictures, and sounds\\n to be transmitted by means of wire\\n communications in interstate commerce for\\n the purpose of executing such scheme and\\n artifice, to wit: executing an online payment\\n from M.R.’s Sovereign Bank account, ending\\n\\n\\n\\n\\n 4\\n\\f in 8497, to the defendant’s Chase credit card\\n account, ending in 6567, in the amount of\\n $2,290.53.\\n\\n(App. 590). The Information further contained forfeiture\\nallegations, which directed that, upon conviction of the sole\\ncount of the Information, Ku “forfeit to the United States . . .\\nany property, real or personal, that constitutes, or is derived\\nfrom, proceeds traceable to the commission of the offense,\\nincluding but not limited to at least $950,000 in United States\\ncurrency.” (App. 591).\\n\\n Ku pleaded guilty, pursuant to a plea agreement,1 to the\\nsingle count of the Information. In her sentencing\\nmemorandum, Ku, through counsel, acknowledged that she\\nwas “now subject to automatic deportation as a result of her\\nconviction in this case.” (App. 740). Ku was ultimately\\nsentenced to a term of 18 months’ imprisonment, followed by\\none year of supervised release. The judgment includes a total\\nloss determination of $954,515.71 and orders restitution in that\\namount. (App. 582).\\n\\n After Ku completed her sentence, she was served with\\na Notice to Appear and placed in removal proceedings. The\\nNotice to Appear charged Ku with being removable under\\n§ 237(a)(2)(A)(iii) of the Immigration and Nationality Act\\n(“INA” or the “Act”), 8 U.S.C. § 1227(a)(2)(A)(iii), as an\\nindividual convicted of an aggravated felony as defined in 8\\nU.S.C. § 1101(a)(43)(M)(i). The Immigration Judge\\nconcluded that Ku was removable as charged because the\\n\\n\\n 1\\n The plea agreement is not part of the administrative\\nrecord before us, nor was it in the record before the IJ or BIA.\\n\\n\\n\\n\\n 5\\n\\frecord of conviction substantiated a finding that the wire fraud\\ninvolved a loss of more than $10,000.\\n\\n In order to avoid deportation, Ku sought to re-adjust her\\nstatus based on her U.S. Citizen husband.2 The Immigration\\nJudge granted Ku’s application for a waiver of inadmissibility\\nunder § 212(h)(1)(B) of the Act, 8 U.S.C. § 1182(h)(1)(B),\\nbased on the extreme hardship that her deportation would cause\\nher U.S. Citizen children, and granted Ku’s adjustment of\\nstatus pursuant to § 245(a) of the INA, 8 U.S.C. § 1255(a).\\n\\n On appeal, the Board affirmed that the Government\\ndemonstrated by clear and convincing evidence that Ku was\\nremovable as an aggravated felon as defined at\\n§ 1101(a)(43)(M)(i) in that her offense involved fraud or deceit\\nin which the loss to the victims exceeded $10,000. In doing so,\\nthe Board noted that the Information alleged that Ku stole more\\nthan $950,000 in funds belonging to her in-laws, and that this\\nallegation was incorporated by reference into the count to\\nwhich Ku pleaded guilty. It also observed that the Information\\nalso contained a forfeiture allegation stating that, upon\\nconviction, Ku would forfeit over $950,000 in currency.\\nFinally, the Board considered relevant that the Judgment of\\nConviction found a total loss of over $950,000 and ordered\\nrestitution in that amount.\\n\\n The Board further concluded that Ku’s conviction was\\nfor a crime involving moral turpitude, making her inadmissible\\nunder § 212(a)(2)(A)(i)(I) of the INA, 8 U.S.C.\\n§ 1182(a)(2)(A)(i)(I), such that she required a § 212(h) waiver\\n\\n 2\\n Ku's present husband is not the man to whom she was\\npreviously married and whose parents are the elderly in-laws\\nshe defrauded.\\n\\n\\n\\n\\n 6\\n\\fin order to adjust her status. See 8 U.S.C. § 1255(a) (providing\\nfor adjustment of status of certain aliens to that of an alien\\nlawfully admitted for permanent residence); see also 8 U.S.C.\\n§ 1182(h)(1)(B) (providing for waiver of inadmissibility at the\\ndiscretion of the Attorney General). Although it acknowledged\\nthe hardship posed to her family, the Board ultimately found\\nthat, given the severity of her crime, Ku did not merit a\\n§ 212(h) waiver. It accordingly vacated the decision of the IJ\\nand denied Ku’s applications for a § 212(h) waiver and for\\nadjustment of status. Ku timely filed a petition for review.\\n\\n II.\\n\\n Although we have jurisdiction to review final orders of\\nremoval under 8 U.S.C. § 1252(a),3 “no court shall have\\n\\n 3\\n We have taken a broad view of what constitutes a\\n“final order of removal” under § 1252. Higgs v. Att’y Gen.,\\n655 F.3d 333, 337–38 (3d Cir. 2011). “[A]n order is final for\\njurisdictional purposes when a removability determination has\\nbeen made that is no longer appealable to the BIA, regardless\\n[of] whether a formal order of removal has been entered.” Id.\\n(quoting Yusupov v. Att’y Gen., 518 F.3d 185, 195 (3d Cir.\\n2008)); see also Shehu v. Att’y Gen., 482 F.3d 652, 656 (3d\\nCir. 2007) (“[D]enial of a . . . petition for asylum, withholding\\nof removal, and relief under the [Convention Against Torture]\\nconstitutes ‘a final order of removal’ within the meaning of\\n[§ 1252], [because] the alien is entitled to no further process\\nbefore deportation.”). Here, although the Board did not\\nexplicitly order Ku removed to Taiwan, it found her removable\\nand denied her application for adjustment of status, her only\\npetition for relief. (App. 5). Furthermore, the Board sustained\\nDHS’s appeal, which requested that Ku be ordered removed to\\nTaiwan. Accordingly, for the purposes of this appeal, we\\n\\n\\n\\n\\n 7\\n\\fjurisdiction to review any final order of removal against an\\nalien who is removable by reason of having committed [an\\naggravated felony].” 8 U.S.C. § 1252(a)(2)(C). “We do,\\nhowever, have jurisdiction to examine ‘constitutional claims or\\nquestions of law.’” Fan Wang v. Att’y Gen., 898 F.3d 341, 343\\n(3d Cir. 2018) (quoting Catwell v. Att’y Gen., 623 F.3d 199,\\n205 (3d Cir. 2010); 8 U.S.C. § 1252(a)(2)(D)). Therefore, we\\nhave authority to take up the issue, applying plenary review, of\\nwhether Ku’s conviction qualifies as an aggravated felony\\nbecause it is “a purely legal question, and one that governs our\\nown jurisdiction.” Id. (quoting Valansi v. Ashcroft, 278 F.3d\\n203, 207 (3d Cir. 2002)). We also review de novo the legal\\nquestion of what elements of a federal criminal statute\\nimplicate moral turpitude, while affording Chevron deference\\nto the Board’s definition of “moral turpitude.” Knapik v.\\nAshcroft, 384 F.3d 84, 88 (3d Cir. 2004).\\n\\n III.\\n\\n On appeal, Ku challenges all three aspects of the BIA’s\\norder. First, she contends that the BIA incorrectly determined\\nthat her wire-fraud conviction involved a loss of more than\\n$10,000 by relying on evidence that was not sufficiently\\ntethered to the sole count of conviction.4 Second, Ku argues\\n\\n\\nconsider the Board’s order to be a final order of removal. The\\nGovernment’s motion to remand this case to the Board for\\nissuance of an order directing that Ku be removed to Taiwan\\nand to allow the IJ to make additional findings on removability\\nwill be denied as moot.\\n 4\\n We note that Ku does not challenge—and did not\\nchallenge before the IJ or the Board—that her wire fraud\\n\\n\\n\\n\\n 8\\n\\fthat the Board erred in finding that her wire-fraud conviction\\nwas for a crime involving moral turpitude because the statute\\nof conviction does not require a showing of intent. Third, Ku\\nasserts that the BIA applied the incorrect legal standard in\\nreversing the IJ’s grant of a discretionary waiver of\\ninadmissibility. We reject all three of Ku’s challenges and\\ntherefore deny the petition for review.\\n\\n A.\\n\\n Section 237(a)(2)(A)(iii) of the INA, as amended,\\nprovides that “[a]ny alien who is convicted of an aggravated\\nfelony at any time after admission is deportable.” 8 U.S.C.\\n§ 1227(a)(2)(A)(iii). The Act defines “aggravated felony,” in\\nrelevant part, as an offense that “involves fraud or deceit in\\nwhich the loss to the victim or victims exceeds $10,000.” 8\\nU.S.C. § 1101(a)(43)(M)(i).\\n\\n In Nijhawan v. Holder, the Supreme Court addressed\\nthe issue of whether the $10,000 threshold of the aggravated\\nfelony statute “refers to an element of a fraud statute or to the\\nfactual circumstances surrounding commission of the crime on\\na specific occasion.” 557 U.S. at 33. The Court adopted the\\nlatter interpretation, characterizing the review as examining\\n“the specific way in which an offender committed the crime on\\na specific occasion.” Id. at 34. The Court distinguished the\\n“circumstance-specific approach” to be used in determining\\nwhether a crime “involves fraud or deceit in which the loss to\\nthe victim or victims exceeds $10,000” from the “categorical\\napproach” used in determining whether a crime is a “violent\\nfelony” under the Armed Career Criminal Act (“ACCA”), 18\\n\\nconviction “involves fraud or deceit” under 8 U.S.C.\\n§ 1101(a)(43)(M).\\n\\n\\n\\n\\n 9\\n\\fU.S.C. § 924(e). Id. at 34–40. It also rejected the use of the\\nso-called “modified categorical approach” employed in some\\ncontexts, which would limit an IJ’s consideration to charging\\ndocuments, jury instructions, special jury findings, or some\\nequivalent judge-made findings and—in the case of a guilty\\nplea—to the written plea documents or plea colloquy. Id. at\\n41. While the Supreme Court acknowledged that “the statute\\nforesees the use of fundamentally fair procedures,” it rejected\\nthe argument that fairness requires such evidentiary\\nlimitations. Id. Accordingly, it found “nothing unfair” about\\nthe IJ’s reliance upon the defendant’s stipulation and the\\ndistrict court’s restitution order to determine that the crime at\\nissue was an “aggravated felony” under § 1101(a)(43)(M)(i).\\nId. at 42–43.\\n\\n Since Nijhawan, we have consistently applied the\\ncircumstance-specific approach to determine the amount of\\nloss in “aggravated felony” cases. See, e.g., Kaplun v. Att’y\\nGen., 602 F.3d 260, 265–66 (3d Cir. 2010); Doe v. Att’y Gen.,\\n659 F.3d 266, 274–76 (3d Cir. 2011). Most recently, we\\naddressed the issue in Fan Wang, in which we reviewed “not\\nonly those documents that may be considered in a modified\\ncategorical approach (the indictment, plea agreement, and\\njudgment),” but also others, including “the presentence\\ninvestigation report and any sentencing-related material.” 898\\nF.3d at 348–49 (citations and internal quotation marks\\nomitted). Relying on Nijhawan, we reasoned that\\nconsideration of such materials “is appropriate so long as the\\npetitioner has been given a ‘fair opportunity’ to challenge the\\nGovernment’s claim.” Id. at 349 (quoting Nijhawan, 557 U.S.\\nat 41). Accordingly, we determined that the Board did not go\\nbeyond the bounds of proper review by examining the record—\\nincluding the sole count of the superseding information, the\\n\\n\\n\\n\\n 10\\n\\fplea colloquy, the presentence investigation report, the “total\\nloss” specified in the judgment, and the restitution order—to\\ndetermine whether the petitioner’s prior conviction was an\\n“aggravated felony.” Id. at 349–50. In determining the proper\\namount of loss in that case, we were persuaded by the\\nGovernment’s argument that the loss amount listed in the\\njudgment and restitution order was “undeniably tethered” to\\nthe conduct for which the petitioner was convicted. Id. at 351.\\n\\n We consider the loss to the victims in this case—as\\nevidenced by the Information, Judgment, and Restitution\\nOrder—to be sufficiently tethered to the count of conviction\\nsuch that Ku’s conviction was an aggravated felony.\\nParagraphs 1 through 10 of the Information allege that Ku stole\\nmore than $950,000 in funds belonging to her in-laws, and\\nthese paragraphs were incorporated by reference into the count\\nto which Ku pleaded guilty. Furthermore, the forfeiture\\nallegation contained in the Information states that, upon\\nconviction, Ku would forfeit the “proceeds traceable to the\\ncommission of the offense, including but not limited to at least\\n$950,000 in United States currency.” (App. 591). Finally, the\\nJudgment of Conviction indicates a loss of $954,515.71 and\\norders restitution in that amount. Each of these documents is\\nreviewable under the circumstance-specific approach laid out\\nby the Supreme Court in Nijhawan. Together, they provide\\nclear and convincing evidence that Ku’s offense involved a\\nloss of over $10,000. Nonetheless, we briefly addresses Ku’s\\narguments to the contrary, all of which lack merit.\\n\\n 1.\\n\\n First, Ku contends that the circumstance-specific\\napproach described in Nijhawan does not apply in her case\\nbecause the single count of the Information made clear that it\\n\\n\\n\\n\\n 11\\n\\fwas for the specified amount of $2,290.53. She urges us to\\nread Nijhawan to have kept intact the modified categorical\\napproach for cases in which the charging document contains a\\nclear indication of the loss amount. Under the modified\\ncategorical approach, she contends, the Board was correct in\\nreviewing the Information but, because the count of conviction\\ncontains a loss amount of $2,290.53, the Board should have\\nstopped there.\\n\\n Contrary to Ku’s assertion, Nijhawan does not stand for\\nthe proposition that, when the count of conviction contains a\\nloss amount, immigration officials must look no further. The\\nSupreme Court explicitly rejected the use of the modified\\ncategorical approach in determining whether a prior conviction\\nis an aggravated felony under § 1101(a)(43)(M)(i). Nijhawan,\\n557 U.S. at 41–42; see also Kaplun, 602 F.3d at 265–66\\n(interpreting Nijhawan). Rather, it determined that the\\ncircumstance-specific approach is required because the\\naggravated felony statute “refers to the particular\\ncircumstances in which an offender committed a (more broadly\\ndefined) fraud or deceit crime on a particular occasion,” and\\nnot to an element of the offense. Nijhawan, 557 U.S. at 32.\\nNoting that the Government in immigration proceedings is\\nheld only to a “clear and convincing” burden of proof, and not\\n“beyond a reasonable doubt,” the Supreme Court found\\n“nothing unfair about [an IJ] rel[ying] upon earlier sentencing-\\nrelated material”—in that case a sentencing stipulation and\\nrestitution order. Id. at 42–43. It also noted that “the sole\\npurpose of the aggravated felony inquiry is to ascertain the\\nnature of a prior conviction; it is not an invitation to relitigate\\nthe conviction itself.” Id. (internal quotation marks omitted).\\n\\n Nothing in Nijhawan suggests that the circumstance-\\nspecific approach applies in some cases but not others, or that\\n\\n\\n\\n\\n 12\\n\\fthe documents reviewable under that approach vary from case\\nto case. Furthermore, we have consistently interpreted\\nNijhawan as allowing an IJ, in determining the loss amount, to\\nlook beyond the charging document to sentencing-related\\nmaterials. See Kaplun, 602 F.3d at 265–66; Fan Wang, 898\\nF.3d at 348–49. Ku has not persuaded us that our reading is\\nincorrect.\\n\\n 2.\\n\\n Second, Ku contends that, because her conviction was\\nfor “a single act of a $2,290.53 on-line transfer,” the losses she\\ncaused through other acts and transactions are not sufficiently\\n“tethered” to the count of conviction for purposes of the\\naggravated felony statute. (Petitioner’s Br. at 27). In doing so,\\nKu asks us to read the Information as charging her in Count\\nOne with a “scheme and artifice to defraud” her in-laws of\\n$2,290.53, and not as charging her with one instance of wire\\nfraud that was part of a broader “scheme and artifice to\\ndefraud” her in-laws of over $950,000. However, such an\\ninterpretation is inconsistent with the language of the\\nInformation. In Count One, the Government “re-alleges and\\nincorporates by reference” the first eight paragraphs, which\\nallege that, over five years, Ku defrauded her in-laws of more\\nthan $950,000 by transferring funds from their accounts to her\\nown accounts, withdrawing funds as cash, making payments to\\ncredit card companies for charges she incurred, and writing and\\ncashing checks payable to herself. (App. 588–90). The explicit\\nincorporation of those paragraphs into the count to which Ku\\npleaded guilty supports an interpretation of the count itself as\\ndescribing Ku’s “scheme and artifice to defraud” her in-laws\\nof more than $950,000.\\n\\n\\n\\n\\n 13\\n\\f We are similarly unpersuaded by Ku’s contention that,\\nbecause Paragraphs 1 through 8 of the Information describe\\nconduct that does not necessarily amount to wire fraud, such\\nconduct cannot count toward the total loss resulting from her\\nconviction. It is incontrovertible that the “scheme and artifice\\nto defraud” charged in Count One of the Information\\nencompassed the whole course of Ku’s unlawful conduct,\\nincluding the one incident in which Ku committed wire fraud\\nin the amount of $2,390.53, and which resulted in a total loss\\nof over $950,000. In short, because Ku pleaded guilty to\\ncommitting wire fraud as part of a scheme to defraud her in-\\nlaws of more than $950,000, the total loss amount is, to use our\\nlanguage from Fan Wang, “undeniably tethered” to her wire\\nfraud conviction.\\n\\n 3.\\n\\n Finally, Ku contends that the single-count Information\\nto which she pleaded guilty is part of the “justice package”\\nworked out between her and the Government and urges the\\nCourt to defer to that agreement. (Petitioner’s Br. at 35). In\\ndoing so, Ku relies on our opinion in Alaka v. Attorney\\nGeneral, 456 F.3d 88 (3d Cir. 2006). However, the facts of\\nthis case make it distinguishable from Alaka.\\n\\n In Alaka—which we decided prior to Nijhawan5—we\\nheld that the IJ erred by considering the amount of intended\\n\\n\\n 5\\n Because Alaka was decided prior to the Supreme\\nCourt’s decision in Nijhawan, its application of the modified\\ncategorical approach to the aggravated-felony analysis does\\nnot affect our decision. However, to the extent that Alaka\\nstands for the proposition that an IJ may not consider dismissed\\n\\n\\n\\n\\n 14\\n\\floss for all of the charges against the petitioner rather than the\\nsingle count for which she was convicted. Alaka, 456 F.3d at\\n106. The petitioner had been indicted on three counts for\\nconduct involving fraudulent checks, but was convicted of only\\none count, for which the actual loss was $4,716.68. Id. at 92.\\nThe sentencing court nonetheless held that the petitioner’s\\nconduct was part of a “common scheme or plan,” and therefore\\nfound the total intended loss to be nearly $50,000. Id. It\\nordered her to pay $4,716.68 in restitution. Id. In subsequent\\nimmigration proceedings, the IJ concluded that the petitioner\\nhad been convicted of an aggravated felony on the ground that\\nthe intended loss was more than $10,000. Id. at 105, n.27. On\\nappeal, we determined that, while the IJ properly considered\\nthe factual findings of the sentencing report in determining\\nwhether the offense was an aggravated felony, the loss amount\\ntied to the dismissed charges was not properly considered as\\npart of the aggravated-felony analysis. Id. at 106–08. In doing\\nso, we noted that “the plain and unambiguous language of the\\nstatute . . . predicates removal on a convicted offense resulting\\nin losses greater than $10,000,” thereby foreclosing inclusion\\nof losses stemming from unconvicted offenses. Id. 106–07\\n(citations omitted). Furthermore, we considered that, because\\nit is “the plea agreement that establishes the offense for which\\nthe defendant will be convicted, it is to that agreement, and not\\nthe indictment or the sentence, that we look in determining the\\nintended loss.” Id. at 107. The petitioner “unmistakably pled\\nguilty to one count, and the plea agreement plainly documented\\nthat loss at less than $10,000.” Id. at 108 (citations and\\nalterations omitted). Because the plea agreement “spell[ed] it\\nout for us in black and white,” we concluded that the plea\\n\\n\\ncharges when calculating the loss attributable to the conviction,\\nit remains good law.\\n\\n\\n\\n\\n 15\\n\\fagreement alone established the loss amount, and “not . . . the\\nloss charged in the indictment, tabulated for restitution\\npurposes, or calculated for sentencing.” Id. (citations omitted).\\n\\n Here, in stark contrast to the petitioner in Alaka, the\\nrecord before us contains no plea agreement, and certainly not\\none which explicitly spells out the loss amount to which Ku\\npleaded guilty. Instead, Ku urges us to find that, based on the\\nfact that the Government could have charged her with a much\\nlonger list of crimes but did not, the loss amount as indicated\\nin Count One was part of an explicit bargain between her and\\nthe Government. However, this argument is based on pure\\nconjecture. Absent a clear and unmistakable indication of loss\\nin a written plea agreement, we are left with only the\\nInformation, Judgment, and Restitution Order to determine the\\nloss attributable to Ku’s conviction. As explained above, these\\ndocuments, taken together, provide clear and convincing\\nevidence that the loss amount attributable to Ku’s wire fraud\\nconviction exceeded $10,000, and Ku has provided no plea\\nagreement or any other document to the contrary.6\\n\\n 6\\n The sentencing court in Alaka calculated the total loss\\namount based on the “common scheme or plan,” which, it\\nconsidered, included both the count of conviction and the\\ndismissed counts, and we considered the IJ’s reliance on that\\ncalculation to be in error in light of the plea agreement. 456\\nF.3d at 106. But this does not help Ku. As explained above,\\nthe wire fraud count to which Ku pleaded guilty was based in\\npart on her “scheme and artifice to defraud” her in-laws of over\\n$950,000. (App. 590). Unlike the sentencing court in Alaka,\\nthe sentencing court in this case did not base its loss calculation\\non any acts that were not explicitly incorporated into the count\\nof conviction.\\n\\n\\n\\n\\n 16\\n\\f Ku’s argument that this Court should respect the\\n“justice package” between her and the Government also\\ntouches on the Supreme Court’s landmark holdings in Padilla\\nv. Kentucky, 559 U.S. 356 (2010), and Descamps v. United\\nStates, 570 U.S. 254 (2013), both of which, she argues, counsel\\ntoward respecting agreements between criminal defendants\\nand the Government with respect to the collateral\\nconsequences of a conviction. But this line of argument merely\\nhighlights another critical shortcoming of Ku’s case. To the\\nextent Ku argues that the Information was designed\\nspecifically to avoid immigration consequences, there is no\\nevidence in the record to support such a finding. Indeed, Ku’s\\nattorney indicated in her sentencing memorandum that Ku “is\\nnow subject to automatic deportation as a result of her\\nconviction in this case.” (App. 740). This statement, while not\\nconclusive, certainly undermines any assertion that the “justice\\npackage” referred to by Ku was designed to avoid an\\naggravated felony conviction. Indeed, absent any other\\nevidence in the record to the contrary, the sentencing\\nmemorandum supports a finding that, at the time of her guilty\\nplea, Ku understood that she was pleading guilty to an\\naggravated felony.\\n\\n B.\\n\\n Having concluded that the Board did not err in finding\\nthat Ku was convicted of an aggravated felony, we turn to the\\nquestion of whether Ku’s conviction constituted a “crime\\ninvolving moral turpitude” under the INA. Ku argues that wire\\nfraud is not a “crime involving moral turpitude” under 8 U.S.C.\\n§ 1182(a)(2)(A)(i)(I) because it does not include as an element\\nthe specific intent to defraud. This is incorrect.\\n\\n\\n\\n\\n 17\\n\\f The statute provides that a person is guilty of wire fraud\\nif, “having devised or intending to devise any scheme or\\nartifice to defraud,” that person “transmits or causes to be\\ntransmitted by means of wire, radio, or television\\ncommunication in interstate or foreign commerce, any\\nwritings, signs, signals, pictures, or sounds for the purpose of\\nexecuting such scheme or artifice.” 18 U.S.C. § 1343. Courts\\nhave long treated fraud crimes as “involving moral turpitude.”\\nJordan v. De George, 341 U.S. 223, 232 (1951) (“[T]he\\ndecided cases make it plain that crimes in which fraud was an\\ningredient have always been regarded as involving moral\\nturpitude.”); Singh v. Att’y Gen., 807 F.3d 547, 550 (3d Cir.\\n2015) (“Crimes . . . involving allegations of dishonesty or fraud\\nfall well within the recognized definition of ‘crimes involving\\nmoral turpitude.’”). Furthermore, we have also consistently\\nread the wire fraud statute as containing the element of specific\\nintent. See, e.g., United States v. Andrews, 681 F.3d 509, 518\\n(3d Cir. 2012) (“To prove wire fraud, the Government must\\nestablish (1) the defendant’s knowing and willful participation\\nin a scheme or artifice to defraud, (2) with the specific intent to\\ndefraud, and (3) the use of . . . interstate wire communications\\nin furtherance of the scheme.”) (internal quotation marks\\nomitted) (emphasis added).\\n\\n Seeking to persuade us to revisit these tenets, Ku asks\\nus to read the statutory terms “having devised” and “intending\\nto devise” as disjunctive means of committing wire fraud, the\\nlatter containing the mens rea of intent, and the former\\neschewing any mens rea at all. But the language of the statute\\ndoes not lend itself to such an interpretation. The specific\\nintent requirement is contained in the latter part of the statute—\\n“for the purpose of executing [a] scheme or artifice [to\\ndefraud]”—and must be proved regardless of whether the\\n\\n\\n\\n\\n 18\\n\\fperson made the transmission after “having devised” or while\\n“intending to devise” the scheme to defraud. 18 U.S.C. § 1343.\\nPlainly read, the language Ku seizes on, “having devised or\\nintending to devise,” refers not to the requisite mens rea but to\\nthe temporal relationship between the formation of the fraud\\nscheme and the transmission itself. Either way, the person\\nmust have made the transmission for the purpose of executing\\nthe fraud scheme in order to be convicted.\\n\\n Ku’s statutory interpretation argument holds no weight.\\nAccordingly, we see no need to revisit the long-held tenet that\\nfraud crimes—including wire fraud—are crimes involving\\nmoral turpitude under the INA.\\n\\n C.\\n\\n Finally, Ku asks us to find that the Board committed\\nerror in its reversal of the IJ’s finding that she was eligible for\\na discretionary waiver of inadmissibility based on the hardship\\nher deportation would cause her U.S. citizen children.\\nHowever, we lack jurisdiction over the Board’s decision on\\nthis point.\\n\\n The INA provides that an alien is inadmissible to the\\nUnited States if she has been convicted of a crime involving\\nmoral turpitude. 8 U.S.C. § 1182(a)(2)(A)(i)(I). The Act also\\nprovides, however, that the Attorney General may waive\\ninadmissibility to allow an applicant to obtain adjustment of\\nstatus under § 1182(h), “if the alien is a spouse, parent, or child\\nof a United States citizen . . . and can show that denial of\\nadmission would cause extreme hardship to the citizen . . . .”\\nDe Leon–Reynoso v. Ashcroft, 293 F.3d 633, 637 (3d Cir.\\n2002). The authority to waive one or more grounds of\\ninadmissibility is vested solely in the Attorney General and “no\\n\\n\\n\\n\\n 19\\n\\fcourt shall have jurisdiction to review” a decision to deny such\\na request. 8 U.S.C. § 1252(a)(2)(B)(i).\\n\\n We may, however, review “constitutional claims or\\nquestions of law raised upon a petition for review . . . .” Id. at\\n§ 1252(a)(2)(D). Our jurisdiction in that respect is “narrowly\\ncircumscribed” in that it is limited to “colorable claims or\\nquestions of law.” Cospito v. Att’y Gen., 539 F.3d 166, 170 (3d\\nCir. 2008) (per curiam) (quotation marks and citation omitted).\\nWhile “[t]he question of our jurisdiction over a colorable legal\\nclaim does not turn on whether that claim is ultimately\\nmeritorious . . . , a party may not dress up a claim with legal\\nclothing to invoke this Court's jurisdiction.” Pareja v. Att’y\\nGen., 615 F.3d 180, 187 (3d Cir. 2010) (citations omitted).\\n\\n Ku argues that we have jurisdiction to consider her\\npetition for review on the waiver issue because it presents a\\nquestion of law, namely whether the Board applied the proper\\nlegal standard in making the discretionary determination. But\\nKu’s argument boils down to her contention that the Board\\nfailed to consider certain equities relevant to the hardship\\ndetermination. As we have consistently held, “arguments such\\nas that an Immigration Judge or the BIA incorrectly weighed\\nevidence, failed to consider evidence or improperly weighed\\nequitable factors are not questions of law under\\n§ 1252(a)(2)(D).” Jarbough v. Att’y Gen., 483 F.3d 184, 189\\n(3d Cir. 2007). Because the substance of Ku’s petition for\\nreview amounts to contesting the weight the Board should have\\ngiven to the positive equities of her case, we do not have\\njurisdiction over it and will dismiss in part that aspect of the\\npetition.\\n\\n IV.\\n\\n\\n\\n\\n 20\\n\\f For the foregoing reasons, we will deny in part and\\ndismiss in part Ku's petition for review, and we will deny as\\nmoot the Government's motion to remand.\\n\\n\\n\\n\\n 21\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4355862/\", \"author_raw\": \"VANASKIE, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"JORDAN"},"judge2":{"kind":"string","value":"VANASKIE"},"judge3":{"kind":"string","value":"NYGAARD"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4578609/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: CHIAO FANG KU, AKA Chiao Fang Ronan, AKA Anna Ronan, Petitioner v. ATTORNEY GENERAL UNITED STATES OF AMERICA, Respondent\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-03\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-3001\n _____________\n\n CHIAO FANG KU,\n AKA Chiao Fang Ronan, AKA Anna Ronan,\n Petitioner\n v.\n\nATTORNEY GENERAL UNITED STATES OF AMERICA,\n Respondent\n _____________\n\n On Petition for Review of an Order of the\n Board of Immigration Appeals\n (Agency No. A077-160-352)\n Immigration Judge: Walter A. Durling\n ______________\n\n Argued September 12, 2018\n ______________\n\n Before: JORDAN, VANASKIE, and NYGAARD, Circuit\n Judges\n\n\n The Honorable Judge Vanaskie transmitted the opinion to the Clerk for\nfiling prior to retiring from the bench on January 1, 2019. Due to the\nintervening holiday, the opinion has been entered on the docket by the\nClerk this day.\n\f (Opinion Filed: January 3, 2019)\n\n\nThomas M. Griffin [Argued]\nSurin & Griffin\n718 Arch Street\nSuite 701N\nPhiladelphia, PA 19106\n Counsel for Petitioner\n\nChad A. Readler, Acting Assistant Attorney General\nNancy E. Friedman, Senior Litigation Counsel\nJustin R. Markel, Senior Litigation Counsel\nGregory A. Pennington, Jr. [Argued]\nUnited States Department of Justice\nOffice of Immigration Litigation\nCivil Division\nP.O. Box 878\nBen Franklin Station\nWashington, DC 20044\n Counsel for Respondent\n\n ________________\n\n OPINION\n ________________\n\n\nVANASKIE, Circuit Judge.\n\n Seeking to remain in this country, Chiao Fang Ku\npetitions for review of a final order of removal issued by the\nBoard of Immigration Appeals (“BIA” or “Board”). The\nBoard determined that Ku had committed an aggravated felony\n\n\n\n\n 2\n\funder 8 U.S.C. § 1101(a)(43)(M)(i) because her prior\nconviction for wire fraud constituted an offense involving\nfraud or deceit in which the loss to the victims exceeded\n$10,000. The Board also found that Ku’s wire fraud conviction\nconstituted a “crime involving moral turpitude” under 8 U.S.C.\n§ 1182(a)(2)(A)(i)(I) such that, without a waiver, she is\nineligible for an adjustment of status. Although the\nImmigration Judge (“IJ”) granted Ku a waiver of\ninadmissibility under 8 U.S.C. § 1182(h)(1)(B) based on the\nextreme hardship that her deportation would cause her U.S.\nCitizen children, the Board reversed that decision. Ku\nchallenges each of the Board’s decisions.\n\n In Nijhawan v. Holder, 557 U.S. 29 (2009), the Court\nheld that determination of whether a fraud offense involved\nloss to the victims of $10,000 or more requires a circumstance-\nspecific approach, allowing the immigration court to review\nboth the charging document and sentencing-related materials\nto determine the loss amount attributable to the offense. On\nthe facts of this case, we find that the undisputed loss to the\nvictims of well over $10,000 was sufficiently tethered to Ku’s\nwire fraud conviction such that the conviction qualifies as an\naggravated felony. Furthermore, we find no error in the\nBoard’s determination that wire fraud constitutes a crime of\nmoral turpitude. Lastly, regarding the waiver of admissibility,\nwe do not have jurisdiction to review the discretionary denial\nof a waiver under § 212(h) of the INA. Accordingly, we will\ndeny in part and dismiss in part Ku’s petition for review.\n\n I.\n\n Ku is a native and citizen of Taiwan. She was admitted\nto the United States in 1997 and gained status as a lawful\npermanent resident in 2002. In 2014, Ku was charged with a\n\n\n\n\n 3\n\fsingle count of wire fraud, in violation of 18 U.S.C. § 1343.\nKu waived her right to an indictment and was charged by\ninformation only. The Information alleged that Ku was tasked\nwith managing the finances of her in-laws, E.R. and M.R, and\nthat she was provided access to her in-laws’ bank accounts in\nconnection with this role. The Information further alleged that,\nbetween May 2008 and July 2013, Ku defrauded her in-laws\nby using her access to their accounts to take money from them\nfor her personal use. In particular, it alleged that Ku: (1)\ntransferred funds from her in-laws’ accounts to her own\naccounts; (2) withdrew funds from her in-laws’ accounts as\ncash; (3) made payments from her in-laws’ accounts to pay off\nher personal credit cards; (4) wrote and cashed checks payable\nto herself by forging her mother-in-law’s signature; and (5)\nfraudulently applied for and obtained credit cards in her\nmother-in-law’s name and used them for her own purposes.\nThe Information alleged that, in total, Ku stole more than\n$950,000 from her in-laws.\n\n These allegations were incorporated by reference into\nthe sole count of the Information, which alleged that, on or\nabout November 7, 2011, Ku,\n\n having devised and intending to devise a\n scheme and artifice to defraud and to obtain\n money and property by means of materially\n false and fraudulent pretenses,\n representations, and promises, did cause\n writings, signs, signals, pictures, and sounds\n to be transmitted by means of wire\n communications in interstate commerce for\n the purpose of executing such scheme and\n artifice, to wit: executing an online payment\n from M.R.’s Sovereign Bank account, ending\n\n\n\n\n 4\n\f in 8497, to the defendant’s Chase credit card\n account, ending in 6567, in the amount of\n $2,290.53.\n\n(App. 590). The Information further contained forfeiture\nallegations, which directed that, upon conviction of the sole\ncount of the Information, Ku “forfeit to the United States . . .\nany property, real or personal, that constitutes, or is derived\nfrom, proceeds traceable to the commission of the offense,\nincluding but not limited to at least $950,000 in United States\ncurrency.” (App. 591).\n\n Ku pleaded guilty, pursuant to a plea agreement,1 to the\nsingle count of the Information. In her sentencing\nmemorandum, Ku, through counsel, acknowledged that she\nwas “now subject to automatic deportation as a result of her\nconviction in this case.” (App. 740). Ku was ultimately\nsentenced to a term of 18 months’ imprisonment, followed by\none year of supervised release. The judgment includes a total\nloss determination of $954,515.71 and orders restitution in that\namount. (App. 582).\n\n After Ku completed her sentence, she was served with\na Notice to Appear and placed in removal proceedings. The\nNotice to Appear charged Ku with being removable under\n§ 237(a)(2)(A)(iii) of the Immigration and Nationality Act\n(“INA” or the “Act”), 8 U.S.C. § 1227(a)(2)(A)(iii), as an\nindividual convicted of an aggravated felony as defined in 8\nU.S.C. § 1101(a)(43)(M)(i). The Immigration Judge\nconcluded that Ku was removable as charged because the\n\n\n 1\n The plea agreement is not part of the administrative\nrecord before us, nor was it in the record before the IJ or BIA.\n\n\n\n\n 5\n\frecord of conviction substantiated a finding that the wire fraud\ninvolved a loss of more than $10,000.\n\n In order to avoid deportation, Ku sought to re-adjust her\nstatus based on her U.S. Citizen husband.2 The Immigration\nJudge granted Ku’s application for a waiver of inadmissibility\nunder § 212(h)(1)(B) of the Act, 8 U.S.C. § 1182(h)(1)(B),\nbased on the extreme hardship that her deportation would cause\nher U.S. Citizen children, and granted Ku’s adjustment of\nstatus pursuant to § 245(a) of the INA, 8 U.S.C. § 1255(a).\n\n On appeal, the Board affirmed that the Government\ndemonstrated by clear and convincing evidence that Ku was\nremovable as an aggravated felon as defined at\n§ 1101(a)(43)(M)(i) in that her offense involved fraud or deceit\nin which the loss to the victims exceeded $10,000. In doing so,\nthe Board noted that the Information alleged that Ku stole more\nthan $950,000 in funds belonging to her in-laws, and that this\nallegation was incorporated by reference into the count to\nwhich Ku pleaded guilty. It also observed that the Information\nalso contained a forfeiture allegation stating that, upon\nconviction, Ku would forfeit over $950,000 in currency.\nFinally, the Board considered relevant that the Judgment of\nConviction found a total loss of over $950,000 and ordered\nrestitution in that amount.\n\n The Board further concluded that Ku’s conviction was\nfor a crime involving moral turpitude, making her inadmissible\nunder § 212(a)(2)(A)(i)(I) of the INA, 8 U.S.C.\n§ 1182(a)(2)(A)(i)(I), such that she required a § 212(h) waiver\n\n 2\n Ku's present husband is not the man to whom she was\npreviously married and whose parents are the elderly in-laws\nshe defrauded.\n\n\n\n\n 6\n\fin order to adjust her status. See 8 U.S.C. § 1255(a) (providing\nfor adjustment of status of certain aliens to that of an alien\nlawfully admitted for permanent residence); see also 8 U.S.C.\n§ 1182(h)(1)(B) (providing for waiver of inadmissibility at the\ndiscretion of the Attorney General). Although it acknowledged\nthe hardship posed to her family, the Board ultimately found\nthat, given the severity of her crime, Ku did not merit a\n§ 212(h) waiver. It accordingly vacated the decision of the IJ\nand denied Ku’s applications for a § 212(h) waiver and for\nadjustment of status. Ku timely filed a petition for review.\n\n II.\n\n Although we have jurisdiction to review final orders of\nremoval under 8 U.S.C. § 1252(a),3 “no court shall have\n\n 3\n We have taken a broad view of what constitutes a\n“final order of removal” under § 1252. Higgs v. Att’y Gen.,\n655 F.3d 333, 337–38 (3d Cir. 2011). “[A]n order is final for\njurisdictional purposes when a removability determination has\nbeen made that is no longer appealable to the BIA, regardless\n[of] whether a formal order of removal has been entered.” Id.\n(quoting Yusupov v. Att’y Gen., 518 F.3d 185, 195 (3d Cir.\n2008)); see also Shehu v. Att’y Gen., 482 F.3d 652, 656 (3d\nCir. 2007) (“[D]enial of a . . . petition for asylum, withholding\nof removal, and relief under the [Convention Against Torture]\nconstitutes ‘a final order of removal’ within the meaning of\n[§ 1252], [because] the alien is entitled to no further process\nbefore deportation.”). Here, although the Board did not\nexplicitly order Ku removed to Taiwan, it found her removable\nand denied her application for adjustment of status, her only\npetition for relief. (App. 5). Furthermore, the Board sustained\nDHS’s appeal, which requested that Ku be ordered removed to\nTaiwan. Accordingly, for the purposes of this appeal, we\n\n\n\n\n 7\n\fjurisdiction to review any final order of removal against an\nalien who is removable by reason of having committed [an\naggravated felony].” 8 U.S.C. § 1252(a)(2)(C). “We do,\nhowever, have jurisdiction to examine ‘constitutional claims or\nquestions of law.’” Fan Wang v. Att’y Gen., 898 F.3d 341, 343\n(3d Cir. 2018) (quoting Catwell v. Att’y Gen., 623 F.3d 199,\n205 (3d Cir. 2010); 8 U.S.C. § 1252(a)(2)(D)). Therefore, we\nhave authority to take up the issue, applying plenary review, of\nwhether Ku’s conviction qualifies as an aggravated felony\nbecause it is “a purely legal question, and one that governs our\nown jurisdiction.” Id. (quoting Valansi v. Ashcroft, 278 F.3d\n203, 207 (3d Cir. 2002)). We also review de novo the legal\nquestion of what elements of a federal criminal statute\nimplicate moral turpitude, while affording Chevron deference\nto the Board’s definition of “moral turpitude.” Knapik v.\nAshcroft, 384 F.3d 84, 88 (3d Cir. 2004).\n\n III.\n\n On appeal, Ku challenges all three aspects of the BIA’s\norder. First, she contends that the BIA incorrectly determined\nthat her wire-fraud conviction involved a loss of more than\n$10,000 by relying on evidence that was not sufficiently\ntethered to the sole count of conviction.4 Second, Ku argues\n\n\nconsider the Board’s order to be a final order of removal. The\nGovernment’s motion to remand this case to the Board for\nissuance of an order directing that Ku be removed to Taiwan\nand to allow the IJ to make additional findings on removability\nwill be denied as moot.\n 4\n We note that Ku does not challenge—and did not\nchallenge before the IJ or the Board—that her wire fraud\n\n\n\n\n 8\n\fthat the Board erred in finding that her wire-fraud conviction\nwas for a crime involving moral turpitude because the statute\nof conviction does not require a showing of intent. Third, Ku\nasserts that the BIA applied the incorrect legal standard in\nreversing the IJ’s grant of a discretionary waiver of\ninadmissibility. We reject all three of Ku’s challenges and\ntherefore deny the petition for review.\n\n A.\n\n Section 237(a)(2)(A)(iii) of the INA, as amended,\nprovides that “[a]ny alien who is convicted of an aggravated\nfelony at any time after admission is deportable.” 8 U.S.C.\n§ 1227(a)(2)(A)(iii). The Act defines “aggravated felony,” in\nrelevant part, as an offense that “involves fraud or deceit in\nwhich the loss to the victim or victims exceeds $10,000.” 8\nU.S.C. § 1101(a)(43)(M)(i).\n\n In Nijhawan v. Holder, the Supreme Court addressed\nthe issue of whether the $10,000 threshold of the aggravated\nfelony statute “refers to an element of a fraud statute or to the\nfactual circumstances surrounding commission of the crime on\na specific occasion.” 557 U.S. at 33. The Court adopted the\nlatter interpretation, characterizing the review as examining\n“the specific way in which an offender committed the crime on\na specific occasion.” Id. at 34. The Court distinguished the\n“circumstance-specific approach” to be used in determining\nwhether a crime “involves fraud or deceit in which the loss to\nthe victim or victims exceeds $10,000” from the “categorical\napproach” used in determining whether a crime is a “violent\nfelony” under the Armed Career Criminal Act (“ACCA”), 18\n\nconviction “involves fraud or deceit” under 8 U.S.C.\n§ 1101(a)(43)(M).\n\n\n\n\n 9\n\fU.S.C. § 924(e). Id. at 34–40. It also rejected the use of the\nso-called “modified categorical approach” employed in some\ncontexts, which would limit an IJ’s consideration to charging\ndocuments, jury instructions, special jury findings, or some\nequivalent judge-made findings and—in the case of a guilty\nplea—to the written plea documents or plea colloquy. Id. at\n41. While the Supreme Court acknowledged that “the statute\nforesees the use of fundamentally fair procedures,” it rejected\nthe argument that fairness requires such evidentiary\nlimitations. Id. Accordingly, it found “nothing unfair” about\nthe IJ’s reliance upon the defendant’s stipulation and the\ndistrict court’s restitution order to determine that the crime at\nissue was an “aggravated felony” under § 1101(a)(43)(M)(i).\nId. at 42–43.\n\n Since Nijhawan, we have consistently applied the\ncircumstance-specific approach to determine the amount of\nloss in “aggravated felony” cases. See, e.g., Kaplun v. Att’y\nGen., 602 F.3d 260, 265–66 (3d Cir. 2010); Doe v. Att’y Gen.,\n659 F.3d 266, 274–76 (3d Cir. 2011). Most recently, we\naddressed the issue in Fan Wang, in which we reviewed “not\nonly those documents that may be considered in a modified\ncategorical approach (the indictment, plea agreement, and\njudgment),” but also others, including “the presentence\ninvestigation report and any sentencing-related material.” 898\nF.3d at 348–49 (citations and internal quotation marks\nomitted). Relying on Nijhawan, we reasoned that\nconsideration of such materials “is appropriate so long as the\npetitioner has been given a ‘fair opportunity’ to challenge the\nGovernment’s claim.” Id. at 349 (quoting Nijhawan, 557 U.S.\nat 41). Accordingly, we determined that the Board did not go\nbeyond the bounds of proper review by examining the record—\nincluding the sole count of the superseding information, the\n\n\n\n\n 10\n\fplea colloquy, the presentence investigation report, the “total\nloss” specified in the judgment, and the restitution order—to\ndetermine whether the petitioner’s prior conviction was an\n“aggravated felony.” Id. at 349–50. In determining the proper\namount of loss in that case, we were persuaded by the\nGovernment’s argument that the loss amount listed in the\njudgment and restitution order was “undeniably tethered” to\nthe conduct for which the petitioner was convicted. Id. at 351.\n\n We consider the loss to the victims in this case—as\nevidenced by the Information, Judgment, and Restitution\nOrder—to be sufficiently tethered to the count of conviction\nsuch that Ku’s conviction was an aggravated felony.\nParagraphs 1 through 10 of the Information allege that Ku stole\nmore than $950,000 in funds belonging to her in-laws, and\nthese paragraphs were incorporated by reference into the count\nto which Ku pleaded guilty. Furthermore, the forfeiture\nallegation contained in the Information states that, upon\nconviction, Ku would forfeit the “proceeds traceable to the\ncommission of the offense, including but not limited to at least\n$950,000 in United States currency.” (App. 591). Finally, the\nJudgment of Conviction indicates a loss of $954,515.71 and\norders restitution in that amount. Each of these documents is\nreviewable under the circumstance-specific approach laid out\nby the Supreme Court in Nijhawan. Together, they provide\nclear and convincing evidence that Ku’s offense involved a\nloss of over $10,000. Nonetheless, we briefly addresses Ku’s\narguments to the contrary, all of which lack merit.\n\n 1.\n\n First, Ku contends that the circumstance-specific\napproach described in Nijhawan does not apply in her case\nbecause the single count of the Information made clear that it\n\n\n\n\n 11\n\fwas for the specified amount of $2,290.53. She urges us to\nread Nijhawan to have kept intact the modified categorical\napproach for cases in which the charging document contains a\nclear indication of the loss amount. Under the modified\ncategorical approach, she contends, the Board was correct in\nreviewing the Information but, because the count of conviction\ncontains a loss amount of $2,290.53, the Board should have\nstopped there.\n\n Contrary to Ku’s assertion, Nijhawan does not stand for\nthe proposition that, when the count of conviction contains a\nloss amount, immigration officials must look no further. The\nSupreme Court explicitly rejected the use of the modified\ncategorical approach in determining whether a prior conviction\nis an aggravated felony under § 1101(a)(43)(M)(i). Nijhawan,\n557 U.S. at 41–42; see also Kaplun, 602 F.3d at 265–66\n(interpreting Nijhawan). Rather, it determined that the\ncircumstance-specific approach is required because the\naggravated felony statute “refers to the particular\ncircumstances in which an offender committed a (more broadly\ndefined) fraud or deceit crime on a particular occasion,” and\nnot to an element of the offense. Nijhawan, 557 U.S. at 32.\nNoting that the Government in immigration proceedings is\nheld only to a “clear and convincing” burden of proof, and not\n“beyond a reasonable doubt,” the Supreme Court found\n“nothing unfair about [an IJ] rel[ying] upon earlier sentencing-\nrelated material”—in that case a sentencing stipulation and\nrestitution order. Id. at 42–43. It also noted that “the sole\npurpose of the aggravated felony inquiry is to ascertain the\nnature of a prior conviction; it is not an invitation to relitigate\nthe conviction itself.” Id. (internal quotation marks omitted).\n\n Nothing in Nijhawan suggests that the circumstance-\nspecific approach applies in some cases but not others, or that\n\n\n\n\n 12\n\fthe documents reviewable under that approach vary from case\nto case. Furthermore, we have consistently interpreted\nNijhawan as allowing an IJ, in determining the loss amount, to\nlook beyond the charging document to sentencing-related\nmaterials. See Kaplun, 602 F.3d at 265–66; Fan Wang, 898\nF.3d at 348–49. Ku has not persuaded us that our reading is\nincorrect.\n\n 2.\n\n Second, Ku contends that, because her conviction was\nfor “a single act of a $2,290.53 on-line transfer,” the losses she\ncaused through other acts and transactions are not sufficiently\n“tethered” to the count of conviction for purposes of the\naggravated felony statute. (Petitioner’s Br. at 27). In doing so,\nKu asks us to read the Information as charging her in Count\nOne with a “scheme and artifice to defraud” her in-laws of\n$2,290.53, and not as charging her with one instance of wire\nfraud that was part of a broader “scheme and artifice to\ndefraud” her in-laws of over $950,000. However, such an\ninterpretation is inconsistent with the language of the\nInformation. In Count One, the Government “re-alleges and\nincorporates by reference” the first eight paragraphs, which\nallege that, over five years, Ku defrauded her in-laws of more\nthan $950,000 by transferring funds from their accounts to her\nown accounts, withdrawing funds as cash, making payments to\ncredit card companies for charges she incurred, and writing and\ncashing checks payable to herself. (App. 588–90). The explicit\nincorporation of those paragraphs into the count to which Ku\npleaded guilty supports an interpretation of the count itself as\ndescribing Ku’s “scheme and artifice to defraud” her in-laws\nof more than $950,000.\n\n\n\n\n 13\n\f We are similarly unpersuaded by Ku’s contention that,\nbecause Paragraphs 1 through 8 of the Information describe\nconduct that does not necessarily amount to wire fraud, such\nconduct cannot count toward the total loss resulting from her\nconviction. It is incontrovertible that the “scheme and artifice\nto defraud” charged in Count One of the Information\nencompassed the whole course of Ku’s unlawful conduct,\nincluding the one incident in which Ku committed wire fraud\nin the amount of $2,390.53, and which resulted in a total loss\nof over $950,000. In short, because Ku pleaded guilty to\ncommitting wire fraud as part of a scheme to defraud her in-\nlaws of more than $950,000, the total loss amount is, to use our\nlanguage from Fan Wang, “undeniably tethered” to her wire\nfraud conviction.\n\n 3.\n\n Finally, Ku contends that the single-count Information\nto which she pleaded guilty is part of the “justice package”\nworked out between her and the Government and urges the\nCourt to defer to that agreement. (Petitioner’s Br. at 35). In\ndoing so, Ku relies on our opinion in Alaka v. Attorney\nGeneral, 456 F.3d 88 (3d Cir. 2006). However, the facts of\nthis case make it distinguishable from Alaka.\n\n In Alaka—which we decided prior to Nijhawan5—we\nheld that the IJ erred by considering the amount of intended\n\n\n 5\n Because Alaka was decided prior to the Supreme\nCourt’s decision in Nijhawan, its application of the modified\ncategorical approach to the aggravated-felony analysis does\nnot affect our decision. However, to the extent that Alaka\nstands for the proposition that an IJ may not consider dismissed\n\n\n\n\n 14\n\floss for all of the charges against the petitioner rather than the\nsingle count for which she was convicted. Alaka, 456 F.3d at\n106. The petitioner had been indicted on three counts for\nconduct involving fraudulent checks, but was convicted of only\none count, for which the actual loss was $4,716.68. Id. at 92.\nThe sentencing court nonetheless held that the petitioner’s\nconduct was part of a “common scheme or plan,” and therefore\nfound the total intended loss to be nearly $50,000. Id. It\nordered her to pay $4,716.68 in restitution. Id. In subsequent\nimmigration proceedings, the IJ concluded that the petitioner\nhad been convicted of an aggravated felony on the ground that\nthe intended loss was more than $10,000. Id. at 105, n.27. On\nappeal, we determined that, while the IJ properly considered\nthe factual findings of the sentencing report in determining\nwhether the offense was an aggravated felony, the loss amount\ntied to the dismissed charges was not properly considered as\npart of the aggravated-felony analysis. Id. at 106–08. In doing\nso, we noted that “the plain and unambiguous language of the\nstatute . . . predicates removal on a convicted offense resulting\nin losses greater than $10,000,” thereby foreclosing inclusion\nof losses stemming from unconvicted offenses. Id. 106–07\n(citations omitted). Furthermore, we considered that, because\nit is “the plea agreement that establishes the offense for which\nthe defendant will be convicted, it is to that agreement, and not\nthe indictment or the sentence, that we look in determining the\nintended loss.” Id. at 107. The petitioner “unmistakably pled\nguilty to one count, and the plea agreement plainly documented\nthat loss at less than $10,000.” Id. at 108 (citations and\nalterations omitted). Because the plea agreement “spell[ed] it\nout for us in black and white,” we concluded that the plea\n\n\ncharges when calculating the loss attributable to the conviction,\nit remains good law.\n\n\n\n\n 15\n\fagreement alone established the loss amount, and “not . . . the\nloss charged in the indictment, tabulated for restitution\npurposes, or calculated for sentencing.” Id. (citations omitted).\n\n Here, in stark contrast to the petitioner in Alaka, the\nrecord before us contains no plea agreement, and certainly not\none which explicitly spells out the loss amount to which Ku\npleaded guilty. Instead, Ku urges us to find that, based on the\nfact that the Government could have charged her with a much\nlonger list of crimes but did not, the loss amount as indicated\nin Count One was part of an explicit bargain between her and\nthe Government. However, this argument is based on pure\nconjecture. Absent a clear and unmistakable indication of loss\nin a written plea agreement, we are left with only the\nInformation, Judgment, and Restitution Order to determine the\nloss attributable to Ku’s conviction. As explained above, these\ndocuments, taken together, provide clear and convincing\nevidence that the loss amount attributable to Ku’s wire fraud\nconviction exceeded $10,000, and Ku has provided no plea\nagreement or any other document to the contrary.6\n\n 6\n The sentencing court in Alaka calculated the total loss\namount based on the “common scheme or plan,” which, it\nconsidered, included both the count of conviction and the\ndismissed counts, and we considered the IJ’s reliance on that\ncalculation to be in error in light of the plea agreement. 456\nF.3d at 106. But this does not help Ku. As explained above,\nthe wire fraud count to which Ku pleaded guilty was based in\npart on her “scheme and artifice to defraud” her in-laws of over\n$950,000. (App. 590). Unlike the sentencing court in Alaka,\nthe sentencing court in this case did not base its loss calculation\non any acts that were not explicitly incorporated into the count\nof conviction.\n\n\n\n\n 16\n\f Ku’s argument that this Court should respect the\n“justice package” between her and the Government also\ntouches on the Supreme Court’s landmark holdings in Padilla\nv. Kentucky, 559 U.S. 356 (2010), and Descamps v. United\nStates, 570 U.S. 254 (2013), both of which, she argues, counsel\ntoward respecting agreements between criminal defendants\nand the Government with respect to the collateral\nconsequences of a conviction. But this line of argument merely\nhighlights another critical shortcoming of Ku’s case. To the\nextent Ku argues that the Information was designed\nspecifically to avoid immigration consequences, there is no\nevidence in the record to support such a finding. Indeed, Ku’s\nattorney indicated in her sentencing memorandum that Ku “is\nnow subject to automatic deportation as a result of her\nconviction in this case.” (App. 740). This statement, while not\nconclusive, certainly undermines any assertion that the “justice\npackage” referred to by Ku was designed to avoid an\naggravated felony conviction. Indeed, absent any other\nevidence in the record to the contrary, the sentencing\nmemorandum supports a finding that, at the time of her guilty\nplea, Ku understood that she was pleading guilty to an\naggravated felony.\n\n B.\n\n Having concluded that the Board did not err in finding\nthat Ku was convicted of an aggravated felony, we turn to the\nquestion of whether Ku’s conviction constituted a “crime\ninvolving moral turpitude” under the INA. Ku argues that wire\nfraud is not a “crime involving moral turpitude” under 8 U.S.C.\n§ 1182(a)(2)(A)(i)(I) because it does not include as an element\nthe specific intent to defraud. This is incorrect.\n\n\n\n\n 17\n\f The statute provides that a person is guilty of wire fraud\nif, “having devised or intending to devise any scheme or\nartifice to defraud,” that person “transmits or causes to be\ntransmitted by means of wire, radio, or television\ncommunication in interstate or foreign commerce, any\nwritings, signs, signals, pictures, or sounds for the purpose of\nexecuting such scheme or artifice.” 18 U.S.C. § 1343. Courts\nhave long treated fraud crimes as “involving moral turpitude.”\nJordan v. De George, 341 U.S. 223, 232 (1951) (“[T]he\ndecided cases make it plain that crimes in which fraud was an\ningredient have always been regarded as involving moral\nturpitude.”); Singh v. Att’y Gen., 807 F.3d 547, 550 (3d Cir.\n2015) (“Crimes . . . involving allegations of dishonesty or fraud\nfall well within the recognized definition of ‘crimes involving\nmoral turpitude.’”). Furthermore, we have also consistently\nread the wire fraud statute as containing the element of specific\nintent. See, e.g., United States v. Andrews, 681 F.3d 509, 518\n(3d Cir. 2012) (“To prove wire fraud, the Government must\nestablish (1) the defendant’s knowing and willful participation\nin a scheme or artifice to defraud, (2) with the specific intent to\ndefraud, and (3) the use of . . . interstate wire communications\nin furtherance of the scheme.”) (internal quotation marks\nomitted) (emphasis added).\n\n Seeking to persuade us to revisit these tenets, Ku asks\nus to read the statutory terms “having devised” and “intending\nto devise” as disjunctive means of committing wire fraud, the\nlatter containing the mens rea of intent, and the former\neschewing any mens rea at all. But the language of the statute\ndoes not lend itself to such an interpretation. The specific\nintent requirement is contained in the latter part of the statute—\n“for the purpose of executing [a] scheme or artifice [to\ndefraud]”—and must be proved regardless of whether the\n\n\n\n\n 18\n\fperson made the transmission after “having devised” or while\n“intending to devise” the scheme to defraud. 18 U.S.C. § 1343.\nPlainly read, the language Ku seizes on, “having devised or\nintending to devise,” refers not to the requisite mens rea but to\nthe temporal relationship between the formation of the fraud\nscheme and the transmission itself. Either way, the person\nmust have made the transmission for the purpose of executing\nthe fraud scheme in order to be convicted.\n\n Ku’s statutory interpretation argument holds no weight.\nAccordingly, we see no need to revisit the long-held tenet that\nfraud crimes—including wire fraud—are crimes involving\nmoral turpitude under the INA.\n\n C.\n\n Finally, Ku asks us to find that the Board committed\nerror in its reversal of the IJ’s finding that she was eligible for\na discretionary waiver of inadmissibility based on the hardship\nher deportation would cause her U.S. citizen children.\nHowever, we lack jurisdiction over the Board’s decision on\nthis point.\n\n The INA provides that an alien is inadmissible to the\nUnited States if she has been convicted of a crime involving\nmoral turpitude. 8 U.S.C. § 1182(a)(2)(A)(i)(I). The Act also\nprovides, however, that the Attorney General may waive\ninadmissibility to allow an applicant to obtain adjustment of\nstatus under § 1182(h), “if the alien is a spouse, parent, or child\nof a United States citizen . . . and can show that denial of\nadmission would cause extreme hardship to the citizen . . . .”\nDe Leon–Reynoso v. Ashcroft, 293 F.3d 633, 637 (3d Cir.\n2002). The authority to waive one or more grounds of\ninadmissibility is vested solely in the Attorney General and “no\n\n\n\n\n 19\n\fcourt shall have jurisdiction to review” a decision to deny such\na request. 8 U.S.C. § 1252(a)(2)(B)(i).\n\n We may, however, review “constitutional claims or\nquestions of law raised upon a petition for review . . . .” Id. at\n§ 1252(a)(2)(D). Our jurisdiction in that respect is “narrowly\ncircumscribed” in that it is limited to “colorable claims or\nquestions of law.” Cospito v. Att’y Gen., 539 F.3d 166, 170 (3d\nCir. 2008) (per curiam) (quotation marks and citation omitted).\nWhile “[t]he question of our jurisdiction over a colorable legal\nclaim does not turn on whether that claim is ultimately\nmeritorious . . . , a party may not dress up a claim with legal\nclothing to invoke this Court's jurisdiction.” Pareja v. Att’y\nGen., 615 F.3d 180, 187 (3d Cir. 2010) (citations omitted).\n\n Ku argues that we have jurisdiction to consider her\npetition for review on the waiver issue because it presents a\nquestion of law, namely whether the Board applied the proper\nlegal standard in making the discretionary determination. But\nKu’s argument boils down to her contention that the Board\nfailed to consider certain equities relevant to the hardship\ndetermination. As we have consistently held, “arguments such\nas that an Immigration Judge or the BIA incorrectly weighed\nevidence, failed to consider evidence or improperly weighed\nequitable factors are not questions of law under\n§ 1252(a)(2)(D).” Jarbough v. Att’y Gen., 483 F.3d 184, 189\n(3d Cir. 2007). Because the substance of Ku’s petition for\nreview amounts to contesting the weight the Board should have\ngiven to the positive equities of her case, we do not have\njurisdiction over it and will dismiss in part that aspect of the\npetition.\n\n IV.\n\n\n\n\n 20\n\f For the foregoing reasons, we will deny in part and\ndismiss in part Ku's petition for review, and we will deny as\nmoot the Government's motion to remand.\n\n\n\n\n 21\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: CHIAO FANG KU, AKA Chiao Fang Ronan, AKA Anna Ronan, Petitioner v. ATTORNEY GENERAL UNITED STATES OF AMERICA, Respondent\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-03\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-3001\\n _____________\\n\\n CHIAO FANG KU,\\n AKA Chiao Fang Ronan, AKA Anna Ronan,\\n Petitioner\\n v.\\n\\nATTORNEY GENERAL UNITED STATES OF AMERICA,\\n Respondent\\n _____________\\n\\n On Petition for Review of an Order of the\\n Board of Immigration Appeals\\n (Agency No. A077-160-352)\\n Immigration Judge: Walter A. Durling\\n ______________\\n\\n Argued September 12, 2018\\n ______________\\n\\n Before: JORDAN, VANASKIE, and NYGAARD, Circuit\\n Judges\\n\\n\\n The Honorable Judge Vanaskie transmitted the opinion to the Clerk for\\nfiling prior to retiring from the bench on January 1, 2019. Due to the\\nintervening holiday, the opinion has been entered on the docket by the\\nClerk this day.\\n\\f (Opinion Filed: January 3, 2019)\\n\\n\\nThomas M. Griffin [Argued]\\nSurin & Griffin\\n718 Arch Street\\nSuite 701N\\nPhiladelphia, PA 19106\\n Counsel for Petitioner\\n\\nChad A. Readler, Acting Assistant Attorney General\\nNancy E. Friedman, Senior Litigation Counsel\\nJustin R. Markel, Senior Litigation Counsel\\nGregory A. Pennington, Jr. [Argued]\\nUnited States Department of Justice\\nOffice of Immigration Litigation\\nCivil Division\\nP.O. Box 878\\nBen Franklin Station\\nWashington, DC 20044\\n Counsel for Respondent\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\n\\nVANASKIE, Circuit Judge.\\n\\n Seeking to remain in this country, Chiao Fang Ku\\npetitions for review of a final order of removal issued by the\\nBoard of Immigration Appeals (“BIA” or “Board”). The\\nBoard determined that Ku had committed an aggravated felony\\n\\n\\n\\n\\n 2\\n\\funder 8 U.S.C. § 1101(a)(43)(M)(i) because her prior\\nconviction for wire fraud constituted an offense involving\\nfraud or deceit in which the loss to the victims exceeded\\n$10,000. The Board also found that Ku’s wire fraud conviction\\nconstituted a “crime involving moral turpitude” under 8 U.S.C.\\n§ 1182(a)(2)(A)(i)(I) such that, without a waiver, she is\\nineligible for an adjustment of status. Although the\\nImmigration Judge (“IJ”) granted Ku a waiver of\\ninadmissibility under 8 U.S.C. § 1182(h)(1)(B) based on the\\nextreme hardship that her deportation would cause her U.S.\\nCitizen children, the Board reversed that decision. Ku\\nchallenges each of the Board’s decisions.\\n\\n In Nijhawan v. Holder, 557 U.S. 29 (2009), the Court\\nheld that determination of whether a fraud offense involved\\nloss to the victims of $10,000 or more requires a circumstance-\\nspecific approach, allowing the immigration court to review\\nboth the charging document and sentencing-related materials\\nto determine the loss amount attributable to the offense. On\\nthe facts of this case, we find that the undisputed loss to the\\nvictims of well over $10,000 was sufficiently tethered to Ku’s\\nwire fraud conviction such that the conviction qualifies as an\\naggravated felony. Furthermore, we find no error in the\\nBoard’s determination that wire fraud constitutes a crime of\\nmoral turpitude. Lastly, regarding the waiver of admissibility,\\nwe do not have jurisdiction to review the discretionary denial\\nof a waiver under § 212(h) of the INA. Accordingly, we will\\ndeny in part and dismiss in part Ku’s petition for review.\\n\\n I.\\n\\n Ku is a native and citizen of Taiwan. She was admitted\\nto the United States in 1997 and gained status as a lawful\\npermanent resident in 2002. In 2014, Ku was charged with a\\n\\n\\n\\n\\n 3\\n\\fsingle count of wire fraud, in violation of 18 U.S.C. § 1343.\\nKu waived her right to an indictment and was charged by\\ninformation only. The Information alleged that Ku was tasked\\nwith managing the finances of her in-laws, E.R. and M.R, and\\nthat she was provided access to her in-laws’ bank accounts in\\nconnection with this role. The Information further alleged that,\\nbetween May 2008 and July 2013, Ku defrauded her in-laws\\nby using her access to their accounts to take money from them\\nfor her personal use. In particular, it alleged that Ku: (1)\\ntransferred funds from her in-laws’ accounts to her own\\naccounts; (2) withdrew funds from her in-laws’ accounts as\\ncash; (3) made payments from her in-laws’ accounts to pay off\\nher personal credit cards; (4) wrote and cashed checks payable\\nto herself by forging her mother-in-law’s signature; and (5)\\nfraudulently applied for and obtained credit cards in her\\nmother-in-law’s name and used them for her own purposes.\\nThe Information alleged that, in total, Ku stole more than\\n$950,000 from her in-laws.\\n\\n These allegations were incorporated by reference into\\nthe sole count of the Information, which alleged that, on or\\nabout November 7, 2011, Ku,\\n\\n having devised and intending to devise a\\n scheme and artifice to defraud and to obtain\\n money and property by means of materially\\n false and fraudulent pretenses,\\n representations, and promises, did cause\\n writings, signs, signals, pictures, and sounds\\n to be transmitted by means of wire\\n communications in interstate commerce for\\n the purpose of executing such scheme and\\n artifice, to wit: executing an online payment\\n from M.R.’s Sovereign Bank account, ending\\n\\n\\n\\n\\n 4\\n\\f in 8497, to the defendant’s Chase credit card\\n account, ending in 6567, in the amount of\\n $2,290.53.\\n\\n(App. 590). The Information further contained forfeiture\\nallegations, which directed that, upon conviction of the sole\\ncount of the Information, Ku “forfeit to the United States . . .\\nany property, real or personal, that constitutes, or is derived\\nfrom, proceeds traceable to the commission of the offense,\\nincluding but not limited to at least $950,000 in United States\\ncurrency.” (App. 591).\\n\\n Ku pleaded guilty, pursuant to a plea agreement,1 to the\\nsingle count of the Information. In her sentencing\\nmemorandum, Ku, through counsel, acknowledged that she\\nwas “now subject to automatic deportation as a result of her\\nconviction in this case.” (App. 740). Ku was ultimately\\nsentenced to a term of 18 months’ imprisonment, followed by\\none year of supervised release. The judgment includes a total\\nloss determination of $954,515.71 and orders restitution in that\\namount. (App. 582).\\n\\n After Ku completed her sentence, she was served with\\na Notice to Appear and placed in removal proceedings. The\\nNotice to Appear charged Ku with being removable under\\n§ 237(a)(2)(A)(iii) of the Immigration and Nationality Act\\n(“INA” or the “Act”), 8 U.S.C. § 1227(a)(2)(A)(iii), as an\\nindividual convicted of an aggravated felony as defined in 8\\nU.S.C. § 1101(a)(43)(M)(i). The Immigration Judge\\nconcluded that Ku was removable as charged because the\\n\\n\\n 1\\n The plea agreement is not part of the administrative\\nrecord before us, nor was it in the record before the IJ or BIA.\\n\\n\\n\\n\\n 5\\n\\frecord of conviction substantiated a finding that the wire fraud\\ninvolved a loss of more than $10,000.\\n\\n In order to avoid deportation, Ku sought to re-adjust her\\nstatus based on her U.S. Citizen husband.2 The Immigration\\nJudge granted Ku’s application for a waiver of inadmissibility\\nunder § 212(h)(1)(B) of the Act, 8 U.S.C. § 1182(h)(1)(B),\\nbased on the extreme hardship that her deportation would cause\\nher U.S. Citizen children, and granted Ku’s adjustment of\\nstatus pursuant to § 245(a) of the INA, 8 U.S.C. § 1255(a).\\n\\n On appeal, the Board affirmed that the Government\\ndemonstrated by clear and convincing evidence that Ku was\\nremovable as an aggravated felon as defined at\\n§ 1101(a)(43)(M)(i) in that her offense involved fraud or deceit\\nin which the loss to the victims exceeded $10,000. In doing so,\\nthe Board noted that the Information alleged that Ku stole more\\nthan $950,000 in funds belonging to her in-laws, and that this\\nallegation was incorporated by reference into the count to\\nwhich Ku pleaded guilty. It also observed that the Information\\nalso contained a forfeiture allegation stating that, upon\\nconviction, Ku would forfeit over $950,000 in currency.\\nFinally, the Board considered relevant that the Judgment of\\nConviction found a total loss of over $950,000 and ordered\\nrestitution in that amount.\\n\\n The Board further concluded that Ku’s conviction was\\nfor a crime involving moral turpitude, making her inadmissible\\nunder § 212(a)(2)(A)(i)(I) of the INA, 8 U.S.C.\\n§ 1182(a)(2)(A)(i)(I), such that she required a § 212(h) waiver\\n\\n 2\\n Ku's present husband is not the man to whom she was\\npreviously married and whose parents are the elderly in-laws\\nshe defrauded.\\n\\n\\n\\n\\n 6\\n\\fin order to adjust her status. See 8 U.S.C. § 1255(a) (providing\\nfor adjustment of status of certain aliens to that of an alien\\nlawfully admitted for permanent residence); see also 8 U.S.C.\\n§ 1182(h)(1)(B) (providing for waiver of inadmissibility at the\\ndiscretion of the Attorney General). Although it acknowledged\\nthe hardship posed to her family, the Board ultimately found\\nthat, given the severity of her crime, Ku did not merit a\\n§ 212(h) waiver. It accordingly vacated the decision of the IJ\\nand denied Ku’s applications for a § 212(h) waiver and for\\nadjustment of status. Ku timely filed a petition for review.\\n\\n II.\\n\\n Although we have jurisdiction to review final orders of\\nremoval under 8 U.S.C. § 1252(a),3 “no court shall have\\n\\n 3\\n We have taken a broad view of what constitutes a\\n“final order of removal” under § 1252. Higgs v. Att’y Gen.,\\n655 F.3d 333, 337–38 (3d Cir. 2011). “[A]n order is final for\\njurisdictional purposes when a removability determination has\\nbeen made that is no longer appealable to the BIA, regardless\\n[of] whether a formal order of removal has been entered.” Id.\\n(quoting Yusupov v. Att’y Gen., 518 F.3d 185, 195 (3d Cir.\\n2008)); see also Shehu v. Att’y Gen., 482 F.3d 652, 656 (3d\\nCir. 2007) (“[D]enial of a . . . petition for asylum, withholding\\nof removal, and relief under the [Convention Against Torture]\\nconstitutes ‘a final order of removal’ within the meaning of\\n[§ 1252], [because] the alien is entitled to no further process\\nbefore deportation.”). Here, although the Board did not\\nexplicitly order Ku removed to Taiwan, it found her removable\\nand denied her application for adjustment of status, her only\\npetition for relief. (App. 5). Furthermore, the Board sustained\\nDHS’s appeal, which requested that Ku be ordered removed to\\nTaiwan. Accordingly, for the purposes of this appeal, we\\n\\n\\n\\n\\n 7\\n\\fjurisdiction to review any final order of removal against an\\nalien who is removable by reason of having committed [an\\naggravated felony].” 8 U.S.C. § 1252(a)(2)(C). “We do,\\nhowever, have jurisdiction to examine ‘constitutional claims or\\nquestions of law.’” Fan Wang v. Att’y Gen., 898 F.3d 341, 343\\n(3d Cir. 2018) (quoting Catwell v. Att’y Gen., 623 F.3d 199,\\n205 (3d Cir. 2010); 8 U.S.C. § 1252(a)(2)(D)). Therefore, we\\nhave authority to take up the issue, applying plenary review, of\\nwhether Ku’s conviction qualifies as an aggravated felony\\nbecause it is “a purely legal question, and one that governs our\\nown jurisdiction.” Id. (quoting Valansi v. Ashcroft, 278 F.3d\\n203, 207 (3d Cir. 2002)). We also review de novo the legal\\nquestion of what elements of a federal criminal statute\\nimplicate moral turpitude, while affording Chevron deference\\nto the Board’s definition of “moral turpitude.” Knapik v.\\nAshcroft, 384 F.3d 84, 88 (3d Cir. 2004).\\n\\n III.\\n\\n On appeal, Ku challenges all three aspects of the BIA’s\\norder. First, she contends that the BIA incorrectly determined\\nthat her wire-fraud conviction involved a loss of more than\\n$10,000 by relying on evidence that was not sufficiently\\ntethered to the sole count of conviction.4 Second, Ku argues\\n\\n\\nconsider the Board’s order to be a final order of removal. The\\nGovernment’s motion to remand this case to the Board for\\nissuance of an order directing that Ku be removed to Taiwan\\nand to allow the IJ to make additional findings on removability\\nwill be denied as moot.\\n 4\\n We note that Ku does not challenge—and did not\\nchallenge before the IJ or the Board—that her wire fraud\\n\\n\\n\\n\\n 8\\n\\fthat the Board erred in finding that her wire-fraud conviction\\nwas for a crime involving moral turpitude because the statute\\nof conviction does not require a showing of intent. Third, Ku\\nasserts that the BIA applied the incorrect legal standard in\\nreversing the IJ’s grant of a discretionary waiver of\\ninadmissibility. We reject all three of Ku’s challenges and\\ntherefore deny the petition for review.\\n\\n A.\\n\\n Section 237(a)(2)(A)(iii) of the INA, as amended,\\nprovides that “[a]ny alien who is convicted of an aggravated\\nfelony at any time after admission is deportable.” 8 U.S.C.\\n§ 1227(a)(2)(A)(iii). The Act defines “aggravated felony,” in\\nrelevant part, as an offense that “involves fraud or deceit in\\nwhich the loss to the victim or victims exceeds $10,000.” 8\\nU.S.C. § 1101(a)(43)(M)(i).\\n\\n In Nijhawan v. Holder, the Supreme Court addressed\\nthe issue of whether the $10,000 threshold of the aggravated\\nfelony statute “refers to an element of a fraud statute or to the\\nfactual circumstances surrounding commission of the crime on\\na specific occasion.” 557 U.S. at 33. The Court adopted the\\nlatter interpretation, characterizing the review as examining\\n“the specific way in which an offender committed the crime on\\na specific occasion.” Id. at 34. The Court distinguished the\\n“circumstance-specific approach” to be used in determining\\nwhether a crime “involves fraud or deceit in which the loss to\\nthe victim or victims exceeds $10,000” from the “categorical\\napproach” used in determining whether a crime is a “violent\\nfelony” under the Armed Career Criminal Act (“ACCA”), 18\\n\\nconviction “involves fraud or deceit” under 8 U.S.C.\\n§ 1101(a)(43)(M).\\n\\n\\n\\n\\n 9\\n\\fU.S.C. § 924(e). Id. at 34–40. It also rejected the use of the\\nso-called “modified categorical approach” employed in some\\ncontexts, which would limit an IJ’s consideration to charging\\ndocuments, jury instructions, special jury findings, or some\\nequivalent judge-made findings and—in the case of a guilty\\nplea—to the written plea documents or plea colloquy. Id. at\\n41. While the Supreme Court acknowledged that “the statute\\nforesees the use of fundamentally fair procedures,” it rejected\\nthe argument that fairness requires such evidentiary\\nlimitations. Id. Accordingly, it found “nothing unfair” about\\nthe IJ’s reliance upon the defendant’s stipulation and the\\ndistrict court’s restitution order to determine that the crime at\\nissue was an “aggravated felony” under § 1101(a)(43)(M)(i).\\nId. at 42–43.\\n\\n Since Nijhawan, we have consistently applied the\\ncircumstance-specific approach to determine the amount of\\nloss in “aggravated felony” cases. See, e.g., Kaplun v. Att’y\\nGen., 602 F.3d 260, 265–66 (3d Cir. 2010); Doe v. Att’y Gen.,\\n659 F.3d 266, 274–76 (3d Cir. 2011). Most recently, we\\naddressed the issue in Fan Wang, in which we reviewed “not\\nonly those documents that may be considered in a modified\\ncategorical approach (the indictment, plea agreement, and\\njudgment),” but also others, including “the presentence\\ninvestigation report and any sentencing-related material.” 898\\nF.3d at 348–49 (citations and internal quotation marks\\nomitted). Relying on Nijhawan, we reasoned that\\nconsideration of such materials “is appropriate so long as the\\npetitioner has been given a ‘fair opportunity’ to challenge the\\nGovernment’s claim.” Id. at 349 (quoting Nijhawan, 557 U.S.\\nat 41). Accordingly, we determined that the Board did not go\\nbeyond the bounds of proper review by examining the record—\\nincluding the sole count of the superseding information, the\\n\\n\\n\\n\\n 10\\n\\fplea colloquy, the presentence investigation report, the “total\\nloss” specified in the judgment, and the restitution order—to\\ndetermine whether the petitioner’s prior conviction was an\\n“aggravated felony.” Id. at 349–50. In determining the proper\\namount of loss in that case, we were persuaded by the\\nGovernment’s argument that the loss amount listed in the\\njudgment and restitution order was “undeniably tethered” to\\nthe conduct for which the petitioner was convicted. Id. at 351.\\n\\n We consider the loss to the victims in this case—as\\nevidenced by the Information, Judgment, and Restitution\\nOrder—to be sufficiently tethered to the count of conviction\\nsuch that Ku’s conviction was an aggravated felony.\\nParagraphs 1 through 10 of the Information allege that Ku stole\\nmore than $950,000 in funds belonging to her in-laws, and\\nthese paragraphs were incorporated by reference into the count\\nto which Ku pleaded guilty. Furthermore, the forfeiture\\nallegation contained in the Information states that, upon\\nconviction, Ku would forfeit the “proceeds traceable to the\\ncommission of the offense, including but not limited to at least\\n$950,000 in United States currency.” (App. 591). Finally, the\\nJudgment of Conviction indicates a loss of $954,515.71 and\\norders restitution in that amount. Each of these documents is\\nreviewable under the circumstance-specific approach laid out\\nby the Supreme Court in Nijhawan. Together, they provide\\nclear and convincing evidence that Ku’s offense involved a\\nloss of over $10,000. Nonetheless, we briefly addresses Ku’s\\narguments to the contrary, all of which lack merit.\\n\\n 1.\\n\\n First, Ku contends that the circumstance-specific\\napproach described in Nijhawan does not apply in her case\\nbecause the single count of the Information made clear that it\\n\\n\\n\\n\\n 11\\n\\fwas for the specified amount of $2,290.53. She urges us to\\nread Nijhawan to have kept intact the modified categorical\\napproach for cases in which the charging document contains a\\nclear indication of the loss amount. Under the modified\\ncategorical approach, she contends, the Board was correct in\\nreviewing the Information but, because the count of conviction\\ncontains a loss amount of $2,290.53, the Board should have\\nstopped there.\\n\\n Contrary to Ku’s assertion, Nijhawan does not stand for\\nthe proposition that, when the count of conviction contains a\\nloss amount, immigration officials must look no further. The\\nSupreme Court explicitly rejected the use of the modified\\ncategorical approach in determining whether a prior conviction\\nis an aggravated felony under § 1101(a)(43)(M)(i). Nijhawan,\\n557 U.S. at 41–42; see also Kaplun, 602 F.3d at 265–66\\n(interpreting Nijhawan). Rather, it determined that the\\ncircumstance-specific approach is required because the\\naggravated felony statute “refers to the particular\\ncircumstances in which an offender committed a (more broadly\\ndefined) fraud or deceit crime on a particular occasion,” and\\nnot to an element of the offense. Nijhawan, 557 U.S. at 32.\\nNoting that the Government in immigration proceedings is\\nheld only to a “clear and convincing” burden of proof, and not\\n“beyond a reasonable doubt,” the Supreme Court found\\n“nothing unfair about [an IJ] rel[ying] upon earlier sentencing-\\nrelated material”—in that case a sentencing stipulation and\\nrestitution order. Id. at 42–43. It also noted that “the sole\\npurpose of the aggravated felony inquiry is to ascertain the\\nnature of a prior conviction; it is not an invitation to relitigate\\nthe conviction itself.” Id. (internal quotation marks omitted).\\n\\n Nothing in Nijhawan suggests that the circumstance-\\nspecific approach applies in some cases but not others, or that\\n\\n\\n\\n\\n 12\\n\\fthe documents reviewable under that approach vary from case\\nto case. Furthermore, we have consistently interpreted\\nNijhawan as allowing an IJ, in determining the loss amount, to\\nlook beyond the charging document to sentencing-related\\nmaterials. See Kaplun, 602 F.3d at 265–66; Fan Wang, 898\\nF.3d at 348–49. Ku has not persuaded us that our reading is\\nincorrect.\\n\\n 2.\\n\\n Second, Ku contends that, because her conviction was\\nfor “a single act of a $2,290.53 on-line transfer,” the losses she\\ncaused through other acts and transactions are not sufficiently\\n“tethered” to the count of conviction for purposes of the\\naggravated felony statute. (Petitioner’s Br. at 27). In doing so,\\nKu asks us to read the Information as charging her in Count\\nOne with a “scheme and artifice to defraud” her in-laws of\\n$2,290.53, and not as charging her with one instance of wire\\nfraud that was part of a broader “scheme and artifice to\\ndefraud” her in-laws of over $950,000. However, such an\\ninterpretation is inconsistent with the language of the\\nInformation. In Count One, the Government “re-alleges and\\nincorporates by reference” the first eight paragraphs, which\\nallege that, over five years, Ku defrauded her in-laws of more\\nthan $950,000 by transferring funds from their accounts to her\\nown accounts, withdrawing funds as cash, making payments to\\ncredit card companies for charges she incurred, and writing and\\ncashing checks payable to herself. (App. 588–90). The explicit\\nincorporation of those paragraphs into the count to which Ku\\npleaded guilty supports an interpretation of the count itself as\\ndescribing Ku’s “scheme and artifice to defraud” her in-laws\\nof more than $950,000.\\n\\n\\n\\n\\n 13\\n\\f We are similarly unpersuaded by Ku’s contention that,\\nbecause Paragraphs 1 through 8 of the Information describe\\nconduct that does not necessarily amount to wire fraud, such\\nconduct cannot count toward the total loss resulting from her\\nconviction. It is incontrovertible that the “scheme and artifice\\nto defraud” charged in Count One of the Information\\nencompassed the whole course of Ku’s unlawful conduct,\\nincluding the one incident in which Ku committed wire fraud\\nin the amount of $2,390.53, and which resulted in a total loss\\nof over $950,000. In short, because Ku pleaded guilty to\\ncommitting wire fraud as part of a scheme to defraud her in-\\nlaws of more than $950,000, the total loss amount is, to use our\\nlanguage from Fan Wang, “undeniably tethered” to her wire\\nfraud conviction.\\n\\n 3.\\n\\n Finally, Ku contends that the single-count Information\\nto which she pleaded guilty is part of the “justice package”\\nworked out between her and the Government and urges the\\nCourt to defer to that agreement. (Petitioner’s Br. at 35). In\\ndoing so, Ku relies on our opinion in Alaka v. Attorney\\nGeneral, 456 F.3d 88 (3d Cir. 2006). However, the facts of\\nthis case make it distinguishable from Alaka.\\n\\n In Alaka—which we decided prior to Nijhawan5—we\\nheld that the IJ erred by considering the amount of intended\\n\\n\\n 5\\n Because Alaka was decided prior to the Supreme\\nCourt’s decision in Nijhawan, its application of the modified\\ncategorical approach to the aggravated-felony analysis does\\nnot affect our decision. However, to the extent that Alaka\\nstands for the proposition that an IJ may not consider dismissed\\n\\n\\n\\n\\n 14\\n\\floss for all of the charges against the petitioner rather than the\\nsingle count for which she was convicted. Alaka, 456 F.3d at\\n106. The petitioner had been indicted on three counts for\\nconduct involving fraudulent checks, but was convicted of only\\none count, for which the actual loss was $4,716.68. Id. at 92.\\nThe sentencing court nonetheless held that the petitioner’s\\nconduct was part of a “common scheme or plan,” and therefore\\nfound the total intended loss to be nearly $50,000. Id. It\\nordered her to pay $4,716.68 in restitution. Id. In subsequent\\nimmigration proceedings, the IJ concluded that the petitioner\\nhad been convicted of an aggravated felony on the ground that\\nthe intended loss was more than $10,000. Id. at 105, n.27. On\\nappeal, we determined that, while the IJ properly considered\\nthe factual findings of the sentencing report in determining\\nwhether the offense was an aggravated felony, the loss amount\\ntied to the dismissed charges was not properly considered as\\npart of the aggravated-felony analysis. Id. at 106–08. In doing\\nso, we noted that “the plain and unambiguous language of the\\nstatute . . . predicates removal on a convicted offense resulting\\nin losses greater than $10,000,” thereby foreclosing inclusion\\nof losses stemming from unconvicted offenses. Id. 106–07\\n(citations omitted). Furthermore, we considered that, because\\nit is “the plea agreement that establishes the offense for which\\nthe defendant will be convicted, it is to that agreement, and not\\nthe indictment or the sentence, that we look in determining the\\nintended loss.” Id. at 107. The petitioner “unmistakably pled\\nguilty to one count, and the plea agreement plainly documented\\nthat loss at less than $10,000.” Id. at 108 (citations and\\nalterations omitted). Because the plea agreement “spell[ed] it\\nout for us in black and white,” we concluded that the plea\\n\\n\\ncharges when calculating the loss attributable to the conviction,\\nit remains good law.\\n\\n\\n\\n\\n 15\\n\\fagreement alone established the loss amount, and “not . . . the\\nloss charged in the indictment, tabulated for restitution\\npurposes, or calculated for sentencing.” Id. (citations omitted).\\n\\n Here, in stark contrast to the petitioner in Alaka, the\\nrecord before us contains no plea agreement, and certainly not\\none which explicitly spells out the loss amount to which Ku\\npleaded guilty. Instead, Ku urges us to find that, based on the\\nfact that the Government could have charged her with a much\\nlonger list of crimes but did not, the loss amount as indicated\\nin Count One was part of an explicit bargain between her and\\nthe Government. However, this argument is based on pure\\nconjecture. Absent a clear and unmistakable indication of loss\\nin a written plea agreement, we are left with only the\\nInformation, Judgment, and Restitution Order to determine the\\nloss attributable to Ku’s conviction. As explained above, these\\ndocuments, taken together, provide clear and convincing\\nevidence that the loss amount attributable to Ku’s wire fraud\\nconviction exceeded $10,000, and Ku has provided no plea\\nagreement or any other document to the contrary.6\\n\\n 6\\n The sentencing court in Alaka calculated the total loss\\namount based on the “common scheme or plan,” which, it\\nconsidered, included both the count of conviction and the\\ndismissed counts, and we considered the IJ’s reliance on that\\ncalculation to be in error in light of the plea agreement. 456\\nF.3d at 106. But this does not help Ku. As explained above,\\nthe wire fraud count to which Ku pleaded guilty was based in\\npart on her “scheme and artifice to defraud” her in-laws of over\\n$950,000. (App. 590). Unlike the sentencing court in Alaka,\\nthe sentencing court in this case did not base its loss calculation\\non any acts that were not explicitly incorporated into the count\\nof conviction.\\n\\n\\n\\n\\n 16\\n\\f Ku’s argument that this Court should respect the\\n“justice package” between her and the Government also\\ntouches on the Supreme Court’s landmark holdings in Padilla\\nv. Kentucky, 559 U.S. 356 (2010), and Descamps v. United\\nStates, 570 U.S. 254 (2013), both of which, she argues, counsel\\ntoward respecting agreements between criminal defendants\\nand the Government with respect to the collateral\\nconsequences of a conviction. But this line of argument merely\\nhighlights another critical shortcoming of Ku’s case. To the\\nextent Ku argues that the Information was designed\\nspecifically to avoid immigration consequences, there is no\\nevidence in the record to support such a finding. Indeed, Ku’s\\nattorney indicated in her sentencing memorandum that Ku “is\\nnow subject to automatic deportation as a result of her\\nconviction in this case.” (App. 740). This statement, while not\\nconclusive, certainly undermines any assertion that the “justice\\npackage” referred to by Ku was designed to avoid an\\naggravated felony conviction. Indeed, absent any other\\nevidence in the record to the contrary, the sentencing\\nmemorandum supports a finding that, at the time of her guilty\\nplea, Ku understood that she was pleading guilty to an\\naggravated felony.\\n\\n B.\\n\\n Having concluded that the Board did not err in finding\\nthat Ku was convicted of an aggravated felony, we turn to the\\nquestion of whether Ku’s conviction constituted a “crime\\ninvolving moral turpitude” under the INA. Ku argues that wire\\nfraud is not a “crime involving moral turpitude” under 8 U.S.C.\\n§ 1182(a)(2)(A)(i)(I) because it does not include as an element\\nthe specific intent to defraud. This is incorrect.\\n\\n\\n\\n\\n 17\\n\\f The statute provides that a person is guilty of wire fraud\\nif, “having devised or intending to devise any scheme or\\nartifice to defraud,” that person “transmits or causes to be\\ntransmitted by means of wire, radio, or television\\ncommunication in interstate or foreign commerce, any\\nwritings, signs, signals, pictures, or sounds for the purpose of\\nexecuting such scheme or artifice.” 18 U.S.C. § 1343. Courts\\nhave long treated fraud crimes as “involving moral turpitude.”\\nJordan v. De George, 341 U.S. 223, 232 (1951) (“[T]he\\ndecided cases make it plain that crimes in which fraud was an\\ningredient have always been regarded as involving moral\\nturpitude.”); Singh v. Att’y Gen., 807 F.3d 547, 550 (3d Cir.\\n2015) (“Crimes . . . involving allegations of dishonesty or fraud\\nfall well within the recognized definition of ‘crimes involving\\nmoral turpitude.’”). Furthermore, we have also consistently\\nread the wire fraud statute as containing the element of specific\\nintent. See, e.g., United States v. Andrews, 681 F.3d 509, 518\\n(3d Cir. 2012) (“To prove wire fraud, the Government must\\nestablish (1) the defendant’s knowing and willful participation\\nin a scheme or artifice to defraud, (2) with the specific intent to\\ndefraud, and (3) the use of . . . interstate wire communications\\nin furtherance of the scheme.”) (internal quotation marks\\nomitted) (emphasis added).\\n\\n Seeking to persuade us to revisit these tenets, Ku asks\\nus to read the statutory terms “having devised” and “intending\\nto devise” as disjunctive means of committing wire fraud, the\\nlatter containing the mens rea of intent, and the former\\neschewing any mens rea at all. But the language of the statute\\ndoes not lend itself to such an interpretation. The specific\\nintent requirement is contained in the latter part of the statute—\\n“for the purpose of executing [a] scheme or artifice [to\\ndefraud]”—and must be proved regardless of whether the\\n\\n\\n\\n\\n 18\\n\\fperson made the transmission after “having devised” or while\\n“intending to devise” the scheme to defraud. 18 U.S.C. § 1343.\\nPlainly read, the language Ku seizes on, “having devised or\\nintending to devise,” refers not to the requisite mens rea but to\\nthe temporal relationship between the formation of the fraud\\nscheme and the transmission itself. Either way, the person\\nmust have made the transmission for the purpose of executing\\nthe fraud scheme in order to be convicted.\\n\\n Ku’s statutory interpretation argument holds no weight.\\nAccordingly, we see no need to revisit the long-held tenet that\\nfraud crimes—including wire fraud—are crimes involving\\nmoral turpitude under the INA.\\n\\n C.\\n\\n Finally, Ku asks us to find that the Board committed\\nerror in its reversal of the IJ’s finding that she was eligible for\\na discretionary waiver of inadmissibility based on the hardship\\nher deportation would cause her U.S. citizen children.\\nHowever, we lack jurisdiction over the Board’s decision on\\nthis point.\\n\\n The INA provides that an alien is inadmissible to the\\nUnited States if she has been convicted of a crime involving\\nmoral turpitude. 8 U.S.C. § 1182(a)(2)(A)(i)(I). The Act also\\nprovides, however, that the Attorney General may waive\\ninadmissibility to allow an applicant to obtain adjustment of\\nstatus under § 1182(h), “if the alien is a spouse, parent, or child\\nof a United States citizen . . . and can show that denial of\\nadmission would cause extreme hardship to the citizen . . . .”\\nDe Leon–Reynoso v. Ashcroft, 293 F.3d 633, 637 (3d Cir.\\n2002). The authority to waive one or more grounds of\\ninadmissibility is vested solely in the Attorney General and “no\\n\\n\\n\\n\\n 19\\n\\fcourt shall have jurisdiction to review” a decision to deny such\\na request. 8 U.S.C. § 1252(a)(2)(B)(i).\\n\\n We may, however, review “constitutional claims or\\nquestions of law raised upon a petition for review . . . .” Id. at\\n§ 1252(a)(2)(D). Our jurisdiction in that respect is “narrowly\\ncircumscribed” in that it is limited to “colorable claims or\\nquestions of law.” Cospito v. Att’y Gen., 539 F.3d 166, 170 (3d\\nCir. 2008) (per curiam) (quotation marks and citation omitted).\\nWhile “[t]he question of our jurisdiction over a colorable legal\\nclaim does not turn on whether that claim is ultimately\\nmeritorious . . . , a party may not dress up a claim with legal\\nclothing to invoke this Court's jurisdiction.” Pareja v. Att’y\\nGen., 615 F.3d 180, 187 (3d Cir. 2010) (citations omitted).\\n\\n Ku argues that we have jurisdiction to consider her\\npetition for review on the waiver issue because it presents a\\nquestion of law, namely whether the Board applied the proper\\nlegal standard in making the discretionary determination. But\\nKu’s argument boils down to her contention that the Board\\nfailed to consider certain equities relevant to the hardship\\ndetermination. As we have consistently held, “arguments such\\nas that an Immigration Judge or the BIA incorrectly weighed\\nevidence, failed to consider evidence or improperly weighed\\nequitable factors are not questions of law under\\n§ 1252(a)(2)(D).” Jarbough v. Att’y Gen., 483 F.3d 184, 189\\n(3d Cir. 2007). Because the substance of Ku’s petition for\\nreview amounts to contesting the weight the Board should have\\ngiven to the positive equities of her case, we do not have\\njurisdiction over it and will dismiss in part that aspect of the\\npetition.\\n\\n IV.\\n\\n\\n\\n\\n 20\\n\\f For the foregoing reasons, we will deny in part and\\ndismiss in part Ku's petition for review, and we will deny as\\nmoot the Government's motion to remand.\\n\\n\\n\\n\\n 21\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":61,"cells":{"id":{"kind":"number","value":4580566,"string":"4,580,566"},"name":{"kind":"string","value":"T MOBILE NORTHEAST LLC, Appellant v. CITY OF WILMINGTON, DELAWARE ; City of Wilmington Zoning Board of Adjustment"},"name_abbreviation":{"kind":"string","value":"T Mobile Northeast LLC v. City of Wilmington"},"decision_date":{"kind":"string","value":"2019-01-10"},"docket_number":{"kind":"string","value":"18-1831"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Jordan, Nygaard, Vanaskie\", \"parties\": \"\", \"opinions\": [{\"author\": \"JORDAN, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 18-1831\\n _____________\\n\\n T MOBILE NORTHEAST LLC,\\n Appellant\\n\\n v.\\n\\n CITY OF WILMINGTON, DELAWARE;\\nCITY OF WILMINGTON ZONING BOARD OF ADJUSTMENT\\n _____________\\n\\n On Appeal from the United States District Court\\n for the District of Delaware\\n (D.C. No. 1-16-cv-01108)\\n District Judge: Hon. Eduardo C. Robreno\\n _______________\\n\\n Argued\\n September 12, 2018\\n\\nBefore: JORDAN, NYGAARD, and VANASKIE, * Circuit Judge\\n (Filed: January 10, 2019)\\n\\n\\n *\\n The Honorable Thomas I. Vanaskie retired from the\\nCourt on January 1, 2019 after the argument and conference\\nin this case, but before the filing of the opinion. This opinion\\nis filed by a quorum of the panel pursuant to 28 U.S.C.\\n§ 46(d) and Third Circuit I.O.P. Chapter 12.\\n\\f _______________\\n\\nThomas S. Thompson [ARGUED]\\nDavis Wright Tremaine\\n1919 Pennsylvania Avenue, NW\\nSte. 800\\nWashington, DC 20006\\n\\nCounsel for Appellant\\n\\nJoseph Van Eaton [ARGUED]\\nBest Best & Krieger\\n2000 Pennsylvania Avenue\\nSte. 5300\\nWashington, DC 20006\\n\\nCounsel for Appellees\\n _______________\\n\\n OPINION OF THE COURT\\n _______________\\n\\n\\nJORDAN, Circuit Judge.\\n\\n No one likes bad cell phone reception or slow\\nstreaming data on their smartphone, but that does not mean\\nanyone wants a cellular antenna in their neighborhood, which\\nis why there are zoning battles like the one central to this\\ncase.\\n\\n T Mobile Northeast LLC (“T Mobile”), a wireless\\ntelecommunications service provider, applied to the Zoning\\nBoard of Adjustment (“ZBA”) of the City of Wilmington,\\nDelaware for permission to erect an antenna in the City. The\\n\\n\\n\\n\\n 2\\n\\fZBA said no. So, relying on a provision of federal law that\\nallows a disappointed wireless service provider like T Mobile\\nto seek review in a district court “within 30 days after” a\\nzoning authority’s “final action,” 47 U.S.C.\\n§ 332(c)(7)(B)(v), T Mobile filed suit. After the case had\\nproceeded for over a year, however, the District Court\\nconcluded that it lacked jurisdiction. The Court reasoned that\\nbecause T Mobile filed its complaint before the ZBA released\\na written decision confirming an earlier oral rejection of the\\nzoning application, the claim was not ripe. And, since\\nT Mobile did not supplement its complaint to include the\\nZBA’s written decision within 30 days of its issuance, the\\nCourt also concluded that relation back could not remedy the\\nripeness defect. The District Court thus granted the City’s\\nmotion for summary judgment.\\n\\n T Mobile now appeals. It argues that its complaint\\nwas not premature or, in the alternative, that its supplemental\\npleading cured any ripeness problem. We agree that the grant\\nof summary judgment was improper and, for the reasons that\\nfollow, will remand the case for further proceedings\\nconsistent with this opinion.\\n\\nI. BACKGROUND\\n\\n A. Statutory Framework\\n\\n This dispute is governed by the Telecommunications\\nAct of 1996 (“TCA”), which amended the Federal\\nCommunications Act of 1934 and includes provisions on\\nmobile phone services. Pub. L. No. 104-104, §§ 1, 704, 110\\nStat. 56, 56, 151 (1996); 47 U.S.C. § 332. Passed to\\n“encourage the rapid deployment of new telecommunications\\n\\n\\n\\n\\n 3\\n\\ftechnologies,” Preamble, 110 Stat. at 56, the TCA provides\\nfor expedited review in federal court of a denial of permission\\nto build a cell phone antenna, id. § 704, 110 Stat. at 151-52.\\nSuch review is a “benefit Congress expressly intended to\\nconfer on wireless providers[.]” Nextel W. Corp. v. Unity\\nTwp., 282 F.3d 257, 264 (3d Cir. 2002). At the same time,\\nthe TCA also serves to preserve local zoning authority. 47\\nU.S.C. § 332(c)(7).\\n\\n At issue here are three key sections of the statute.\\nFirst, the TCA mandates that “[a] State or local government\\nor instrumentality thereof shall act on any request for\\nauthorization to place, construct, or modify personal wireless\\nservice facilities within a reasonable period of time after the\\nrequest is duly filed[.]” Id. § 332(c)(7)(B)(ii). The Federal\\nCommunications Commission (“FCC”) has interpreted\\n“reasonable period of time” in that statutory provision to\\nmean that zoning authorities have a “shot clock” 1 and must\\nact within 90 days of an application to attach an antenna to an\\nexisting structure or 150 days of an application where a new\\nsupport structure is to be built. Petition for Declaratory\\n\\n 1\\n “Shot clock” is a term borrowed from basketball. In\\nthat game, it signifies a time limit to make a shot attempt,\\nbeginning once a team has possession of the basketball. See,\\ne.g., Nat’s Basketball Ass’n, NBA Rulebook Rule No. 7: Shot\\nClock (2018-2019), http://official.nba.com/rule-no-7-24-\\nsecond-clock/. If the team has not made a shot attempt, i.e.,\\nacted, within the prescribed time limit, it forfeits possession\\nof the ball. Id. Here, the permitting authority has exclusive\\njurisdiction over an application until it fails to act within a\\n“reasonable period of time.” 47 U.S.C. §§ 332(c)(7)(A),\\n332(c)(7)(B)(ii).\\n\\n\\n\\n\\n 4\\n\\fRuling to Clarify Provisions of Section 332(c)(7)(B), 24 FCC\\nRcd. 13994, 14008, 14012 (2009). Second, in what we will\\ncall the “review provision” of the statute, the TCA grants\\n“[a]ny person adversely affected by any final action or failure\\nto act by a State or local government or any instrumentality\\nthereof” a right to have that locality’s decision reviewed by\\n“commenc[ing] an action” “within 30 days” in district court.\\n47 U.S.C. § 332(c)(7)(B)(v). Third, in the statute’s “denial\\nprovision,” the TCA states that “[a]ny decision by a State or\\nlocal government or instrumentality thereof to deny a request\\nto place, construct, or modify personal wireless service\\nfacilities shall be in writing and supported by substantial\\nevidence contained in a written record.” Id.\\n§ 332(c)(7)(B)(iii). Notably, the terms “act,” “final action,”\\nand “decision … to deny” are not defined in the TCA.\\nFurthermore, the statute does not make clear whether “final\\naction” should be read to encompass all decisions to deny,\\nincluding oral ones, nor does it address whether there is a\\ndifference between an “act” for purposes of the shot clock\\nand a “final action” for purposes of judicial review.\\n\\n B. Factual Background\\n\\n T Mobile is a telecommunications service provider. It\\nsays that it needs to erect a cellular antenna to fill “a\\nsignificant gap” in coverage for its customers in Wilmington,\\nDelaware, (Opening Br. at 3) presumably where there has\\nbeen an increase in phone calls and data usage. T Mobile\\nwants to put its antenna on top of a senior living high-rise in\\nthe City, but, because a special exception to local zoning laws\\nis needed, it first had to go to the ZBA. It filed an initial\\napplication and then, on August 25, 2016, a final amended\\napplication, seeking the exception.\\n\\n\\n\\n\\n 5\\n\\f The ZBA held a hearing on October 26, 2016, to\\nconsider T Mobile’s request, some two months after the final\\namended application was submitted. During the hearing,\\nT Mobile presented evidence of the need for the antenna and\\ndiscussed proposals to address aesthetic concerns. The ZBA\\nalso received objections from members of the local\\ncommunity, some of whom were outspoken in worrying\\nabout the effects of radio frequency emissions. At the end of\\nthe hearing, the ZBA denied T Mobile’s application in a\\nunanimous oral decision.\\n\\n The Board gave several reasons for the denial. One\\nboard member said the ZBA should not encourage the use of\\na senior living community rooftop as the base for an antenna\\nbecause of the potential adverse effect on the properties in the\\nneighborhood. Another board member said there was not\\nenough proof of a need for additional coverage to support the\\napplication. The Chairman said there was not enough\\nevidence that T Mobile needed the antenna and that it did not\\nappear to satisfy the zoning code in terms of placement and\\nheight restrictions.\\n\\n The ZBA’s oral decision to deny the application was\\nnot put in writing on October 26 or anytime soon thereafter.\\nAccording to T Mobile, that fits a “pattern and practice of\\n[the ZBA] not issuing a written decision of land use denials\\nunless or until the City is sued.” (Opening Br. at 7.) Only\\nafter T Mobile had filed its initial complaint in the District\\nCourt, and after the City filed its answer, did the ZBA issue\\nits written decision and explanation of its reasoning for\\ndenying the application.\\n\\n\\n\\n\\n 6\\n\\f T Mobile asserts that the denial of its application\\nviolates the TCA. Under the statute, such a denial is invalid\\nif it has the “effect of prohibiting the provision of personal\\nwireless services[,]” 47 U.S.C. § 332(c)(7)(B)(i)(II), or is “on\\nthe basis of the environmental effects of radio frequency\\nemissions[,]” id. at § 332(c)(7)(B)(iv). T Mobile claims that\\nWilmington’s denial was improper on both of those grounds. 2\\nBut those assertions go to the merits and are not actually\\nbefore us on this appeal. At issue now is whether T Mobile’s\\nclaim can be heard at all.\\n\\n C. Procedural History\\n\\n Evidently with its eye on the 30-day deadline in the\\nTCA’s review provision, T Mobile filed a lawsuit in the\\nUnited States District Court for the District of Delaware\\nwithin 30 days of the ZBA’s oral decision, challenging that\\ndenial. 3 In addition to its claims on the merits, T Mobile’s\\ninitial complaint alleged that the City violated procedures\\nmandated in the TCA, specifically those in the denial\\nprovision, by failing to provide a written decision\\n\\n 2\\n T Mobile also raised a Delaware state law claim.\\nThat claim is not at issue here and does not impact\\nT Mobile’s claims under federal law.\\n 3\\n For reasons discussed herein, the 30-day filing\\ndeadline was not triggered by the oral decision. See infra pp.\\n12-20. If it were, however, T Mobile’s complaint would have\\nbeen timely. The oral decision was delivered at the\\nOctober 26, 2016 hearing. Suit was filed on November 28,\\n2016, but because the thirtieth day from October 26 fell on a\\nweekend, the November 28 filing was within the 30-day\\nwindow. Fed. R. Civ. P. 6(a)(1).\\n\\n\\n\\n\\n 7\\n\\fcontemporaneous with its oral decision and by not supporting\\nthe denial with substantial evidence.\\n\\n The parties entered into a stipulation asking the\\nDistrict Court for an expedited case schedule, as provided for\\nin the review provision of the TCA. 47 U.S.C.\\n§ 332(c)(7)(B)(v). That request was granted. Wilmington\\nthen answered the complaint, asserting a number of\\naffirmative defenses, including that the complaint was not\\nripe because the ZBA had not yet issued a final written\\ndecision. Nevertheless, the City did not, at that time, file a\\nmotion to dismiss for failure to state a claim or for lack of\\njurisdiction. Two days after the City filed its answer, the\\nZBA issued a written decision on T Mobile’s application.\\nThe parties pressed forward with the suit and prepared a\\ndiscovery plan, which specifically mentioned the written\\ndecision. T Mobile filed a motion for summary judgment,\\nwhich the City met with a cross-motion for summary\\njudgment. The City’s motion was styled in the alternative as\\na motion to dismiss the complaint as unripe because it was\\nfiled prematurely, i.e., before the written decision had been\\nissued.\\n\\n Not until December 21, 2017, nearly a year after the\\nZBA issued its written denial, did T Mobile file a motion\\nseeking leave to amend or supplement the initial complaint to\\nnote the issuance of that written decision. 4 The District Court\\n\\n 4\\n When “[a] claim or defense set out in a pleading [is]\\naffected by events that occur after the pleading is filed ….\\nRule 15(d) allows a court,” to permit a supplemental\\npleading. 3 James Wm. Moore et al., Moore’s Federal\\nPractice ¶ 15.30 (3d ed. 2018). Supplemental pleadings\\n\\n\\n\\n\\n 8\\n\\fgranted the motion to supplement. Wilmington then\\nresponded by moving to dismiss the supplemental complaint\\nas untimely because it failed to cure the defect.\\n\\n Ultimately, the District Court granted Wilmington’s\\ncross-motion for summary judgment for want of jurisdiction,\\nwithout ruling on the City’s motion to dismiss. The Court\\nfirst concluded that the initial complaint was irreparably\\nunripe because both the TCA and Delaware law require the\\nZBA to issue a written decision before the agency’s action\\ncould be considered final, and T Mobile had thus filed its\\ninitial complaint too soon. Second, the Court said that the\\nsupplemental complaint could not fix the ripeness problem\\nbecause it was filed past the 30-day window for seeking\\nreview of the ZBA’s final action. Because the Court reached\\n\\n\\n\\nunder Rule 15(d) differ from amended pleadings made under\\nRule 15(a). First, amended pleadings “relate to matters that\\noccurred prior to the filing of the original pleading and\\nentirely replace the earlier pleading; [supplemental pleadings]\\ndeal with events subsequent to the pleading to be altered and\\nrepresent additions to or continuations of the earlier\\npleadings.” 6A Charles Alan Wright et al., Federal Practice\\n& Procedure § 1504 (3d ed. 2018). Second “certain\\namendments may be made as a matter of course within stated\\ntime periods, whereas all supplemental pleadings require\\nleave of court under Rule 15(d).” Id. “Parties and courts\\noccasionally confuse supplemental pleadings with amended\\npleadings and mislabeling is common.” Id. Here, T Mobile’s\\ncomplaint was filed as an amended complaint but it is\\nproperly categorized as a supplemental complaint, and we\\nwill refer to it as such herein.\\n\\n\\n\\n\\n 9\\n\\fthat determination, it found it unnecessary to conclude\\nwhether T Mobile’s supplemental complaint was entitled to\\nthe benefit of the relation-back doctrine under Rule 15(c).\\n\\n This appeal followed.\\nII. DISCUSSION 5\\n\\n T Mobile challenges the District Court’s grant of\\nsummary judgment in favor of Wilmington, contending that\\nthere is jurisdiction to hear its case. It advances two\\nalternative grounds for reversal: that its complaint was ripe\\nbecause the ZBA’s oral decision qualifies as a “final action”\\nunder the review provision of the TCA, and, in the\\nalternative, that the supplemental complaint relates back to\\nand cures any ripeness problem with its initial complaint.\\nThose arguments in turn raise three questions for determining\\nwhether the District Court’s jurisdictional ruling was proper.\\nFirst, whether the oral decision of the ZBA was a final action.\\nSecond, whether the timing requirement in the TCA’s review\\nprovision is jurisdictional. And third, whether an untimely\\n\\n 5\\n The District Court had jurisdiction to consider its\\njurisdiction under 28 U.S.C. §§ 1331 and 1367(a), but\\ndetermined the complaint contained incurable jurisdictional\\ndefects and declined to reach the merits. We have jurisdiction\\npursuant to 28 U.S.C. § 1291. We review all the issues\\npresented in this case de novo, as they involve only legal\\nissues, i.e., interpretation of a federal statute and of a Federal\\nRule of Civil Procedure. Giles v. Campbell, 698 F.3d 153,\\n155 (3d Cir. 2012); Viera v. Life Ins. Co. of N. Am., 642 F.3d\\n407, 413 (3d Cir. 2011); DIRECTV Inc. v. Seijas, 508 F.3d\\n123, 125 (3d Cir. 2007).\\n\\n\\n\\n\\n 10\\n\\fsupplemental complaint can relate back and cure an unripe\\ninitial complaint. Although we disagree with T Mobile that\\nan oral decision of the ZBA qualifies as a “final action,” we\\nagree that jurisdiction was proper in the District Court\\nbecause the timing requirement in the TCA’s review\\nprovision is non-jurisdictional, and T Mobile’s supplemental\\ncomplaint therefore relates back and cures the ripeness\\nproblem with the initial complaint. The District Court should\\nthus have reached the merits of the dispute.\\n\\n A. The Oral Decision Was Not a Final Action of\\n the ZBA.\\n\\n The ripeness of T Mobile’s initial complaint depends\\nupon whether the ZBA’s oral decision was a “final action”\\nwithin the meaning of the TCA. Consideration of that issue\\nuncovers another: whether the TCA requires a locality to\\nrender its decision in writing for that decision to qualify as a\\nfinal action. The District Court held that, under both federal\\nand Delaware law, only a written decision can serve as a final\\naction of the ZBA. Because traditional hallmarks of agency\\naction and the statutory text and structure of the TCA favor\\nthat approach, we agree that only a written decision can serve\\nas a locality’s final action when denying an application.\\n\\n In Delaware Riverkeeper Network v. Secretary\\nPennsylvania Department of Environmental Protection,\\n(Riverkeeper III), we determined that, when reviewing\\nfinality under the Natural Gas Act, “[a]lthough the\\ndecisionmaking process we are reviewing is defined by [state]\\nlaw, we nevertheless apply a federal finality standard to\\ndetermine whether Congress has made the results of that\\nprocess reviewable[.]” 903 F.3d 65, 72 (3d Cir. 2018). The\\n\\n\\n\\n\\n 11\\n\\fsame reasoning holds true here, since, for the TCA just as for\\nthe Natural Gas Act, “the finality requirement itself, along\\nwith the presumption that Congress intended us to apply it,\\nare creatures of federal, not state, law.” Id. at 71.\\n\\n Under federal law, not all agency determinations are\\nfinal actions. Bacon v. Sullivan, 969 F.2d 1517, 1519 (3d Cir.\\n1992). Final agency actions bear certain “traditional\\nhallmarks” that demonstrate “[t]here is nothing left for the\\nagency to do[,]” Del. Riverkeeper Network v. Sec’y of Pa.\\nDep’t of Envtl. Prot., (Riverkeeper II), 870 F.3d 171, 178 (3d\\nCir. 2017). We noted those hallmarks on an earlier occasion\\nwhen we said that, “[f]inal agency action must mark the\\nconsummation of the agency’s decisionmaking process, must\\nnot be of a merely tentative or interlocutory nature, and must\\nbe one by which rights or obligations have been determined,\\nor from which legal consequences will flow.” Riverkeeper\\nIII, 903 F.3d at 72, 75 (citation and internal quotation marks\\nomitted).\\n\\n To decide what the TCA requires for finality, we\\nbegin, of course, with the text. See, e.g., Ross v. Blake, 136 S.\\nCt. 1850, 1856 (2016) (“Statutory interpretation … begins\\nwith the text[.]”) Here, the statutory text makes it clear that,\\nif a denial is not in writing, there is something left for the\\nagency to do. The denial provision of the TCA states that\\n“[a]ny decision … to deny … shall be in writing and\\nsupported by substantial evidence contained in a written\\nrecord.” 47 U.S.C. § 332(c)(7)(B)(iii). We see no reason\\nwhy the same should not be true for actions besides denial, 6\\n\\n 6\\n For instance, it is not apparent why community\\nmembers aggrieved by a decision to grant some permit to a\\n\\n\\n\\n\\n 12\\n\\fbut we need not decide that today. It is enough to say that, in\\nthose zoning decisions governed by the TCA, a locality’s oral\\ndeclaration of a denial is “of a merely tentative or\\ninterlocutory nature.” Riverkeeper III, 903 F.3d at 72\\n(citation omitted) (speaking in reference to the Natural Gas\\nAct); cf. Athens Cellular, Inc. v. Oconee Cty., 886 F.3d 1094,\\n1104-05, 1107 (11th Cir. 2018) (noting that a zoning board\\ncould have approved the minutes, revised them, or rejected\\nthem, and thus until the board approved the minutes its\\ndecision was not final).\\n\\n Moreover, an oral decision is not an action from which\\nlegal consequences flow. Federal law governs finality, but\\nDelaware’s procedures still matter, and the Delaware\\nSuperior Court has concluded that a written document must\\nbe filed for a ZBA action to be final. McDonald’s Corp. v.\\nZoning Bd. of Adjustment for the City of Wilmington, No.\\nCIV. A. 01A-05-011CG, 2002 WL 88944, at *1 (Del. Super.\\nCt. Jan. 10, 2002). The court reasoned that Section 328 of\\nTitle 22 of the Delaware Code, the section that governs\\nappeals from ZBA proceedings, requires a written document\\nto be filed because the statute “provides that [s]uch petition\\nshall be presented to the Court within 30 days after the filing\\nof the decision in the office of the board.” Id. (internal\\nquotation marks omitted). That reasoning is persuasive and\\n\\n\\n\\n\\nwireless provider, assuming those members have standing to\\nsue, would not be equally entitled to a zoning authority’s\\nwritten decision before the time limit in the TCA’s review\\nprovision is triggered.\\n\\n\\n\\n\\n 13\\n\\fshows that, under Delaware law, the ZBA’s oral decision is\\nwithout legal consequences. 7\\n\\n There are distinct policy advantages to forestalling\\njudicial scrutiny until a written denial is issued. Requiring a\\nwritten decision focuses review on a particular, documented\\nstatement of reasons. See USCOC of Greater Mo. v. City of\\nFerguson, 583 F.3d 1035, 1042 (8th Cir. 2009) (“Because the\\nwritten decision is the central object of our scrutiny under the\\nTCA, the process of judicial review is best served by delaying\\nthe ripening of a TCA claim until the local authority has\\nissued its written decision.”). It also prevents ambiguity with\\nrespect to when a claim can be brought. As the District Court\\nhere stated, to hold otherwise “would promote a pernicious\\nambiguity as to when that short period of time begins to run.”\\n(App. at 7.) And it promotes uniformity of federal procedures\\nby clarifying when, across all jurisdictions, an action becomes\\nfinal.\\n\\n 7\\n T Mobile cites to a different opinion, Schmalhofer v.\\nBoard of Adjustment of Newark, to advance a contrary\\nposition. No. C.A. 99A-05-010-WTQ, 2000 WL 703510\\n(Del. Super. Ct. May 9, 2000). Schmalhofer states in a\\nfootnote that “a written decision is not required or expressly\\ncontemplated by this section.” Id. at *3 n.3. But T Mobile is\\nstretching the Schmalhofer court’s language too far. In that\\ncase, the City of Newark had issued a verbatim transcript of\\nthe hearing, so there was a writing. Id. at *3; see infra note\\n11. There is no indication of any written decision in this case,\\nprior to December 22, 2016, when the City issued the written\\ndenial bearing the date of December 21, 2016.\\n\\n\\n\\n\\n 14\\n\\f The Supreme Court’s decision in T-Mobile South, LLC\\nv. City of Roswell, Georgia, also adds support to the\\nconclusion that only a written denial can constitute final\\naction, triggering a party’s right to review. 135 S. Ct. 808\\n(2015). In that case, the Court held that the “substantial\\nevidence” supporting a locality’s decision to deny must be\\nreleased contemporaneously with the written decision to\\ndeny. 8 Id. at 811-12. In doing so, the Court tied together a\\nlocal zoning authority’s final action, which triggers judicial\\nreview, and its decision to deny, which must be in writing.\\nIndeed, the Supreme Court said in no uncertain terms that,\\n“[t]he relevant ‘final action’ [in that case, was] the issuance of\\nthe written notice of denial[.]” Id. at 817 n.4. The Court\\nlinked the locality’s decision to deny to the 30-day time limit\\nto file a complaint after a final action has been taken. Id. at\\n817 (“Only once the denial is issued would the 30-day\\ncommencement-of-suit clock begin.”); id. at 813 (“[N]ow 29\\ndays after the City denied petitioner’s application—petitioner\\nfiled suit in Federal District Court.”).\\n\\n The Court went on to discuss timing, saying, “the\\nlocality must provide or make available its written reasons at\\nessentially the same time as it communicates its denial[,]”\\n“[b]ecause an entity may not be able to make a considered\\n\\n 8\\n The Court was interpreting the denial provision,\\nwhich, as we noted earlier, states that, “[a]ny decision by a\\nState or local government or instrumentality thereof to deny a\\nrequest to place, construct, or modify personal wireless\\nservice facilities shall be in writing and supported by\\nsubstantial evidence contained in a written record.” 47\\nU.S.C. § 332(c)(7)(B)(iii), City of Roswell, 135 S. Ct. at 811.\\n\\n\\n\\n\\n 15\\n\\fdecision whether to seek judicial review without knowing the\\nreasons for the denial of its application, and because a court\\ncannot review the denial without knowing the locality’s\\nreasons[.]” Id. at 816. The majority opinion was critical of\\nthe dissent for attempting to “fashion a world in which a\\nlocality can wait until a lawsuit is commenced and a court\\norders it to state its reasons[,] … [leaving the challenging\\nentity to] risk being sandbagged by the written reasons that\\nthe locality subsequently provides in litigation after the\\nchallenging entity has shown its cards.” Id. at 816 n.3. That\\ncritique is premised on the written decision being the final\\naction that starts the 30-day time limit for commencing suit. 9\\n\\n The Supreme Court anticipated that localities might\\nneed to delay issuing a written denial if they are not ready to\\nrelease their substantial reasons. See id. at 817 (noting that\\n\\n 9\\n T Mobile asserts that Wilmington has a “pattern and\\npractice of not issuing a written decision of land use denials\\nunless or until the City is sued.” (Opening Br. at 7.) But if\\nonly a written denial is a final action, the shot clock requires\\nthe City to issue that written decision within a given time\\nperiod. 24 FCC Rcd. 13994, 14012 (2009). T Mobile also\\nasserts that when a locality has a pattern and practice of not\\nreleasing written decisions, that practice delays the overall\\nprocess, since a cellular service provider would be required to\\ninitiate two causes of action: one to compel a written decision\\nand another to challenge that written decision. That,\\nhowever, is precisely what Congress envisioned by providing\\nseparate remedies for a failure to “act” within a reasonable\\ntime period and for an improper denial. 47 U.S.C.\\n§ 332(c)(7)(B)(iii).\\n\\n\\n\\n\\n 16\\n\\f“[i]f a locality is not in a position to provide its reasons\\npromptly, the locality can delay the issuance of its denial\\nwithin this 90– or 150–day window, and instead release it\\nalong with its reasons once those reasons are ready to be\\nprovided.”). That further counsels against treating an oral\\ndetermination as a final action since, if an oral determination\\nis deemed a final action, localities will be unable to take\\nadvantage of the permissible delay afforded by the shot clock\\nfor publishing their reasoning.\\n\\n Two of our sister courts of appeals agree that only a\\nwritten decision can constitute final action. The Eighth\\nCircuit in USCOC of Greater Missouri v. City of Ferguson\\nstated that “[t]he plain language of the TCA indicates that\\n‘final action’ does not occur until issuance of a written\\ndecision.” 583 F.3d at 1041. The Eleventh Circuit in\\nPreferred Sites LLC v. Troup County likewise held a\\ncomplaint to be timely when it was filed within 30 days of a\\nwritten decision, even though it was filed more than 30 days\\nafter an oral decision. 10 296 F.3d 1210, 1217-18 (11th Cir.\\n\\n 10\\n T Mobile attempts to distinguish Preferred Sites by\\nstating that, unlike here, the case did “not address a city that\\ndoes not issue a written decision close in time to when it\\nmakes the decision to deny.” (Opening Br. at 37.) But that\\nargument is irrelevant to whether the statutory text requires a\\nwriting for an agency decision to be final. T Mobile also cites\\nto Preferred Sites to argue that it should not matter if there is\\na writing requirement since the oral denial could be seen as\\nakin to a court announcing a decision. It explains that “when\\nan appeal is filed after the court announces a decision, but\\nbefore the entry of the judgment, it is treated as being filed on\\nthe date of entry.” (Opening Br. at 28-29 (citing Preferred\\n\\n\\n\\n\\n 17\\n\\f2002) (concluding that, “[b]ased on the plain language of the\\nstatute,” that “a ‘final action’ occurs when the state or local\\nauthority issues its written decision. The statute expressly\\nmandates a … decision … committed to writing. Until the\\nstate or local authority issues its written notification, its task\\nunder the statute is not complete.”). No circuit has held\\notherwise.\\n\\n Persuasive authority thus indicates that any action, and\\ncertainly a denial, must be in writing to be final. But, there is\\nanother possible interpretation of the statutory text. The\\nwords “shall be in writing” could be read not as a condition of\\nfinality, but instead as a simple directive to state and local\\ngovernments to place their final action in writing. “The TCA\\nprovides no express answer to … when a local government’s\\npermitting decision becomes a ‘final action,’ which starts the\\nthirty-day clock.” Athens Cellular, 886 F.3d at 1102-03. The\\nstatute only states that denials must be in writing. 47 U.S.C.\\n§ 332(c)(7)(b)(iii). Decisions to grant are not limited in the\\nsame way. Id. And, Congress used the words “decision to\\ndeny” in one statutory subsection and “final action” in\\nanother, which could evince an intent to give those terms\\ndifferent meanings. As the Supreme Court has “recognized\\n… Congress’s use of certain language in one part of the\\nstatute and different language in another can indicate that\\ndifferent meanings were intended.” Sebelius v. Auburn Reg’l\\nMed. Ctr., 568 U.S. 145, 156 (2013) (citation and quotation\\n\\n\\n\\nSites, 296 F.3d at 1217 n.7).) That analogy did appear in\\nPreferred Sites, but it was only contained in a footnote. No\\nother court has followed that line of reasoning, and we\\ndecline to follow it here.\\n\\n\\n\\n\\n 18\\n\\fmarks omitted). Thus, it could be argued, if Congress wanted\\nto mandate a writing for zoning denials to constitute final\\naction, it could have been more explicit, providing, for\\ninstance, that a “decision must be in writing to qualify as a\\nfinal action.”\\n\\n But, of course, one can almost always fault legislative\\ndrafting, like other kinds of writing, after the fact. That\\nsomething might have been said even more clearly does not\\nmean it is not clear enough. So, “[r]ather than expecting (let\\nalone demanding) perfection in drafting,” we can “construe[]\\nstatutes to have a particular meaning even as we\\nacknowledge[] that Congress could have expressed itself\\nmore clearly.” Torres v. Lynch, 136 S. Ct. 1619, 1633\\n(2016).\\n\\n The text and structure of the statute, Delaware\\nprocedures, Supreme Court reasoning, our sister circuits’\\ndecisions, and policy arguments all support the conclusion\\nthat a writing is in fact a requirement for a denial to be final. 11\\nIn light of that conclusion, the ZBA’s oral determination on\\n\\n 11\\n What constitutes a “writing” has some flexibility,\\nthough. See, e.g., Omnipoint Holdings, Inc. v. City of\\nSouthfield, 355 F.3d 601, 605-07 (6th Cir. 2004) (approving\\nminutes by written resolution was a final action that bound\\nthe parties). In City of Roswell, for example, the Supreme\\nCourt indicated that minutes of an oral meeting could be\\nsufficient. 135 S. Ct. at 816. Here, however, there is no\\nevidence that the ZBA’s oral determination was noted in the\\nminutes of the October 26th meeting and issued by the City as\\nits formal decision.\\n\\n\\n\\n\\n 19\\n\\fOctober 26, 2016, was not a final action ripe for judicial\\nreview. Therefore, as that oral determination was not reduced\\nto writing until December 22, 2016, preceding the filing of\\nT Mobile’s initial complaint, that complaint’s cause of action\\nwas not ripe.\\n\\n\\n\\n\\n 20\\n\\f B. No Separate Time Limit Exists Following an\\n Oral Determination.\\n\\n As an alternative to its argument that the ZBA’s oral\\ndecision was a final action, T Mobile asks us to consider\\nwhether a “local government must issue the ‘writing’ close in\\ntime to the ‘decision … to deny’ to establish a ‘final action’\\nthat will be subject to expedited review.” 12 (Opening Br. at\\n41.) Essentially, T Mobile is asserting that the “shot clock”\\ngoverning the time to act, which allows a wireless carrier to\\nsue for a locality’s failure to act, is insufficient, and that a\\nnew requirement, albeit not in the statute, should be imposed\\non localities. Under T Mobile’s proposed rule, an oral\\ndecision would have to be reduced to writing within a\\nspecified time period. That argument assumes that an oral\\ndetermination can serve to satisfy the requirement to “act” on\\na request within the limits of the shot clock, and that, without\\na separate judicially created time limit, there would be no\\ndeadline for the locality to release its written decision to deny,\\ndespite City of Rowell’s contemporaneous writing\\nrequirement. Because we conclude that a denial must be in\\nwriting to be a final action, the issuance of that writing is the\\ngovernment “act” ruled by the shot clock. 13 Aside from the\\n\\n 12\\n Wilmington argues that T Mobile has waived that\\nissue, but we need not address that argument because we\\nconclude that no such requirement exists.\\n 13\\n Again, the Supreme Court held in City of Roswell\\nthat a locality’s decision to deny must be accompanied by\\nsubstantial reasons. 135 S. Ct. at 811-12. Otherwise, if a\\nlocality were able to withhold its reasoning for its decision,\\nthose aggrieved by the locality’s actions would “be left to\\n\\n\\n\\n\\n 21\\n\\ftime limits associated with the “shot clock,” there is no other\\ndeadline governing the issuance of a written decision\\nfollowing an oral determination. 47 U.S.C. § 332(c)(7)(b).\\nAny time limit we fabricated would be inappropriate.\\n\\n T Mobile argues that, without a requirement for\\nlocalities to issue a written decision within a set amount of\\ntime following an oral determination, wireless carriers are left\\n“to wait until the FCC ‘shot clock’ expires – which could be\\n90 or 150 days depending on the type of installation involved\\n– and then [to] file an action alleging that the City has failed\\nto act in a reasonable time[.]” (Opening Br. at 45.) It also\\ncontends that a “failure to act” lawsuit is insufficient because\\nthe remedy for a successful suit is simply an order telling the\\nCity to issue a written decision. In T Mobile’s view, forcing\\nwireless providers to sue both to compel a written decision\\nonce the shot clock is violated and again to contest the written\\ndecision serves only to “create yet further delay.” (Opening\\nBr. at 46.)\\n\\n\\n\\n\\nguess at what the locality’s written reasons will be, write a\\ncomplaint that contains those hypotheses, and risk being\\nsandbagged by the written reasons that the locality\\nsubsequently provides in litigation after the challenging entity\\nhas shown its cards.” Id. at 816 n.3. If an applicant cannot\\nfile suit, however, because the locality’s “final action” has not\\nyet occurred, those concerns vanish. The ZBA’s decision\\nhere, when reduced to writing, was both its decision to deny\\nand its final action.\\n\\n\\n\\n\\n 22\\n\\f Those concerns are overstated and, in any case,\\nirrelevant. The shot clock begins to run once a wireless\\nprovider files its application, so it is already ticking before\\nany oral decision is made. If the locality fails to meet that\\ndeadline by not issuing a written decision before the shot\\nclock expires, the wireless provider can bring a claim for a\\n“failure to act.” 14 24 FCC Rcd. 13994, 14012 (2009). T\\nMobile asserts that requiring a separate failure-to-act suit, in\\naddition to a suit on the merits, undercuts the statutory\\npurpose of expedited judicial review, particularly in cases\\nwhere the locality has a “pattern and practice of not issuing a\\nwritten decision of land use denials unless or until [it] is\\nsued.” (Opening Br. at 7.) But the statute’s own remedies\\ncannot possibly undercut its purpose. A separate failure-to-\\nact claim is the very remedy Congress chose for shot clock\\nviolations. 24 FCC Rcd. 14013 at ¶ 4 (2009). Whether or not\\nT Mobile likes that policy choice, it is the one Congress\\nmade, and we are not free to change it.\\n\\n C. The Timing Requirement Is Not\\n Jurisdictional.\\n\\n Because we hold that a writing is required for a denial\\nto constitute a final action, T Mobile’s initial complaint was\\nnot ripe for review when filed. And, T Mobile’s\\nsupplemental complaint was filed more than 30 days after the\\nZBA issued its written decision and was therefore untimely\\nunder the TCA’s review provision. 47 U.S.C.\\n§ 332(c)(7)(B)(v). Thus, the District Court only had\\njurisdiction if T Mobile’s supplemental complaint cured the\\n\\n 14\\n It is not clear which time limit would have applied in\\nthis case and whether it would have been violated.\\n\\n\\n\\n\\n 23\\n\\fripeness flaw in its initial complaint by relating back to the\\noriginal filing date. If the 30-day time limit in the TCA’s\\nreview provision is nonjurisdictional, we can safely say that\\nrelation back is possible and allows a supplemental complaint\\nto cure a defective premature filing. 15 At the outset, then, we\\nmust determine whether that 30-day time limit is\\njurisdictional, being mindful both of the Supreme Court’s\\ncounsel to exercise caution before holding timing\\nrequirements to be jurisdictional and of its guidance regarding\\nwhat constitutes a jurisdictional limit. 16 Sebelius, 568 U.S. at\\n149, 153-54. Caution is indeed warranted because statutes of\\nlimitations and other filing deadlines “ordinarily are not\\njurisdictional.” Id. at 154; see also United States v. Kwai Fun\\nWong, 135 S. Ct. 1625, 1632 (2015) (“[M]ost time bars are\\nnonjurisdictional.”).\\n\\n\\n 15\\n We do not reach the issue of whether an unripe\\ncomplaint can be cured by a supplemental or amended\\npleading over which the Court lacked jurisdiction.\\n 16\\n The City claims that our decision in Nextel Partners\\nInc. v. Kingston Township, 286 F.3d 687 (3d Cir. 2002) is\\neffectively determinative. Not so. In Kingston Township,\\nthen-Judge Alito noted that the District Court had held the\\ntiming requirement in the TCA’s review provision was\\njurisdictional. Id. at 695. But we did not address whether\\nthat determination was correct, nor did we rely on it. Instead,\\nwe concluded that there could be no “failure to act” towards\\nan application that was not submitted. Id. at 692. Since our\\ndecision in that case, the Supreme Court has clarified the\\nprocess for determining if a time limit is jurisdictional.\\nSebelius, 568 U.S. at 149.\\n\\n\\n\\n\\n 24\\n\\f “[T]o ward off profligate use of the term ‘jurisdiction,’\\n[the Supreme Court has] adopted a readily administrable\\nbright line for determining whether to classify a statutory\\nlimitation as jurisdictional.” Sebelius, 568 U.S. at 153 (citing\\nArbaugh v. Y & H Corp., 546 U.S. 500, 516 (2006))\\n(quotation marks omitted). We are to ask “whether Congress\\nhas clearly state[d] that the rule is jurisdictional; absent such a\\nclear statement, we … should treat the restriction as\\nnonjurisdictional in character.” Id. (alteration in original)\\n(citation and quotation marks omitted); see also Musacchio v.\\nUnited States, 136 S. Ct. 709, 716 (2016) (Thus, “[w]e treat a\\ntime bar as jurisdictional only if Congress has ‘clearly stated’\\nthat it is.”). In deciding whether Congress has made such a\\nclear statement, “we evaluate the ‘text, context, and relevant\\nhistorical treatment.’” United States v. Kalb, 891 F.3d 455,\\n460 (2018) (quoting Reed Elsevier, 559 U.S. 154, 166\\n(2010)).\\n\\n Referencing that last test, Wilmington asserts that\\n“[s]ection 332’s statutory grant of jurisdiction to district\\ncourts, the text of the statute, the placement of the filing\\nwindow in that same section, and the well-established\\ntreatment of the filing window as jurisdictional, [all\\ndemonstrate] that the filing window is jurisdictional.”\\n(Answering Br. at 15.) We disagree. The differences\\nbetween the review provision’s timing requirement and the\\ntiming requirement we held to be jurisdictional in Kalb, and\\nthe similarities between the review provision’s timing\\nrequirements and those at issue in Sebelius and Musacchio,\\nwhich the Supreme Court held to be nonjurisdictional,\\nactually support treating the timing requirement in the TCA’s\\nreview provision as nonjurisdictional.\\n\\n\\n\\n\\n 25\\n\\f First, although Wilmington says that the text of the\\nstatute indicates Congress’s desire to make the 30-day timing\\nrequirement jurisdictional, the text does not use the term\\n“jurisdictional” or any variation of it to describe the timing\\nrequirement. 47 U.S.C. § 332(c)(7)(B)(v). To the contrary,\\nthe statute uses permissive rather than mandatory language.\\nUnlike the timing requirement we held to be jurisdictional in\\nKalb, which mandated that an action would be barred if not\\nfiled in time, the TCA’s review provision states that an action\\n“may” be filed within 30-days. Compare Kalb, 891 F.3d at\\n460 with 47 U.S.C. § 332(c)(7)(B)(v). The language is much\\ncloser to that which the Supreme Court decided was\\nnonjurisdictional in Sebelius. The statute at issue in that case,\\nlike the review provision here, uses a permissive phrase –\\n“may obtain a hearing” – before it states the timing\\nrequirement. 17 Compare Sebelius, 568 U.S. at 154, with 47\\nU.S.C. § 332(c)(7)(B)(v) (“may … commence an action”).\\nSimilar to the timing requirement the Supreme Court held to\\nbe nonjurisdictional in Musacchio, the review provision does\\nnot confer jurisdiction, instead it allows an action to be\\n\\n 17\\n T Mobile also points to Henderson v. Shinseki,\\nwhich held a timing requirement to be nonjurisdictional even\\nthough it used the mandatory “shall” before stating the timing\\nrequirement. 562 U.S. 428, 441-42 (2011). But the decision\\nin Shinseki, where the pertinent timing requirement could\\nhave barred a veteran’s appeal, was partly based on “the\\ncanon that provisions for benefits to members of the Armed\\nServices are to be construed in the beneficiaries’ favor,” and\\nso it is of less utility in deciding this dispute. Id. at 441\\n(quotation marks and citations omitted).\\n\\n\\n\\n\\n 26\\n\\fcommenced “in any court of competent jurisdiction.” See\\nMusacchio, 136 S. Ct. at 717 (“[The provision] does not\\nexpressly refer to subject-matter jurisdiction or speak in\\njurisdictional terms.”). The text of the statute therefore favors\\na holding that the timing requirement is nonjurisdictional.\\n\\n Wilmington next contends that the context of the\\ntiming requirement favors the view that the requirement is\\njurisdictional, because the Supreme Court has stated that it is\\n“inextricably linked to … the language that creates the right\\nof action[.]” (Answering Br. at 13-14 (citing City of Rancho\\nPalos Verdes v. Abrams, 544 U.S. 113, 125 (2005)).) Thus,\\nsays the City, the “filing window created by [the review\\nprovision] is jurisdictional [because] it is integral to the\\nexpress purpose of the section, to this Court’s jurisdiction,\\nand to the parties’ rights and obligations[.]” (Answering Br.\\nat 8.)\\n\\n True enough, the review provision’s timing\\nrequirement does appear in the same subsection as the\\nstatutory text granting jurisdiction. 47 U.S.C.\\n§ 332(c)(7)(B)(v). And, as we stated in Kalb, the Supreme\\nCourt’s decisions in Bowles v. Russell, 551 U.S. 205, 210\\n(2007), and Reed Elsevier, Inc. v. Muchnick, 559 U.S. at 166,\\nboth found the source of the timing requirement to be\\nimportant in determining whether that requirement was\\njurisdictional. 891 F.3d at 462. In Kalb, moreover, we made\\nthe same point the City now does, stating that a timing\\nrequirement was jurisdictional because “the thirty-day appeal\\nperiod here is embedded in the same statutory section that\\ngrants jurisdiction to the court of appeals.” Id.\\n\\n\\n\\n\\n 27\\n\\f But the location of the timing requirement within the\\nstatutory structure, without more, does not clearly reveal\\nCongressional intent. As noted by the Supreme Court in\\nSebelius, a timing requirement should not be classified as\\njurisdictional solely based on its placement in a jurisdictional\\nprovision. Sebelius, 568 U.S. at 155 (“A requirement we\\nwould otherwise classify as nonjurisdictional … does not\\nbecome jurisdictional simply because it is placed in a section\\nof a statute that also contains jurisdictional provisions.”\\n(citing Gonzalez v. Thaler, 565 U.S. 134, 146-47 (2012))). In\\nMusacchio too, the Supreme Court held that a timing\\nrequirement was nonjurisdictional despite its presence in the\\njurisdiction-granting section of the statute at issue. 136 S. Ct.\\nat 717. The Court emphasized that the statute did not directly\\nspeak of the timing requirement as jurisdictional, despite its\\nmandatory language. Id. That reasoning applies with at least\\nequal force here, so the context of the review provision’s\\ntiming requirement does not make the requirement\\njurisdictional.\\n\\n Finally, Wilmington asserts that the timing\\nrequirement is jurisdictional because of the historical\\ntreatment of similar provisions. The City asserts that the\\nphrase “within 30 days after” creates a “window,” during\\nwhich a complaint must be filed, and not a “deadline.”\\n(Answering Br. at 11-12 (citing W. Union Tel. Co. v. FCC,\\n773 F.2d 375, 377 (D.C. Cir. 1985)) (noting that “within 60\\ndays after” creates a 60-day filing window while “no later\\nthan 60 days after” creates a filing deadline).) But that\\nargument misses the point because it goes to whether the rule\\nbars suit between certain dates or only after a certain date, not\\nto whether the timing requirement is jurisdictional. See, e.g.,\\nUnion Tel. Co., 773 F.2d at 377-78 (discussing whether the\\n\\n\\n\\n\\n 28\\n\\ffiling window is a jurisdictional bar for suits filed before the\\nwindow opens). And just because a complaint may be unripe\\nbefore a particular date does not mean that a deadline by\\nwhich suit must be filed is jurisdictional. As we stated in\\nKalb, the Supreme Court’s decisions in Bowles and Reed\\nElsevier both looked to “the Court’s prior treatment of\\n[similar timing requirements.]” Kalb, 891 F.3d at 460. In\\nSebelius, the timing requirement, as here, used the phrase\\n“within” and thus, under Wilmington’s logic, it would have\\nbeen a jurisdictional limit. Sebelius, 568 U.S. at 154. But the\\nSupreme Court held otherwise, id., and that is of high\\nimportance.\\n\\n Because the text and context of this statute, and\\nhistorical treatment of timing requirements in similar statutes,\\ndo not reveal a clear intent from Congress to make the review\\nprovision’s timing requirement jurisdictional, we conclude\\nthat it is not. 18\\n\\n D. Rule 15 Allows a Supplemental Complaint\\n Filed After a Claims Processing Deadline To\\n Relate Back and Cure an Unripe Initial\\n Complaint.\\n\\n We next consider whether an untimely supplemental\\ncomplaint can, by relating back, cure an initial complaint that\\nwas unripe. We believe it can, and because T Mobile’s\\n\\n 18\\n That conclusion is further supported by the\\nthoughtful concurrence in Athens Cellular, concluding after\\nSebelius that the timing requirement “imposed by Congress in\\nthe TCA … is not a jurisdictional bar.” Athens Cellular, 886\\nF.3d at 1113 (Kaplan, J. concurring).\\n\\n\\n\\n\\n 29\\n\\fmotion to supplement its complaint was properly granted, that\\nsupplemental complaint relates back and is ripe. The District\\nCourt therefore had jurisdiction and should not have granted\\nWilmington’s motion for summary judgment.\\n\\n At the outset, we note that the parties do not dispute,\\nand we agree, that the District Court was within its discretion\\nto grant T Mobile’s motion to supplement its complaint.\\nPursuant to Federal Rule of Civil Procedure 15(d), “[o]n\\nmotion and reasonable notice, the [district] court may, on just\\nterms, permit a [moving] party to serve a supplemental\\npleading setting out any … event that happened after the date\\nof the pleading to be supplemented.” Fed. R. Civ. P. 15(d);\\nsee also 3 James Wm. Moore et al., Moore’s Federal Practice\\n¶ 15.30 (3d ed. 2018) (“Supplemental pleadings … are\\nlimited to subsequent events related to the claim or defense\\npresented in the original pleading.”). Here, the District Court\\nrightly granted T Mobile’s motion to supplement. That\\ndecision was just, since Wilmington had long since had notice\\nof the event – the filing of the written denial – that occurred\\nafter the initial pleading. After all, the City issued that denial,\\nand the denial was featured in the parties’ discovery plan.\\nThe issuance of it was also plainly related to T Mobile’s\\ninitial complaint.\\n\\n That the initial complaint was premature is not a bar\\nsince, under Rule 15(d), “[t]he court may permit\\nsupplementation even though the original pleading is\\ndefective in stating a claim for relief or defense.” Fed. R.\\nCiv. P. 15(d). As the Advisory Committee Notes make clear,\\n“Rule 15(d) is intended to give the [district] court broad\\ndiscretion in allowing a supplemental pleading.” Fed. R. Civ.\\nP. 15(d) advisory committee’s note to 1963 amendment. It is\\n\\n\\n\\n\\n 30\\n\\ffurthermore “within the discretion of the court to allow a\\nsupplemental pleading to be filed at any stage of the case[.]”\\nMoore et al., supra, ¶ 15.30. The District Court here was thus\\nwell within its discretion in granting T Mobile’s motion to\\nsupplement the complaint.\\n\\n Rule 15 does not indicate whether or under what\\ncircumstances a supplemental pleading can relate back to the\\ndate of the original pleading to avoid the effect of a time\\nlimit. 6A Charles Alan Wright et al., Federal Practice &\\nProcedure § 1508 (3d ed. 2018). Subsection (c) of the Rule,\\nwhich provides for the relation back of amended pleadings,\\ndoes not specifically refer to supplemental pleadings. Fed. R.\\nCiv. P. 15(c). Nor does Rule 15(d) make any mention of\\nrelation back. Fed. R. Civ. P. 15(d). But case law and\\nsecondary sources have long instructed that once a\\nsupplemental complaint is granted, it is treated like an\\namended complaint for purposes of relation back. 19 Thus,\\neven though Rule 15(d) is in a separate statutory provision\\nfrom Rule 15(c), a supplemental complaint can relate back.\\nWright et al., supra, § 1508; see also F.D.I.C. v. Knostman,\\n966 F.2d 1133, 1138 (7th Cir. 1992) (“The distinction\\nbetween an amended pleading and a supplemental pleading is\\n\\n 19\\n Courts have generally held that a supplemental\\ncomplaint is eligible for relation back, but rely on different\\nrationales to do so. See Wright et al., supra, § 1508 (“[S]ome\\ncourts have held that for purposes of applying the relation-\\nback doctrine a supplemental pleading may be treated as an\\namended pleading under Rule 15(c); other courts have\\napplied the relation-back principle directly to supplemental\\npleadings even though Rule 15(d) does not mention it.”)\\n(internal citations omitted).\\n\\n\\n\\n\\n 31\\n\\foften disregarded for purposes of relation back under Rule\\n15(c).”); Russell v. New Amsterdam Cas. Co., 303 F.2d 674,\\n680-81 (8th Cir. 1962) (finding supplemental pleading related\\nback despite plaintiff suing in the wrong capacity and not\\nachieving appropriate status for diversity jurisdiction until\\nafter the limitations period had expired). That stands to\\nreason, since, if a “defendant had notice of the subject matter\\nof the dispute and was not prejudiced in preparing a defense\\n…[,] the policy against stale claims becomes subsidiary to the\\npolicy expressed throughout the rules in favor of allowing a\\nparty to set forth all the grievances against another party in\\none action and resolving them on their merits.” Wright et al.,\\nsupra, § 1508.\\n\\n So a pleading filed according to Rule 15(d) can relate\\nback, assuming it meets “the basic test for relation back\\nprescribed by Rule 15(c).” Id.; see also Moore et al., supra,\\n¶ 15.30 (“A supplemental pleading may relate back to the\\ndate of the original complaint if the requirements under Rule\\n15(c) for relation back are satisfied”); Davis v. Piper Aircraft\\nCorp., 615 F.2d 606, 609 n.3 (4th Cir. 1980) (supplemental\\npleading relates back if Rule 15(c)’s test is met). In fact, as\\nthe District Court observed, if a supplemental complaint\\nmeets the requirements for relation back then “[r]elation back\\nis mandatory,” and not subject to additional equitable\\nconsiderations. 20 (App. at 6 (citing Arthur v. Maersk, Inc.,\\n434 F.3d 196, 202-03 (3d Cir. 2006)).)\\n\\n 20\\n We note, however, that “[a] party opposing the\\nintroduction of a supplemental pleading might wish to raise\\nthe statute-of-limitations defense when the additional\\npleading (1) alleges new matter that brings the earlier\\npleading up to date; (2) cures a defect in the original pleading;\\n\\n\\n\\n\\n 32\\n\\f Looking then to Rule 15(c), a complaint “relates back\\nto the date of the original pleading when … [it] asserts a\\nclaim or defense that arose out of the conduct, transaction, or\\noccurrence set out -- or attempted to be set out -- in the\\noriginal pleading[.]” Fed. R. Civ. P. 15(c)(1)(B). The\\nDistrict Court here concluded that there was no need to\\ndetermine whether T Mobile’s supplemental complaint\\nrelated back, because, even if it did, “it fail[ed] to cure the\\ndeficiencies of the initial complaint[.]” (App. at 8.) But\\ngiven our view that the supplemental complaint could indeed\\ncure the ripeness problem with the initial complaint, we must\\ncontend with the relation-back question.\\n\\n To determine if relation back is proper, the only issue\\nis whether there is a “common core of operative facts in the\\ntwo pleadings.” Bensel v. Allied Pilots Ass’n, 387 F.3d 298,\\n310 (3d Cir. 2004.) Here, that test is met. Both complaints\\nrely on the same core facts. The written denial was a\\ncertification and restatement of the earlier oral denial.\\n\\n Thus, the only question remaining is whether a\\ncomplaint that relates back can cure an untimely initial\\ncomplaint, and the answer is yes. The clear preference\\nembodied in Rule 15 is for merits-based decision making. Cf.\\nMoore et al., supra, ¶ 15.30 (“The same principles that\\nsupport the liberal amendment of pleadings also apply to\\nsupplemental pleadings.”). As the Supreme Court has stated,\\nthe purpose of Rule 15 is “to balance the interests of the\\n\\n\\nor (3) states a new claim that arose after the filing of the\\ncomplaint.” Wright et al., supra, § 1508.\\n\\n\\n\\n\\n 33\\n\\fdefendant protected by the statute of limitations with the\\npreference expressed in the Federal Rules of Civil Procedure\\nin general, and Rule 15 in particular, for resolving disputes on\\ntheir merits.” Krupski v. Costa Crociere S.p.A., 560 U.S. 538,\\n550 (2010). The requirements of Rule 15 itself protect\\ndefendants from an unfair relation back. 21 Under that Rule,\\ncourts “look[s] to whether the opposing party has had fair\\nnotice of the general fact situation and legal theory upon\\nwhich the amending party proceeds.” Bensel, 387 F.3d at\\n310. In this instance, Wilmington had sufficient notice since\\nthe supplemented complaint simply alleged the issuance of\\nthe ZBA’s written denial. And, of course, Wilmington had\\nnotice of everything in the supplemental complaint. It not\\nonly knew of the written denial and the reasons given, it\\ngenerated them.\\n\\n Relation back has been allowed to address\\njurisdictional problems. We said in Berkshire Fashions, Inc.\\nv. M.V. Hakusan II that relation back may be used to cure\\ndefects in jurisdictional allegations. 954 F.2d 874, 878 (3rd\\nCir. 1992). In that case, the District Court had dismissed the\\nplaintiff’s claim based on admiralty jurisdiction and denied\\nthe plaintiff’s motion to amend its complaint to allege\\ndiversity jurisdiction. Id. at 877. We concluded that both\\ndecisions were in error, holding that an amended complaint\\nrelates back and can cure insufficient pleading of subject\\nmatter jurisdiction. Id. at 878. Recently, our Circuit allowed\\n\\n 21\\n This is not a pass for endless delay in\\nsupplementing a complaint. Indeed, we have endeavored to\\nemphasize that whether to allow supplemental pleading\\ndepends on equitable considerations of fairness and notice\\nthat district courts must take into account.\\n\\n\\n\\n\\n 34\\n\\fa plaintiff to cure a diversity defect when the case had been\\nlitigated for years. See GBForefront, L.P., v. Forefront\\nMgmt. Grp., LLC, 888 F.3d 29, 32 (3d Cir. 2018)\\n(“instruct[ing] the [d]istrict [c]ourt to give leave to further\\namend the complaint … to cure defective jurisdictional\\nallegations”).\\n\\n Other circuits have held the same. See Woods v. Ind.\\nUniv.-Purdue Univ. at Indianapolis, 996 F.2d 880, 884 (7th\\nCir. 1993) (“Consistent with its history and purpose, Rule\\n15(c) has uniformly been applied to relate back [filings] that\\ncure defective statements of jurisdiction ….”); Boyce v.\\nAnderson, 405 F.2d 605, 607 (9th Cir. 1968) (allowing\\namendment alleging that no previous appeal had been taken\\nto the United States Court of Customs and Patent Appeals to\\ncure jurisdictional defect in complaint after statute of\\nlimitations had expired). That conclusion is also consistent\\nwith 28 U.S.C. § 1653, which allows “[d]efective allegations\\nof jurisdiction [to] be amended, upon terms, in the trial or\\nappellate courts.” Id.\\n\\n Courts have similarly permitted cure of actual defects\\nin the court’s jurisdiction, going beyond just jurisdictional\\nallegations. For instance, although not in a case involving a\\nlater complaint, the Supreme Court has said that a court can\\ndrop a dispensable non-diverse party to cure a defect in\\ndiversity jurisdiction. Newman-Green, Inc. v. Alfonzo-\\nLarrain, 490 U.S. 826, 837-38 (1989); see also E.R. Squibb &\\nSons, Inc. v. Lloyd’s & Cos., 241 F.3d 154, 163 (2d Cir.\\n2001) (stating that, “where it is appropriate to relate back an\\namendment to a pleading under Rule 15, jurisdiction is\\nassessed as if the amendment had taken place at the time the\\ncomplaint was first filed[,]” and thus replacing a non-diverse\\n\\n\\n\\n\\n 35\\n\\fplaintiff with a diverse plaintiff cured any jurisdiction\\nproblem); Rowe v. United States Fid. & Guar. Co., 421 F.2d\\n937, 939, 944 (4th Cir. 1970) (concluding that a defective\\ncomplaint could be cured by a later complaint that pled an\\nassignment occurring after the original complaint was filed).\\n\\n Nonetheless, “[a]mendments that go beyond the mere\\ncorrection or factual modification of the original pleading and\\nsignificantly alter the claim or defense alleged in that\\npleading are treated more cautiously by the courts in applying\\nthe relation-back doctrine.” Wright et al., supra, § 1497. The\\nSecond Circuit, for instance, only sometimes allows\\njurisdictional defects to be cured “when the underlying facts,\\nif properly pled, would have supported jurisdiction at the time\\nthe action commenced.” Correspondent Servs. Corp. v. First\\nEquities Corp. of Fla., 338 F.3d 119, 125 (2d Cir. 2003); see\\nalso, e.g., Barton v. Ellis, No. 75-1188, 1977 WL 15469, at\\n*1 (D.S.C. Apr. 26, 1977) (denying using relation back to\\ncure the original complaint since they were defects “not [in\\nthe] allegations of existing underlying jurisdictional facts but\\nrather [in] the prerequisite jurisdictional facts themselves”).\\nWilmington argues such hesitance is appropriate here because\\nallowing relation back to cure the jurisdictional problem with\\nT Mobile’s initial complaint “would allow two wrongs under\\nSection 332 [(filing early and filing late)] to make a right.”\\n(Answering Br. at 2.)\\n\\n We again disagree with the City. It is quite true that\\nT Mobile has made procedural matters more difficult than\\nthey should be in this case. But denying relation-back to cure\\nthe defect in this instance would not comport with Rule 15’s\\naim to encourage resolution of disputes on the merits\\nwhenever possible. The ripeness requirement exists so that\\n\\n\\n\\n\\n 36\\n\\fcourts avoid issuing essentially advisory opinions. See\\nRichard H. Fallon, Jr. et al., Hart and Wechsler’s the Federal\\nCourts and the Federal System 224 (5th ed. 2003) (noting that\\nthe ripeness doctrine allows courts to avoid a “dispute … too\\n‘ill-defined’ to be appropriate for judicial resolution until\\nfurther developments … more sharply framed the issues for\\ndecision.”). That concern ceased to exist here once the\\nsupplemental pleading was in place. At that point, the dispute\\nhad matured and become capable of judicial review,\\ndemonstrating that, “actions taken after the filing of the initial\\ncomplaint can be used to establish subject matter\\njurisdiction.” Prasco, LLC v. Medicis Pharm. Corp., 537\\nF.3d 1329, 1337 (Fed. Cir. 2008).\\n\\n If a supplemental complaint cannot cure an unripe\\ncomplaint, an endless feedback loop would be created\\nwhereby the ripeness problem could never be overcome, even\\nthough, as here, the dispute later became obviously ripe. Our\\nsister circuits have recognized that problem and concluded\\nthat a supplemental complaint is the solution. 22 In Wilson v.\\nWestinghouse Electric Corp., the Eighth Circuit determined\\nthat prohibiting an amended (or supplemental) complaint\\nfrom alleging facts that occurred after the date the initial\\n\\n 22\\n In our Circuit, a thoughtful district court decision\\nhad long ago reached that conclusion. It held that an\\nuntimely supplement adding facts occurring after the initial\\nfiling that showed exhaustion of administrative remedies\\ncould relate back to the initial premature complaint and allow\\nmaintenance of the lawsuit. Bates v. W. Elec., 420 F. Supp.\\n521, 526-27 (E.D. Pa. 1976).\\n\\n\\n\\n\\n 37\\n\\fcomplaint was filed would turn a premature complaint into an\\n“irretrievable mistake that bars jurisdiction” and would be\\n“precisely the kind of procedural mousetrap that the Federal\\nRules were designed to dismantle.” 838 F.2d 286, 289 (8th\\nCir. 1988). The court held that, “[e]ven when the District\\nCourt lacks jurisdiction over a claim at the time of its original\\nfiling, a supplemental complaint may cure the defect by\\nalleging the subsequent fact which eliminates the\\njurisdictional bar.” Id. at 290 (citing Mathews, 426 U.S. at\\n75). While Wilson addressed a circumstance in which the\\nsupplemental complaint was timely filed, the proposition still\\napplies in a case like ours because, if a party was limited to\\nrefiling within an applicable time limit, there would be little\\nneed to make provision for supplementation of a complaint,\\nas a new complaint could be filed. 23\\n\\n 23\\n We note that sparing the cost of refiling and\\nproviding convenience to the Court would remain legitimate\\nreasons for allowing supplemental complaints. But the\\npurpose of Rule 15(d) is broader. See Wright et al., supra, §\\n1504 (“The purpose of subdivision (d) is to promote as\\ncomplete an adjudication of the dispute between the parties as\\nis possible. … A supplemental pleading may be employed\\nfor a variety of purposes.”). Wilmington contends that\\nWilson is inapposite since it involved a timely supplemental\\ncomplaint. Thus, concern about a perpetual loop outcome\\nwas not proper because the plaintiff could have simply refiled\\nhis complaint. But we agree that “a plaintiff need not\\ncommence a new action when after-occurring events\\ndemonstrate that it has a right to relief even if the original\\ncomplaint was insufficient. A plaintiff may also be allowed\\nto supplement the complaint even if jurisdiction … would not\\nhave been proper if the claim had been asserted in an\\n\\n\\n\\n\\n 38\\n\\f The Ninth Circuit, in Security Insurance Co. of New\\nHaven v. United States ex rel. Haydis, also relied on that logic\\nto find that relation back could cure an unripe complaint filed\\nbefore a statutory filing window opened. 338 F.2d 444, 448-\\n49 (9th Cir. 1964). In a fact scenario with striking similarities\\nto the present appeal, the plaintiff had filed its claim before a\\nstatutory waiting period was over and then did not file an\\namended complaint until after the statute of limitations period\\nhad run. Id. at 445-46. The appeals court held that the\\ndistrict court was “not required to apply the doctrine of\\nrelation back so literally as to carry it to a time [before it was\\nripe] so as to prevent the maintenance of the action in the first\\nplace.” Id. at 449.\\n\\n The Supreme Court has favorably cited Security\\nInsurance’s ruling. In Mathews, the plaintiff had not satisfied\\na precondition of filing a complaint by first filing an\\napplication with a particular agency. 426 U.S. at 72, 75. The\\nCourt noted that a supplemental complaint, alleging that the\\napplication had since been filed, would have cured the\\njurisdictional defect. Id. at 75. In saying so, the Court relied\\n\\n\\n\\nindependent action.” Moore et al., supra, ¶ 15.30 (3d ed.\\n2018) (citation omitted). If supplemental complaints could\\nnot cure ripeness, “then all supplemental pleadings of this\\nnature would be defeated for lack of jurisdiction – [the]\\n‘procedural mousetrap’ would render all supplemental\\npleadings void.” George v. IRS, No. C05-00955 MJJ, 2006\\nWL 3499230, at *3 (N.D. Cal. Dec. 4, 2006) (citation\\nomitted).\\n\\n\\n\\n\\n 39\\n\\fon Security Insurance. Id. at 75 n.8 (citing Security\\nInsurance, 338 F.2d at 447-49). 24\\n\\n Yet Wilmington asserts that ripeness can never be\\ncured by a later complaint. It advances four cases for that\\nproposition, but none are helpful. First, the City cites\\nDelaware Riverkeeper Network v. Secretary Pennsylvania\\nDepartment of Environmental Protection, (Riverkeeper I),\\n833 F.3d 360 (3d Cir. 2016), in which we concluded that,\\n“even though the underlying claim became ripe for review\\nduring the pendency of the case, the ripening of the claim did\\nnot cure deficient pleadings.” (App. at 8.) In that case,\\nhowever, no attempt to file a later complaint alleging ripeness\\nwas made. Riverkeeper I, 833 F.3d at 369-70.\\n\\n Likewise, in another two of the four cases that\\nWilmington cites, there was no effort made to amend or\\nsupplement the complaint. See TeleSTAR, Inc. v. FCC, 888\\nF.2d 132, 134 (D.C. Cir. 1989) (concluding non-final agency\\naction at the time of filing of petition may only be reviewed\\nupon the filing of another petition); W. Union Tel. Co., 773\\nF.2d at 377-78 (concluding that the court lacked jurisdiction\\nover challenges filed before the action became final).\\nTherefore, neither case determined whether relation back of a\\nlater-filed complaint could cure a ripeness problem in the\\ninitial complaint.\\n\\n 24\\n Wilmington contends that Mathews is inapposite\\nsince the statute of limitations was waived. That argument\\nhas no traction since, if it were a jurisdictional bar, it could\\nnot be waived.\\n\\n\\n\\n\\n 40\\n\\f The City fares no better relying on Council Tree\\nCommunications v. FCC, in which we stated that “[a] petition\\nto review a non-final agency order is incurably premature.”\\n503 F.3d 284, 291 (3d Cir. 2007). At no point in that case\\nwas the complaint ripe, and the petitioner still had a petition\\nfor reconsideration pending before the relevant agency on the\\ndate the case was decided. Id. at 287. Furthermore, Council\\nTree explicitly acknowledged that a supplemental complaint\\ncan cure an unripe complaint when there is jurisdiction over\\nthat supplemental pleading. See id. at 291 (“[W]e note that\\n‘nothing prevented [the petitioners] from supplementing their\\npremature petition with a later protective petition.’” (second\\nalteration in original) (quoting Horsehead Res. Dev. Co. v.\\nE.P.A., 130 F.3d 1090, 1095 (D.C. Cir. 1997))).\\n\\n Wilmington also makes three policy arguments in\\nsupport of its position that an untimely supplemental\\ncomplaint should not be able to cure an unripe complaint.\\nFirst, it contends that allowing suits to be filed before an\\naction is ripe would “extend[] federal court jurisdiction over\\nlocal government actions before those actions are final[.]”\\n(Answering Br. at 9.) Second, such filings would waste\\njudicial resources and, in this case, cost taxpayers money, by\\nforcing courts to deal with a higher volume of unripe\\ncomplaints. Third, the purpose of § 332 is to preserve local\\nzoning authority, which would be undermined by allowing\\nplaintiffs to file suit early and thereby places undue pressure\\non zoning commissions.\\n\\n Those contentions, however, are unpersuasive. First, a\\ncourt would remain without jurisdiction if the claim had not\\nripened by the time of the supplemental complaint. Second, it\\n\\n\\n\\n\\n 41\\n\\fseems that Wilmington overstates the impact that a decision\\nallowing an unripe complaint to be cured would have, since\\nour holding today makes it clear that an action is not final\\nuntil a written decision has been issued. Clarifying when a\\ndetermination is ripe for review should end any incentive for\\naggrieved parties to file early to ensure they have not filed too\\nlate.\\n\\n Perhaps more importantly, however, courts can police\\nany potential abuse on a case-by-case basis using Rule 15(d)\\nand the Rule 15(c) test for relation back. It is understood that\\n“relation back of a supplemental pleading should not result in\\nproviding unfair procedural advantages to a plaintiff[,] so …\\nrelation back may not be for all purposes.” Wright et al.,\\nsupra, § 1508. But here no unfair advantage has resulted, and\\ndefendants in general will be adequately protected by a\\ndistrict court’s Rule 15(d) analysis, which will determine if a\\nsupplemental complaint should be allowed at all. For\\ninstance, if a locality’s action is not yet a final action at the\\ntime a Rule 15(d) motion is filed, the motion can easily be\\ndenied. See Beezley v. Fremont Indem. Co., 804 F.2d 530,\\n530 (9th Cir. 1986) (supplemental pleading denied when it\\nstill failed to cure defective original pleading).\\n\\n When all is said and done here, we conclude that, to\\neffectuate the liberal purpose of Rule 15 and to avoid the\\nendless feedback loop that the City’s legal argument would\\ncreate, Rule 15 allows an untimely supplemental complaint to\\nrelate back and cure an unripe initial complaint.\\n\\n\\n\\n\\n 42\\n\\fIII. CONCLUSION\\n\\n For the foregoing reasons, we will reverse the District\\nCourt’s grant of the City’s motion for summary judgment,\\nvacate the District Court’s denial of T Mobile’s motion for\\nsummary judgment, and remand to the District Court for\\nfurther proceedings consistent with this opinion.25\\n\\n\\n\\n\\n 25\\n We will vacate the District Court’s denial of\\nT Mobile’s motion for summary judgment because it was\\nsolely based on a finding that T Mobile’s suit was not timely\\nbrought.\\n\\n\\n\\n\\n 43\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4357819/\", \"author_raw\": \"JORDAN, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"JORDAN"},"judge2":{"kind":"string","value":"NYGAARD"},"judge3":{"kind":"string","value":"VANASKIE"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4580566/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: T MOBILE NORTHEAST LLC, Appellant v. CITY OF WILMINGTON, DELAWARE ; City of Wilmington Zoning Board of Adjustment\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-10\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 18-1831\n _____________\n\n T MOBILE NORTHEAST LLC,\n Appellant\n\n v.\n\n CITY OF WILMINGTON, DELAWARE;\nCITY OF WILMINGTON ZONING BOARD OF ADJUSTMENT\n _____________\n\n On Appeal from the United States District Court\n for the District of Delaware\n (D.C. No. 1-16-cv-01108)\n District Judge: Hon. Eduardo C. Robreno\n _______________\n\n Argued\n September 12, 2018\n\nBefore: JORDAN, NYGAARD, and VANASKIE, * Circuit Judge\n (Filed: January 10, 2019)\n\n\n *\n The Honorable Thomas I. Vanaskie retired from the\nCourt on January 1, 2019 after the argument and conference\nin this case, but before the filing of the opinion. This opinion\nis filed by a quorum of the panel pursuant to 28 U.S.C.\n§ 46(d) and Third Circuit I.O.P. Chapter 12.\n\f _______________\n\nThomas S. Thompson [ARGUED]\nDavis Wright Tremaine\n1919 Pennsylvania Avenue, NW\nSte. 800\nWashington, DC 20006\n\nCounsel for Appellant\n\nJoseph Van Eaton [ARGUED]\nBest Best & Krieger\n2000 Pennsylvania Avenue\nSte. 5300\nWashington, DC 20006\n\nCounsel for Appellees\n _______________\n\n OPINION OF THE COURT\n _______________\n\n\nJORDAN, Circuit Judge.\n\n No one likes bad cell phone reception or slow\nstreaming data on their smartphone, but that does not mean\nanyone wants a cellular antenna in their neighborhood, which\nis why there are zoning battles like the one central to this\ncase.\n\n T Mobile Northeast LLC (“T Mobile”), a wireless\ntelecommunications service provider, applied to the Zoning\nBoard of Adjustment (“ZBA”) of the City of Wilmington,\nDelaware for permission to erect an antenna in the City. The\n\n\n\n\n 2\n\fZBA said no. So, relying on a provision of federal law that\nallows a disappointed wireless service provider like T Mobile\nto seek review in a district court “within 30 days after” a\nzoning authority’s “final action,” 47 U.S.C.\n§ 332(c)(7)(B)(v), T Mobile filed suit. After the case had\nproceeded for over a year, however, the District Court\nconcluded that it lacked jurisdiction. The Court reasoned that\nbecause T Mobile filed its complaint before the ZBA released\na written decision confirming an earlier oral rejection of the\nzoning application, the claim was not ripe. And, since\nT Mobile did not supplement its complaint to include the\nZBA’s written decision within 30 days of its issuance, the\nCourt also concluded that relation back could not remedy the\nripeness defect. The District Court thus granted the City’s\nmotion for summary judgment.\n\n T Mobile now appeals. It argues that its complaint\nwas not premature or, in the alternative, that its supplemental\npleading cured any ripeness problem. We agree that the grant\nof summary judgment was improper and, for the reasons that\nfollow, will remand the case for further proceedings\nconsistent with this opinion.\n\nI. BACKGROUND\n\n A. Statutory Framework\n\n This dispute is governed by the Telecommunications\nAct of 1996 (“TCA”), which amended the Federal\nCommunications Act of 1934 and includes provisions on\nmobile phone services. Pub. L. No. 104-104, §§ 1, 704, 110\nStat. 56, 56, 151 (1996); 47 U.S.C. § 332. Passed to\n“encourage the rapid deployment of new telecommunications\n\n\n\n\n 3\n\ftechnologies,” Preamble, 110 Stat. at 56, the TCA provides\nfor expedited review in federal court of a denial of permission\nto build a cell phone antenna, id. § 704, 110 Stat. at 151-52.\nSuch review is a “benefit Congress expressly intended to\nconfer on wireless providers[.]” Nextel W. Corp. v. Unity\nTwp., 282 F.3d 257, 264 (3d Cir. 2002). At the same time,\nthe TCA also serves to preserve local zoning authority. 47\nU.S.C. § 332(c)(7).\n\n At issue here are three key sections of the statute.\nFirst, the TCA mandates that “[a] State or local government\nor instrumentality thereof shall act on any request for\nauthorization to place, construct, or modify personal wireless\nservice facilities within a reasonable period of time after the\nrequest is duly filed[.]” Id. § 332(c)(7)(B)(ii). The Federal\nCommunications Commission (“FCC”) has interpreted\n“reasonable period of time” in that statutory provision to\nmean that zoning authorities have a “shot clock” 1 and must\nact within 90 days of an application to attach an antenna to an\nexisting structure or 150 days of an application where a new\nsupport structure is to be built. Petition for Declaratory\n\n 1\n “Shot clock” is a term borrowed from basketball. In\nthat game, it signifies a time limit to make a shot attempt,\nbeginning once a team has possession of the basketball. See,\ne.g., Nat’s Basketball Ass’n, NBA Rulebook Rule No. 7: Shot\nClock (2018-2019), http://official.nba.com/rule-no-7-24-\nsecond-clock/. If the team has not made a shot attempt, i.e.,\nacted, within the prescribed time limit, it forfeits possession\nof the ball. Id. Here, the permitting authority has exclusive\njurisdiction over an application until it fails to act within a\n“reasonable period of time.” 47 U.S.C. §§ 332(c)(7)(A),\n332(c)(7)(B)(ii).\n\n\n\n\n 4\n\fRuling to Clarify Provisions of Section 332(c)(7)(B), 24 FCC\nRcd. 13994, 14008, 14012 (2009). Second, in what we will\ncall the “review provision” of the statute, the TCA grants\n“[a]ny person adversely affected by any final action or failure\nto act by a State or local government or any instrumentality\nthereof” a right to have that locality’s decision reviewed by\n“commenc[ing] an action” “within 30 days” in district court.\n47 U.S.C. § 332(c)(7)(B)(v). Third, in the statute’s “denial\nprovision,” the TCA states that “[a]ny decision by a State or\nlocal government or instrumentality thereof to deny a request\nto place, construct, or modify personal wireless service\nfacilities shall be in writing and supported by substantial\nevidence contained in a written record.” Id.\n§ 332(c)(7)(B)(iii). Notably, the terms “act,” “final action,”\nand “decision … to deny” are not defined in the TCA.\nFurthermore, the statute does not make clear whether “final\naction” should be read to encompass all decisions to deny,\nincluding oral ones, nor does it address whether there is a\ndifference between an “act” for purposes of the shot clock\nand a “final action” for purposes of judicial review.\n\n B. Factual Background\n\n T Mobile is a telecommunications service provider. It\nsays that it needs to erect a cellular antenna to fill “a\nsignificant gap” in coverage for its customers in Wilmington,\nDelaware, (Opening Br. at 3) presumably where there has\nbeen an increase in phone calls and data usage. T Mobile\nwants to put its antenna on top of a senior living high-rise in\nthe City, but, because a special exception to local zoning laws\nis needed, it first had to go to the ZBA. It filed an initial\napplication and then, on August 25, 2016, a final amended\napplication, seeking the exception.\n\n\n\n\n 5\n\f The ZBA held a hearing on October 26, 2016, to\nconsider T Mobile’s request, some two months after the final\namended application was submitted. During the hearing,\nT Mobile presented evidence of the need for the antenna and\ndiscussed proposals to address aesthetic concerns. The ZBA\nalso received objections from members of the local\ncommunity, some of whom were outspoken in worrying\nabout the effects of radio frequency emissions. At the end of\nthe hearing, the ZBA denied T Mobile’s application in a\nunanimous oral decision.\n\n The Board gave several reasons for the denial. One\nboard member said the ZBA should not encourage the use of\na senior living community rooftop as the base for an antenna\nbecause of the potential adverse effect on the properties in the\nneighborhood. Another board member said there was not\nenough proof of a need for additional coverage to support the\napplication. The Chairman said there was not enough\nevidence that T Mobile needed the antenna and that it did not\nappear to satisfy the zoning code in terms of placement and\nheight restrictions.\n\n The ZBA’s oral decision to deny the application was\nnot put in writing on October 26 or anytime soon thereafter.\nAccording to T Mobile, that fits a “pattern and practice of\n[the ZBA] not issuing a written decision of land use denials\nunless or until the City is sued.” (Opening Br. at 7.) Only\nafter T Mobile had filed its initial complaint in the District\nCourt, and after the City filed its answer, did the ZBA issue\nits written decision and explanation of its reasoning for\ndenying the application.\n\n\n\n\n 6\n\f T Mobile asserts that the denial of its application\nviolates the TCA. Under the statute, such a denial is invalid\nif it has the “effect of prohibiting the provision of personal\nwireless services[,]” 47 U.S.C. § 332(c)(7)(B)(i)(II), or is “on\nthe basis of the environmental effects of radio frequency\nemissions[,]” id. at § 332(c)(7)(B)(iv). T Mobile claims that\nWilmington’s denial was improper on both of those grounds. 2\nBut those assertions go to the merits and are not actually\nbefore us on this appeal. At issue now is whether T Mobile’s\nclaim can be heard at all.\n\n C. Procedural History\n\n Evidently with its eye on the 30-day deadline in the\nTCA’s review provision, T Mobile filed a lawsuit in the\nUnited States District Court for the District of Delaware\nwithin 30 days of the ZBA’s oral decision, challenging that\ndenial. 3 In addition to its claims on the merits, T Mobile’s\ninitial complaint alleged that the City violated procedures\nmandated in the TCA, specifically those in the denial\nprovision, by failing to provide a written decision\n\n 2\n T Mobile also raised a Delaware state law claim.\nThat claim is not at issue here and does not impact\nT Mobile’s claims under federal law.\n 3\n For reasons discussed herein, the 30-day filing\ndeadline was not triggered by the oral decision. See infra pp.\n12-20. If it were, however, T Mobile’s complaint would have\nbeen timely. The oral decision was delivered at the\nOctober 26, 2016 hearing. Suit was filed on November 28,\n2016, but because the thirtieth day from October 26 fell on a\nweekend, the November 28 filing was within the 30-day\nwindow. Fed. R. Civ. P. 6(a)(1).\n\n\n\n\n 7\n\fcontemporaneous with its oral decision and by not supporting\nthe denial with substantial evidence.\n\n The parties entered into a stipulation asking the\nDistrict Court for an expedited case schedule, as provided for\nin the review provision of the TCA. 47 U.S.C.\n§ 332(c)(7)(B)(v). That request was granted. Wilmington\nthen answered the complaint, asserting a number of\naffirmative defenses, including that the complaint was not\nripe because the ZBA had not yet issued a final written\ndecision. Nevertheless, the City did not, at that time, file a\nmotion to dismiss for failure to state a claim or for lack of\njurisdiction. Two days after the City filed its answer, the\nZBA issued a written decision on T Mobile’s application.\nThe parties pressed forward with the suit and prepared a\ndiscovery plan, which specifically mentioned the written\ndecision. T Mobile filed a motion for summary judgment,\nwhich the City met with a cross-motion for summary\njudgment. The City’s motion was styled in the alternative as\na motion to dismiss the complaint as unripe because it was\nfiled prematurely, i.e., before the written decision had been\nissued.\n\n Not until December 21, 2017, nearly a year after the\nZBA issued its written denial, did T Mobile file a motion\nseeking leave to amend or supplement the initial complaint to\nnote the issuance of that written decision. 4 The District Court\n\n 4\n When “[a] claim or defense set out in a pleading [is]\naffected by events that occur after the pleading is filed ….\nRule 15(d) allows a court,” to permit a supplemental\npleading. 3 James Wm. Moore et al., Moore’s Federal\nPractice ¶ 15.30 (3d ed. 2018). Supplemental pleadings\n\n\n\n\n 8\n\fgranted the motion to supplement. Wilmington then\nresponded by moving to dismiss the supplemental complaint\nas untimely because it failed to cure the defect.\n\n Ultimately, the District Court granted Wilmington’s\ncross-motion for summary judgment for want of jurisdiction,\nwithout ruling on the City’s motion to dismiss. The Court\nfirst concluded that the initial complaint was irreparably\nunripe because both the TCA and Delaware law require the\nZBA to issue a written decision before the agency’s action\ncould be considered final, and T Mobile had thus filed its\ninitial complaint too soon. Second, the Court said that the\nsupplemental complaint could not fix the ripeness problem\nbecause it was filed past the 30-day window for seeking\nreview of the ZBA’s final action. Because the Court reached\n\n\n\nunder Rule 15(d) differ from amended pleadings made under\nRule 15(a). First, amended pleadings “relate to matters that\noccurred prior to the filing of the original pleading and\nentirely replace the earlier pleading; [supplemental pleadings]\ndeal with events subsequent to the pleading to be altered and\nrepresent additions to or continuations of the earlier\npleadings.” 6A Charles Alan Wright et al., Federal Practice\n& Procedure § 1504 (3d ed. 2018). Second “certain\namendments may be made as a matter of course within stated\ntime periods, whereas all supplemental pleadings require\nleave of court under Rule 15(d).” Id. “Parties and courts\noccasionally confuse supplemental pleadings with amended\npleadings and mislabeling is common.” Id. Here, T Mobile’s\ncomplaint was filed as an amended complaint but it is\nproperly categorized as a supplemental complaint, and we\nwill refer to it as such herein.\n\n\n\n\n 9\n\fthat determination, it found it unnecessary to conclude\nwhether T Mobile’s supplemental complaint was entitled to\nthe benefit of the relation-back doctrine under Rule 15(c).\n\n This appeal followed.\nII. DISCUSSION 5\n\n T Mobile challenges the District Court’s grant of\nsummary judgment in favor of Wilmington, contending that\nthere is jurisdiction to hear its case. It advances two\nalternative grounds for reversal: that its complaint was ripe\nbecause the ZBA’s oral decision qualifies as a “final action”\nunder the review provision of the TCA, and, in the\nalternative, that the supplemental complaint relates back to\nand cures any ripeness problem with its initial complaint.\nThose arguments in turn raise three questions for determining\nwhether the District Court’s jurisdictional ruling was proper.\nFirst, whether the oral decision of the ZBA was a final action.\nSecond, whether the timing requirement in the TCA’s review\nprovision is jurisdictional. And third, whether an untimely\n\n 5\n The District Court had jurisdiction to consider its\njurisdiction under 28 U.S.C. §§ 1331 and 1367(a), but\ndetermined the complaint contained incurable jurisdictional\ndefects and declined to reach the merits. We have jurisdiction\npursuant to 28 U.S.C. § 1291. We review all the issues\npresented in this case de novo, as they involve only legal\nissues, i.e., interpretation of a federal statute and of a Federal\nRule of Civil Procedure. Giles v. Campbell, 698 F.3d 153,\n155 (3d Cir. 2012); Viera v. Life Ins. Co. of N. Am., 642 F.3d\n407, 413 (3d Cir. 2011); DIRECTV Inc. v. Seijas, 508 F.3d\n123, 125 (3d Cir. 2007).\n\n\n\n\n 10\n\fsupplemental complaint can relate back and cure an unripe\ninitial complaint. Although we disagree with T Mobile that\nan oral decision of the ZBA qualifies as a “final action,” we\nagree that jurisdiction was proper in the District Court\nbecause the timing requirement in the TCA’s review\nprovision is non-jurisdictional, and T Mobile’s supplemental\ncomplaint therefore relates back and cures the ripeness\nproblem with the initial complaint. The District Court should\nthus have reached the merits of the dispute.\n\n A. The Oral Decision Was Not a Final Action of\n the ZBA.\n\n The ripeness of T Mobile’s initial complaint depends\nupon whether the ZBA’s oral decision was a “final action”\nwithin the meaning of the TCA. Consideration of that issue\nuncovers another: whether the TCA requires a locality to\nrender its decision in writing for that decision to qualify as a\nfinal action. The District Court held that, under both federal\nand Delaware law, only a written decision can serve as a final\naction of the ZBA. Because traditional hallmarks of agency\naction and the statutory text and structure of the TCA favor\nthat approach, we agree that only a written decision can serve\nas a locality’s final action when denying an application.\n\n In Delaware Riverkeeper Network v. Secretary\nPennsylvania Department of Environmental Protection,\n(Riverkeeper III), we determined that, when reviewing\nfinality under the Natural Gas Act, “[a]lthough the\ndecisionmaking process we are reviewing is defined by [state]\nlaw, we nevertheless apply a federal finality standard to\ndetermine whether Congress has made the results of that\nprocess reviewable[.]” 903 F.3d 65, 72 (3d Cir. 2018). The\n\n\n\n\n 11\n\fsame reasoning holds true here, since, for the TCA just as for\nthe Natural Gas Act, “the finality requirement itself, along\nwith the presumption that Congress intended us to apply it,\nare creatures of federal, not state, law.” Id. at 71.\n\n Under federal law, not all agency determinations are\nfinal actions. Bacon v. Sullivan, 969 F.2d 1517, 1519 (3d Cir.\n1992). Final agency actions bear certain “traditional\nhallmarks” that demonstrate “[t]here is nothing left for the\nagency to do[,]” Del. Riverkeeper Network v. Sec’y of Pa.\nDep’t of Envtl. Prot., (Riverkeeper II), 870 F.3d 171, 178 (3d\nCir. 2017). We noted those hallmarks on an earlier occasion\nwhen we said that, “[f]inal agency action must mark the\nconsummation of the agency’s decisionmaking process, must\nnot be of a merely tentative or interlocutory nature, and must\nbe one by which rights or obligations have been determined,\nor from which legal consequences will flow.” Riverkeeper\nIII, 903 F.3d at 72, 75 (citation and internal quotation marks\nomitted).\n\n To decide what the TCA requires for finality, we\nbegin, of course, with the text. See, e.g., Ross v. Blake, 136 S.\nCt. 1850, 1856 (2016) (“Statutory interpretation … begins\nwith the text[.]”) Here, the statutory text makes it clear that,\nif a denial is not in writing, there is something left for the\nagency to do. The denial provision of the TCA states that\n“[a]ny decision … to deny … shall be in writing and\nsupported by substantial evidence contained in a written\nrecord.” 47 U.S.C. § 332(c)(7)(B)(iii). We see no reason\nwhy the same should not be true for actions besides denial, 6\n\n 6\n For instance, it is not apparent why community\nmembers aggrieved by a decision to grant some permit to a\n\n\n\n\n 12\n\fbut we need not decide that today. It is enough to say that, in\nthose zoning decisions governed by the TCA, a locality’s oral\ndeclaration of a denial is “of a merely tentative or\ninterlocutory nature.” Riverkeeper III, 903 F.3d at 72\n(citation omitted) (speaking in reference to the Natural Gas\nAct); cf. Athens Cellular, Inc. v. Oconee Cty., 886 F.3d 1094,\n1104-05, 1107 (11th Cir. 2018) (noting that a zoning board\ncould have approved the minutes, revised them, or rejected\nthem, and thus until the board approved the minutes its\ndecision was not final).\n\n Moreover, an oral decision is not an action from which\nlegal consequences flow. Federal law governs finality, but\nDelaware’s procedures still matter, and the Delaware\nSuperior Court has concluded that a written document must\nbe filed for a ZBA action to be final. McDonald’s Corp. v.\nZoning Bd. of Adjustment for the City of Wilmington, No.\nCIV. A. 01A-05-011CG, 2002 WL 88944, at *1 (Del. Super.\nCt. Jan. 10, 2002). The court reasoned that Section 328 of\nTitle 22 of the Delaware Code, the section that governs\nappeals from ZBA proceedings, requires a written document\nto be filed because the statute “provides that [s]uch petition\nshall be presented to the Court within 30 days after the filing\nof the decision in the office of the board.” Id. (internal\nquotation marks omitted). That reasoning is persuasive and\n\n\n\n\nwireless provider, assuming those members have standing to\nsue, would not be equally entitled to a zoning authority’s\nwritten decision before the time limit in the TCA’s review\nprovision is triggered.\n\n\n\n\n 13\n\fshows that, under Delaware law, the ZBA’s oral decision is\nwithout legal consequences. 7\n\n There are distinct policy advantages to forestalling\njudicial scrutiny until a written denial is issued. Requiring a\nwritten decision focuses review on a particular, documented\nstatement of reasons. See USCOC of Greater Mo. v. City of\nFerguson, 583 F.3d 1035, 1042 (8th Cir. 2009) (“Because the\nwritten decision is the central object of our scrutiny under the\nTCA, the process of judicial review is best served by delaying\nthe ripening of a TCA claim until the local authority has\nissued its written decision.”). It also prevents ambiguity with\nrespect to when a claim can be brought. As the District Court\nhere stated, to hold otherwise “would promote a pernicious\nambiguity as to when that short period of time begins to run.”\n(App. at 7.) And it promotes uniformity of federal procedures\nby clarifying when, across all jurisdictions, an action becomes\nfinal.\n\n 7\n T Mobile cites to a different opinion, Schmalhofer v.\nBoard of Adjustment of Newark, to advance a contrary\nposition. No. C.A. 99A-05-010-WTQ, 2000 WL 703510\n(Del. Super. Ct. May 9, 2000). Schmalhofer states in a\nfootnote that “a written decision is not required or expressly\ncontemplated by this section.” Id. at *3 n.3. But T Mobile is\nstretching the Schmalhofer court’s language too far. In that\ncase, the City of Newark had issued a verbatim transcript of\nthe hearing, so there was a writing. Id. at *3; see infra note\n11. There is no indication of any written decision in this case,\nprior to December 22, 2016, when the City issued the written\ndenial bearing the date of December 21, 2016.\n\n\n\n\n 14\n\f The Supreme Court’s decision in T-Mobile South, LLC\nv. City of Roswell, Georgia, also adds support to the\nconclusion that only a written denial can constitute final\naction, triggering a party’s right to review. 135 S. Ct. 808\n(2015). In that case, the Court held that the “substantial\nevidence” supporting a locality’s decision to deny must be\nreleased contemporaneously with the written decision to\ndeny. 8 Id. at 811-12. In doing so, the Court tied together a\nlocal zoning authority’s final action, which triggers judicial\nreview, and its decision to deny, which must be in writing.\nIndeed, the Supreme Court said in no uncertain terms that,\n“[t]he relevant ‘final action’ [in that case, was] the issuance of\nthe written notice of denial[.]” Id. at 817 n.4. The Court\nlinked the locality’s decision to deny to the 30-day time limit\nto file a complaint after a final action has been taken. Id. at\n817 (“Only once the denial is issued would the 30-day\ncommencement-of-suit clock begin.”); id. at 813 (“[N]ow 29\ndays after the City denied petitioner’s application—petitioner\nfiled suit in Federal District Court.”).\n\n The Court went on to discuss timing, saying, “the\nlocality must provide or make available its written reasons at\nessentially the same time as it communicates its denial[,]”\n“[b]ecause an entity may not be able to make a considered\n\n 8\n The Court was interpreting the denial provision,\nwhich, as we noted earlier, states that, “[a]ny decision by a\nState or local government or instrumentality thereof to deny a\nrequest to place, construct, or modify personal wireless\nservice facilities shall be in writing and supported by\nsubstantial evidence contained in a written record.” 47\nU.S.C. § 332(c)(7)(B)(iii), City of Roswell, 135 S. Ct. at 811.\n\n\n\n\n 15\n\fdecision whether to seek judicial review without knowing the\nreasons for the denial of its application, and because a court\ncannot review the denial without knowing the locality’s\nreasons[.]” Id. at 816. The majority opinion was critical of\nthe dissent for attempting to “fashion a world in which a\nlocality can wait until a lawsuit is commenced and a court\norders it to state its reasons[,] … [leaving the challenging\nentity to] risk being sandbagged by the written reasons that\nthe locality subsequently provides in litigation after the\nchallenging entity has shown its cards.” Id. at 816 n.3. That\ncritique is premised on the written decision being the final\naction that starts the 30-day time limit for commencing suit. 9\n\n The Supreme Court anticipated that localities might\nneed to delay issuing a written denial if they are not ready to\nrelease their substantial reasons. See id. at 817 (noting that\n\n 9\n T Mobile asserts that Wilmington has a “pattern and\npractice of not issuing a written decision of land use denials\nunless or until the City is sued.” (Opening Br. at 7.) But if\nonly a written denial is a final action, the shot clock requires\nthe City to issue that written decision within a given time\nperiod. 24 FCC Rcd. 13994, 14012 (2009). T Mobile also\nasserts that when a locality has a pattern and practice of not\nreleasing written decisions, that practice delays the overall\nprocess, since a cellular service provider would be required to\ninitiate two causes of action: one to compel a written decision\nand another to challenge that written decision. That,\nhowever, is precisely what Congress envisioned by providing\nseparate remedies for a failure to “act” within a reasonable\ntime period and for an improper denial. 47 U.S.C.\n§ 332(c)(7)(B)(iii).\n\n\n\n\n 16\n\f“[i]f a locality is not in a position to provide its reasons\npromptly, the locality can delay the issuance of its denial\nwithin this 90– or 150–day window, and instead release it\nalong with its reasons once those reasons are ready to be\nprovided.”). That further counsels against treating an oral\ndetermination as a final action since, if an oral determination\nis deemed a final action, localities will be unable to take\nadvantage of the permissible delay afforded by the shot clock\nfor publishing their reasoning.\n\n Two of our sister courts of appeals agree that only a\nwritten decision can constitute final action. The Eighth\nCircuit in USCOC of Greater Missouri v. City of Ferguson\nstated that “[t]he plain language of the TCA indicates that\n‘final action’ does not occur until issuance of a written\ndecision.” 583 F.3d at 1041. The Eleventh Circuit in\nPreferred Sites LLC v. Troup County likewise held a\ncomplaint to be timely when it was filed within 30 days of a\nwritten decision, even though it was filed more than 30 days\nafter an oral decision. 10 296 F.3d 1210, 1217-18 (11th Cir.\n\n 10\n T Mobile attempts to distinguish Preferred Sites by\nstating that, unlike here, the case did “not address a city that\ndoes not issue a written decision close in time to when it\nmakes the decision to deny.” (Opening Br. at 37.) But that\nargument is irrelevant to whether the statutory text requires a\nwriting for an agency decision to be final. T Mobile also cites\nto Preferred Sites to argue that it should not matter if there is\na writing requirement since the oral denial could be seen as\nakin to a court announcing a decision. It explains that “when\nan appeal is filed after the court announces a decision, but\nbefore the entry of the judgment, it is treated as being filed on\nthe date of entry.” (Opening Br. at 28-29 (citing Preferred\n\n\n\n\n 17\n\f2002) (concluding that, “[b]ased on the plain language of the\nstatute,” that “a ‘final action’ occurs when the state or local\nauthority issues its written decision. The statute expressly\nmandates a … decision … committed to writing. Until the\nstate or local authority issues its written notification, its task\nunder the statute is not complete.”). No circuit has held\notherwise.\n\n Persuasive authority thus indicates that any action, and\ncertainly a denial, must be in writing to be final. But, there is\nanother possible interpretation of the statutory text. The\nwords “shall be in writing” could be read not as a condition of\nfinality, but instead as a simple directive to state and local\ngovernments to place their final action in writing. “The TCA\nprovides no express answer to … when a local government’s\npermitting decision becomes a ‘final action,’ which starts the\nthirty-day clock.” Athens Cellular, 886 F.3d at 1102-03. The\nstatute only states that denials must be in writing. 47 U.S.C.\n§ 332(c)(7)(b)(iii). Decisions to grant are not limited in the\nsame way. Id. And, Congress used the words “decision to\ndeny” in one statutory subsection and “final action” in\nanother, which could evince an intent to give those terms\ndifferent meanings. As the Supreme Court has “recognized\n… Congress’s use of certain language in one part of the\nstatute and different language in another can indicate that\ndifferent meanings were intended.” Sebelius v. Auburn Reg’l\nMed. Ctr., 568 U.S. 145, 156 (2013) (citation and quotation\n\n\n\nSites, 296 F.3d at 1217 n.7).) That analogy did appear in\nPreferred Sites, but it was only contained in a footnote. No\nother court has followed that line of reasoning, and we\ndecline to follow it here.\n\n\n\n\n 18\n\fmarks omitted). Thus, it could be argued, if Congress wanted\nto mandate a writing for zoning denials to constitute final\naction, it could have been more explicit, providing, for\ninstance, that a “decision must be in writing to qualify as a\nfinal action.”\n\n But, of course, one can almost always fault legislative\ndrafting, like other kinds of writing, after the fact. That\nsomething might have been said even more clearly does not\nmean it is not clear enough. So, “[r]ather than expecting (let\nalone demanding) perfection in drafting,” we can “construe[]\nstatutes to have a particular meaning even as we\nacknowledge[] that Congress could have expressed itself\nmore clearly.” Torres v. Lynch, 136 S. Ct. 1619, 1633\n(2016).\n\n The text and structure of the statute, Delaware\nprocedures, Supreme Court reasoning, our sister circuits’\ndecisions, and policy arguments all support the conclusion\nthat a writing is in fact a requirement for a denial to be final. 11\nIn light of that conclusion, the ZBA’s oral determination on\n\n 11\n What constitutes a “writing” has some flexibility,\nthough. See, e.g., Omnipoint Holdings, Inc. v. City of\nSouthfield, 355 F.3d 601, 605-07 (6th Cir. 2004) (approving\nminutes by written resolution was a final action that bound\nthe parties). In City of Roswell, for example, the Supreme\nCourt indicated that minutes of an oral meeting could be\nsufficient. 135 S. Ct. at 816. Here, however, there is no\nevidence that the ZBA’s oral determination was noted in the\nminutes of the October 26th meeting and issued by the City as\nits formal decision.\n\n\n\n\n 19\n\fOctober 26, 2016, was not a final action ripe for judicial\nreview. Therefore, as that oral determination was not reduced\nto writing until December 22, 2016, preceding the filing of\nT Mobile’s initial complaint, that complaint’s cause of action\nwas not ripe.\n\n\n\n\n 20\n\f B. No Separate Time Limit Exists Following an\n Oral Determination.\n\n As an alternative to its argument that the ZBA’s oral\ndecision was a final action, T Mobile asks us to consider\nwhether a “local government must issue the ‘writing’ close in\ntime to the ‘decision … to deny’ to establish a ‘final action’\nthat will be subject to expedited review.” 12 (Opening Br. at\n41.) Essentially, T Mobile is asserting that the “shot clock”\ngoverning the time to act, which allows a wireless carrier to\nsue for a locality’s failure to act, is insufficient, and that a\nnew requirement, albeit not in the statute, should be imposed\non localities. Under T Mobile’s proposed rule, an oral\ndecision would have to be reduced to writing within a\nspecified time period. That argument assumes that an oral\ndetermination can serve to satisfy the requirement to “act” on\na request within the limits of the shot clock, and that, without\na separate judicially created time limit, there would be no\ndeadline for the locality to release its written decision to deny,\ndespite City of Rowell’s contemporaneous writing\nrequirement. Because we conclude that a denial must be in\nwriting to be a final action, the issuance of that writing is the\ngovernment “act” ruled by the shot clock. 13 Aside from the\n\n 12\n Wilmington argues that T Mobile has waived that\nissue, but we need not address that argument because we\nconclude that no such requirement exists.\n 13\n Again, the Supreme Court held in City of Roswell\nthat a locality’s decision to deny must be accompanied by\nsubstantial reasons. 135 S. Ct. at 811-12. Otherwise, if a\nlocality were able to withhold its reasoning for its decision,\nthose aggrieved by the locality’s actions would “be left to\n\n\n\n\n 21\n\ftime limits associated with the “shot clock,” there is no other\ndeadline governing the issuance of a written decision\nfollowing an oral determination. 47 U.S.C. § 332(c)(7)(b).\nAny time limit we fabricated would be inappropriate.\n\n T Mobile argues that, without a requirement for\nlocalities to issue a written decision within a set amount of\ntime following an oral determination, wireless carriers are left\n“to wait until the FCC ‘shot clock’ expires – which could be\n90 or 150 days depending on the type of installation involved\n– and then [to] file an action alleging that the City has failed\nto act in a reasonable time[.]” (Opening Br. at 45.) It also\ncontends that a “failure to act” lawsuit is insufficient because\nthe remedy for a successful suit is simply an order telling the\nCity to issue a written decision. In T Mobile’s view, forcing\nwireless providers to sue both to compel a written decision\nonce the shot clock is violated and again to contest the written\ndecision serves only to “create yet further delay.” (Opening\nBr. at 46.)\n\n\n\n\nguess at what the locality’s written reasons will be, write a\ncomplaint that contains those hypotheses, and risk being\nsandbagged by the written reasons that the locality\nsubsequently provides in litigation after the challenging entity\nhas shown its cards.” Id. at 816 n.3. If an applicant cannot\nfile suit, however, because the locality’s “final action” has not\nyet occurred, those concerns vanish. The ZBA’s decision\nhere, when reduced to writing, was both its decision to deny\nand its final action.\n\n\n\n\n 22\n\f Those concerns are overstated and, in any case,\nirrelevant. The shot clock begins to run once a wireless\nprovider files its application, so it is already ticking before\nany oral decision is made. If the locality fails to meet that\ndeadline by not issuing a written decision before the shot\nclock expires, the wireless provider can bring a claim for a\n“failure to act.” 14 24 FCC Rcd. 13994, 14012 (2009). T\nMobile asserts that requiring a separate failure-to-act suit, in\naddition to a suit on the merits, undercuts the statutory\npurpose of expedited judicial review, particularly in cases\nwhere the locality has a “pattern and practice of not issuing a\nwritten decision of land use denials unless or until [it] is\nsued.” (Opening Br. at 7.) But the statute’s own remedies\ncannot possibly undercut its purpose. A separate failure-to-\nact claim is the very remedy Congress chose for shot clock\nviolations. 24 FCC Rcd. 14013 at ¶ 4 (2009). Whether or not\nT Mobile likes that policy choice, it is the one Congress\nmade, and we are not free to change it.\n\n C. The Timing Requirement Is Not\n Jurisdictional.\n\n Because we hold that a writing is required for a denial\nto constitute a final action, T Mobile’s initial complaint was\nnot ripe for review when filed. And, T Mobile’s\nsupplemental complaint was filed more than 30 days after the\nZBA issued its written decision and was therefore untimely\nunder the TCA’s review provision. 47 U.S.C.\n§ 332(c)(7)(B)(v). Thus, the District Court only had\njurisdiction if T Mobile’s supplemental complaint cured the\n\n 14\n It is not clear which time limit would have applied in\nthis case and whether it would have been violated.\n\n\n\n\n 23\n\fripeness flaw in its initial complaint by relating back to the\noriginal filing date. If the 30-day time limit in the TCA’s\nreview provision is nonjurisdictional, we can safely say that\nrelation back is possible and allows a supplemental complaint\nto cure a defective premature filing. 15 At the outset, then, we\nmust determine whether that 30-day time limit is\njurisdictional, being mindful both of the Supreme Court’s\ncounsel to exercise caution before holding timing\nrequirements to be jurisdictional and of its guidance regarding\nwhat constitutes a jurisdictional limit. 16 Sebelius, 568 U.S. at\n149, 153-54. Caution is indeed warranted because statutes of\nlimitations and other filing deadlines “ordinarily are not\njurisdictional.” Id. at 154; see also United States v. Kwai Fun\nWong, 135 S. Ct. 1625, 1632 (2015) (“[M]ost time bars are\nnonjurisdictional.”).\n\n\n 15\n We do not reach the issue of whether an unripe\ncomplaint can be cured by a supplemental or amended\npleading over which the Court lacked jurisdiction.\n 16\n The City claims that our decision in Nextel Partners\nInc. v. Kingston Township, 286 F.3d 687 (3d Cir. 2002) is\neffectively determinative. Not so. In Kingston Township,\nthen-Judge Alito noted that the District Court had held the\ntiming requirement in the TCA’s review provision was\njurisdictional. Id. at 695. But we did not address whether\nthat determination was correct, nor did we rely on it. Instead,\nwe concluded that there could be no “failure to act” towards\nan application that was not submitted. Id. at 692. Since our\ndecision in that case, the Supreme Court has clarified the\nprocess for determining if a time limit is jurisdictional.\nSebelius, 568 U.S. at 149.\n\n\n\n\n 24\n\f “[T]o ward off profligate use of the term ‘jurisdiction,’\n[the Supreme Court has] adopted a readily administrable\nbright line for determining whether to classify a statutory\nlimitation as jurisdictional.” Sebelius, 568 U.S. at 153 (citing\nArbaugh v. Y & H Corp., 546 U.S. 500, 516 (2006))\n(quotation marks omitted). We are to ask “whether Congress\nhas clearly state[d] that the rule is jurisdictional; absent such a\nclear statement, we … should treat the restriction as\nnonjurisdictional in character.” Id. (alteration in original)\n(citation and quotation marks omitted); see also Musacchio v.\nUnited States, 136 S. Ct. 709, 716 (2016) (Thus, “[w]e treat a\ntime bar as jurisdictional only if Congress has ‘clearly stated’\nthat it is.”). In deciding whether Congress has made such a\nclear statement, “we evaluate the ‘text, context, and relevant\nhistorical treatment.’” United States v. Kalb, 891 F.3d 455,\n460 (2018) (quoting Reed Elsevier, 559 U.S. 154, 166\n(2010)).\n\n Referencing that last test, Wilmington asserts that\n“[s]ection 332’s statutory grant of jurisdiction to district\ncourts, the text of the statute, the placement of the filing\nwindow in that same section, and the well-established\ntreatment of the filing window as jurisdictional, [all\ndemonstrate] that the filing window is jurisdictional.”\n(Answering Br. at 15.) We disagree. The differences\nbetween the review provision’s timing requirement and the\ntiming requirement we held to be jurisdictional in Kalb, and\nthe similarities between the review provision’s timing\nrequirements and those at issue in Sebelius and Musacchio,\nwhich the Supreme Court held to be nonjurisdictional,\nactually support treating the timing requirement in the TCA’s\nreview provision as nonjurisdictional.\n\n\n\n\n 25\n\f First, although Wilmington says that the text of the\nstatute indicates Congress’s desire to make the 30-day timing\nrequirement jurisdictional, the text does not use the term\n“jurisdictional” or any variation of it to describe the timing\nrequirement. 47 U.S.C. § 332(c)(7)(B)(v). To the contrary,\nthe statute uses permissive rather than mandatory language.\nUnlike the timing requirement we held to be jurisdictional in\nKalb, which mandated that an action would be barred if not\nfiled in time, the TCA’s review provision states that an action\n“may” be filed within 30-days. Compare Kalb, 891 F.3d at\n460 with 47 U.S.C. § 332(c)(7)(B)(v). The language is much\ncloser to that which the Supreme Court decided was\nnonjurisdictional in Sebelius. The statute at issue in that case,\nlike the review provision here, uses a permissive phrase –\n“may obtain a hearing” – before it states the timing\nrequirement. 17 Compare Sebelius, 568 U.S. at 154, with 47\nU.S.C. § 332(c)(7)(B)(v) (“may … commence an action”).\nSimilar to the timing requirement the Supreme Court held to\nbe nonjurisdictional in Musacchio, the review provision does\nnot confer jurisdiction, instead it allows an action to be\n\n 17\n T Mobile also points to Henderson v. Shinseki,\nwhich held a timing requirement to be nonjurisdictional even\nthough it used the mandatory “shall” before stating the timing\nrequirement. 562 U.S. 428, 441-42 (2011). But the decision\nin Shinseki, where the pertinent timing requirement could\nhave barred a veteran’s appeal, was partly based on “the\ncanon that provisions for benefits to members of the Armed\nServices are to be construed in the beneficiaries’ favor,” and\nso it is of less utility in deciding this dispute. Id. at 441\n(quotation marks and citations omitted).\n\n\n\n\n 26\n\fcommenced “in any court of competent jurisdiction.” See\nMusacchio, 136 S. Ct. at 717 (“[The provision] does not\nexpressly refer to subject-matter jurisdiction or speak in\njurisdictional terms.”). The text of the statute therefore favors\na holding that the timing requirement is nonjurisdictional.\n\n Wilmington next contends that the context of the\ntiming requirement favors the view that the requirement is\njurisdictional, because the Supreme Court has stated that it is\n“inextricably linked to … the language that creates the right\nof action[.]” (Answering Br. at 13-14 (citing City of Rancho\nPalos Verdes v. Abrams, 544 U.S. 113, 125 (2005)).) Thus,\nsays the City, the “filing window created by [the review\nprovision] is jurisdictional [because] it is integral to the\nexpress purpose of the section, to this Court’s jurisdiction,\nand to the parties’ rights and obligations[.]” (Answering Br.\nat 8.)\n\n True enough, the review provision’s timing\nrequirement does appear in the same subsection as the\nstatutory text granting jurisdiction. 47 U.S.C.\n§ 332(c)(7)(B)(v). And, as we stated in Kalb, the Supreme\nCourt’s decisions in Bowles v. Russell, 551 U.S. 205, 210\n(2007), and Reed Elsevier, Inc. v. Muchnick, 559 U.S. at 166,\nboth found the source of the timing requirement to be\nimportant in determining whether that requirement was\njurisdictional. 891 F.3d at 462. In Kalb, moreover, we made\nthe same point the City now does, stating that a timing\nrequirement was jurisdictional because “the thirty-day appeal\nperiod here is embedded in the same statutory section that\ngrants jurisdiction to the court of appeals.” Id.\n\n\n\n\n 27\n\f But the location of the timing requirement within the\nstatutory structure, without more, does not clearly reveal\nCongressional intent. As noted by the Supreme Court in\nSebelius, a timing requirement should not be classified as\njurisdictional solely based on its placement in a jurisdictional\nprovision. Sebelius, 568 U.S. at 155 (“A requirement we\nwould otherwise classify as nonjurisdictional … does not\nbecome jurisdictional simply because it is placed in a section\nof a statute that also contains jurisdictional provisions.”\n(citing Gonzalez v. Thaler, 565 U.S. 134, 146-47 (2012))). In\nMusacchio too, the Supreme Court held that a timing\nrequirement was nonjurisdictional despite its presence in the\njurisdiction-granting section of the statute at issue. 136 S. Ct.\nat 717. The Court emphasized that the statute did not directly\nspeak of the timing requirement as jurisdictional, despite its\nmandatory language. Id. That reasoning applies with at least\nequal force here, so the context of the review provision’s\ntiming requirement does not make the requirement\njurisdictional.\n\n Finally, Wilmington asserts that the timing\nrequirement is jurisdictional because of the historical\ntreatment of similar provisions. The City asserts that the\nphrase “within 30 days after” creates a “window,” during\nwhich a complaint must be filed, and not a “deadline.”\n(Answering Br. at 11-12 (citing W. Union Tel. Co. v. FCC,\n773 F.2d 375, 377 (D.C. Cir. 1985)) (noting that “within 60\ndays after” creates a 60-day filing window while “no later\nthan 60 days after” creates a filing deadline).) But that\nargument misses the point because it goes to whether the rule\nbars suit between certain dates or only after a certain date, not\nto whether the timing requirement is jurisdictional. See, e.g.,\nUnion Tel. Co., 773 F.2d at 377-78 (discussing whether the\n\n\n\n\n 28\n\ffiling window is a jurisdictional bar for suits filed before the\nwindow opens). And just because a complaint may be unripe\nbefore a particular date does not mean that a deadline by\nwhich suit must be filed is jurisdictional. As we stated in\nKalb, the Supreme Court’s decisions in Bowles and Reed\nElsevier both looked to “the Court’s prior treatment of\n[similar timing requirements.]” Kalb, 891 F.3d at 460. In\nSebelius, the timing requirement, as here, used the phrase\n“within” and thus, under Wilmington’s logic, it would have\nbeen a jurisdictional limit. Sebelius, 568 U.S. at 154. But the\nSupreme Court held otherwise, id., and that is of high\nimportance.\n\n Because the text and context of this statute, and\nhistorical treatment of timing requirements in similar statutes,\ndo not reveal a clear intent from Congress to make the review\nprovision’s timing requirement jurisdictional, we conclude\nthat it is not. 18\n\n D. Rule 15 Allows a Supplemental Complaint\n Filed After a Claims Processing Deadline To\n Relate Back and Cure an Unripe Initial\n Complaint.\n\n We next consider whether an untimely supplemental\ncomplaint can, by relating back, cure an initial complaint that\nwas unripe. We believe it can, and because T Mobile’s\n\n 18\n That conclusion is further supported by the\nthoughtful concurrence in Athens Cellular, concluding after\nSebelius that the timing requirement “imposed by Congress in\nthe TCA … is not a jurisdictional bar.” Athens Cellular, 886\nF.3d at 1113 (Kaplan, J. concurring).\n\n\n\n\n 29\n\fmotion to supplement its complaint was properly granted, that\nsupplemental complaint relates back and is ripe. The District\nCourt therefore had jurisdiction and should not have granted\nWilmington’s motion for summary judgment.\n\n At the outset, we note that the parties do not dispute,\nand we agree, that the District Court was within its discretion\nto grant T Mobile’s motion to supplement its complaint.\nPursuant to Federal Rule of Civil Procedure 15(d), “[o]n\nmotion and reasonable notice, the [district] court may, on just\nterms, permit a [moving] party to serve a supplemental\npleading setting out any … event that happened after the date\nof the pleading to be supplemented.” Fed. R. Civ. P. 15(d);\nsee also 3 James Wm. Moore et al., Moore’s Federal Practice\n¶ 15.30 (3d ed. 2018) (“Supplemental pleadings … are\nlimited to subsequent events related to the claim or defense\npresented in the original pleading.”). Here, the District Court\nrightly granted T Mobile’s motion to supplement. That\ndecision was just, since Wilmington had long since had notice\nof the event – the filing of the written denial – that occurred\nafter the initial pleading. After all, the City issued that denial,\nand the denial was featured in the parties’ discovery plan.\nThe issuance of it was also plainly related to T Mobile’s\ninitial complaint.\n\n That the initial complaint was premature is not a bar\nsince, under Rule 15(d), “[t]he court may permit\nsupplementation even though the original pleading is\ndefective in stating a claim for relief or defense.” Fed. R.\nCiv. P. 15(d). As the Advisory Committee Notes make clear,\n“Rule 15(d) is intended to give the [district] court broad\ndiscretion in allowing a supplemental pleading.” Fed. R. Civ.\nP. 15(d) advisory committee’s note to 1963 amendment. It is\n\n\n\n\n 30\n\ffurthermore “within the discretion of the court to allow a\nsupplemental pleading to be filed at any stage of the case[.]”\nMoore et al., supra, ¶ 15.30. The District Court here was thus\nwell within its discretion in granting T Mobile’s motion to\nsupplement the complaint.\n\n Rule 15 does not indicate whether or under what\ncircumstances a supplemental pleading can relate back to the\ndate of the original pleading to avoid the effect of a time\nlimit. 6A Charles Alan Wright et al., Federal Practice &\nProcedure § 1508 (3d ed. 2018). Subsection (c) of the Rule,\nwhich provides for the relation back of amended pleadings,\ndoes not specifically refer to supplemental pleadings. Fed. R.\nCiv. P. 15(c). Nor does Rule 15(d) make any mention of\nrelation back. Fed. R. Civ. P. 15(d). But case law and\nsecondary sources have long instructed that once a\nsupplemental complaint is granted, it is treated like an\namended complaint for purposes of relation back. 19 Thus,\neven though Rule 15(d) is in a separate statutory provision\nfrom Rule 15(c), a supplemental complaint can relate back.\nWright et al., supra, § 1508; see also F.D.I.C. v. Knostman,\n966 F.2d 1133, 1138 (7th Cir. 1992) (“The distinction\nbetween an amended pleading and a supplemental pleading is\n\n 19\n Courts have generally held that a supplemental\ncomplaint is eligible for relation back, but rely on different\nrationales to do so. See Wright et al., supra, § 1508 (“[S]ome\ncourts have held that for purposes of applying the relation-\nback doctrine a supplemental pleading may be treated as an\namended pleading under Rule 15(c); other courts have\napplied the relation-back principle directly to supplemental\npleadings even though Rule 15(d) does not mention it.”)\n(internal citations omitted).\n\n\n\n\n 31\n\foften disregarded for purposes of relation back under Rule\n15(c).”); Russell v. New Amsterdam Cas. Co., 303 F.2d 674,\n680-81 (8th Cir. 1962) (finding supplemental pleading related\nback despite plaintiff suing in the wrong capacity and not\nachieving appropriate status for diversity jurisdiction until\nafter the limitations period had expired). That stands to\nreason, since, if a “defendant had notice of the subject matter\nof the dispute and was not prejudiced in preparing a defense\n…[,] the policy against stale claims becomes subsidiary to the\npolicy expressed throughout the rules in favor of allowing a\nparty to set forth all the grievances against another party in\none action and resolving them on their merits.” Wright et al.,\nsupra, § 1508.\n\n So a pleading filed according to Rule 15(d) can relate\nback, assuming it meets “the basic test for relation back\nprescribed by Rule 15(c).” Id.; see also Moore et al., supra,\n¶ 15.30 (“A supplemental pleading may relate back to the\ndate of the original complaint if the requirements under Rule\n15(c) for relation back are satisfied”); Davis v. Piper Aircraft\nCorp., 615 F.2d 606, 609 n.3 (4th Cir. 1980) (supplemental\npleading relates back if Rule 15(c)’s test is met). In fact, as\nthe District Court observed, if a supplemental complaint\nmeets the requirements for relation back then “[r]elation back\nis mandatory,” and not subject to additional equitable\nconsiderations. 20 (App. at 6 (citing Arthur v. Maersk, Inc.,\n434 F.3d 196, 202-03 (3d Cir. 2006)).)\n\n 20\n We note, however, that “[a] party opposing the\nintroduction of a supplemental pleading might wish to raise\nthe statute-of-limitations defense when the additional\npleading (1) alleges new matter that brings the earlier\npleading up to date; (2) cures a defect in the original pleading;\n\n\n\n\n 32\n\f Looking then to Rule 15(c), a complaint “relates back\nto the date of the original pleading when … [it] asserts a\nclaim or defense that arose out of the conduct, transaction, or\noccurrence set out -- or attempted to be set out -- in the\noriginal pleading[.]” Fed. R. Civ. P. 15(c)(1)(B). The\nDistrict Court here concluded that there was no need to\ndetermine whether T Mobile’s supplemental complaint\nrelated back, because, even if it did, “it fail[ed] to cure the\ndeficiencies of the initial complaint[.]” (App. at 8.) But\ngiven our view that the supplemental complaint could indeed\ncure the ripeness problem with the initial complaint, we must\ncontend with the relation-back question.\n\n To determine if relation back is proper, the only issue\nis whether there is a “common core of operative facts in the\ntwo pleadings.” Bensel v. Allied Pilots Ass’n, 387 F.3d 298,\n310 (3d Cir. 2004.) Here, that test is met. Both complaints\nrely on the same core facts. The written denial was a\ncertification and restatement of the earlier oral denial.\n\n Thus, the only question remaining is whether a\ncomplaint that relates back can cure an untimely initial\ncomplaint, and the answer is yes. The clear preference\nembodied in Rule 15 is for merits-based decision making. Cf.\nMoore et al., supra, ¶ 15.30 (“The same principles that\nsupport the liberal amendment of pleadings also apply to\nsupplemental pleadings.”). As the Supreme Court has stated,\nthe purpose of Rule 15 is “to balance the interests of the\n\n\nor (3) states a new claim that arose after the filing of the\ncomplaint.” Wright et al., supra, § 1508.\n\n\n\n\n 33\n\fdefendant protected by the statute of limitations with the\npreference expressed in the Federal Rules of Civil Procedure\nin general, and Rule 15 in particular, for resolving disputes on\ntheir merits.” Krupski v. Costa Crociere S.p.A., 560 U.S. 538,\n550 (2010). The requirements of Rule 15 itself protect\ndefendants from an unfair relation back. 21 Under that Rule,\ncourts “look[s] to whether the opposing party has had fair\nnotice of the general fact situation and legal theory upon\nwhich the amending party proceeds.” Bensel, 387 F.3d at\n310. In this instance, Wilmington had sufficient notice since\nthe supplemented complaint simply alleged the issuance of\nthe ZBA’s written denial. And, of course, Wilmington had\nnotice of everything in the supplemental complaint. It not\nonly knew of the written denial and the reasons given, it\ngenerated them.\n\n Relation back has been allowed to address\njurisdictional problems. We said in Berkshire Fashions, Inc.\nv. M.V. Hakusan II that relation back may be used to cure\ndefects in jurisdictional allegations. 954 F.2d 874, 878 (3rd\nCir. 1992). In that case, the District Court had dismissed the\nplaintiff’s claim based on admiralty jurisdiction and denied\nthe plaintiff’s motion to amend its complaint to allege\ndiversity jurisdiction. Id. at 877. We concluded that both\ndecisions were in error, holding that an amended complaint\nrelates back and can cure insufficient pleading of subject\nmatter jurisdiction. Id. at 878. Recently, our Circuit allowed\n\n 21\n This is not a pass for endless delay in\nsupplementing a complaint. Indeed, we have endeavored to\nemphasize that whether to allow supplemental pleading\ndepends on equitable considerations of fairness and notice\nthat district courts must take into account.\n\n\n\n\n 34\n\fa plaintiff to cure a diversity defect when the case had been\nlitigated for years. See GBForefront, L.P., v. Forefront\nMgmt. Grp., LLC, 888 F.3d 29, 32 (3d Cir. 2018)\n(“instruct[ing] the [d]istrict [c]ourt to give leave to further\namend the complaint … to cure defective jurisdictional\nallegations”).\n\n Other circuits have held the same. See Woods v. Ind.\nUniv.-Purdue Univ. at Indianapolis, 996 F.2d 880, 884 (7th\nCir. 1993) (“Consistent with its history and purpose, Rule\n15(c) has uniformly been applied to relate back [filings] that\ncure defective statements of jurisdiction ….”); Boyce v.\nAnderson, 405 F.2d 605, 607 (9th Cir. 1968) (allowing\namendment alleging that no previous appeal had been taken\nto the United States Court of Customs and Patent Appeals to\ncure jurisdictional defect in complaint after statute of\nlimitations had expired). That conclusion is also consistent\nwith 28 U.S.C. § 1653, which allows “[d]efective allegations\nof jurisdiction [to] be amended, upon terms, in the trial or\nappellate courts.” Id.\n\n Courts have similarly permitted cure of actual defects\nin the court’s jurisdiction, going beyond just jurisdictional\nallegations. For instance, although not in a case involving a\nlater complaint, the Supreme Court has said that a court can\ndrop a dispensable non-diverse party to cure a defect in\ndiversity jurisdiction. Newman-Green, Inc. v. Alfonzo-\nLarrain, 490 U.S. 826, 837-38 (1989); see also E.R. Squibb &\nSons, Inc. v. Lloyd’s & Cos., 241 F.3d 154, 163 (2d Cir.\n2001) (stating that, “where it is appropriate to relate back an\namendment to a pleading under Rule 15, jurisdiction is\nassessed as if the amendment had taken place at the time the\ncomplaint was first filed[,]” and thus replacing a non-diverse\n\n\n\n\n 35\n\fplaintiff with a diverse plaintiff cured any jurisdiction\nproblem); Rowe v. United States Fid. & Guar. Co., 421 F.2d\n937, 939, 944 (4th Cir. 1970) (concluding that a defective\ncomplaint could be cured by a later complaint that pled an\nassignment occurring after the original complaint was filed).\n\n Nonetheless, “[a]mendments that go beyond the mere\ncorrection or factual modification of the original pleading and\nsignificantly alter the claim or defense alleged in that\npleading are treated more cautiously by the courts in applying\nthe relation-back doctrine.” Wright et al., supra, § 1497. The\nSecond Circuit, for instance, only sometimes allows\njurisdictional defects to be cured “when the underlying facts,\nif properly pled, would have supported jurisdiction at the time\nthe action commenced.” Correspondent Servs. Corp. v. First\nEquities Corp. of Fla., 338 F.3d 119, 125 (2d Cir. 2003); see\nalso, e.g., Barton v. Ellis, No. 75-1188, 1977 WL 15469, at\n*1 (D.S.C. Apr. 26, 1977) (denying using relation back to\ncure the original complaint since they were defects “not [in\nthe] allegations of existing underlying jurisdictional facts but\nrather [in] the prerequisite jurisdictional facts themselves”).\nWilmington argues such hesitance is appropriate here because\nallowing relation back to cure the jurisdictional problem with\nT Mobile’s initial complaint “would allow two wrongs under\nSection 332 [(filing early and filing late)] to make a right.”\n(Answering Br. at 2.)\n\n We again disagree with the City. It is quite true that\nT Mobile has made procedural matters more difficult than\nthey should be in this case. But denying relation-back to cure\nthe defect in this instance would not comport with Rule 15’s\naim to encourage resolution of disputes on the merits\nwhenever possible. The ripeness requirement exists so that\n\n\n\n\n 36\n\fcourts avoid issuing essentially advisory opinions. See\nRichard H. Fallon, Jr. et al., Hart and Wechsler’s the Federal\nCourts and the Federal System 224 (5th ed. 2003) (noting that\nthe ripeness doctrine allows courts to avoid a “dispute … too\n‘ill-defined’ to be appropriate for judicial resolution until\nfurther developments … more sharply framed the issues for\ndecision.”). That concern ceased to exist here once the\nsupplemental pleading was in place. At that point, the dispute\nhad matured and become capable of judicial review,\ndemonstrating that, “actions taken after the filing of the initial\ncomplaint can be used to establish subject matter\njurisdiction.” Prasco, LLC v. Medicis Pharm. Corp., 537\nF.3d 1329, 1337 (Fed. Cir. 2008).\n\n If a supplemental complaint cannot cure an unripe\ncomplaint, an endless feedback loop would be created\nwhereby the ripeness problem could never be overcome, even\nthough, as here, the dispute later became obviously ripe. Our\nsister circuits have recognized that problem and concluded\nthat a supplemental complaint is the solution. 22 In Wilson v.\nWestinghouse Electric Corp., the Eighth Circuit determined\nthat prohibiting an amended (or supplemental) complaint\nfrom alleging facts that occurred after the date the initial\n\n 22\n In our Circuit, a thoughtful district court decision\nhad long ago reached that conclusion. It held that an\nuntimely supplement adding facts occurring after the initial\nfiling that showed exhaustion of administrative remedies\ncould relate back to the initial premature complaint and allow\nmaintenance of the lawsuit. Bates v. W. Elec., 420 F. Supp.\n521, 526-27 (E.D. Pa. 1976).\n\n\n\n\n 37\n\fcomplaint was filed would turn a premature complaint into an\n“irretrievable mistake that bars jurisdiction” and would be\n“precisely the kind of procedural mousetrap that the Federal\nRules were designed to dismantle.” 838 F.2d 286, 289 (8th\nCir. 1988). The court held that, “[e]ven when the District\nCourt lacks jurisdiction over a claim at the time of its original\nfiling, a supplemental complaint may cure the defect by\nalleging the subsequent fact which eliminates the\njurisdictional bar.” Id. at 290 (citing Mathews, 426 U.S. at\n75). While Wilson addressed a circumstance in which the\nsupplemental complaint was timely filed, the proposition still\napplies in a case like ours because, if a party was limited to\nrefiling within an applicable time limit, there would be little\nneed to make provision for supplementation of a complaint,\nas a new complaint could be filed. 23\n\n 23\n We note that sparing the cost of refiling and\nproviding convenience to the Court would remain legitimate\nreasons for allowing supplemental complaints. But the\npurpose of Rule 15(d) is broader. See Wright et al., supra, §\n1504 (“The purpose of subdivision (d) is to promote as\ncomplete an adjudication of the dispute between the parties as\nis possible. … A supplemental pleading may be employed\nfor a variety of purposes.”). Wilmington contends that\nWilson is inapposite since it involved a timely supplemental\ncomplaint. Thus, concern about a perpetual loop outcome\nwas not proper because the plaintiff could have simply refiled\nhis complaint. But we agree that “a plaintiff need not\ncommence a new action when after-occurring events\ndemonstrate that it has a right to relief even if the original\ncomplaint was insufficient. A plaintiff may also be allowed\nto supplement the complaint even if jurisdiction … would not\nhave been proper if the claim had been asserted in an\n\n\n\n\n 38\n\f The Ninth Circuit, in Security Insurance Co. of New\nHaven v. United States ex rel. Haydis, also relied on that logic\nto find that relation back could cure an unripe complaint filed\nbefore a statutory filing window opened. 338 F.2d 444, 448-\n49 (9th Cir. 1964). In a fact scenario with striking similarities\nto the present appeal, the plaintiff had filed its claim before a\nstatutory waiting period was over and then did not file an\namended complaint until after the statute of limitations period\nhad run. Id. at 445-46. The appeals court held that the\ndistrict court was “not required to apply the doctrine of\nrelation back so literally as to carry it to a time [before it was\nripe] so as to prevent the maintenance of the action in the first\nplace.” Id. at 449.\n\n The Supreme Court has favorably cited Security\nInsurance’s ruling. In Mathews, the plaintiff had not satisfied\na precondition of filing a complaint by first filing an\napplication with a particular agency. 426 U.S. at 72, 75. The\nCourt noted that a supplemental complaint, alleging that the\napplication had since been filed, would have cured the\njurisdictional defect. Id. at 75. In saying so, the Court relied\n\n\n\nindependent action.” Moore et al., supra, ¶ 15.30 (3d ed.\n2018) (citation omitted). If supplemental complaints could\nnot cure ripeness, “then all supplemental pleadings of this\nnature would be defeated for lack of jurisdiction – [the]\n‘procedural mousetrap’ would render all supplemental\npleadings void.” George v. IRS, No. C05-00955 MJJ, 2006\nWL 3499230, at *3 (N.D. Cal. Dec. 4, 2006) (citation\nomitted).\n\n\n\n\n 39\n\fon Security Insurance. Id. at 75 n.8 (citing Security\nInsurance, 338 F.2d at 447-49). 24\n\n Yet Wilmington asserts that ripeness can never be\ncured by a later complaint. It advances four cases for that\nproposition, but none are helpful. First, the City cites\nDelaware Riverkeeper Network v. Secretary Pennsylvania\nDepartment of Environmental Protection, (Riverkeeper I),\n833 F.3d 360 (3d Cir. 2016), in which we concluded that,\n“even though the underlying claim became ripe for review\nduring the pendency of the case, the ripening of the claim did\nnot cure deficient pleadings.” (App. at 8.) In that case,\nhowever, no attempt to file a later complaint alleging ripeness\nwas made. Riverkeeper I, 833 F.3d at 369-70.\n\n Likewise, in another two of the four cases that\nWilmington cites, there was no effort made to amend or\nsupplement the complaint. See TeleSTAR, Inc. v. FCC, 888\nF.2d 132, 134 (D.C. Cir. 1989) (concluding non-final agency\naction at the time of filing of petition may only be reviewed\nupon the filing of another petition); W. Union Tel. Co., 773\nF.2d at 377-78 (concluding that the court lacked jurisdiction\nover challenges filed before the action became final).\nTherefore, neither case determined whether relation back of a\nlater-filed complaint could cure a ripeness problem in the\ninitial complaint.\n\n 24\n Wilmington contends that Mathews is inapposite\nsince the statute of limitations was waived. That argument\nhas no traction since, if it were a jurisdictional bar, it could\nnot be waived.\n\n\n\n\n 40\n\f The City fares no better relying on Council Tree\nCommunications v. FCC, in which we stated that “[a] petition\nto review a non-final agency order is incurably premature.”\n503 F.3d 284, 291 (3d Cir. 2007). At no point in that case\nwas the complaint ripe, and the petitioner still had a petition\nfor reconsideration pending before the relevant agency on the\ndate the case was decided. Id. at 287. Furthermore, Council\nTree explicitly acknowledged that a supplemental complaint\ncan cure an unripe complaint when there is jurisdiction over\nthat supplemental pleading. See id. at 291 (“[W]e note that\n‘nothing prevented [the petitioners] from supplementing their\npremature petition with a later protective petition.’” (second\nalteration in original) (quoting Horsehead Res. Dev. Co. v.\nE.P.A., 130 F.3d 1090, 1095 (D.C. Cir. 1997))).\n\n Wilmington also makes three policy arguments in\nsupport of its position that an untimely supplemental\ncomplaint should not be able to cure an unripe complaint.\nFirst, it contends that allowing suits to be filed before an\naction is ripe would “extend[] federal court jurisdiction over\nlocal government actions before those actions are final[.]”\n(Answering Br. at 9.) Second, such filings would waste\njudicial resources and, in this case, cost taxpayers money, by\nforcing courts to deal with a higher volume of unripe\ncomplaints. Third, the purpose of § 332 is to preserve local\nzoning authority, which would be undermined by allowing\nplaintiffs to file suit early and thereby places undue pressure\non zoning commissions.\n\n Those contentions, however, are unpersuasive. First, a\ncourt would remain without jurisdiction if the claim had not\nripened by the time of the supplemental complaint. Second, it\n\n\n\n\n 41\n\fseems that Wilmington overstates the impact that a decision\nallowing an unripe complaint to be cured would have, since\nour holding today makes it clear that an action is not final\nuntil a written decision has been issued. Clarifying when a\ndetermination is ripe for review should end any incentive for\naggrieved parties to file early to ensure they have not filed too\nlate.\n\n Perhaps more importantly, however, courts can police\nany potential abuse on a case-by-case basis using Rule 15(d)\nand the Rule 15(c) test for relation back. It is understood that\n“relation back of a supplemental pleading should not result in\nproviding unfair procedural advantages to a plaintiff[,] so …\nrelation back may not be for all purposes.” Wright et al.,\nsupra, § 1508. But here no unfair advantage has resulted, and\ndefendants in general will be adequately protected by a\ndistrict court’s Rule 15(d) analysis, which will determine if a\nsupplemental complaint should be allowed at all. For\ninstance, if a locality’s action is not yet a final action at the\ntime a Rule 15(d) motion is filed, the motion can easily be\ndenied. See Beezley v. Fremont Indem. Co., 804 F.2d 530,\n530 (9th Cir. 1986) (supplemental pleading denied when it\nstill failed to cure defective original pleading).\n\n When all is said and done here, we conclude that, to\neffectuate the liberal purpose of Rule 15 and to avoid the\nendless feedback loop that the City’s legal argument would\ncreate, Rule 15 allows an untimely supplemental complaint to\nrelate back and cure an unripe initial complaint.\n\n\n\n\n 42\n\fIII. CONCLUSION\n\n For the foregoing reasons, we will reverse the District\nCourt’s grant of the City’s motion for summary judgment,\nvacate the District Court’s denial of T Mobile’s motion for\nsummary judgment, and remand to the District Court for\nfurther proceedings consistent with this opinion.25\n\n\n\n\n 25\n We will vacate the District Court’s denial of\nT Mobile’s motion for summary judgment because it was\nsolely based on a finding that T Mobile’s suit was not timely\nbrought.\n\n\n\n\n 43\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: T MOBILE NORTHEAST LLC, Appellant v. CITY OF WILMINGTON, DELAWARE ; City of Wilmington Zoning Board of Adjustment\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-10\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 18-1831\\n _____________\\n\\n T MOBILE NORTHEAST LLC,\\n Appellant\\n\\n v.\\n\\n CITY OF WILMINGTON, DELAWARE;\\nCITY OF WILMINGTON ZONING BOARD OF ADJUSTMENT\\n _____________\\n\\n On Appeal from the United States District Court\\n for the District of Delaware\\n (D.C. No. 1-16-cv-01108)\\n District Judge: Hon. Eduardo C. Robreno\\n _______________\\n\\n Argued\\n September 12, 2018\\n\\nBefore: JORDAN, NYGAARD, and VANASKIE, * Circuit Judge\\n (Filed: January 10, 2019)\\n\\n\\n *\\n The Honorable Thomas I. Vanaskie retired from the\\nCourt on January 1, 2019 after the argument and conference\\nin this case, but before the filing of the opinion. This opinion\\nis filed by a quorum of the panel pursuant to 28 U.S.C.\\n§ 46(d) and Third Circuit I.O.P. Chapter 12.\\n\\f _______________\\n\\nThomas S. Thompson [ARGUED]\\nDavis Wright Tremaine\\n1919 Pennsylvania Avenue, NW\\nSte. 800\\nWashington, DC 20006\\n\\nCounsel for Appellant\\n\\nJoseph Van Eaton [ARGUED]\\nBest Best & Krieger\\n2000 Pennsylvania Avenue\\nSte. 5300\\nWashington, DC 20006\\n\\nCounsel for Appellees\\n _______________\\n\\n OPINION OF THE COURT\\n _______________\\n\\n\\nJORDAN, Circuit Judge.\\n\\n No one likes bad cell phone reception or slow\\nstreaming data on their smartphone, but that does not mean\\nanyone wants a cellular antenna in their neighborhood, which\\nis why there are zoning battles like the one central to this\\ncase.\\n\\n T Mobile Northeast LLC (“T Mobile”), a wireless\\ntelecommunications service provider, applied to the Zoning\\nBoard of Adjustment (“ZBA”) of the City of Wilmington,\\nDelaware for permission to erect an antenna in the City. The\\n\\n\\n\\n\\n 2\\n\\fZBA said no. So, relying on a provision of federal law that\\nallows a disappointed wireless service provider like T Mobile\\nto seek review in a district court “within 30 days after” a\\nzoning authority’s “final action,” 47 U.S.C.\\n§ 332(c)(7)(B)(v), T Mobile filed suit. After the case had\\nproceeded for over a year, however, the District Court\\nconcluded that it lacked jurisdiction. The Court reasoned that\\nbecause T Mobile filed its complaint before the ZBA released\\na written decision confirming an earlier oral rejection of the\\nzoning application, the claim was not ripe. And, since\\nT Mobile did not supplement its complaint to include the\\nZBA’s written decision within 30 days of its issuance, the\\nCourt also concluded that relation back could not remedy the\\nripeness defect. The District Court thus granted the City’s\\nmotion for summary judgment.\\n\\n T Mobile now appeals. It argues that its complaint\\nwas not premature or, in the alternative, that its supplemental\\npleading cured any ripeness problem. We agree that the grant\\nof summary judgment was improper and, for the reasons that\\nfollow, will remand the case for further proceedings\\nconsistent with this opinion.\\n\\nI. BACKGROUND\\n\\n A. Statutory Framework\\n\\n This dispute is governed by the Telecommunications\\nAct of 1996 (“TCA”), which amended the Federal\\nCommunications Act of 1934 and includes provisions on\\nmobile phone services. Pub. L. No. 104-104, §§ 1, 704, 110\\nStat. 56, 56, 151 (1996); 47 U.S.C. § 332. Passed to\\n“encourage the rapid deployment of new telecommunications\\n\\n\\n\\n\\n 3\\n\\ftechnologies,” Preamble, 110 Stat. at 56, the TCA provides\\nfor expedited review in federal court of a denial of permission\\nto build a cell phone antenna, id. § 704, 110 Stat. at 151-52.\\nSuch review is a “benefit Congress expressly intended to\\nconfer on wireless providers[.]” Nextel W. Corp. v. Unity\\nTwp., 282 F.3d 257, 264 (3d Cir. 2002). At the same time,\\nthe TCA also serves to preserve local zoning authority. 47\\nU.S.C. § 332(c)(7).\\n\\n At issue here are three key sections of the statute.\\nFirst, the TCA mandates that “[a] State or local government\\nor instrumentality thereof shall act on any request for\\nauthorization to place, construct, or modify personal wireless\\nservice facilities within a reasonable period of time after the\\nrequest is duly filed[.]” Id. § 332(c)(7)(B)(ii). The Federal\\nCommunications Commission (“FCC”) has interpreted\\n“reasonable period of time” in that statutory provision to\\nmean that zoning authorities have a “shot clock” 1 and must\\nact within 90 days of an application to attach an antenna to an\\nexisting structure or 150 days of an application where a new\\nsupport structure is to be built. Petition for Declaratory\\n\\n 1\\n “Shot clock” is a term borrowed from basketball. In\\nthat game, it signifies a time limit to make a shot attempt,\\nbeginning once a team has possession of the basketball. See,\\ne.g., Nat’s Basketball Ass’n, NBA Rulebook Rule No. 7: Shot\\nClock (2018-2019), http://official.nba.com/rule-no-7-24-\\nsecond-clock/. If the team has not made a shot attempt, i.e.,\\nacted, within the prescribed time limit, it forfeits possession\\nof the ball. Id. Here, the permitting authority has exclusive\\njurisdiction over an application until it fails to act within a\\n“reasonable period of time.” 47 U.S.C. §§ 332(c)(7)(A),\\n332(c)(7)(B)(ii).\\n\\n\\n\\n\\n 4\\n\\fRuling to Clarify Provisions of Section 332(c)(7)(B), 24 FCC\\nRcd. 13994, 14008, 14012 (2009). Second, in what we will\\ncall the “review provision” of the statute, the TCA grants\\n“[a]ny person adversely affected by any final action or failure\\nto act by a State or local government or any instrumentality\\nthereof” a right to have that locality’s decision reviewed by\\n“commenc[ing] an action” “within 30 days” in district court.\\n47 U.S.C. § 332(c)(7)(B)(v). Third, in the statute’s “denial\\nprovision,” the TCA states that “[a]ny decision by a State or\\nlocal government or instrumentality thereof to deny a request\\nto place, construct, or modify personal wireless service\\nfacilities shall be in writing and supported by substantial\\nevidence contained in a written record.” Id.\\n§ 332(c)(7)(B)(iii). Notably, the terms “act,” “final action,”\\nand “decision … to deny” are not defined in the TCA.\\nFurthermore, the statute does not make clear whether “final\\naction” should be read to encompass all decisions to deny,\\nincluding oral ones, nor does it address whether there is a\\ndifference between an “act” for purposes of the shot clock\\nand a “final action” for purposes of judicial review.\\n\\n B. Factual Background\\n\\n T Mobile is a telecommunications service provider. It\\nsays that it needs to erect a cellular antenna to fill “a\\nsignificant gap” in coverage for its customers in Wilmington,\\nDelaware, (Opening Br. at 3) presumably where there has\\nbeen an increase in phone calls and data usage. T Mobile\\nwants to put its antenna on top of a senior living high-rise in\\nthe City, but, because a special exception to local zoning laws\\nis needed, it first had to go to the ZBA. It filed an initial\\napplication and then, on August 25, 2016, a final amended\\napplication, seeking the exception.\\n\\n\\n\\n\\n 5\\n\\f The ZBA held a hearing on October 26, 2016, to\\nconsider T Mobile’s request, some two months after the final\\namended application was submitted. During the hearing,\\nT Mobile presented evidence of the need for the antenna and\\ndiscussed proposals to address aesthetic concerns. The ZBA\\nalso received objections from members of the local\\ncommunity, some of whom were outspoken in worrying\\nabout the effects of radio frequency emissions. At the end of\\nthe hearing, the ZBA denied T Mobile’s application in a\\nunanimous oral decision.\\n\\n The Board gave several reasons for the denial. One\\nboard member said the ZBA should not encourage the use of\\na senior living community rooftop as the base for an antenna\\nbecause of the potential adverse effect on the properties in the\\nneighborhood. Another board member said there was not\\nenough proof of a need for additional coverage to support the\\napplication. The Chairman said there was not enough\\nevidence that T Mobile needed the antenna and that it did not\\nappear to satisfy the zoning code in terms of placement and\\nheight restrictions.\\n\\n The ZBA’s oral decision to deny the application was\\nnot put in writing on October 26 or anytime soon thereafter.\\nAccording to T Mobile, that fits a “pattern and practice of\\n[the ZBA] not issuing a written decision of land use denials\\nunless or until the City is sued.” (Opening Br. at 7.) Only\\nafter T Mobile had filed its initial complaint in the District\\nCourt, and after the City filed its answer, did the ZBA issue\\nits written decision and explanation of its reasoning for\\ndenying the application.\\n\\n\\n\\n\\n 6\\n\\f T Mobile asserts that the denial of its application\\nviolates the TCA. Under the statute, such a denial is invalid\\nif it has the “effect of prohibiting the provision of personal\\nwireless services[,]” 47 U.S.C. § 332(c)(7)(B)(i)(II), or is “on\\nthe basis of the environmental effects of radio frequency\\nemissions[,]” id. at § 332(c)(7)(B)(iv). T Mobile claims that\\nWilmington’s denial was improper on both of those grounds. 2\\nBut those assertions go to the merits and are not actually\\nbefore us on this appeal. At issue now is whether T Mobile’s\\nclaim can be heard at all.\\n\\n C. Procedural History\\n\\n Evidently with its eye on the 30-day deadline in the\\nTCA’s review provision, T Mobile filed a lawsuit in the\\nUnited States District Court for the District of Delaware\\nwithin 30 days of the ZBA’s oral decision, challenging that\\ndenial. 3 In addition to its claims on the merits, T Mobile’s\\ninitial complaint alleged that the City violated procedures\\nmandated in the TCA, specifically those in the denial\\nprovision, by failing to provide a written decision\\n\\n 2\\n T Mobile also raised a Delaware state law claim.\\nThat claim is not at issue here and does not impact\\nT Mobile’s claims under federal law.\\n 3\\n For reasons discussed herein, the 30-day filing\\ndeadline was not triggered by the oral decision. See infra pp.\\n12-20. If it were, however, T Mobile’s complaint would have\\nbeen timely. The oral decision was delivered at the\\nOctober 26, 2016 hearing. Suit was filed on November 28,\\n2016, but because the thirtieth day from October 26 fell on a\\nweekend, the November 28 filing was within the 30-day\\nwindow. Fed. R. Civ. P. 6(a)(1).\\n\\n\\n\\n\\n 7\\n\\fcontemporaneous with its oral decision and by not supporting\\nthe denial with substantial evidence.\\n\\n The parties entered into a stipulation asking the\\nDistrict Court for an expedited case schedule, as provided for\\nin the review provision of the TCA. 47 U.S.C.\\n§ 332(c)(7)(B)(v). That request was granted. Wilmington\\nthen answered the complaint, asserting a number of\\naffirmative defenses, including that the complaint was not\\nripe because the ZBA had not yet issued a final written\\ndecision. Nevertheless, the City did not, at that time, file a\\nmotion to dismiss for failure to state a claim or for lack of\\njurisdiction. Two days after the City filed its answer, the\\nZBA issued a written decision on T Mobile’s application.\\nThe parties pressed forward with the suit and prepared a\\ndiscovery plan, which specifically mentioned the written\\ndecision. T Mobile filed a motion for summary judgment,\\nwhich the City met with a cross-motion for summary\\njudgment. The City’s motion was styled in the alternative as\\na motion to dismiss the complaint as unripe because it was\\nfiled prematurely, i.e., before the written decision had been\\nissued.\\n\\n Not until December 21, 2017, nearly a year after the\\nZBA issued its written denial, did T Mobile file a motion\\nseeking leave to amend or supplement the initial complaint to\\nnote the issuance of that written decision. 4 The District Court\\n\\n 4\\n When “[a] claim or defense set out in a pleading [is]\\naffected by events that occur after the pleading is filed ….\\nRule 15(d) allows a court,” to permit a supplemental\\npleading. 3 James Wm. Moore et al., Moore’s Federal\\nPractice ¶ 15.30 (3d ed. 2018). Supplemental pleadings\\n\\n\\n\\n\\n 8\\n\\fgranted the motion to supplement. Wilmington then\\nresponded by moving to dismiss the supplemental complaint\\nas untimely because it failed to cure the defect.\\n\\n Ultimately, the District Court granted Wilmington’s\\ncross-motion for summary judgment for want of jurisdiction,\\nwithout ruling on the City’s motion to dismiss. The Court\\nfirst concluded that the initial complaint was irreparably\\nunripe because both the TCA and Delaware law require the\\nZBA to issue a written decision before the agency’s action\\ncould be considered final, and T Mobile had thus filed its\\ninitial complaint too soon. Second, the Court said that the\\nsupplemental complaint could not fix the ripeness problem\\nbecause it was filed past the 30-day window for seeking\\nreview of the ZBA’s final action. Because the Court reached\\n\\n\\n\\nunder Rule 15(d) differ from amended pleadings made under\\nRule 15(a). First, amended pleadings “relate to matters that\\noccurred prior to the filing of the original pleading and\\nentirely replace the earlier pleading; [supplemental pleadings]\\ndeal with events subsequent to the pleading to be altered and\\nrepresent additions to or continuations of the earlier\\npleadings.” 6A Charles Alan Wright et al., Federal Practice\\n& Procedure § 1504 (3d ed. 2018). Second “certain\\namendments may be made as a matter of course within stated\\ntime periods, whereas all supplemental pleadings require\\nleave of court under Rule 15(d).” Id. “Parties and courts\\noccasionally confuse supplemental pleadings with amended\\npleadings and mislabeling is common.” Id. Here, T Mobile’s\\ncomplaint was filed as an amended complaint but it is\\nproperly categorized as a supplemental complaint, and we\\nwill refer to it as such herein.\\n\\n\\n\\n\\n 9\\n\\fthat determination, it found it unnecessary to conclude\\nwhether T Mobile’s supplemental complaint was entitled to\\nthe benefit of the relation-back doctrine under Rule 15(c).\\n\\n This appeal followed.\\nII. DISCUSSION 5\\n\\n T Mobile challenges the District Court’s grant of\\nsummary judgment in favor of Wilmington, contending that\\nthere is jurisdiction to hear its case. It advances two\\nalternative grounds for reversal: that its complaint was ripe\\nbecause the ZBA’s oral decision qualifies as a “final action”\\nunder the review provision of the TCA, and, in the\\nalternative, that the supplemental complaint relates back to\\nand cures any ripeness problem with its initial complaint.\\nThose arguments in turn raise three questions for determining\\nwhether the District Court’s jurisdictional ruling was proper.\\nFirst, whether the oral decision of the ZBA was a final action.\\nSecond, whether the timing requirement in the TCA’s review\\nprovision is jurisdictional. And third, whether an untimely\\n\\n 5\\n The District Court had jurisdiction to consider its\\njurisdiction under 28 U.S.C. §§ 1331 and 1367(a), but\\ndetermined the complaint contained incurable jurisdictional\\ndefects and declined to reach the merits. We have jurisdiction\\npursuant to 28 U.S.C. § 1291. We review all the issues\\npresented in this case de novo, as they involve only legal\\nissues, i.e., interpretation of a federal statute and of a Federal\\nRule of Civil Procedure. Giles v. Campbell, 698 F.3d 153,\\n155 (3d Cir. 2012); Viera v. Life Ins. Co. of N. Am., 642 F.3d\\n407, 413 (3d Cir. 2011); DIRECTV Inc. v. Seijas, 508 F.3d\\n123, 125 (3d Cir. 2007).\\n\\n\\n\\n\\n 10\\n\\fsupplemental complaint can relate back and cure an unripe\\ninitial complaint. Although we disagree with T Mobile that\\nan oral decision of the ZBA qualifies as a “final action,” we\\nagree that jurisdiction was proper in the District Court\\nbecause the timing requirement in the TCA’s review\\nprovision is non-jurisdictional, and T Mobile’s supplemental\\ncomplaint therefore relates back and cures the ripeness\\nproblem with the initial complaint. The District Court should\\nthus have reached the merits of the dispute.\\n\\n A. The Oral Decision Was Not a Final Action of\\n the ZBA.\\n\\n The ripeness of T Mobile’s initial complaint depends\\nupon whether the ZBA’s oral decision was a “final action”\\nwithin the meaning of the TCA. Consideration of that issue\\nuncovers another: whether the TCA requires a locality to\\nrender its decision in writing for that decision to qualify as a\\nfinal action. The District Court held that, under both federal\\nand Delaware law, only a written decision can serve as a final\\naction of the ZBA. Because traditional hallmarks of agency\\naction and the statutory text and structure of the TCA favor\\nthat approach, we agree that only a written decision can serve\\nas a locality’s final action when denying an application.\\n\\n In Delaware Riverkeeper Network v. Secretary\\nPennsylvania Department of Environmental Protection,\\n(Riverkeeper III), we determined that, when reviewing\\nfinality under the Natural Gas Act, “[a]lthough the\\ndecisionmaking process we are reviewing is defined by [state]\\nlaw, we nevertheless apply a federal finality standard to\\ndetermine whether Congress has made the results of that\\nprocess reviewable[.]” 903 F.3d 65, 72 (3d Cir. 2018). The\\n\\n\\n\\n\\n 11\\n\\fsame reasoning holds true here, since, for the TCA just as for\\nthe Natural Gas Act, “the finality requirement itself, along\\nwith the presumption that Congress intended us to apply it,\\nare creatures of federal, not state, law.” Id. at 71.\\n\\n Under federal law, not all agency determinations are\\nfinal actions. Bacon v. Sullivan, 969 F.2d 1517, 1519 (3d Cir.\\n1992). Final agency actions bear certain “traditional\\nhallmarks” that demonstrate “[t]here is nothing left for the\\nagency to do[,]” Del. Riverkeeper Network v. Sec’y of Pa.\\nDep’t of Envtl. Prot., (Riverkeeper II), 870 F.3d 171, 178 (3d\\nCir. 2017). We noted those hallmarks on an earlier occasion\\nwhen we said that, “[f]inal agency action must mark the\\nconsummation of the agency’s decisionmaking process, must\\nnot be of a merely tentative or interlocutory nature, and must\\nbe one by which rights or obligations have been determined,\\nor from which legal consequences will flow.” Riverkeeper\\nIII, 903 F.3d at 72, 75 (citation and internal quotation marks\\nomitted).\\n\\n To decide what the TCA requires for finality, we\\nbegin, of course, with the text. See, e.g., Ross v. Blake, 136 S.\\nCt. 1850, 1856 (2016) (“Statutory interpretation … begins\\nwith the text[.]”) Here, the statutory text makes it clear that,\\nif a denial is not in writing, there is something left for the\\nagency to do. The denial provision of the TCA states that\\n“[a]ny decision … to deny … shall be in writing and\\nsupported by substantial evidence contained in a written\\nrecord.” 47 U.S.C. § 332(c)(7)(B)(iii). We see no reason\\nwhy the same should not be true for actions besides denial, 6\\n\\n 6\\n For instance, it is not apparent why community\\nmembers aggrieved by a decision to grant some permit to a\\n\\n\\n\\n\\n 12\\n\\fbut we need not decide that today. It is enough to say that, in\\nthose zoning decisions governed by the TCA, a locality’s oral\\ndeclaration of a denial is “of a merely tentative or\\ninterlocutory nature.” Riverkeeper III, 903 F.3d at 72\\n(citation omitted) (speaking in reference to the Natural Gas\\nAct); cf. Athens Cellular, Inc. v. Oconee Cty., 886 F.3d 1094,\\n1104-05, 1107 (11th Cir. 2018) (noting that a zoning board\\ncould have approved the minutes, revised them, or rejected\\nthem, and thus until the board approved the minutes its\\ndecision was not final).\\n\\n Moreover, an oral decision is not an action from which\\nlegal consequences flow. Federal law governs finality, but\\nDelaware’s procedures still matter, and the Delaware\\nSuperior Court has concluded that a written document must\\nbe filed for a ZBA action to be final. McDonald’s Corp. v.\\nZoning Bd. of Adjustment for the City of Wilmington, No.\\nCIV. A. 01A-05-011CG, 2002 WL 88944, at *1 (Del. Super.\\nCt. Jan. 10, 2002). The court reasoned that Section 328 of\\nTitle 22 of the Delaware Code, the section that governs\\nappeals from ZBA proceedings, requires a written document\\nto be filed because the statute “provides that [s]uch petition\\nshall be presented to the Court within 30 days after the filing\\nof the decision in the office of the board.” Id. (internal\\nquotation marks omitted). That reasoning is persuasive and\\n\\n\\n\\n\\nwireless provider, assuming those members have standing to\\nsue, would not be equally entitled to a zoning authority’s\\nwritten decision before the time limit in the TCA’s review\\nprovision is triggered.\\n\\n\\n\\n\\n 13\\n\\fshows that, under Delaware law, the ZBA’s oral decision is\\nwithout legal consequences. 7\\n\\n There are distinct policy advantages to forestalling\\njudicial scrutiny until a written denial is issued. Requiring a\\nwritten decision focuses review on a particular, documented\\nstatement of reasons. See USCOC of Greater Mo. v. City of\\nFerguson, 583 F.3d 1035, 1042 (8th Cir. 2009) (“Because the\\nwritten decision is the central object of our scrutiny under the\\nTCA, the process of judicial review is best served by delaying\\nthe ripening of a TCA claim until the local authority has\\nissued its written decision.”). It also prevents ambiguity with\\nrespect to when a claim can be brought. As the District Court\\nhere stated, to hold otherwise “would promote a pernicious\\nambiguity as to when that short period of time begins to run.”\\n(App. at 7.) And it promotes uniformity of federal procedures\\nby clarifying when, across all jurisdictions, an action becomes\\nfinal.\\n\\n 7\\n T Mobile cites to a different opinion, Schmalhofer v.\\nBoard of Adjustment of Newark, to advance a contrary\\nposition. No. C.A. 99A-05-010-WTQ, 2000 WL 703510\\n(Del. Super. Ct. May 9, 2000). Schmalhofer states in a\\nfootnote that “a written decision is not required or expressly\\ncontemplated by this section.” Id. at *3 n.3. But T Mobile is\\nstretching the Schmalhofer court’s language too far. In that\\ncase, the City of Newark had issued a verbatim transcript of\\nthe hearing, so there was a writing. Id. at *3; see infra note\\n11. There is no indication of any written decision in this case,\\nprior to December 22, 2016, when the City issued the written\\ndenial bearing the date of December 21, 2016.\\n\\n\\n\\n\\n 14\\n\\f The Supreme Court’s decision in T-Mobile South, LLC\\nv. City of Roswell, Georgia, also adds support to the\\nconclusion that only a written denial can constitute final\\naction, triggering a party’s right to review. 135 S. Ct. 808\\n(2015). In that case, the Court held that the “substantial\\nevidence” supporting a locality’s decision to deny must be\\nreleased contemporaneously with the written decision to\\ndeny. 8 Id. at 811-12. In doing so, the Court tied together a\\nlocal zoning authority’s final action, which triggers judicial\\nreview, and its decision to deny, which must be in writing.\\nIndeed, the Supreme Court said in no uncertain terms that,\\n“[t]he relevant ‘final action’ [in that case, was] the issuance of\\nthe written notice of denial[.]” Id. at 817 n.4. The Court\\nlinked the locality’s decision to deny to the 30-day time limit\\nto file a complaint after a final action has been taken. Id. at\\n817 (“Only once the denial is issued would the 30-day\\ncommencement-of-suit clock begin.”); id. at 813 (“[N]ow 29\\ndays after the City denied petitioner’s application—petitioner\\nfiled suit in Federal District Court.”).\\n\\n The Court went on to discuss timing, saying, “the\\nlocality must provide or make available its written reasons at\\nessentially the same time as it communicates its denial[,]”\\n“[b]ecause an entity may not be able to make a considered\\n\\n 8\\n The Court was interpreting the denial provision,\\nwhich, as we noted earlier, states that, “[a]ny decision by a\\nState or local government or instrumentality thereof to deny a\\nrequest to place, construct, or modify personal wireless\\nservice facilities shall be in writing and supported by\\nsubstantial evidence contained in a written record.” 47\\nU.S.C. § 332(c)(7)(B)(iii), City of Roswell, 135 S. Ct. at 811.\\n\\n\\n\\n\\n 15\\n\\fdecision whether to seek judicial review without knowing the\\nreasons for the denial of its application, and because a court\\ncannot review the denial without knowing the locality’s\\nreasons[.]” Id. at 816. The majority opinion was critical of\\nthe dissent for attempting to “fashion a world in which a\\nlocality can wait until a lawsuit is commenced and a court\\norders it to state its reasons[,] … [leaving the challenging\\nentity to] risk being sandbagged by the written reasons that\\nthe locality subsequently provides in litigation after the\\nchallenging entity has shown its cards.” Id. at 816 n.3. That\\ncritique is premised on the written decision being the final\\naction that starts the 30-day time limit for commencing suit. 9\\n\\n The Supreme Court anticipated that localities might\\nneed to delay issuing a written denial if they are not ready to\\nrelease their substantial reasons. See id. at 817 (noting that\\n\\n 9\\n T Mobile asserts that Wilmington has a “pattern and\\npractice of not issuing a written decision of land use denials\\nunless or until the City is sued.” (Opening Br. at 7.) But if\\nonly a written denial is a final action, the shot clock requires\\nthe City to issue that written decision within a given time\\nperiod. 24 FCC Rcd. 13994, 14012 (2009). T Mobile also\\nasserts that when a locality has a pattern and practice of not\\nreleasing written decisions, that practice delays the overall\\nprocess, since a cellular service provider would be required to\\ninitiate two causes of action: one to compel a written decision\\nand another to challenge that written decision. That,\\nhowever, is precisely what Congress envisioned by providing\\nseparate remedies for a failure to “act” within a reasonable\\ntime period and for an improper denial. 47 U.S.C.\\n§ 332(c)(7)(B)(iii).\\n\\n\\n\\n\\n 16\\n\\f“[i]f a locality is not in a position to provide its reasons\\npromptly, the locality can delay the issuance of its denial\\nwithin this 90– or 150–day window, and instead release it\\nalong with its reasons once those reasons are ready to be\\nprovided.”). That further counsels against treating an oral\\ndetermination as a final action since, if an oral determination\\nis deemed a final action, localities will be unable to take\\nadvantage of the permissible delay afforded by the shot clock\\nfor publishing their reasoning.\\n\\n Two of our sister courts of appeals agree that only a\\nwritten decision can constitute final action. The Eighth\\nCircuit in USCOC of Greater Missouri v. City of Ferguson\\nstated that “[t]he plain language of the TCA indicates that\\n‘final action’ does not occur until issuance of a written\\ndecision.” 583 F.3d at 1041. The Eleventh Circuit in\\nPreferred Sites LLC v. Troup County likewise held a\\ncomplaint to be timely when it was filed within 30 days of a\\nwritten decision, even though it was filed more than 30 days\\nafter an oral decision. 10 296 F.3d 1210, 1217-18 (11th Cir.\\n\\n 10\\n T Mobile attempts to distinguish Preferred Sites by\\nstating that, unlike here, the case did “not address a city that\\ndoes not issue a written decision close in time to when it\\nmakes the decision to deny.” (Opening Br. at 37.) But that\\nargument is irrelevant to whether the statutory text requires a\\nwriting for an agency decision to be final. T Mobile also cites\\nto Preferred Sites to argue that it should not matter if there is\\na writing requirement since the oral denial could be seen as\\nakin to a court announcing a decision. It explains that “when\\nan appeal is filed after the court announces a decision, but\\nbefore the entry of the judgment, it is treated as being filed on\\nthe date of entry.” (Opening Br. at 28-29 (citing Preferred\\n\\n\\n\\n\\n 17\\n\\f2002) (concluding that, “[b]ased on the plain language of the\\nstatute,” that “a ‘final action’ occurs when the state or local\\nauthority issues its written decision. The statute expressly\\nmandates a … decision … committed to writing. Until the\\nstate or local authority issues its written notification, its task\\nunder the statute is not complete.”). No circuit has held\\notherwise.\\n\\n Persuasive authority thus indicates that any action, and\\ncertainly a denial, must be in writing to be final. But, there is\\nanother possible interpretation of the statutory text. The\\nwords “shall be in writing” could be read not as a condition of\\nfinality, but instead as a simple directive to state and local\\ngovernments to place their final action in writing. “The TCA\\nprovides no express answer to … when a local government’s\\npermitting decision becomes a ‘final action,’ which starts the\\nthirty-day clock.” Athens Cellular, 886 F.3d at 1102-03. The\\nstatute only states that denials must be in writing. 47 U.S.C.\\n§ 332(c)(7)(b)(iii). Decisions to grant are not limited in the\\nsame way. Id. And, Congress used the words “decision to\\ndeny” in one statutory subsection and “final action” in\\nanother, which could evince an intent to give those terms\\ndifferent meanings. As the Supreme Court has “recognized\\n… Congress’s use of certain language in one part of the\\nstatute and different language in another can indicate that\\ndifferent meanings were intended.” Sebelius v. Auburn Reg’l\\nMed. Ctr., 568 U.S. 145, 156 (2013) (citation and quotation\\n\\n\\n\\nSites, 296 F.3d at 1217 n.7).) That analogy did appear in\\nPreferred Sites, but it was only contained in a footnote. No\\nother court has followed that line of reasoning, and we\\ndecline to follow it here.\\n\\n\\n\\n\\n 18\\n\\fmarks omitted). Thus, it could be argued, if Congress wanted\\nto mandate a writing for zoning denials to constitute final\\naction, it could have been more explicit, providing, for\\ninstance, that a “decision must be in writing to qualify as a\\nfinal action.”\\n\\n But, of course, one can almost always fault legislative\\ndrafting, like other kinds of writing, after the fact. That\\nsomething might have been said even more clearly does not\\nmean it is not clear enough. So, “[r]ather than expecting (let\\nalone demanding) perfection in drafting,” we can “construe[]\\nstatutes to have a particular meaning even as we\\nacknowledge[] that Congress could have expressed itself\\nmore clearly.” Torres v. Lynch, 136 S. Ct. 1619, 1633\\n(2016).\\n\\n The text and structure of the statute, Delaware\\nprocedures, Supreme Court reasoning, our sister circuits’\\ndecisions, and policy arguments all support the conclusion\\nthat a writing is in fact a requirement for a denial to be final. 11\\nIn light of that conclusion, the ZBA’s oral determination on\\n\\n 11\\n What constitutes a “writing” has some flexibility,\\nthough. See, e.g., Omnipoint Holdings, Inc. v. City of\\nSouthfield, 355 F.3d 601, 605-07 (6th Cir. 2004) (approving\\nminutes by written resolution was a final action that bound\\nthe parties). In City of Roswell, for example, the Supreme\\nCourt indicated that minutes of an oral meeting could be\\nsufficient. 135 S. Ct. at 816. Here, however, there is no\\nevidence that the ZBA’s oral determination was noted in the\\nminutes of the October 26th meeting and issued by the City as\\nits formal decision.\\n\\n\\n\\n\\n 19\\n\\fOctober 26, 2016, was not a final action ripe for judicial\\nreview. Therefore, as that oral determination was not reduced\\nto writing until December 22, 2016, preceding the filing of\\nT Mobile’s initial complaint, that complaint’s cause of action\\nwas not ripe.\\n\\n\\n\\n\\n 20\\n\\f B. No Separate Time Limit Exists Following an\\n Oral Determination.\\n\\n As an alternative to its argument that the ZBA’s oral\\ndecision was a final action, T Mobile asks us to consider\\nwhether a “local government must issue the ‘writing’ close in\\ntime to the ‘decision … to deny’ to establish a ‘final action’\\nthat will be subject to expedited review.” 12 (Opening Br. at\\n41.) Essentially, T Mobile is asserting that the “shot clock”\\ngoverning the time to act, which allows a wireless carrier to\\nsue for a locality’s failure to act, is insufficient, and that a\\nnew requirement, albeit not in the statute, should be imposed\\non localities. Under T Mobile’s proposed rule, an oral\\ndecision would have to be reduced to writing within a\\nspecified time period. That argument assumes that an oral\\ndetermination can serve to satisfy the requirement to “act” on\\na request within the limits of the shot clock, and that, without\\na separate judicially created time limit, there would be no\\ndeadline for the locality to release its written decision to deny,\\ndespite City of Rowell’s contemporaneous writing\\nrequirement. Because we conclude that a denial must be in\\nwriting to be a final action, the issuance of that writing is the\\ngovernment “act” ruled by the shot clock. 13 Aside from the\\n\\n 12\\n Wilmington argues that T Mobile has waived that\\nissue, but we need not address that argument because we\\nconclude that no such requirement exists.\\n 13\\n Again, the Supreme Court held in City of Roswell\\nthat a locality’s decision to deny must be accompanied by\\nsubstantial reasons. 135 S. Ct. at 811-12. Otherwise, if a\\nlocality were able to withhold its reasoning for its decision,\\nthose aggrieved by the locality’s actions would “be left to\\n\\n\\n\\n\\n 21\\n\\ftime limits associated with the “shot clock,” there is no other\\ndeadline governing the issuance of a written decision\\nfollowing an oral determination. 47 U.S.C. § 332(c)(7)(b).\\nAny time limit we fabricated would be inappropriate.\\n\\n T Mobile argues that, without a requirement for\\nlocalities to issue a written decision within a set amount of\\ntime following an oral determination, wireless carriers are left\\n“to wait until the FCC ‘shot clock’ expires – which could be\\n90 or 150 days depending on the type of installation involved\\n– and then [to] file an action alleging that the City has failed\\nto act in a reasonable time[.]” (Opening Br. at 45.) It also\\ncontends that a “failure to act” lawsuit is insufficient because\\nthe remedy for a successful suit is simply an order telling the\\nCity to issue a written decision. In T Mobile’s view, forcing\\nwireless providers to sue both to compel a written decision\\nonce the shot clock is violated and again to contest the written\\ndecision serves only to “create yet further delay.” (Opening\\nBr. at 46.)\\n\\n\\n\\n\\nguess at what the locality’s written reasons will be, write a\\ncomplaint that contains those hypotheses, and risk being\\nsandbagged by the written reasons that the locality\\nsubsequently provides in litigation after the challenging entity\\nhas shown its cards.” Id. at 816 n.3. If an applicant cannot\\nfile suit, however, because the locality’s “final action” has not\\nyet occurred, those concerns vanish. The ZBA’s decision\\nhere, when reduced to writing, was both its decision to deny\\nand its final action.\\n\\n\\n\\n\\n 22\\n\\f Those concerns are overstated and, in any case,\\nirrelevant. The shot clock begins to run once a wireless\\nprovider files its application, so it is already ticking before\\nany oral decision is made. If the locality fails to meet that\\ndeadline by not issuing a written decision before the shot\\nclock expires, the wireless provider can bring a claim for a\\n“failure to act.” 14 24 FCC Rcd. 13994, 14012 (2009). T\\nMobile asserts that requiring a separate failure-to-act suit, in\\naddition to a suit on the merits, undercuts the statutory\\npurpose of expedited judicial review, particularly in cases\\nwhere the locality has a “pattern and practice of not issuing a\\nwritten decision of land use denials unless or until [it] is\\nsued.” (Opening Br. at 7.) But the statute’s own remedies\\ncannot possibly undercut its purpose. A separate failure-to-\\nact claim is the very remedy Congress chose for shot clock\\nviolations. 24 FCC Rcd. 14013 at ¶ 4 (2009). Whether or not\\nT Mobile likes that policy choice, it is the one Congress\\nmade, and we are not free to change it.\\n\\n C. The Timing Requirement Is Not\\n Jurisdictional.\\n\\n Because we hold that a writing is required for a denial\\nto constitute a final action, T Mobile’s initial complaint was\\nnot ripe for review when filed. And, T Mobile’s\\nsupplemental complaint was filed more than 30 days after the\\nZBA issued its written decision and was therefore untimely\\nunder the TCA’s review provision. 47 U.S.C.\\n§ 332(c)(7)(B)(v). Thus, the District Court only had\\njurisdiction if T Mobile’s supplemental complaint cured the\\n\\n 14\\n It is not clear which time limit would have applied in\\nthis case and whether it would have been violated.\\n\\n\\n\\n\\n 23\\n\\fripeness flaw in its initial complaint by relating back to the\\noriginal filing date. If the 30-day time limit in the TCA’s\\nreview provision is nonjurisdictional, we can safely say that\\nrelation back is possible and allows a supplemental complaint\\nto cure a defective premature filing. 15 At the outset, then, we\\nmust determine whether that 30-day time limit is\\njurisdictional, being mindful both of the Supreme Court’s\\ncounsel to exercise caution before holding timing\\nrequirements to be jurisdictional and of its guidance regarding\\nwhat constitutes a jurisdictional limit. 16 Sebelius, 568 U.S. at\\n149, 153-54. Caution is indeed warranted because statutes of\\nlimitations and other filing deadlines “ordinarily are not\\njurisdictional.” Id. at 154; see also United States v. Kwai Fun\\nWong, 135 S. Ct. 1625, 1632 (2015) (“[M]ost time bars are\\nnonjurisdictional.”).\\n\\n\\n 15\\n We do not reach the issue of whether an unripe\\ncomplaint can be cured by a supplemental or amended\\npleading over which the Court lacked jurisdiction.\\n 16\\n The City claims that our decision in Nextel Partners\\nInc. v. Kingston Township, 286 F.3d 687 (3d Cir. 2002) is\\neffectively determinative. Not so. In Kingston Township,\\nthen-Judge Alito noted that the District Court had held the\\ntiming requirement in the TCA’s review provision was\\njurisdictional. Id. at 695. But we did not address whether\\nthat determination was correct, nor did we rely on it. Instead,\\nwe concluded that there could be no “failure to act” towards\\nan application that was not submitted. Id. at 692. Since our\\ndecision in that case, the Supreme Court has clarified the\\nprocess for determining if a time limit is jurisdictional.\\nSebelius, 568 U.S. at 149.\\n\\n\\n\\n\\n 24\\n\\f “[T]o ward off profligate use of the term ‘jurisdiction,’\\n[the Supreme Court has] adopted a readily administrable\\nbright line for determining whether to classify a statutory\\nlimitation as jurisdictional.” Sebelius, 568 U.S. at 153 (citing\\nArbaugh v. Y & H Corp., 546 U.S. 500, 516 (2006))\\n(quotation marks omitted). We are to ask “whether Congress\\nhas clearly state[d] that the rule is jurisdictional; absent such a\\nclear statement, we … should treat the restriction as\\nnonjurisdictional in character.” Id. (alteration in original)\\n(citation and quotation marks omitted); see also Musacchio v.\\nUnited States, 136 S. Ct. 709, 716 (2016) (Thus, “[w]e treat a\\ntime bar as jurisdictional only if Congress has ‘clearly stated’\\nthat it is.”). In deciding whether Congress has made such a\\nclear statement, “we evaluate the ‘text, context, and relevant\\nhistorical treatment.’” United States v. Kalb, 891 F.3d 455,\\n460 (2018) (quoting Reed Elsevier, 559 U.S. 154, 166\\n(2010)).\\n\\n Referencing that last test, Wilmington asserts that\\n“[s]ection 332’s statutory grant of jurisdiction to district\\ncourts, the text of the statute, the placement of the filing\\nwindow in that same section, and the well-established\\ntreatment of the filing window as jurisdictional, [all\\ndemonstrate] that the filing window is jurisdictional.”\\n(Answering Br. at 15.) We disagree. The differences\\nbetween the review provision’s timing requirement and the\\ntiming requirement we held to be jurisdictional in Kalb, and\\nthe similarities between the review provision’s timing\\nrequirements and those at issue in Sebelius and Musacchio,\\nwhich the Supreme Court held to be nonjurisdictional,\\nactually support treating the timing requirement in the TCA’s\\nreview provision as nonjurisdictional.\\n\\n\\n\\n\\n 25\\n\\f First, although Wilmington says that the text of the\\nstatute indicates Congress’s desire to make the 30-day timing\\nrequirement jurisdictional, the text does not use the term\\n“jurisdictional” or any variation of it to describe the timing\\nrequirement. 47 U.S.C. § 332(c)(7)(B)(v). To the contrary,\\nthe statute uses permissive rather than mandatory language.\\nUnlike the timing requirement we held to be jurisdictional in\\nKalb, which mandated that an action would be barred if not\\nfiled in time, the TCA’s review provision states that an action\\n“may” be filed within 30-days. Compare Kalb, 891 F.3d at\\n460 with 47 U.S.C. § 332(c)(7)(B)(v). The language is much\\ncloser to that which the Supreme Court decided was\\nnonjurisdictional in Sebelius. The statute at issue in that case,\\nlike the review provision here, uses a permissive phrase –\\n“may obtain a hearing” – before it states the timing\\nrequirement. 17 Compare Sebelius, 568 U.S. at 154, with 47\\nU.S.C. § 332(c)(7)(B)(v) (“may … commence an action”).\\nSimilar to the timing requirement the Supreme Court held to\\nbe nonjurisdictional in Musacchio, the review provision does\\nnot confer jurisdiction, instead it allows an action to be\\n\\n 17\\n T Mobile also points to Henderson v. Shinseki,\\nwhich held a timing requirement to be nonjurisdictional even\\nthough it used the mandatory “shall” before stating the timing\\nrequirement. 562 U.S. 428, 441-42 (2011). But the decision\\nin Shinseki, where the pertinent timing requirement could\\nhave barred a veteran’s appeal, was partly based on “the\\ncanon that provisions for benefits to members of the Armed\\nServices are to be construed in the beneficiaries’ favor,” and\\nso it is of less utility in deciding this dispute. Id. at 441\\n(quotation marks and citations omitted).\\n\\n\\n\\n\\n 26\\n\\fcommenced “in any court of competent jurisdiction.” See\\nMusacchio, 136 S. Ct. at 717 (“[The provision] does not\\nexpressly refer to subject-matter jurisdiction or speak in\\njurisdictional terms.”). The text of the statute therefore favors\\na holding that the timing requirement is nonjurisdictional.\\n\\n Wilmington next contends that the context of the\\ntiming requirement favors the view that the requirement is\\njurisdictional, because the Supreme Court has stated that it is\\n“inextricably linked to … the language that creates the right\\nof action[.]” (Answering Br. at 13-14 (citing City of Rancho\\nPalos Verdes v. Abrams, 544 U.S. 113, 125 (2005)).) Thus,\\nsays the City, the “filing window created by [the review\\nprovision] is jurisdictional [because] it is integral to the\\nexpress purpose of the section, to this Court’s jurisdiction,\\nand to the parties’ rights and obligations[.]” (Answering Br.\\nat 8.)\\n\\n True enough, the review provision’s timing\\nrequirement does appear in the same subsection as the\\nstatutory text granting jurisdiction. 47 U.S.C.\\n§ 332(c)(7)(B)(v). And, as we stated in Kalb, the Supreme\\nCourt’s decisions in Bowles v. Russell, 551 U.S. 205, 210\\n(2007), and Reed Elsevier, Inc. v. Muchnick, 559 U.S. at 166,\\nboth found the source of the timing requirement to be\\nimportant in determining whether that requirement was\\njurisdictional. 891 F.3d at 462. In Kalb, moreover, we made\\nthe same point the City now does, stating that a timing\\nrequirement was jurisdictional because “the thirty-day appeal\\nperiod here is embedded in the same statutory section that\\ngrants jurisdiction to the court of appeals.” Id.\\n\\n\\n\\n\\n 27\\n\\f But the location of the timing requirement within the\\nstatutory structure, without more, does not clearly reveal\\nCongressional intent. As noted by the Supreme Court in\\nSebelius, a timing requirement should not be classified as\\njurisdictional solely based on its placement in a jurisdictional\\nprovision. Sebelius, 568 U.S. at 155 (“A requirement we\\nwould otherwise classify as nonjurisdictional … does not\\nbecome jurisdictional simply because it is placed in a section\\nof a statute that also contains jurisdictional provisions.”\\n(citing Gonzalez v. Thaler, 565 U.S. 134, 146-47 (2012))). In\\nMusacchio too, the Supreme Court held that a timing\\nrequirement was nonjurisdictional despite its presence in the\\njurisdiction-granting section of the statute at issue. 136 S. Ct.\\nat 717. The Court emphasized that the statute did not directly\\nspeak of the timing requirement as jurisdictional, despite its\\nmandatory language. Id. That reasoning applies with at least\\nequal force here, so the context of the review provision’s\\ntiming requirement does not make the requirement\\njurisdictional.\\n\\n Finally, Wilmington asserts that the timing\\nrequirement is jurisdictional because of the historical\\ntreatment of similar provisions. The City asserts that the\\nphrase “within 30 days after” creates a “window,” during\\nwhich a complaint must be filed, and not a “deadline.”\\n(Answering Br. at 11-12 (citing W. Union Tel. Co. v. FCC,\\n773 F.2d 375, 377 (D.C. Cir. 1985)) (noting that “within 60\\ndays after” creates a 60-day filing window while “no later\\nthan 60 days after” creates a filing deadline).) But that\\nargument misses the point because it goes to whether the rule\\nbars suit between certain dates or only after a certain date, not\\nto whether the timing requirement is jurisdictional. See, e.g.,\\nUnion Tel. Co., 773 F.2d at 377-78 (discussing whether the\\n\\n\\n\\n\\n 28\\n\\ffiling window is a jurisdictional bar for suits filed before the\\nwindow opens). And just because a complaint may be unripe\\nbefore a particular date does not mean that a deadline by\\nwhich suit must be filed is jurisdictional. As we stated in\\nKalb, the Supreme Court’s decisions in Bowles and Reed\\nElsevier both looked to “the Court’s prior treatment of\\n[similar timing requirements.]” Kalb, 891 F.3d at 460. In\\nSebelius, the timing requirement, as here, used the phrase\\n“within” and thus, under Wilmington’s logic, it would have\\nbeen a jurisdictional limit. Sebelius, 568 U.S. at 154. But the\\nSupreme Court held otherwise, id., and that is of high\\nimportance.\\n\\n Because the text and context of this statute, and\\nhistorical treatment of timing requirements in similar statutes,\\ndo not reveal a clear intent from Congress to make the review\\nprovision’s timing requirement jurisdictional, we conclude\\nthat it is not. 18\\n\\n D. Rule 15 Allows a Supplemental Complaint\\n Filed After a Claims Processing Deadline To\\n Relate Back and Cure an Unripe Initial\\n Complaint.\\n\\n We next consider whether an untimely supplemental\\ncomplaint can, by relating back, cure an initial complaint that\\nwas unripe. We believe it can, and because T Mobile’s\\n\\n 18\\n That conclusion is further supported by the\\nthoughtful concurrence in Athens Cellular, concluding after\\nSebelius that the timing requirement “imposed by Congress in\\nthe TCA … is not a jurisdictional bar.” Athens Cellular, 886\\nF.3d at 1113 (Kaplan, J. concurring).\\n\\n\\n\\n\\n 29\\n\\fmotion to supplement its complaint was properly granted, that\\nsupplemental complaint relates back and is ripe. The District\\nCourt therefore had jurisdiction and should not have granted\\nWilmington’s motion for summary judgment.\\n\\n At the outset, we note that the parties do not dispute,\\nand we agree, that the District Court was within its discretion\\nto grant T Mobile’s motion to supplement its complaint.\\nPursuant to Federal Rule of Civil Procedure 15(d), “[o]n\\nmotion and reasonable notice, the [district] court may, on just\\nterms, permit a [moving] party to serve a supplemental\\npleading setting out any … event that happened after the date\\nof the pleading to be supplemented.” Fed. R. Civ. P. 15(d);\\nsee also 3 James Wm. Moore et al., Moore’s Federal Practice\\n¶ 15.30 (3d ed. 2018) (“Supplemental pleadings … are\\nlimited to subsequent events related to the claim or defense\\npresented in the original pleading.”). Here, the District Court\\nrightly granted T Mobile’s motion to supplement. That\\ndecision was just, since Wilmington had long since had notice\\nof the event – the filing of the written denial – that occurred\\nafter the initial pleading. After all, the City issued that denial,\\nand the denial was featured in the parties’ discovery plan.\\nThe issuance of it was also plainly related to T Mobile’s\\ninitial complaint.\\n\\n That the initial complaint was premature is not a bar\\nsince, under Rule 15(d), “[t]he court may permit\\nsupplementation even though the original pleading is\\ndefective in stating a claim for relief or defense.” Fed. R.\\nCiv. P. 15(d). As the Advisory Committee Notes make clear,\\n“Rule 15(d) is intended to give the [district] court broad\\ndiscretion in allowing a supplemental pleading.” Fed. R. Civ.\\nP. 15(d) advisory committee’s note to 1963 amendment. It is\\n\\n\\n\\n\\n 30\\n\\ffurthermore “within the discretion of the court to allow a\\nsupplemental pleading to be filed at any stage of the case[.]”\\nMoore et al., supra, ¶ 15.30. The District Court here was thus\\nwell within its discretion in granting T Mobile’s motion to\\nsupplement the complaint.\\n\\n Rule 15 does not indicate whether or under what\\ncircumstances a supplemental pleading can relate back to the\\ndate of the original pleading to avoid the effect of a time\\nlimit. 6A Charles Alan Wright et al., Federal Practice &\\nProcedure § 1508 (3d ed. 2018). Subsection (c) of the Rule,\\nwhich provides for the relation back of amended pleadings,\\ndoes not specifically refer to supplemental pleadings. Fed. R.\\nCiv. P. 15(c). Nor does Rule 15(d) make any mention of\\nrelation back. Fed. R. Civ. P. 15(d). But case law and\\nsecondary sources have long instructed that once a\\nsupplemental complaint is granted, it is treated like an\\namended complaint for purposes of relation back. 19 Thus,\\neven though Rule 15(d) is in a separate statutory provision\\nfrom Rule 15(c), a supplemental complaint can relate back.\\nWright et al., supra, § 1508; see also F.D.I.C. v. Knostman,\\n966 F.2d 1133, 1138 (7th Cir. 1992) (“The distinction\\nbetween an amended pleading and a supplemental pleading is\\n\\n 19\\n Courts have generally held that a supplemental\\ncomplaint is eligible for relation back, but rely on different\\nrationales to do so. See Wright et al., supra, § 1508 (“[S]ome\\ncourts have held that for purposes of applying the relation-\\nback doctrine a supplemental pleading may be treated as an\\namended pleading under Rule 15(c); other courts have\\napplied the relation-back principle directly to supplemental\\npleadings even though Rule 15(d) does not mention it.”)\\n(internal citations omitted).\\n\\n\\n\\n\\n 31\\n\\foften disregarded for purposes of relation back under Rule\\n15(c).”); Russell v. New Amsterdam Cas. Co., 303 F.2d 674,\\n680-81 (8th Cir. 1962) (finding supplemental pleading related\\nback despite plaintiff suing in the wrong capacity and not\\nachieving appropriate status for diversity jurisdiction until\\nafter the limitations period had expired). That stands to\\nreason, since, if a “defendant had notice of the subject matter\\nof the dispute and was not prejudiced in preparing a defense\\n…[,] the policy against stale claims becomes subsidiary to the\\npolicy expressed throughout the rules in favor of allowing a\\nparty to set forth all the grievances against another party in\\none action and resolving them on their merits.” Wright et al.,\\nsupra, § 1508.\\n\\n So a pleading filed according to Rule 15(d) can relate\\nback, assuming it meets “the basic test for relation back\\nprescribed by Rule 15(c).” Id.; see also Moore et al., supra,\\n¶ 15.30 (“A supplemental pleading may relate back to the\\ndate of the original complaint if the requirements under Rule\\n15(c) for relation back are satisfied”); Davis v. Piper Aircraft\\nCorp., 615 F.2d 606, 609 n.3 (4th Cir. 1980) (supplemental\\npleading relates back if Rule 15(c)’s test is met). In fact, as\\nthe District Court observed, if a supplemental complaint\\nmeets the requirements for relation back then “[r]elation back\\nis mandatory,” and not subject to additional equitable\\nconsiderations. 20 (App. at 6 (citing Arthur v. Maersk, Inc.,\\n434 F.3d 196, 202-03 (3d Cir. 2006)).)\\n\\n 20\\n We note, however, that “[a] party opposing the\\nintroduction of a supplemental pleading might wish to raise\\nthe statute-of-limitations defense when the additional\\npleading (1) alleges new matter that brings the earlier\\npleading up to date; (2) cures a defect in the original pleading;\\n\\n\\n\\n\\n 32\\n\\f Looking then to Rule 15(c), a complaint “relates back\\nto the date of the original pleading when … [it] asserts a\\nclaim or defense that arose out of the conduct, transaction, or\\noccurrence set out -- or attempted to be set out -- in the\\noriginal pleading[.]” Fed. R. Civ. P. 15(c)(1)(B). The\\nDistrict Court here concluded that there was no need to\\ndetermine whether T Mobile’s supplemental complaint\\nrelated back, because, even if it did, “it fail[ed] to cure the\\ndeficiencies of the initial complaint[.]” (App. at 8.) But\\ngiven our view that the supplemental complaint could indeed\\ncure the ripeness problem with the initial complaint, we must\\ncontend with the relation-back question.\\n\\n To determine if relation back is proper, the only issue\\nis whether there is a “common core of operative facts in the\\ntwo pleadings.” Bensel v. Allied Pilots Ass’n, 387 F.3d 298,\\n310 (3d Cir. 2004.) Here, that test is met. Both complaints\\nrely on the same core facts. The written denial was a\\ncertification and restatement of the earlier oral denial.\\n\\n Thus, the only question remaining is whether a\\ncomplaint that relates back can cure an untimely initial\\ncomplaint, and the answer is yes. The clear preference\\nembodied in Rule 15 is for merits-based decision making. Cf.\\nMoore et al., supra, ¶ 15.30 (“The same principles that\\nsupport the liberal amendment of pleadings also apply to\\nsupplemental pleadings.”). As the Supreme Court has stated,\\nthe purpose of Rule 15 is “to balance the interests of the\\n\\n\\nor (3) states a new claim that arose after the filing of the\\ncomplaint.” Wright et al., supra, § 1508.\\n\\n\\n\\n\\n 33\\n\\fdefendant protected by the statute of limitations with the\\npreference expressed in the Federal Rules of Civil Procedure\\nin general, and Rule 15 in particular, for resolving disputes on\\ntheir merits.” Krupski v. Costa Crociere S.p.A., 560 U.S. 538,\\n550 (2010). The requirements of Rule 15 itself protect\\ndefendants from an unfair relation back. 21 Under that Rule,\\ncourts “look[s] to whether the opposing party has had fair\\nnotice of the general fact situation and legal theory upon\\nwhich the amending party proceeds.” Bensel, 387 F.3d at\\n310. In this instance, Wilmington had sufficient notice since\\nthe supplemented complaint simply alleged the issuance of\\nthe ZBA’s written denial. And, of course, Wilmington had\\nnotice of everything in the supplemental complaint. It not\\nonly knew of the written denial and the reasons given, it\\ngenerated them.\\n\\n Relation back has been allowed to address\\njurisdictional problems. We said in Berkshire Fashions, Inc.\\nv. M.V. Hakusan II that relation back may be used to cure\\ndefects in jurisdictional allegations. 954 F.2d 874, 878 (3rd\\nCir. 1992). In that case, the District Court had dismissed the\\nplaintiff’s claim based on admiralty jurisdiction and denied\\nthe plaintiff’s motion to amend its complaint to allege\\ndiversity jurisdiction. Id. at 877. We concluded that both\\ndecisions were in error, holding that an amended complaint\\nrelates back and can cure insufficient pleading of subject\\nmatter jurisdiction. Id. at 878. Recently, our Circuit allowed\\n\\n 21\\n This is not a pass for endless delay in\\nsupplementing a complaint. Indeed, we have endeavored to\\nemphasize that whether to allow supplemental pleading\\ndepends on equitable considerations of fairness and notice\\nthat district courts must take into account.\\n\\n\\n\\n\\n 34\\n\\fa plaintiff to cure a diversity defect when the case had been\\nlitigated for years. See GBForefront, L.P., v. Forefront\\nMgmt. Grp., LLC, 888 F.3d 29, 32 (3d Cir. 2018)\\n(“instruct[ing] the [d]istrict [c]ourt to give leave to further\\namend the complaint … to cure defective jurisdictional\\nallegations”).\\n\\n Other circuits have held the same. See Woods v. Ind.\\nUniv.-Purdue Univ. at Indianapolis, 996 F.2d 880, 884 (7th\\nCir. 1993) (“Consistent with its history and purpose, Rule\\n15(c) has uniformly been applied to relate back [filings] that\\ncure defective statements of jurisdiction ….”); Boyce v.\\nAnderson, 405 F.2d 605, 607 (9th Cir. 1968) (allowing\\namendment alleging that no previous appeal had been taken\\nto the United States Court of Customs and Patent Appeals to\\ncure jurisdictional defect in complaint after statute of\\nlimitations had expired). That conclusion is also consistent\\nwith 28 U.S.C. § 1653, which allows “[d]efective allegations\\nof jurisdiction [to] be amended, upon terms, in the trial or\\nappellate courts.” Id.\\n\\n Courts have similarly permitted cure of actual defects\\nin the court’s jurisdiction, going beyond just jurisdictional\\nallegations. For instance, although not in a case involving a\\nlater complaint, the Supreme Court has said that a court can\\ndrop a dispensable non-diverse party to cure a defect in\\ndiversity jurisdiction. Newman-Green, Inc. v. Alfonzo-\\nLarrain, 490 U.S. 826, 837-38 (1989); see also E.R. Squibb &\\nSons, Inc. v. Lloyd’s & Cos., 241 F.3d 154, 163 (2d Cir.\\n2001) (stating that, “where it is appropriate to relate back an\\namendment to a pleading under Rule 15, jurisdiction is\\nassessed as if the amendment had taken place at the time the\\ncomplaint was first filed[,]” and thus replacing a non-diverse\\n\\n\\n\\n\\n 35\\n\\fplaintiff with a diverse plaintiff cured any jurisdiction\\nproblem); Rowe v. United States Fid. & Guar. Co., 421 F.2d\\n937, 939, 944 (4th Cir. 1970) (concluding that a defective\\ncomplaint could be cured by a later complaint that pled an\\nassignment occurring after the original complaint was filed).\\n\\n Nonetheless, “[a]mendments that go beyond the mere\\ncorrection or factual modification of the original pleading and\\nsignificantly alter the claim or defense alleged in that\\npleading are treated more cautiously by the courts in applying\\nthe relation-back doctrine.” Wright et al., supra, § 1497. The\\nSecond Circuit, for instance, only sometimes allows\\njurisdictional defects to be cured “when the underlying facts,\\nif properly pled, would have supported jurisdiction at the time\\nthe action commenced.” Correspondent Servs. Corp. v. First\\nEquities Corp. of Fla., 338 F.3d 119, 125 (2d Cir. 2003); see\\nalso, e.g., Barton v. Ellis, No. 75-1188, 1977 WL 15469, at\\n*1 (D.S.C. Apr. 26, 1977) (denying using relation back to\\ncure the original complaint since they were defects “not [in\\nthe] allegations of existing underlying jurisdictional facts but\\nrather [in] the prerequisite jurisdictional facts themselves”).\\nWilmington argues such hesitance is appropriate here because\\nallowing relation back to cure the jurisdictional problem with\\nT Mobile’s initial complaint “would allow two wrongs under\\nSection 332 [(filing early and filing late)] to make a right.”\\n(Answering Br. at 2.)\\n\\n We again disagree with the City. It is quite true that\\nT Mobile has made procedural matters more difficult than\\nthey should be in this case. But denying relation-back to cure\\nthe defect in this instance would not comport with Rule 15’s\\naim to encourage resolution of disputes on the merits\\nwhenever possible. The ripeness requirement exists so that\\n\\n\\n\\n\\n 36\\n\\fcourts avoid issuing essentially advisory opinions. See\\nRichard H. Fallon, Jr. et al., Hart and Wechsler’s the Federal\\nCourts and the Federal System 224 (5th ed. 2003) (noting that\\nthe ripeness doctrine allows courts to avoid a “dispute … too\\n‘ill-defined’ to be appropriate for judicial resolution until\\nfurther developments … more sharply framed the issues for\\ndecision.”). That concern ceased to exist here once the\\nsupplemental pleading was in place. At that point, the dispute\\nhad matured and become capable of judicial review,\\ndemonstrating that, “actions taken after the filing of the initial\\ncomplaint can be used to establish subject matter\\njurisdiction.” Prasco, LLC v. Medicis Pharm. Corp., 537\\nF.3d 1329, 1337 (Fed. Cir. 2008).\\n\\n If a supplemental complaint cannot cure an unripe\\ncomplaint, an endless feedback loop would be created\\nwhereby the ripeness problem could never be overcome, even\\nthough, as here, the dispute later became obviously ripe. Our\\nsister circuits have recognized that problem and concluded\\nthat a supplemental complaint is the solution. 22 In Wilson v.\\nWestinghouse Electric Corp., the Eighth Circuit determined\\nthat prohibiting an amended (or supplemental) complaint\\nfrom alleging facts that occurred after the date the initial\\n\\n 22\\n In our Circuit, a thoughtful district court decision\\nhad long ago reached that conclusion. It held that an\\nuntimely supplement adding facts occurring after the initial\\nfiling that showed exhaustion of administrative remedies\\ncould relate back to the initial premature complaint and allow\\nmaintenance of the lawsuit. Bates v. W. Elec., 420 F. Supp.\\n521, 526-27 (E.D. Pa. 1976).\\n\\n\\n\\n\\n 37\\n\\fcomplaint was filed would turn a premature complaint into an\\n“irretrievable mistake that bars jurisdiction” and would be\\n“precisely the kind of procedural mousetrap that the Federal\\nRules were designed to dismantle.” 838 F.2d 286, 289 (8th\\nCir. 1988). The court held that, “[e]ven when the District\\nCourt lacks jurisdiction over a claim at the time of its original\\nfiling, a supplemental complaint may cure the defect by\\nalleging the subsequent fact which eliminates the\\njurisdictional bar.” Id. at 290 (citing Mathews, 426 U.S. at\\n75). While Wilson addressed a circumstance in which the\\nsupplemental complaint was timely filed, the proposition still\\napplies in a case like ours because, if a party was limited to\\nrefiling within an applicable time limit, there would be little\\nneed to make provision for supplementation of a complaint,\\nas a new complaint could be filed. 23\\n\\n 23\\n We note that sparing the cost of refiling and\\nproviding convenience to the Court would remain legitimate\\nreasons for allowing supplemental complaints. But the\\npurpose of Rule 15(d) is broader. See Wright et al., supra, §\\n1504 (“The purpose of subdivision (d) is to promote as\\ncomplete an adjudication of the dispute between the parties as\\nis possible. … A supplemental pleading may be employed\\nfor a variety of purposes.”). Wilmington contends that\\nWilson is inapposite since it involved a timely supplemental\\ncomplaint. Thus, concern about a perpetual loop outcome\\nwas not proper because the plaintiff could have simply refiled\\nhis complaint. But we agree that “a plaintiff need not\\ncommence a new action when after-occurring events\\ndemonstrate that it has a right to relief even if the original\\ncomplaint was insufficient. A plaintiff may also be allowed\\nto supplement the complaint even if jurisdiction … would not\\nhave been proper if the claim had been asserted in an\\n\\n\\n\\n\\n 38\\n\\f The Ninth Circuit, in Security Insurance Co. of New\\nHaven v. United States ex rel. Haydis, also relied on that logic\\nto find that relation back could cure an unripe complaint filed\\nbefore a statutory filing window opened. 338 F.2d 444, 448-\\n49 (9th Cir. 1964). In a fact scenario with striking similarities\\nto the present appeal, the plaintiff had filed its claim before a\\nstatutory waiting period was over and then did not file an\\namended complaint until after the statute of limitations period\\nhad run. Id. at 445-46. The appeals court held that the\\ndistrict court was “not required to apply the doctrine of\\nrelation back so literally as to carry it to a time [before it was\\nripe] so as to prevent the maintenance of the action in the first\\nplace.” Id. at 449.\\n\\n The Supreme Court has favorably cited Security\\nInsurance’s ruling. In Mathews, the plaintiff had not satisfied\\na precondition of filing a complaint by first filing an\\napplication with a particular agency. 426 U.S. at 72, 75. The\\nCourt noted that a supplemental complaint, alleging that the\\napplication had since been filed, would have cured the\\njurisdictional defect. Id. at 75. In saying so, the Court relied\\n\\n\\n\\nindependent action.” Moore et al., supra, ¶ 15.30 (3d ed.\\n2018) (citation omitted). If supplemental complaints could\\nnot cure ripeness, “then all supplemental pleadings of this\\nnature would be defeated for lack of jurisdiction – [the]\\n‘procedural mousetrap’ would render all supplemental\\npleadings void.” George v. IRS, No. C05-00955 MJJ, 2006\\nWL 3499230, at *3 (N.D. Cal. Dec. 4, 2006) (citation\\nomitted).\\n\\n\\n\\n\\n 39\\n\\fon Security Insurance. Id. at 75 n.8 (citing Security\\nInsurance, 338 F.2d at 447-49). 24\\n\\n Yet Wilmington asserts that ripeness can never be\\ncured by a later complaint. It advances four cases for that\\nproposition, but none are helpful. First, the City cites\\nDelaware Riverkeeper Network v. Secretary Pennsylvania\\nDepartment of Environmental Protection, (Riverkeeper I),\\n833 F.3d 360 (3d Cir. 2016), in which we concluded that,\\n“even though the underlying claim became ripe for review\\nduring the pendency of the case, the ripening of the claim did\\nnot cure deficient pleadings.” (App. at 8.) In that case,\\nhowever, no attempt to file a later complaint alleging ripeness\\nwas made. Riverkeeper I, 833 F.3d at 369-70.\\n\\n Likewise, in another two of the four cases that\\nWilmington cites, there was no effort made to amend or\\nsupplement the complaint. See TeleSTAR, Inc. v. FCC, 888\\nF.2d 132, 134 (D.C. Cir. 1989) (concluding non-final agency\\naction at the time of filing of petition may only be reviewed\\nupon the filing of another petition); W. Union Tel. Co., 773\\nF.2d at 377-78 (concluding that the court lacked jurisdiction\\nover challenges filed before the action became final).\\nTherefore, neither case determined whether relation back of a\\nlater-filed complaint could cure a ripeness problem in the\\ninitial complaint.\\n\\n 24\\n Wilmington contends that Mathews is inapposite\\nsince the statute of limitations was waived. That argument\\nhas no traction since, if it were a jurisdictional bar, it could\\nnot be waived.\\n\\n\\n\\n\\n 40\\n\\f The City fares no better relying on Council Tree\\nCommunications v. FCC, in which we stated that “[a] petition\\nto review a non-final agency order is incurably premature.”\\n503 F.3d 284, 291 (3d Cir. 2007). At no point in that case\\nwas the complaint ripe, and the petitioner still had a petition\\nfor reconsideration pending before the relevant agency on the\\ndate the case was decided. Id. at 287. Furthermore, Council\\nTree explicitly acknowledged that a supplemental complaint\\ncan cure an unripe complaint when there is jurisdiction over\\nthat supplemental pleading. See id. at 291 (“[W]e note that\\n‘nothing prevented [the petitioners] from supplementing their\\npremature petition with a later protective petition.’” (second\\nalteration in original) (quoting Horsehead Res. Dev. Co. v.\\nE.P.A., 130 F.3d 1090, 1095 (D.C. Cir. 1997))).\\n\\n Wilmington also makes three policy arguments in\\nsupport of its position that an untimely supplemental\\ncomplaint should not be able to cure an unripe complaint.\\nFirst, it contends that allowing suits to be filed before an\\naction is ripe would “extend[] federal court jurisdiction over\\nlocal government actions before those actions are final[.]”\\n(Answering Br. at 9.) Second, such filings would waste\\njudicial resources and, in this case, cost taxpayers money, by\\nforcing courts to deal with a higher volume of unripe\\ncomplaints. Third, the purpose of § 332 is to preserve local\\nzoning authority, which would be undermined by allowing\\nplaintiffs to file suit early and thereby places undue pressure\\non zoning commissions.\\n\\n Those contentions, however, are unpersuasive. First, a\\ncourt would remain without jurisdiction if the claim had not\\nripened by the time of the supplemental complaint. Second, it\\n\\n\\n\\n\\n 41\\n\\fseems that Wilmington overstates the impact that a decision\\nallowing an unripe complaint to be cured would have, since\\nour holding today makes it clear that an action is not final\\nuntil a written decision has been issued. Clarifying when a\\ndetermination is ripe for review should end any incentive for\\naggrieved parties to file early to ensure they have not filed too\\nlate.\\n\\n Perhaps more importantly, however, courts can police\\nany potential abuse on a case-by-case basis using Rule 15(d)\\nand the Rule 15(c) test for relation back. It is understood that\\n“relation back of a supplemental pleading should not result in\\nproviding unfair procedural advantages to a plaintiff[,] so …\\nrelation back may not be for all purposes.” Wright et al.,\\nsupra, § 1508. But here no unfair advantage has resulted, and\\ndefendants in general will be adequately protected by a\\ndistrict court’s Rule 15(d) analysis, which will determine if a\\nsupplemental complaint should be allowed at all. For\\ninstance, if a locality’s action is not yet a final action at the\\ntime a Rule 15(d) motion is filed, the motion can easily be\\ndenied. See Beezley v. Fremont Indem. Co., 804 F.2d 530,\\n530 (9th Cir. 1986) (supplemental pleading denied when it\\nstill failed to cure defective original pleading).\\n\\n When all is said and done here, we conclude that, to\\neffectuate the liberal purpose of Rule 15 and to avoid the\\nendless feedback loop that the City’s legal argument would\\ncreate, Rule 15 allows an untimely supplemental complaint to\\nrelate back and cure an unripe initial complaint.\\n\\n\\n\\n\\n 42\\n\\fIII. CONCLUSION\\n\\n For the foregoing reasons, we will reverse the District\\nCourt’s grant of the City’s motion for summary judgment,\\nvacate the District Court’s denial of T Mobile’s motion for\\nsummary judgment, and remand to the District Court for\\nfurther proceedings consistent with this opinion.25\\n\\n\\n\\n\\n 25\\n We will vacate the District Court’s denial of\\nT Mobile’s motion for summary judgment because it was\\nsolely based on a finding that T Mobile’s suit was not timely\\nbrought.\\n\\n\\n\\n\\n 43\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":62,"cells":{"id":{"kind":"number","value":4582001,"string":"4,582,001"},"name":{"kind":"string","value":"UNITED STATES of America, Appellant in 17-1346 v. Chaka FATTAH, Sr., Appellant in 16-4397 Karen Nicholas, Appellant in 16-4410 Robert Brand, Appellant in 16-4411 Herbert Vederman, Appellant in 16-4427"},"name_abbreviation":{"kind":"string","value":"United States v. Herbert Vederman"},"decision_date":{"kind":"string","value":"2019-01-16"},"docket_number":{"kind":"string","value":"16-4397; 16-4410; 16-4411; 16-4427; 17-1346"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Smith, Greenaway, Krause\", \"parties\": \"\", \"opinions\": [{\"author\": \"SMITH, Chief Judge\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n Nos. 16-4397, 16-4410, 16-4411,\\n 16-4427, 17-1346\\n _____________\\n\\n UNITED STATES OF AMERICA\\n Appellant in 17-1346\\n\\n v.\\n\\n CHAKA FATTAH, SR.,\\n Appellant in 16-4397\\n\\n KAREN NICHOLAS,\\n Appellant in 16-4410\\n\\n ROBERT BRAND,\\n Appellant in 16-4411\\n\\n HERBERT VEDERMAN,\\n Appellant in 16-4427\\n _____________\\n\\nOn Appeal from the United States District Court\\n for the Eastern District of Pennsylvania\\n District Court Nos. 2-15-cr-00346-001,\\n\\f 2-15-cr-00346-002, 2-15-cr-00346-003,\\n 2-15-cr-00346-004\\n District Judge: The Honorable Harvey Bartle III\\n\\n Argued January 18, 2018\\n\\nBefore: SMITH, Chief Judge, GREENAWAY, JR., and\\n KRAUSE, Circuit Judges\\n\\n (Filed: January 16, 2019)\\n\\nAndrea G. Foulkes\\nEric L. Gibson\\nPaul L. Gray\\nRobert A. Zauzmer\\nOffice of United States Attorney\\n615 Chestnut Street\\nSuite 1250\\nPhiladelphia, PA 19106\\n\\nJonathan Ian Kravis [ARGUED]\\nUnited States Department of Justice\\nCriminal Division, Public Integrity Section\\n1400 New York Avenue, N.W.\\nWashington, DC 20005\\n Counsel for the United States\\n\\nMark M. Lee\\nBruce P. Merenstein [ARGUED]\\nSamuel W. Silver\\n 2\\n\\fSchnader Harrison Segal & Lewis\\n1600 Market Street\\nSuite 3600\\nPhiladelphia, PA 19103\\n Counsel for Appellant Fattah\\n\\nAnn C. Flannery [ARGUED]\\nSuite 2700\\n1835 Market Street\\nPhiladelphia, PA 19103\\n\\nLisa A. Mathewson\\nSuite 810\\n123 South Broad Street\\nPhiladelphia, PA 19109\\n Counsel for Appellant Nicholas\\n\\nAlan Silber\\nPashman Stein Walder Hayden\\n21 Main Street\\nSuite 200\\nHackensack, NJ 07601\\n Counsel for National Association of Criminal\\n Defense Lawyers, Amicus Appellant Nicholas\\n\\nMira E. Baylson\\nBarry Gross [ARGUED]\\nMeredith C. Slawe\\nDrinker Biddle & Reath\\nOne Logan Square\\n 3\\n\\fSuite 2000\\nPhiladelphia, PA 19103\\n Counsel for Appellant Brand\\n\\nHenry W. Asbill\\nBuckley Sandler\\n1250 24th Street, N.W.\\nSuite 700\\nWashington, DC 20037\\n\\nGlen D. Nager [ARGUED]\\nJacob M. Roth\\nJulia W. M. F. Sheketoff\\nJones Day\\n51 Louisiana Avenue, N.W.\\nWashington, DC 20001\\n Counsel for Appellant Vederman\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\n\\nSMITH, Chief Judge.\\n\\n\\n\\n\\n 4\\n\\f Table of Contents\\nI. Introduction ................................................................... 8\\nII. Background .................................................................. 9\\n A. The Fattah for Mayor Scheme ................................. 9\\n 1. The Lord Loan and Its Repayment ..................... 10\\n 2. The College Tuition Component of the FFM\\n Scheme ................................................................ 27\\n 3. The NOAA Grant and the Phantom Conference 28\\n B. The Blue Guardians Scheme.................................. 31\\n C. The Fattah–Vederman Bribery Scheme................. 33\\n D. The Indictment and Trial ....................................... 39\\nIII. Juror Misconduct and Dismissal of Juror 12 ........... 58\\n A. Investigation of Alleged Juror Misconduct ........... 58\\n B. Dismissal of Juror 12 ............................................. 64\\nIV. The District Court’s Instructions Under McDonnell 70\\n A. The McDonnell Framework................................... 71\\n B. The Kirk Meeting ................................................... 76\\n C. Fattah’s Efforts to Secure Vederman an\\n Ambassadorship.......................................................... 79\\n D. The Zionts Hiring .................................................. 82\\n E. Vederman’s Sufficiency Challenge to Counts 16–18\\n and 22–23.................................................................... 89\\n F. Blue Guardians ....................................................... 91\\n\\n 5\\n\\fV. Sufficiency of the Evidence for the RICO Conspiracy\\nConviction ...................................................................... 95\\nVI. Variance from the Indictment and Sufficiency of the\\nEvidence for Count 2.................................................... 110\\nVII. The District Court’s Instruction to the Jury on the\\nMeaning of Intent ......................................................... 120\\nVIII. Sending the Indictment to the Jury ...................... 126\\nIX. The District Court’s Evidentiary Rulings .............. 129\\n A. The District Court’s Application of Rule 404(b) 129\\n B. Evidentiary Rulings Regarding Nicholas’s\\n Defense ..................................................................... 134\\n 1. The EAA Board Minutes .................................. 134\\n 2. Jones’ Memory Regarding Other Contracts ..... 136\\n 3. Exclusion of NOAA Evidence.......................... 137\\n C. The Cooperating Witness’s Mental Health\\n Records ..................................................................... 138\\n 1. The District Court’s Denial of Access to the\\n Mental Health Records ..................................... 140\\n 2. The District Court’s Grant of the Motion in\\n Limine ............................................................... 142\\nX. The Government’s Cross-Appeal ............................ 147\\n A. CUMA is a Mortgage Lending Business............. 148\\n B. Sufficiency of the Evidence ................................. 155\\nXI. Prejudicial Spillover ............................................... 158\\n A. Fattah’s Claim of Prejudicial Spillover ............... 159\\n 6\\n\\f B. Vederman’s Assertion of Prejudicial Spillover ... 160\\nXII. Conclusion ............................................................ 164\\n\\n\\n\\n\\n 7\\n\\f I. Introduction\\n Chaka Fattah, Sr., a powerful and prominent fixture\\nin Philadelphia politics, financially overextended himself\\nin both his personal life and his professional career during\\nan ultimately unsuccessful run for mayor. Fattah received\\na substantial illicit loan to his mayoral campaign and used\\nhis political influence and personal connections to engage\\nfriends, employees, and others in an elaborate series of\\nschemes aimed at preserving his political status by hiding\\nthe source of the illicit loan and its repayment. In so doing,\\nFattah and his allies engaged in shady and, at times, illegal\\nbehavior, including the misuse of federal grant money and\\nfederal appropriations, the siphoning of money from\\nnonprofit organizations to pay campaign debts, and the\\nmisappropriation of campaign funds to pay personal\\nobligations.\\n Based upon their actions, Fattah and four of his\\nassociates—Herbert Vederman, Robert Brand, Bonnie\\nBowser, and Karen Nicholas—were charged with\\nnumerous criminal acts in a twenty-nine count indictment.\\nAfter a jury trial, each was convicted on multiple counts.\\nAll but Bowser appealed. As we explain below, the\\nDistrict Court’s judgment will be affirmed in part and\\nreversed in part.\\n\\n\\n\\n\\n 8\\n\\f II. Background1\\n During the 1980s and ’90s, Fattah served in both\\nhouses of the Pennsylvania General Assembly, first as a\\nmember of the House of Representatives and later as a\\nSenator. In 1995, Fattah was elected to the United States\\nHouse of Representatives for Pennsylvania’s Second\\nCongressional District. In 2006, Fattah launched an\\nunsuccessful run for Mayor of Philadelphia, setting in\\nmotion the events that would lead to his criminal\\nconviction and resignation from Congress ten years later.\\n\\n A. The Fattah for Mayor Scheme\\n Fattah declared his candidacy for mayor in\\nNovember of 2006. Thomas Lindenfeld, a political\\nconsultant on Fattah’s exploratory committee, believed\\nthat “[a]t the beginning of the campaign, [Fattah] was a\\nconsiderable . . . candidate and somebody who had a very\\nlikely chance of success.” JA1618. But Fattah’s campaign\\nsoon began to experience difficulties, particularly with\\nfundraising. Philadelphia had adopted its first-ever\\ncampaign contribution limits, which limited contributions\\nto $2,500 from individuals and $10,000 from political\\naction committees and certain types of business\\norganizations. Fattah’s fundraising difficulties led him to\\n\\n\\n\\n1\\n The facts are drawn from the trial record unless otherwise\\nnoted.\\n 9\\n\\fseek a substantial loan, far in excess of the new\\ncontribution limits.\\n\\n 1. The Lord Loan and Its Repayment\\n While serving in Congress, Fattah became\\nacquainted with Albert Lord, II. The two first met around\\n1998, when Lord was a member of the Board of Directors\\nof Sallie Mae.\\n As the May 15, 2007 primary date for the\\nPhiladelphia mayoral race approached, Fattah met Lord to\\nask for assistance, telling Lord that the Fattah for Mayor\\n(FFM) campaign was running low on funds. Fattah asked\\nLord to meet with Thomas Lindenfeld, a political\\nconsultant in Washington, D.C., and part-owner of LSG\\nStrategies, Inc. (Strategies), a company that was working\\nwith the FFM campaign and that specialized in direct voter\\ncontact initiatives. Lindenfeld had been part of the\\nexploratory group that initially considered Fattah’s\\nviability as a candidate for mayor. Lindenfeld had known\\nFattah since 1999, when Fattah endorsed Philadelphia\\nMayor John Street. Through Fattah, Lindenfeld had also\\ngotten to know several of Fattah’s associates, including\\nHerbert Vederman, Robert Brand, and Bonnie Bowser.\\nHerbert Vederman, a businessman and former state\\nofficial, was the finance director for the FFM campaign.\\nRobert Brand owned Solutions for Progress (Solutions), a\\n“Philadelphia-based public policy technology company,\\nwhose mission [was] to deliver technology that directly\\nassists low and middle income families [in obtaining]\\n 10\\n\\fpublic benefits.” JA6551. Bowser was Fattah’s Chief of\\nStaff and campaign treasurer, and served in his district\\noffice in Philadelphia.\\n Lord’s assistant contacted Lindenfeld to arrange a\\nmeeting, and Lindenfeld informed Fattah that he would be\\nmeeting with Lord. Lindenfeld, along with his partner,\\nMichael Matthews, met with Lord and discussed Fattah’s\\nneed for funds to mount an intensive media campaign.\\nAfter that meeting, Lindenfeld reported to Fattah that Lord\\nwanted to help, but that they had not discussed a specific\\ndollar amount. Approximately a week later, Fattah\\ninstructed Lindenfeld to meet with Lord a second time.\\nLord “wanted to know if he could give a substantial\\namount of money, a million dollars” to Fattah’s campaign.\\nJA1630. That prompted Lindenfeld to reply that the\\namount “would be beyond the campaign finance limits.”\\nId.\\n\\n Lord proposed a solution: he offered to instead give\\na million dollars to Strategies in the form of a loan. To that\\nend, Lindenfeld had a promissory note drafted which\\nspecified that Lord was lending Strategies $1 million, and\\nthat Strategies promised to repay the $1 million at 9.25%\\ninterest, with repayment to commence January 31, 2008.\\nLindenfeld later acknowledged that the promissory note\\nwould make it appear as though Lord’s $1 million was not\\na contribution directly to the Congressman, although he\\nknew that it was actually a loan to the FFM campaign.\\nIndeed, Lindenfeld confirmed with Fattah that neither\\n\\n 11\\n\\fLindenfeld nor Strategies would be responsible for\\nrepayment. With that understanding, Lindenfeld executed\\nboth the note and a security agreement purporting to\\nencumber Strategies’ accounts receivable and all its assets.\\n\\n On May 1, shortly before the primary election, Lord\\nwired $1 million to Lindenfeld. Lindenfeld held the money\\nin Strategies’ operating account until Fattah told him how\\nit was to be spent. Some of the money was eventually used\\nfor print materials mailed directly to voters. And, at\\nFattah’s direction, Lindenfeld wired a substantial sum to\\nSydney Lei and Associates (SLA), a company owned by\\nGregory Naylor which specialized in “get out the vote”\\nefforts.\\n Naylor had known Fattah for more than 30 years.2\\nDuring the campaign, Naylor worked as the field director\\nand was in charge of getting out the vote on election day.\\n\\n2\\n Naylor first worked with Fattah when he was in the state\\nlegislature. When Fattah was elected to Congress, Naylor\\nworked in his Philadelphia office. Naylor met Nicholas\\nwhen she joined Fattah’s staff at some point in the 1990s.\\nAfter concluding her employment with Fattah’s office,\\nNicholas worked with the Educational Advancement\\nAlliance (EAA), an education nonprofit entity founded by\\nFattah. This entity helped to recruit underrepresented\\nstudents for scholarship and college opportunities. Around\\n2009, Naylor left Fattah’s office to work exclusively with\\nSLA. Naylor also knew Brand.\\n 12\\n\\fOn the final day of the campaign, Naylor worked with\\nVederman, who allowed Naylor to use his credit card to\\nrent vans that would transport Fattah voters to the polls.\\n As the primary date neared, Fattah and Naylor knew\\nthe campaign was running out of money. The campaign\\nwas unable to finance “media buys,” and Naylor needed\\nmoney for field operations to cover Philadelphia’s more\\nthan one thousand polling places. In early May,\\nLindenfeld called Naylor to say that Lindenfeld “would be\\nsending some money [Naylor’s] way.” JA3057. Within\\ndays, SLA received a six-figure sum for Naylor to use in\\nthe campaign and on election day. Naylor used the money\\nto pay some outstanding bills, including salaries for FFM\\nemployees, and allocated $200,000 to field operations for\\nelection day.\\n\\n Fattah lost the mayoral primary on May 15, 2007.\\nAfterward, Lindenfeld spoke with Fattah, Naylor and\\nBowser about accounting for the FFM campaign money\\nfrom Lord that had been spent. They decided that the\\namounts should not appear in the FFM campaign finance\\nreports, and Fattah instructed Naylor to have his firm,\\nSLA, create an invoice. Naylor did so, creating an invoice\\ndated June 1, 2007 from SLA to FFM, seeking payment of\\n$193,580.19. Naylor later acknowledged that the FFM\\ncampaign did not actually owe money to SLA, and that the\\nfalse invoice was created to “hide the transaction that took\\nplace earlier” and “make it look like [SLA] was owed\\nmoney.” JA3075–76. Although FFM did not owe SLA\\n\\n 13\\n\\fanything for the election day expenses, the FFM campaign\\nfinance reports from 2009 through 2013 listed a $20,000\\nin-kind contribution from SLA for each year, thereby\\nlowering FFM’s alleged outstanding debt to SLA.\\n\\n Of the total $1 million Lord loan, $400,000 had not\\nbeen spent. Lindenfeld returned that sum to Lord on June\\n3, 2007. He included a cover letter which stated: “As it\\nturns out the business opportunities we had contemplated\\ndo not seem to be as fruitful as previously expected.”\\nJA1254. Lindenfeld later admitted that there were no such\\n“business opportunities” and that the letter was simply an\\neffort to conceal the loan.\\n In late 2007, faced with financial pressures, Lord\\nasked his son, Albert Lord, III, to collect the outstanding\\n$600,000 balance on the loan to Strategies. Lord III\\ncontacted Lindenfeld about repayment and expressed a\\nwillingness to forgive the interest owed if the principal\\nwas paid. Lindenfeld immediately called Fattah and\\ninformed him that repayment could not be put off any\\nlonger. Fattah told Lindenfeld more than once that “[h]e\\nwould take care of it,” JA1652, but Fattah did not act.\\nNeeding someone who might have Fattah’s ear,\\nLindenfeld reached out to Naylor and Bowser. Naylor\\ntalked to Fattah on several occasions and told him that\\nLindenfeld was under considerable pressure to repay the\\nloan. Fattah told Naylor more than once that he was\\n“working on it.” JA3082–83.\\n\\n\\n 14\\n\\f During his political career, Fattah had focused on\\neducation, especially for the underprivileged. Indeed,\\nFattah founded two nonprofit organizations: College\\nOpportunity Resources for Education (CORE), and the\\nEducational Advancement Alliance (EAA).\\n\\n EAA held the annual Fattah Conference on Higher\\nEducation (the “annual conference”) to acquaint high\\nschool students with higher education options. JA3079.\\nSallie Mae regularly sponsored the conference. According\\nto Raymond Jones, EAA’s chairman of the board from\\n2004 through 2007, EAA offered a variety of programs to\\nprovide “marginalized students with educational\\nopportunities so they could continue and go to college.”\\nJA1360. EAA was funded with federal grant money which\\ncould only be spent for the purposes described in the\\nparticular grant. Karen Nicholas served as EAA’s\\nexecutive director, handling the organization’s day-to-day\\nadministrative responsibilities. Nicholas had previously\\nbeen a staffer for Fattah when he was a member of\\nPennsylvania’s House of Representatives.\\n CORE was an organization that awarded\\nscholarships to graduating high school students in\\nPhiladelphia who had gained admission to a state\\nuniversity or the Community College of Philadelphia.\\nCORE received funding from a variety of sources,\\nincluding Sallie Mae. Because CORE also received\\nfederal funds, and because EAA had experience working\\nwith federal grants, EAA received and handled the federal\\n\\n 15\\n\\ffunds awarded to CORE. In short, EAA functioned as a\\nfiduciary for CORE. When money became a problem for\\nthe FFM campaign, Fattah’s involvement with EAA and\\nCORE soon became less about helping underprivileged\\nstudents, and more about providing an avenue for\\ndisguising efforts to repay the illicit campaign funds from\\nLord.\\n\\n On January 7, 2008, Robert Brand contacted Fattah\\nby telephone. Shortly thereafter, Lindenfeld received an\\nunexpected call from Brand proposing an arrangement for\\nBrand’s company, Solutions, to work with Strategies.\\nSolutions had developed a software tool called “The\\nBenefit Bank,” which was designed to “assist low and\\nmoderate income families to have enhanced access to\\nbenefits and taxes.” JA1993. During the telephone call,\\nBrand referred to The Benefit Bank and suggested a\\ncontract under which Strategies would be paid $600,000\\nupfront. JA1666. Shortly thereafter, on January 9, 2008,\\nBrand followed up on his call to Lindenfeld with an email\\nabout “develop[ing] a working relationship where you\\ncould help us to grow The Benefit Bank and our process\\nof civic engagement. While I know this is not your core\\nbusiness I would like to try to convince you to take us on\\nas a client.” JA6427. Lindenfeld responded that he was\\ninterested. To Lindenfeld, “this was the way that\\nCongressman Fattah was going to repay the debt to Al\\nLord.” JA1654. When Lindenfeld called Fattah and told\\nhim of the contact from Brand, Fattah simply replied that\\nLindenfeld “should just proceed.” JA1666–67.\\n 16\\n\\f A few days later, Brand emailed Nicholas at EAA a\\nproposal from Solutions concerning The Benefit Bank,\\nwhich sought EAA’s support in developing an education\\nedition of The Benefit Bank and a $900,000 upfront\\npayment.\\n\\n As the January 31 date for repayment of the balance\\nof the $1 million Lord loan approached, a flurry of activity\\ntook place. On January 24, both Raymond Jones, chair of\\nthe EAA Board, and Nicholas signed a check from EAA\\nmade out to Solutions in the amount of $500,000.\\nAlthough no contract existed between EAA and Solutions,\\nthe memo line of the check indicated that it was for a\\ncontract, and Nicholas entered it into EAA’s ledger.3\\n\\n That same day, Ivy Butts, an employee of\\nStrategies, emailed Lindenfeld the instructions Brand\\nwould need to wire the $600,000 balance on the Lord loan.\\n\\n3\\n Raymond Jones, who was EAA’s Chairman of the Board\\nfrom 2004 through 2007, recalled at trial that the Board\\nhad a limit on the amount that Nicholas could spend\\nwithout board approval. JA1358, 1369. Nicholas was\\nauthorized to sign contracts on behalf of EAA for no more\\nthan $100,000. JA1369–71. Jones did not recall the\\ncontract between EAA and Solutions, nor did the EAA\\nboard minutes for December 2007, February 2008, or May\\n2008 refer to the EAA–Solutions contract or to the\\nsubstantial upfront payment of half a million dollars upon\\nexecution of the agreement. JA6358–63; 6567.\\n 17\\n\\fWithin minutes, Lindenfeld forwarded that email to Brand\\nat Solutions. Brand then made two telephone calls to\\nFattah. By late afternoon, Brand emailed Nicholas,\\ninforming her that he had “met with all the people I need\\nto meet with and have a pretty clear schedule of what\\nworks best for us. I am also seeing what line of credit we\\nhave to stretch out the payments until you get your line of\\ncredit in place.” JA6558. Brand asked if they could talk\\nand “finalize this effort.” JA6558. On January 25 and 26,\\nthere were a number of calls between Fattah, Brand, and\\nNicholas.\\n\\n On Sunday January 27, at 5:46 pm, Brand\\ntelephoned Fattah. At 10:59 pm, Brand emailed Nicholas\\na revised contract between EAA and Solutions for the\\nengagement of services. Brand indicated he would send\\nsomeone to pick up the check at about 1:00 pm the\\nfollowing day. The revised contract called for the same\\n$900,000 payment from EAA to Solutions, yet specified\\nthat $500,000 was to be paid on signing, with $100,000\\ndue three weeks later, and another $100,000 to be paid six\\nweeks out. No due date for the $200,000 balance was\\nspecified. The terms of the contract called for EAA to\\nassist Solutions with further developing The Benefit Bank.\\nIn addition, under the contract, EAA would receive certain\\n\\n\\n\\n\\n 18\\n\\ffunds from the Commonwealth of Pennsylvania for a\\nprogram relating to FAFSA applications. 4\\n\\n The same evening, Brand sent Lindenfeld a contract\\nentitled “Cooperative Development Agreement to Provide\\nServices to Solutions for Progress, Inc. for Growth of The\\nBenefit Bank.” JA6569. The agreement proposed a\\nworking partnership in which Strategies would work with\\nSolutions to identify and secure a Benefit Bank affiliate in\\nthe District of Columbia and two other states, and to\\nfacilitate introductions to key officials in other states\\nwhere The Benefit Bank might expand. The terms of the\\nagreement provided that Solutions would pay $600,000 to\\nStrategies by January 31, 2008, which would “enable\\n[Strategies’] team to assess opportunities and develop\\ndetailed work plans for each area.” JA6572. Brand copied\\nSolutions’ Chief Financial Officer, Michael Golden.\\nLindenfeld responded to Brand’s email within a minute,\\nasking if Brand had received the wiring instructions.\\nBrand immediately confirmed that he had.\\n\\n Concerned that Solutions did not have $600,000 to\\npay Strategies, Golden talked to Brand, who informed him\\nthat Solutions would be receiving a check for $500,000\\nfrom EAA. Early the next morning, Nicholas responded to\\nBrand’s email from the night before. She advised Brand\\nthat he could pick up the check, “but as I stated I am not\\n\\n4\\n FAFSA is an acronym for Free Application for Federal\\nStudent Aid.\\n 19\\n\\fin a position to sign a contract committing funds that I am\\nnot sure that I will have.” Gov’t Supp. App. (GSA) 1. That\\nsame day, a $540,000 transfer was made from the\\nconference account, which EAA handled, into EAA’s\\nchecking account. The conference account was maintained\\nto handle expenses for Fattah’s annual higher education\\nconference. Prior to this transfer, EAA had only\\n$23,170.95 in its account. EAA then tendered a $500,000\\ncheck to Solutions, which promptly deposited the check\\nbefore the close of that day’s business. EAA never\\nreplenished the $540,000 withdrawal from the conference\\naccount.\\n Brand received the executed contract between\\nSolutions and Strategies on January 28. Even though the\\ncontract called for Strategies to perform services in\\nexchange for the $600,000 payment, Lindenfeld neither\\nexpected to do any work for the $600,000, nor did he in\\nfact do any work.\\n\\n In sum, by January 28, Solutions had received\\n$500,000 from EAA, but it still had to come up with\\n$100,000 to provide Strategies with the entire amount\\nneeded to repay the Lord loan. Golden obtained the needed\\nfunds the following day by drawing $150,000 on a line of\\ncredit held by Brand’s wife. Brand and Fattah spoke four\\nmore times on the telephone on January 29. Trial evidence\\nlater showed that, during the month of January 2008,\\nneither the FFM campaign bank account nor Fattah’s\\n\\n\\n 20\\n\\fpersonal account had a sufficient balance to fund a\\n$600,000 payment.\\n On the morning of January 30, frustrated by the\\ndelay, Lindenfeld sent Brand an email with a subject line\\n“You are killing me.” JA6430. Lindenfeld stated that he\\nhad “made a commitment based on yours to me. Please\\ndon’t drag this out. I have a lot on the line.” Id. Brand\\nresponded late in the afternoon, stating: “just met with\\nMichael. He does the transfer at 8 AM tomorrow. It should\\nbe in your account ($600K) early tomorrow morning.” Id.\\nLindenfeld replied: “The earlier the better.” Id. The\\nfollowing morning, Golden wired $600,000 from\\nSolutions’ Pennsylvania bank account into Strategies’\\nWashington D.C. bank account. JA2745, 2874. Strategies\\nin turn, wired the same amount from its Washington D.C.\\nbank account to Lord’s bank account in Virginia. JA2874,\\n6549. Around noon, Brand telephoned Lindenfeld.\\n\\n In the days following the exhaustive efforts to meet\\nthe January 31 loan repayment deadline, four more\\ntelephone calls took place between Brand and Fattah.5\\nNaylor learned at some point that the loan had been paid\\noff. When Naylor asked Fattah about details of the\\nrepayment, Fattah simply replied “[t]hat it went through\\nEAA to Solutions and it was done.” JA3088.\\n\\n5\\n By contrast, between October to December 2007, Brand\\nand Fattah spoke by telephone only “once or twice [a]\\nmonth.” JA2734.\\n 21\\n\\f Meanwhile, at some point in January, EAA received\\nnotice that the Department of Justice Office of the\\nInspector General (DOJ) intended to audit its books.6 DOJ\\nauditors told EAA to provide, at the “entrance\\nconference,” documentation containing budgetary and\\naccounting information. EAA failed to produce any\\naccounting information.\\n Although Lindenfeld was no longer making\\ndemands of Brand, Brand was still owed the remaining\\n$100,000 that Solutions had paid to satisfy the Lord loan.\\nOn March 23, 2008, Brand sent Nicholas an email\\noutlining his efforts to contact her over the previous two\\nweeks about documentation on the CORE work, how to\\nproceed with the paperwork for the Commonwealth of\\nPennsylvania, and “how we can get our proposed contract\\nsigned and the outstanding payments made.” JA2749.\\nNicholas responded that evening, writing:\\n\\n I can appreciate your urgency however I do\\n have EAA work that I continue to do,\\n including the [usual] facilitation of programs,\\n our financial audit, the start-up of two new\\n programs[,] and of course the DOJ audit. I am\\n still trying to obtain a line of credit without a\\n completed 2007 audit and things are getting a\\n\\n\\n\\n6\\n One of the terms and conditions of a federal grant is that\\nthe recipient “be readily prepared for an audit.” JA2314.\\n 22\\n\\f little uncomfortable now as I try to keep us\\n afloat.\\nJA6576. Nicholas told Brand that the DOJ auditors were\\nmaking demands and would soon be on site. She noted that\\n“[t]hey are still very uncomfortable with your contract\\namongst other things and depending on their findings\\nsome of the funding received may have to be returned.” Id.\\nNicholas said that she had submitted the paperwork to the\\nstate, and she told Brand that “in the future . . . as a result\\nof the DOJ audit I will not be in a position to do another\\ncontract such as this.” Id.\\n Shortly after Nicholas’s reply to Brand, Nicholas\\nforwarded the Brand–Nicholas email chain to Fattah. The\\nbody of the email stated, in its entirety: “I really don’t\\nappreciate the tone of Bob’s email. I can appreciate that he\\nhas some things going on however I am doing my best to\\nassist him. Some other things are a priority. He needs to\\nback off.” GSA2. Later that night, Bowser sent Fattah an\\nemail with a subject line that read “Karen N” and a\\ntelephone number. JA2752.\\n\\n As the audit continued, the auditors found other\\ndeficiencies. During April of 2008, DOJ issued a notice of\\nirregularity to EAA, which resulted in the audit being\\nreferred to DOJ’s Investigations Division for a more\\ncomprehensive review.\\n\\n On April 24, 2008, Brand emailed Nicholas asking\\nfor a time to update her on The Benefit Bank. In early May,\\n 23\\n\\fBrand sent another email to Nicholas attaching a revised\\nEAA–Solutions contract proposal, which decreased the\\ninitial upfront cost from $900,000 to $700,000.\\n Although Solutions and EAA had still not signed a\\ncontract, EAA paid Solutions another $100,000 in May.\\nThat money was obtained via a loan to EAA from CORE.\\nThomas Butler, who had worked for Fattah both when\\nFattah was in Congress and when he was in the General\\nAssembly, was CORE’s executive director. Butler had\\nbeen contacted in mid-May by Jackie Barnett, a member\\nof CORE’s Board who had also worked with\\nCongressman Fattah. Barnett informed Butler that\\nNicholas had requested a loan from CORE to EAA, and\\nthat Fattah, as Chairman of CORE’s Board, had approved\\nit. Butler and Barnett withdrew funds from two CORE\\nbank accounts and obtained a cashier’s check, dated May\\n19, in the amount of $225,000 and made payable to EAA.\\nThe withdrawals were from accounts used for Sallie Mae\\nfunds and other scholarship money.\\n After EAA received the $225,000 check, EAA\\ntendered a $100,000 check to Solutions. The check bore\\nthe notation “Commonwealth of Pennsylvania.” EAA\\nrepaid CORE the following month. Because EAA lacked\\nsufficient funds of its own to cover this payment, EAA\\ndrew on grant money that it had received from NASA.\\n\\n Brand and Lindenfeld continued to communicate\\nconcerning The Benefit Bank. In July of 2008, a meeting\\nwas held at Solutions with Brand, Lindenfeld, Golden, and\\n 24\\n\\fother Solutions employees to discuss “an enormous\\namount of work” that Brand wanted Strategies to do.\\nJA1670. Lindenfeld said in response “we’d be glad to do\\nthat, but . . . we would have to be paid.” Id. At that point,\\nsomeone in the meeting stated that Strategies “had already\\nbeen paid” $600,000. Id. Lindenfeld replied: “well, that\\nwas for Congressman Fattah, . . . that’s not for us. So if\\nyou want us to do work, we have to get paid for it\\nseparately.” Id. Brand became upset with Lindenfeld over\\nhis comment about being paid because his colleagues at\\nSolutions were not aware of the reason for the $600,000\\npayment.\\n Meanwhile, EAA was attempting to meet the\\ndemands of the DOJ auditors, who were focused on the\\nrelationship between EAA and CORE. DOJ served a\\nsubpoena upon Solutions to produce “[a]ny and all\\ndocuments including, but not limited to, contract\\ndocuments, invoices, correspondence, timesheets,\\ndeliverables and proof of payment related to any services\\nprovided to or payments received” from CORE or EAA.\\nJA2350.\\n\\n Special Agent Dieffenbach, from the DOJ,\\ninterviewed Nicholas on July 14, 2008. During that\\ninterview, Nicholas discussed the relationship between\\nEAA and CORE, how invoices were paid, and how\\nconsultants were handled. Nicholas also answered\\nquestions about EAA’s relationship with Solutions,\\nincluding the payment of invoices. She did not inform\\n\\n 25\\n\\fAgent Dieffenbach of the $500,000 payment in January or\\nthe subsequent $100,000 payment in May. Nor did the\\ninterview address the EAA–Solutions contract that\\npurportedly required those payments, because the contract\\nhad yet to be produced.\\n\\n Solutions failed to comply with the subpoena,\\nprompting an email from Agent Dieffenbach on August 26\\nasking for an update concerning Solutions’ reply to the\\nDOJ subpoena. Solutions then produced an undated\\nversion of the EAA–Solutions contract that required the\\n$600,000 upfront payment. Neither Brand nor Nicholas\\nprovided the auditors with the January and May checks\\nfrom EAA to Solutions.\\n Efforts to conceal the repayment of the Lord loan\\nand to promote the political and financial interests of\\nFattah continued. The FFM campaign reports indicated in-\\nkind contributions of debt forgiveness by SLA even\\nthough there had been no actual debt. In September of\\n2009, with EAA’s ledgers still under scrutiny, Nicholas\\naltered the description of the entry for the $100,000 check\\nto Solutions from “professional fees consulting” to\\n“CORE Philly.” JA2546. Other FFM campaign debt was\\nreduced further after Vederman negotiated with creditors.\\n\\n EAA never fully recovered from its payment of the\\n$600,000 balance on the Lord loan and the audits that took\\nplace in 2008. It began laying off employees in 2011, and\\nby June of 2012, only four employees remained. JA3659.\\nEAA ceased operations at some point in 2012. JA1530.\\n 26\\n\\f 2. The College Tuition Component of the FFM\\n Scheme\\n Although the FFM campaign was close to insolvent,\\nit nevertheless made tuition payments for Fattah’s son,\\nChaka Fattah Jr., also known as Chip. Chip attended\\nDrexel University, but had yet to complete his coursework\\nbecause he had failed to pay an outstanding tuition\\nbalance. As the FFM campaign got underway in 2007,\\nFattah wanted Chip to re-enroll in classes at Drexel and\\nget a degree. Fattah asked Naylor to help financially, and\\nhe did so by writing checks from SLA to Drexel toward\\nChip’s outstanding tuition. By October of 2007, Chip was\\npermitted to re-enroll in classes.\\n Although Naylor never directly addressed the issue\\nwith Fattah, he agreed to assist with Chip’s outstanding\\ntuition with the expectation that SLA would be repaid. The\\nfirst check to Drexel in the amount of $5,000 was sent in\\nAugust of 2007, with $400 payments in the months that\\nfollowed until August of 2008. At some point, Chip\\ninformed Naylor that the payee was no longer Drexel, but\\nSallie Mae. Naylor then began sending monthly checks\\nfrom SLA to Sallie Mae. Those payments, in the amount\\nof $525.52, began in March of 2009 and continued until\\nApril of 2011, after which Fattah told Naylor he no longer\\nneeded to make them. SLA’s payments to Drexel and\\nSallie Mae totaled $23,063.52.\\n\\n Naylor’s expectation of repayment was eventually\\nrealized. Beginning in January of 2008 and continuing\\n 27\\n\\funtil November 2010, Bowser sporadically sent SLA\\nreimbursement checks from the FFM campaign with a\\nnotation that payment was for “election day operation\\nexpenses.” JA3136. The FFM funds had been transferred\\nfrom the Fattah for Congress campaign. These\\nreimbursement checks totaled $25,400. In an effort to\\nconceal the source of the payments to Drexel and Sallie\\nMae, and to make it appear that the younger Fattah had\\nperformed services for SLA, Naylor created false tax\\nforms for Chip. Chip, however, had never performed\\nservices for SLA.\\n\\n 3. The NOAA Grant and the Phantom Conference\\n In mid-December 2011, when EAA was\\nexperiencing serious financial difficulties, Nicholas\\nsubmitted an email request to the educational partnership\\nprogram of the National Oceanic & Atmospheric\\nAdministration (NOAA) for a grant “designed to provide\\ntraining opportunities and funding to students at minority\\nserving institutions” interested in science, technology,\\nengineering, and math fields related to NOAA’s mission.\\nJA3354–55. The request sought $409,000 to fund EAA’s\\nannual conference scheduled for February 17–19, 2012.\\nJacqueline Rousseau, a supervisory program manager at\\nNOAA, participated in a conference call with Nicholas\\nshortly thereafter and advised Nicholas that the agency\\ncould not afford the $409,000 request but would consider\\na smaller grant. Rousseau advised Nicholas that EAA\\n\\n\\n 28\\n\\fwould need to submit an application if it wished to be\\nconsidered for a grant.\\n Before submitting a grant application, Nicholas\\nemailed Rousseau about sponsoring the conference. On\\nJanuary 11, 2012, Rousseau informed Nicholas that the\\n“NOAA Office of Education, Scholarship Programs has\\nagreed to participate and provide sponsorship funds of\\n$50K to support the referenced conference.” JA6453.\\nRousseau also informed Nicholas that Chantell Haskins,\\nwho also worked with the student scholarship program,\\nwould be the point of contact for NOAA.\\n In February 2012, EAA held its annual conference\\nat the Sheraton Hotel in downtown Philadelphia. The\\nconference had been held at the same location each year\\nsince 2008.\\n\\n Nicholas contacted Haskins at some point in early\\n2012, inquiring about the $50,000 grant. On May 8, 2012,\\nHaskins sent Nicholas an e-mail which included\\ninformation about submitting proposals to fund a\\nconference for students. EAA then submitted a grant\\napplication, which Haskins reviewed. She advised\\nNicholas on June 28, 2012 that the grant could not be used\\nto provide meals, and that the date of the conference would\\nhave to be pushed back, with the new date included in a\\nmodified application. When Nicholas asked if expenses\\nfrom a previous conference could be paid from the new\\ngrant, Haskins informed her that this was not allowed.\\n\\n 29\\n\\f In early July 2012, Nicholas sent a modified grant\\nproposal to Haskins. It eliminated the budget item for food\\nand changed the date of the 2012 conference to October\\n19–21, 2012 at the same Sheraton Hotel in Philadelphia\\nwhere EAA’s annual conference had taken place earlier in\\nthe year. NOAA approved a $50,000 grant for the October\\n2012 conference—a conference that would never be held.\\n\\n Unaware that no October 2012 conference had\\ntaken place, NOAA allowed Nicholas access to the\\n$50,000 grant in March of 2013. She then transferred the\\nentire amount from NOAA to EAA’s bank account a few\\ndays later. Naylor had performed services for EAA for\\nwhich he was still owed $116,590. JA3119. In discussions\\nwith Naylor, Nicholas had informed him that the\\nlikelihood of EAA’s being able to pay him was “[n]ot very\\ngood.” JA3120. Yet several days after EAA had received\\nthe $50,000 from NOAA, Nicholas sent Naylor a check\\nfor $20,000. JA3120, 4283.\\n\\n On April 3, 2013, Nicholas submitted a final report\\nto NOAA concerning EAA’s use of the grant. Notably,\\npage 4 of the report stated the conference had been held in\\nFebruary 2012, while page 17 stated that the conference\\nhad been held from October 19 to 21, 2012. NOAA issued\\na notice asking for clarification and for a list of students\\nwho had been supported at the conference. Nicholas failed\\nto file either a clarifying report regarding the date of the\\nconference or a timely report regarding the disbursement\\nof the grant. Finally, in November of 2013, Nicholas\\n\\n 30\\n\\fsubmitted the final Federal Financial Report in which she\\ncertified, falsely, that the $50,000 had been used for a\\nproject during the period from August 1, 2012 to\\nDecember 30, 2012.\\n\\n B. The Blue Guardians Scheme\\n In addition to functioning as the conduit for Lord’s\\n$1 million loan to Fattah’s campaign, Lindenfeld’s\\ncompany, Strategies, also performed services for the\\ncampaign. The work resulted in indebtedness from FFM\\nto Strategies of approximately $95,000. Fattah made\\nseveral small payments, but failed to pay the full amount\\ndue. Although Lindenfeld spoke to Fattah, Naylor and\\nBowser about the debt, no payments were forthcoming.\\nDuring a meeting in Fattah’s D.C. office, Fattah told\\nLindenfeld “that [repayment] really wasn’t going to be\\npossible because the campaign had been over for a long\\ntime” and the funds were not available. JA1693. Fattah\\nthen asked Lindenfeld if he could write off the debt on his\\nFFM campaign finance reports. Id. Lindenfeld told Fattah\\nthat as long as he was paid, it was not his business how\\nFattah disclosed it on the campaign finance reports.\\nJA1694.\\n In lieu of repayment, Fattah suggested that\\nStrategies could claim to be interested in setting up an\\nentity to address environmental issues and ocean pollution\\nalong the coastline and in the Caribbean. Fattah explained\\nthat creating such an entity would make it possible to\\nobtain an appropriation from the government. Hearing\\n 31\\n\\fthis, Lindenfeld knew he was not going to be paid by the\\nFFM campaign, and was amenable to receiving money\\nfrom an appropriation instead. At a later meeting,\\nLindenfeld told Fattah that the name of the entity would\\nbe “Blue Guardians.” Lindenfeld consulted with an\\nattorney about creating Blue Guardians as an entity to\\nreceive the federal grant. He emailed Fattah, asking\\nquestions about how to complete an application to the\\nHouse Appropriations Committee. Fattah provided\\nsuggestions, and an application was eventually completed.\\nIt indicated that Blue Guardians would be “in operation for\\na minimum of ten years,” and, in accordance with Fattah’s\\nguidance, requested $15 million in federal funds. JA1711–\\n13.\\n Lindenfeld submitted the application to Fattah’s\\noffice in April of 2009. Afterward, a Fattah staffer\\ncontacted Lindenfeld to suggest that he change his\\nWashington, D.C., address to Philadelphia because that\\nwas the location of Fattah’s district. Fattah later suggested\\nto Lindenfeld that Brand might allow the use of his\\nPhiladelphia office address, a plan to which Brand agreed.\\n\\n In February 2010, Lindenfeld submitted a second\\napplication to the Appropriations Committee. In March,\\nFattah submitted a project request using his congressional\\nletterhead and seeking $3,000,000 for the “Blue\\nGuardians, Coastal Environmental Education Outreach\\nProgram.” JA6432. Within a month, Blue Guardians had\\nboth articles of incorporation and a bank account. Around\\n\\n 32\\n\\fthat time, a news reporter contacted Lindenfeld to discuss\\nthe new Blue Guardians entity. The inquiry made\\nLindenfeld uncomfortable, and he ultimately decided to\\nabandon the Blue Guardians project. He continued to seek\\npayment from Fattah, to no avail.\\n\\n Nonetheless, having obtained Lindenfeld’s\\nacquiescence to writing off the campaign’s debt to\\nStrategies, Fattah started falsifying FFM’s campaign\\nreports. Beginning in 2009 and extending through 2013,\\nthe FFM campaign reports executed by Fattah and Bowser\\nstated that Strategies made in-kind contributions of\\n$20,000, until the debt appeared to have been paid in full.\\n\\n C. The Fattah–Vederman Bribery Scheme\\n Vederman and Fattah were personal friends.\\nVederman was a successful businessman who had also\\nserved in prominent roles in the administrations of Ed\\nRendell when he was Mayor of Philadelphia and Governor\\nof Pennsylvania. In November of 2008, Vederman was a\\nsenior consultant in the government and public affairs\\npractice group of a Philadelphia law firm. His assistance\\nto the FFM campaign included paying for rented vans used\\nin the get-out-the-vote effort.\\n\\n After Fattah’s electoral defeat, the campaign still\\nowed more than $84,000 to a different law firm for\\nservices performed for the campaign. Vederman\\napproached that firm in the summer of 2008 asking if it\\nwould forgive FFM’s debt. Negotiations resulted in a\\n 33\\n\\fcommitment from FFM to pay the firm $30,000 by the end\\nof 2008 in exchange for forgiveness of $20,000, all of\\nwhich would appear on the FFM campaign finance report.\\nVederman’s efforts also led to payment by Fattah of an\\nadditional $10,000 in 2009 to the law firm, in exchange\\nfor additional forgiveness of $20,000 of debt. It was not\\nlong after Vederman’s successful efforts to lower Fattah’s\\ncampaign debt, that Fattah wrote a letter to U.S. Senator\\nRobert P. Casey recommending Vederman for an\\nambassadorship.\\n\\n At some point in 2010, Vederman again intervened\\non behalf of the FFM campaign. FFM remained in debt to\\nan advertising and public relations firm owned by Robert\\nDilella. By late 2011, Vederman and Dilella had worked\\nout a settlement to resolve the outstanding debt. Pursuant\\nto that settlement, Dilella received partial payment from\\nthe FFM campaign: $25,000 in satisfaction of a $55,000\\ndebt. Dilella testified at trial that he would not have agreed\\nto retire a portion of the debt had he known the FFM\\ncampaign was paying college tuition for Fattah’s son.\\n Vederman helped Fattah financially in other ways.\\nBefore the 2006 FFM campaign, Fattah and his wife,\\nRenee Chenault-Fattah, sponsored a young woman named\\nSimone Muller to live with them as an au pair exchange\\nvisitor. Muller was from South Africa, and her J-1 visa\\nallowed her to serve as a nanny and to study in the United\\nStates. Muller later applied for and received a second visa,\\nan F-1 student visa that indicated she had been accepted as\\n\\n 34\\n\\fan international student at the Community College of\\nPhiladelphia. The application indicated that Muller would\\nagain be residing with the Fattahs. Notwithstanding this\\nliving arrangement, Fattah identified Vederman as the\\nperson who would be paying for Muller’s trip to the\\nUnited States.\\n By the beginning of 2010, Muller wished to transfer\\nto Philadelphia University. This required her to submit\\nverification that funds were available to pay for her study.\\nAlthough the Fattahs were Muller’s sponsors, Fattah\\nexplained to the University’s Dean of Enrollment Services\\nthat he was submitting a letter of secondary support from\\nVederman. JA3754, 3763–65, 6504. Without Vederman’s\\nJanuary 2010 letter of support, the University would not\\nhave admitted Muller. In addition to this pledge of support,\\nVederman paid $3,000 of Muller’s tuition. Shortly\\nthereafter, Fattah resumed his efforts to secure an\\nambassadorship for Vederman.\\n\\n In February of 2010, Fattah staffer Maisha Leek\\ncontacted Katherine Kochman, a scheduler for White\\nHouse Chief of Staff Rahm Emanuel. Leek requested a\\ntelephone conference with Emanuel, Rendell, and Fattah\\nto discuss Vederman’s “serving his country in an\\ninternational capacity.” JA2893. In a follow-up email on\\nMarch 26, Leek sent documents to Kristin Sheehy, a\\nsecretary to White House Deputy Chief of Staff James\\nMessina. The documents included Fattah’s 2008 letter to\\nSenator Casey and Vederman’s biography. After\\n\\n 35\\n\\fparticipating in a telephone conference about Vederman\\nwith Fattah and Rendell, Messina sent Vederman’s\\nbiography to the White House personnel office for\\nconsideration.\\n\\n As the April 2010 tax deadline approached, Fattah\\nstill owed the City of Philadelphia earned income tax in\\nthe amount of $2,381. Just days before the filing deadline,\\nVederman gave a check to Chip Fattah for $3,500. The\\nyounger Fattah quickly deposited $2,310 into his father’s\\nbank account. Fattah paid his tax bill on April 15. Without\\nChip’s deposit into his father’s bank account, the older\\nFattah would not have had sufficient funds to pay his tax\\nbill.\\n On October 30, 2010, Vederman gave Chip another\\ncheck, this one for $2,800. That same day, Fattah hand-\\ndelivered a letter to President Obama recommending\\nVederman for an ambassadorship. A few weeks later,\\nFattah’s staffer, Leek, sent the letter that Fattah had given\\nto President Obama to Messina’s office. That letter\\npointed out that both Rendell and Fattah had sent letters\\non behalf of Vederman, and that he was an\\n“unquestionably exceptional candidate for an\\nambassadorship.” JA6291–92.\\n\\n Fattah’s efforts to secure Vederman an\\nambassadorship were unsuccessful. Fattah then shifted\\ngears and sought to secure Vederman a position on a\\nfederal trade committee. Fattah approached Ron Kirk, who\\nserved as U.S. Trade Representative, and asked him to\\n 36\\n\\fspeak with a constituent. In May of 2011, Leek followed\\nup on that discussion by emailing Kirk and asking him to\\nmeet with Vederman. Kirk met with Vederman on June 5,\\n2011 and explained to him the role of the trade advisory\\ncommittees. Although the two men “had a very nice\\nconversation,” JA 3566, it soon became “pretty apparent\\nto [Kirk and his staff] that [serving on a trade advisory\\ncommittee was] not what Mr. Vederman was interested\\nin.” JA3567. As Kirk put it, “it was obvious that\\n[Vederman] was looking for something perhaps more\\nrobust in his mind or . . . higher profile than one of our\\nadvisory committees.” Id. Given Vederman’s lukewarm\\ninterest, no appointment to an advisory committee was\\nforthcoming.\\n In late December 2011, the Fattahs applied for a\\nmortgage so they could purchase a second home in the\\nPoconos. Shortly after applying for the mortgage, Fattah\\nemailed Vederman, offering to sell him his wife’s 1989\\nPorsche for $18,000. Vederman accepted the offer. The\\nnext day, Vederman wired $18,000 to Fattah’s Wright\\nPatman Federal Credit Union account.\\n\\n The Credit Union Mortgage Association (CUMA)\\nacted as the loan processing organization for the home\\nmortgage. Because CUMA is required to verify the source\\nof any large deposits, CUMA’s mortgage loan processor,\\nVictoria Souza, contacted Fattah on January 17, 2012, to\\nconfirm the source of the $18,000. Fattah informed Souza\\nthat the $18,000 represented the proceeds of the Porsche\\n\\n 37\\n\\fsale. Souza requested documentation, including a signed\\nbill of sale and title.\\n That same day, Bowser emailed Vederman a blank\\nbill of sale for the Porsche. After Vederman signed the bill\\nof sale, Fattah forwarded it to Souza. The bill of sale was\\ndated January 16, 2012, which was the day before Souza\\nhad requested the documentation. It bore the signatures of\\nRenee Chenault-Fattah and Herbert Vederman, with\\nBonnie Bowser as a witness.\\n\\n Fattah also provided Souza with a copy of the\\nPorsche’s title. It was dated the same day it was sent to\\nSouza, and bore signatures of Chenault-Fattah as the seller\\nand Vederman as buyer, along with a notary’s stamp.\\nNeither Vederman nor Chenault-Fattah actually appeared\\nbefore the notary.\\n\\n Vederman never took possession of the Porsche.\\nRenee Chenault-Fattah continued to have the Porsche\\nserviced and insured long after the purported sale had\\ntaken place. Moreover, the Porsche remained registered in\\nChenault-Fattah’s name, and was never registered to\\nHerbert Vederman. When FBI agents searched the\\nFattahs’ home in 2014, the Porsche was discovered in the\\nFattahs’ garage.\\n\\n On January 24, 2012, the Fattahs wired $25,000 to\\nthe attorney handling the escrow account for the purchase\\nof the vacation home. Without the $18,000 transfer from\\n\\n 38\\n\\fVederman, the Fattahs would not have had sufficient funds\\nin their bank accounts to close on the home.\\n Around the same time that the Fattahs were\\npurchasing the house in the Poconos, Fattah’s Philadelphia\\noffice hired Vederman’s longtime girlfriend, Alexandra\\nZionts. Zionts had long worked for a federal magistrate\\njudge in Florida. Near the end of 2011, the magistrate\\njudge retired, leaving Zionts ten months shy of obtaining\\nthe necessary service required to receive retirement\\nbenefits. If Zionts could find another job in the federal\\ngovernment, her benefits and pension would not be\\nadversely affected. Vederman assisted Zionts in her job\\nsearch, which included calling Fattah. Fattah hired her, a\\nmove that put his congressional office overbudget. Zionts\\nworked in Fattah’s office for only about two months,\\nleaving to work for a congressman from Florida.\\n\\n Tia Watson, who performed constituent services for\\nFattah and worked on the same floor as Zionts in Fattah’s\\ndistrict office, testified she had no idea what work Zionts\\nperformed. Although Zionts contacted Temple University\\nabout archiving Fattah’s papers from his career in both the\\nstate and federal government, an employee from Temple\\nUniversity observed that Zionts’ work contributed nothing\\nof value to the papers project.\\n\\n D. The Indictment and Trial\\n Fattah’s schemes eventually unraveled. On July 29,\\n2015, a federal grand jury in the Eastern District of\\n 39\\n\\fPennsylvania returned a twenty-nine count indictment\\nalleging that Fattah and his associates had engaged in a\\nvariety of criminal acts. Fattah, Vederman, Nicholas,\\nBrand, and Bowser were charged with unlawfully\\nconspiring to violate the Racketeer Influenced and Corrupt\\nOrganizations Act (RICO), 18 U.S.C. § 1962(d). In\\naddition to the RICO charge, the indictment alleged that\\nFattah and certain co-defendants had unlawfully conspired\\nto commit wire fraud, 18 U.S.C. §§ 1343, 1349; honest\\nservices fraud, 18 U.S.C. §§ 1343, 1346, 1349; mail fraud,\\n18 U.S.C. §§ 1341, 1349; money laundering, 18 U.S.C.\\n§ 1956; and to defraud the United States, 18 U.S.C. § 371.\\nSeveral defendants were also charged with making false\\nstatements to banks, 18 U.S.C. § 1014; falsifying records,\\n18 U.S.C. § 1519; laundering money, 18 U.S.C. § 1957;\\nand engaging in mail, wire, and bank fraud, 18 U.S.C.\\n§§ 1341, 1343, and 1344.\\n\\n The RICO charge alleged that the defendants and\\nother co-conspirators constituted an enterprise aimed at\\nsupporting and promoting Fattah’s political and financial\\ninterests. The efforts to conceal the $1 million Lord loan\\nand its repayment are at the heart of the RICO conspiracy\\nand the Fattah for Mayor scheme. The indictment further\\nalleged that the RICO enterprise involved: (1) the scheme\\nto satisfy an outstanding campaign debt by creating the\\nfake “Blue Guardians” nonprofit; and (2) the bribery\\nscheme to obtain payments and things of value from\\nVederman in exchange for Fattah’s efforts to secure\\nVederman an appointment as a United States Ambassador.\\n 40\\n\\f A jury trial, before the Honorable Harvey Bartle III\\nof the Eastern District of Pennsylvania, began on May 16,\\n2016, and lasted about a month. 7 Judge Bartle charged the\\njury on Wednesday, June 15, 2016, and deliberations\\nbegan late that afternoon. The following day, after\\ndeliberating for only four hours, the jury sent a note to the\\njudge. Written by the foreperson, the note read:\\n Juror Number 12 refuses to vote by the letter\\n of the law. He will not, after proof, still\\n change his vote. His answer will not change.\\n He has the 11 of us a total wreck knowing that\\n we are not getting anywhere in the hour of\\n deliberation yesterday and the three hours\\n today. We have zero verdicts at this time all\\n due to Juror Number 12. He will not listen or\\n reason with anybody. He is killing every\\n other juror’s experience. We showed him all\\n the proof. He doesn’t care. Juror Number 12\\n has an agenda or ax to grind w/govt.\\nJA5916.\\n\\n Shortly after receiving the foreperson’s note, the\\nCourt received a second communication—a note signed\\n\\n\\n\\n 7\\n The District Court dismissed one charge prior to\\ntrial: an individual money laundering count against\\nNicholas.\\n 41\\n\\fby nine jurors, including the foreperson. The second note\\nread:\\n We feel that [Juror 12] is argumentative,\\n incapable of making decision. He constantly\\n scream [sic] at all of us.\\nId.\\n Judge Bartle met with counsel in his chambers and\\nadvised them of his intention to voir dire both the\\nforeperson and Juror 12 in an effort to determine whether\\nthe juror was deliberating as required by his oath. The\\nJudge also indicated that he would “stay away from the\\nmerits of the case,” and that whether he would voir dire\\nmore jurors “remain[ed] to be seen.” JA5917.\\n Counsel for the defendants objected to the Court’s\\nproposed inquiry. As a group, they indicated that while the\\nnote could be read as suggesting “a flat refusal to\\ndeliberate,” they were of the opinion that it sounded “more\\nin the manner of a disagreement over the evidence.”\\nJA5918. Nicholas’s counsel specifically argued that\\nquestioning the jurors so quickly after the start of\\ndeliberations would send a message that differences of\\nopinion among a block of jurors could be resolved by\\ncomplaining to the Court. Defense counsel acknowledged\\nthat the case law gave Judge Bartle wide discretion on how\\nto proceed, but suggested that a “less intrusive” course of\\naction was preferred. JA5918–19. They collectively urged\\n\\n 42\\n\\fthe Court to do nothing more than remind the jurors of\\ntheir duty to deliberate.\\n The Government agreed with Judge Bartle’s\\nproposed voir dire. In the prosecution’s view, the Court\\nhad already given proper instructions to the jury on their\\nduty to deliberate. The Government further argued that if\\nJuror 12 had exhibited bias, as suggested in the notes, he\\nwould have lied during the voir dire process and his\\nrefusal to deliberate would be “further evidence of that and\\nhis unsuitability as a juror.” JA5921.\\n\\n With all counsel present, and over defense counsel’s\\nobjections, Judge Bartle ultimately questioned five jurors\\nin chambers. He questioned Juror 2 (the foreperson), Juror\\n12 (the subject of the complaints), Juror 3, Juror 6, and\\nJuror 1.\\n\\n Judge Bartle began each voir dire by informing the\\njuror that he would ask a series of questions, but would not\\ninquire into the merits of the case or how any juror was\\nvoting. Each juror was placed under oath, and Judge Bartle\\nasked, among other questions, whether screaming was\\noccurring; whether the jurors were discussing the\\nevidence; whether Juror 12 was placing his hands on other\\njurors; and whether Juror 12 was unwilling to follow his\\ninstructions.\\n The foreperson acknowledged that he had written\\nthe initial note during lunch earlier that day. He stated that\\nJuror 12 was not willing to follow the law, but instead\\n 43\\n\\f“want[ed] to add his own piece of the law . . . which has\\nnothing to do with it.” JA5927–28. The foreperson further\\ntestified that Juror 12 “was standing up screaming” and\\nthat “[i]t was everybody pretty much against [Juror 12].”\\nJA5929. He testified that Juror 12 “has his own agenda,”\\nand that Juror 12 put his hand on another juror. JA5930.\\nThe foreperson also stated that the jury had discussed only\\na single count since the day before, and that they were still\\ndiscussing it. When the District Court responded that the\\njurors should understand that they could take as much time\\nas they needed, the foreperson responded: “I understand\\nthat. . . . [W]e all understand it. But we feel that he’s just—\\nhe’s got another agenda.” JA5934.\\n Judge Bartle advised counsel that he considered this\\n“a very serious situation” and that he would proceed to\\nvoir dire Juror 12. JA5937. Fattah’s counsel renewed his\\nobjection to questioning Juror 12, which the Court\\noverruled. Brand’s counsel argued that because the Court\\nhad decided to voir dire Juror 12, it should also voir dire\\nan additional juror. The Court agreed to do so.\\n When the Court questioned Juror 12, he admitted to\\nhaving “yelled back” at others, but only when they raised\\ntheir voices to him. JA5939. Juror 12 contended that he, in\\nfact, was “the only one” deliberating. Id. When an initial\\nvote was taken the previous afternoon, his vote “was\\ndifferent than everybody else’s.” Id. Juror 12 explained to\\nthe other jurors why his vote was different, bringing up\\nspecific evidence. In response, the other jurors said “that\\n\\n 44\\n\\fdoesn’t mean anything” and “pointed to the indictment.”\\nJA5940. Juror 12 told the other jurors that the indictment\\nis not evidence. Id. In response, the others “threatened to\\nhave [him] thrown off.” Id.\\n\\n Juror 12 testified that a similar sequence of events\\nhad taken place that morning. After a brief period of\\ndeliberations, another vote was taken, and with the same\\nresult as the previous afternoon. A discussion ensued, and\\nthe other jurors again “point[ed] to the indictment.” Id.\\nJuror 12 told them to “read the charge,” “[t]he indictment\\nis not evidence.” Id. They read the charge, and Juror 12\\nagain attempted to explain his view, but the other jurors\\npaid little attention. Accordingly, Juror 12 told the others\\nthat if they did not want him there, he “[didn’t] want to be\\n[there]”—he would be “[o]kay with it” if they wanted him\\ntaken off the jury. JA5941.\\n Upon hearing this testimony, Judge Bartle again\\nasked about the tone of deliberations. Juror 12 repeated\\nthat he raised his voice only in response to others who did\\nso—he did “not want to yell at anybody.” JA5942. Judge\\nBartle then asked whether he had touched other jurors.\\nJuror 12 replied that he had not hurt anyone. When asked\\nif he had put his hand on anybody’s shoulder, Juror 12\\nanswered: “I couldn’t remember to be honest with you.”\\nJA5946.\\n\\n Following Juror 12’s voir dire, the Court summoned\\nJuror 3 to chambers. Juror 3 testified that, after discussion\\nof a particular count, there was one juror at odds with the\\n 45\\n\\fothers. According to Juror 3, “the rest of the jurors\\npounced on the gentleman with the . . . dissenting\\nopinion.” JA5948. Juror 3 testified that Juror 12 “got very\\ndefensive and just a little bit [] impatient” and that “the\\nother jurors were very impatient with him.” Id. Juror 3 did\\nnot recall witnessing Juror 12 putting his hand on any\\nother jurors.\\n\\n The Government requested that the Court voir dire\\nanother juror. Defense counsel objected, claiming that the\\nquestioning “threaten[ed] . . . the entire deliberative\\nprocess.” JA5949–50. Judge Bartle reminded counsel that\\nhe had the authority to question each juror, and called for\\nvoir dire of Juror 6.\\n Juror 6 testified that the jury had been discussing the\\ncase and reviewing the evidence, but that Juror 12 “wants\\nto be seen” and was “being obstinate.” JA5951–52.\\nAccording to Juror 6, Juror 12 “may not agree” with the\\nconclusion of other jurors but “doesn’t give valid reasons\\nas to why he may disagree with the charge.” JA5952. Juror\\n6 also revealed that Juror 12 was the first to raise his voice,\\nand that he may have touched her and another juror. When\\nasked to clarify what she meant by Juror 12 disagreeing\\nwith “the charge,” Juror 6 testified that Juror 12 was\\n“reading maybe too deeply into it and putting his own\\nemotions into it instead of just looking at what it says [and]\\nwhat the facts are.” JA5952, 5955. According to Juror 6,\\nJuror 12 “just continues to read past that into his own mind\\nof what he feels it should be.” JA5955. Juror 6 testified\\n\\n 46\\n\\fthat Juror 12’s “justification for some of his responses [did\\nnot] seem to relate to what the matter [was] before\\n[them].” JA5957.\\n Judge Bartle chose to hear from yet another juror.\\nJuror 1 was called and informed the Court and counsel that\\nthe jury “really [hadn’t] been able to even start the\\ndeliberation process” in light of the disruptive behavior of\\n“one particular individual.” JA5958–59. The particular\\nindividual, according to Juror 1, was “very opinionated”\\nand “[came] into the process with his view already\\nestablished, refusing to even listen to any of the evidence\\n. . . [being] very forceful . . . standing up, yelling, pointing\\nhis finger.” JA5959. When asked if this individual was\\nwilling to follow the Court’s instructions, Juror 1 testified\\nthat he “pours [sic] over the documents very well” but that\\nhe was adding other factors to answer the question on the\\nverdict form, such as “what did this person feel.” JA5961.\\nWhen Judge Bartle advised that intent was an appropriate\\nconsideration, Juror 1 agreed but said that Juror 12 was\\n“trying to investigate . . . going way beyond the scope” of\\nthe evidence before them. JA5961–62. Juror 12, he said,\\n“has an opinion and that opinion is established.” JA5962.\\nHe stated that Juror 12 was “not willing to listen to any\\nsort of reason or any sort of what everyone else is saying”\\nbut instead, was “trying to force everyone else to get to his\\npoint of view.” Id. “[I]f he feels like he’s not getting there,\\nhe gets louder and louder and points and puts his hand on\\nyour shoulder . . . .” Id.\\n\\n 47\\n\\f After questioning the five jurors (Jurors 1, 2, 3, 6,\\nand 12), Judge Bartle heard argument from counsel. The\\nattorney for the Government pointed out that the Court\\nwould have to make a credibility determination because\\nJuror 12 stated that he did not recall touching anyone. In\\nthe Government’s view, Juror 12 was disrupting the\\nprocess and should be removed. Defense counsel\\ndisagreed. They argued that Juror 12 was conscientious\\nand was engaging with the evidence. They pointed out that\\ndespite the testimony that Juror 12 was reading too deeply\\ninto the instructions or introducing new factors for the jury\\nto consider, Juror 6 had testified that the jurors “talked it\\nthrough” and resolved the concern. JA5965. Defense\\ncounsel argued that the jury was discussing intent, an issue\\nthat was at the heart of the case. Defense counsel perceived\\nno breakdown in deliberations and argued that dismissal\\nwould be premature. They suggested, instead, that the\\nCourt provide a supplemental instruction.\\n\\n Judge Bartle decided to adjourn for the afternoon.\\nBut before he left the courtroom, defense counsel brought\\ntwo matters to his attention. First, in light of testimony\\nduring the voir dire, they asked that the jury be\\nreinstructed that the verdict form and indictment were not\\nevidence. Second, they apprised the Judge of the standard\\nfor juror dismissal set forth in United States v. Kemp, 500\\nF.3d 257 (3d Cir. 2007). Defense counsel stated that under\\nKemp, a request to discharge a juror must be denied if there\\nis a possibility that the request stems from the juror’s view\\nof the evidence. Judge Bartle expressed hesitation on\\n 48\\n\\freinstructing the jury, but agreed that Kemp would control\\nhis determination as to whether dismissal was appropriate.\\n With the following morning came a new revelation.\\nWith counsel in chambers, the Judge informed them that\\n“additional significant evidence” had come to light since\\nthe previous day’s recess. JA5980. He placed his\\ncourtroom deputy under oath, and she proceeded to testify\\nto an exchange that had occurred the previous day as she\\nwas escorting Juror 12 back to the jury room after he had\\nbeen voir dired. According to the deputy, Juror 12 stopped\\nher in the hallway, placed his hand on her shoulder, and\\nlooked her “straight in the eye.” JA5981. He then said:\\n“I’m going to hang this jury.” Id. The deputy then related\\nthat before any further conversation could take place\\nbetween Juror 12 and the deputy, Judge Bartle summoned\\nJuror 12 back to his chambers. Later that day, however,\\nJuror 12 and the courtroom deputy had another exchange.\\nShe testified that after all five jurors had been questioned,\\nJuror 12 emerged from the jury room and told her “I really\\nneed to talk to you.” JA5982. She informed Judge Bartle\\nand counsel that Juror 12 “said more about how they’re\\ntreating him and what he’s saying to them.” Id. He flatly\\nstated that “it’s going to be 11 to 1 no matter what.” Id.\\n\\n There were no follow-up questions for the deputy.\\nInstead, defense counsel suggested that what Juror 12 may\\nhave meant was that he was willing to hang the jury\\nbecause of a lack of evidence. They requested that Juror\\n12 be asked about his comments to the deputy.\\n\\n 49\\n\\f After once again summoning Juror 12 to his\\nchambers, the Judge advised him that “[s]ome questions\\nhave arisen” about what he may have done after being voir\\ndired the previous day. JA5985. Juror 12 acknowledged\\nhaving conversations with the courtroom deputy. When\\nasked “what happened” and “[w]hat occurred,” Juror 12\\nresponded: “Basically, I said that there was a lot of name\\ncalling going on.” JA5985. He said comments had been\\nmade by other jurors about his service in the military. He\\nspecifically referred to other jurors’ suggesting that he had\\npossibly “hit [his] head . . . hard a few times” while\\nserving in a parachute regiment. JA5986. He testified he\\nhad conveyed these comments to the deputy and that he\\nfound them offensive. When asked if he said anything else\\nto the deputy, Juror 12 responded: “I may have. I really\\ncan’t recall.” JA5987. And when Judge Bartle followed up\\nby asking if he could recall anything else that he said to\\nthe deputy, Juror 12 simply replied: “No. To me, that was\\nthe most important thing.” Id. Juror 12 was then excused\\nfrom chambers.\\n Defense counsel next requested that the juror be\\nasked directly whether he told the courtroom deputy that\\nhe was going to “hang this jury.” JA5988. Juror 12 was\\nrecalled to chambers, and the following back and forth\\ntook place:\\n\\n The Court: You may be seated. And, of\\n course, [Juror 12], you know you’re under\\n oath here from yesterday?\\n\\n 50\\n\\f Juror 12: Yes, sir.\\n The Court: . . . Did you say to [the courtroom\\n deputy] that you’re going to hang this jury?\\n Juror 12: I said I would.\\n The Court: You did?\\n Juror 12: I did. I said—I told her—I said, we\\n don’t agree; I’m not just going to say guilty\\n because everybody wants me to, and if that\\n hangs this jury, so be it.\\n ....\\n Juror 12: I did say that, sir.\\n The Court: You didn’t remember that before?\\n Juror 12: I’m more concerned about people\\n spitting on my military record.\\n The Court: Did you say that you’d hang the\\n jury no matter what?\\n Juror 12: If they do—if we cannot come to—\\n The Court: No. The question is what you said\\n to her. Did you say to her you would hang the\\n jury no matter what?\\n Juror 12: I can’t really remember that. I did\\n say that if we didn’t—a person—no matter\\n what, I can’t recall that exactly.\\n The Court: All right. Thank you very much.\\n You can wait just out there in the anteroom.\\nJA5989–90.\\n\\n Defense counsel continued to oppose Juror 12’s\\ndismissal. They argued that the juror’s concern was about\\n\\n 51\\n\\fthe evidence, and that his comments to the courtroom\\ndeputy reflected a conviction that “he’s not going to agree\\njust because others want him to agree.” JA5991. They also\\nargued that nothing should be made of Juror 12’s failure\\nto mention the comments when initially questioned by the\\nCourt, and that a supplemental instruction was all that was\\nwarranted given the early stage of the deliberations.\\n\\n The Government strongly disagreed. The Assistant\\nUnited States Attorney argued that Juror 12 “should\\nabsolutely be removed” because “his demeanor ha[d]\\ndemonstrated a hostility . . . both to the other jurors and to\\nthe court.” JA5993. The Government also suggested that\\nJuror 12’s comments that he would hang the jury meant\\nthat he was not participating in the deliberations and was\\nignoring the evidence and the law.\\n\\n Ruling from the bench, Judge Bartle announced:\\n I find [the deputy clerk] to be credible. I find\\n [Juror 12], not to be credible. I find that [Juror\\n 12] did tell [the deputy clerk] that he was\\n going to hang this jury no matter what.\\n There have been only approximately\\n four hours of deliberation. There’s no way in\\n the world he could have reviewed and\\n considered all of the evidence in the case and\\n my instructions on the law.\\n I instructed the jury to deliberate,\\n meaning to discuss the evidence; obviously,\\n to hold onto your honestly held beliefs, but at\\n 52\\n\\f least you have to be willing to discuss the\\n evidence and participate in the discussion\\n with other jurors.\\n Juror number 12 has delayed,\\n disrupted, impeded, and obstructed the\\n deliberative process and had the intent to do\\n so. I base that having observed him, based on\\n his words and his demeanor before me.\\n He wants only to have his own voice\\n heard. He has preconceived notions about the\\n case. He has violated his oath as a juror.\\n And I do not believe that any further\\n instructions or admonitions would do any\\n good. I think he’s intent on, as he said,\\n hanging this jury no matter what the law is,\\n no matter what the evidence is.\\n Therefore, he will be excused, and I\\n will replace him with the next alternate . . . .\\n\\nJA5994–95.\\n In response, defense counsel moved for a mistrial,\\nwhich the judge promptly denied. He then informed the\\nreconstituted jury that deliberations would need to start\\nover, and reinstructed them on certain points of law,\\nincluding that the verdict slip does not constitute evidence.\\n\\n Judge Bartle elaborated upon his decision to remove\\nJuror 12 in two post-trial memorandum opinions. In the\\nfirst, ruling on a media request for the sealed transcripts,\\nhe explained:\\n 53\\n\\f Here, there is no doubt that Juror 12\\n intentionally refused to deliberate when he\\n declared so early in the process that he would\\n hang the jury no matter what. This finding\\n was predicated on the admission of Juror 12\\n as reported by the court’s deputy clerk. The\\n facts became clear to the court after hearing\\n the credible testimony of the deputy clerk and\\n the less credible testimony of Juror 12. The\\n demeanor of Juror 12 before the court\\n confirmed the court’s findings.\\n\\nGSA23–24. The second opinion addressed motions for\\nbail pending appeal from Nicholas and Brand. GSA25.\\nThere, Judge Bartle explained:\\n\\n The law is well-settled that the court has\\n discretion to act as it did under these\\n circumstances. See United States v. Kemp,\\n 500 F.3d 257, 304 (3d Cir. 2007). The court,\\n after taking testimony, specifically found that\\n the juror, following only a few hours of\\n deliberation, stated to the court’s courtroom\\n deputy clerk that he would hang this jury no\\n matter what. He could not possibly have\\n reviewed all of the law and evidence of this\\n five-week trial at the time he made his\\n remark. The court examined the deputy clerk\\n and the juror under oath in the presence of\\n counsel for all parties. The undersigned\\n\\n 54\\n\\f found the deputy clerk to be credible and the\\n juror not to be credible. Based on the juror’s\\n demeanor, it was clear he would not change\\n his attitude and that his intent had been and\\n would continue to be to refuse to deliberate\\n in good faith concerning the law and the\\n evidence.\\n\\nGSA32.\\n After deliberating for approximately 15 hours, the\\njury returned with its verdicts on June 21, 2016, finding\\nthe defendants guilty on most counts. Fattah, Vederman,\\nand Brand were convicted on all counts. The jury acquitted\\nBowser on sixteen counts, but found her guilty of the\\nbribery conspiracy and the associated charges of bank\\nfraud, making false statements to a financial institution,\\nfalsifying records, and money laundering (Counts 16, 19,\\n20, 21 and 22). The jury also acquitted Nicholas of wire\\nfraud (Count 24). See Nicholas Supp. App. (NSA) 36.\\n The following week, on June 27, the Supreme Court\\nissued its opinion in McDonnell v. United States, 136 S.\\nCt. 2355 (2016). McDonnell provided new limitations on\\nthe definition of “official acts” as used in the honest\\nservices fraud and bribery statutes under which Fattah and\\nVederman had been convicted. Id. at 2369–72. Fattah and\\nVederman both moved to set aside their convictions. The\\nDistrict Court “acknowledge[d] that under McDonnell our\\ninstructions to the jury on the meaning of official act\\nturned out to be incomplete and thus erroneous.” JA103.\\n 55\\n\\fBut the Court held that “the incomplete and thus erroneous\\njury instruction on the meaning of official acts did not\\ninfluence the verdict on the bribery counts” and upheld the\\nverdict on Counts 16–18 and 22–23. JA107, 121.\\n\\n Fattah, Vederman, and Bowser had more success\\nwith their other post-verdict motions. The District Court,\\nin a thoughtful opinion, granted relief under Federal Rule\\nof Criminal Procedure 29, acquitting Vederman of the\\nRICO conspiracy (Count 1) and Fattah, Vederman, and\\nBowser of bank fraud, making false statements to a\\nfinancial institution, and falsifying records (Counts 19, 20,\\nand 21). JA37–139.\\n This appeal followed. 8 The defendants raise a\\nvariety of challenges to their convictions. All defendants\\nbut Bowser challenge the District Court’s decision to\\ndismiss Juror 12. Fattah and Vederman argue that the\\nDistrict Court erred in upholding the jury’s verdict on the\\nbribery and honest services fraud counts in light of the\\nSupreme Court’s decision in McDonnell. Fattah, Brand\\nand Nicholas challenge the sufficiency of the evidence\\nunderlying the RICO conviction. Several of the defendants\\ncontend the District Court erred in its instruction on intent\\nand by sending the indictment out to the jury. There are\\n\\n\\n\\n8\\n Fattah, Brand, Vederman, and Nicholas each filed a\\ntimely notice of appeal, but Bowser did not challenge her\\nconvictions.\\n 56\\n\\falso several evidentiary challenges.9 The Government\\ncross-appeals from the District Court’s judgment\\nacquitting Fattah and Vederman on Counts 19 and 20,\\narguing that the District Court erred in interpreting the\\ndefinition of a “mortgage lending business” under 18\\nU.S.C. § 27. We address these arguments in turn.\\n\\n We hold that the District Court erred in upholding\\nthe jury verdict in light of McDonnell, and we will\\ntherefore reverse and remand for retrial on Counts 16, 17,\\n18, 22, and 23. We also hold that the District Court erred\\n\\n9\\n Pursuant to Rule 28(i), “Fattah joins in the arguments of\\nHerbert Vederman, Robert Brand, and Karen Nicholas to\\nthe extent their arguments on appeal apply to Mr. Fattah.”\\nFattah Br. 19 n.69. Federal Rule of Appellate Procedure\\n28(i) provides that a defendant, “[i]n a case involving\\nmore than one appellant . . . may adopt by reference a part\\nof another’s brief.” Here, Fattah’s decision to join fails to\\nspecify which of the many issues of his codefendants he\\nbelieves worthy of our consideration. Rather, it appears\\nthat he presumes we will scour the record and make that\\ndetermination for him. This type of blanket request fails to\\nsatisfy Rule 28(a)(5)’s directive requiring that the\\n“appellant’s brief must contain . . . a statement of the\\nissues presented for review.” Fed. R. App. P. 28(a)(5). We\\nconclude that expecting the appellate court to identify the\\nissues to be adopted simply results in the abandonment and\\nwaiver of the unspecified issues. See Kost v. Kozakiewicz,\\n1 F.3d 176, 182 (3d Cir. 1993).\\n 57\\n\\fin acquitting Fattah and Vederman on Counts 19 and 20.\\nBecause the jury’s verdict was supported by the evidence,\\nwe will reinstate the convictions as to those counts. In all\\nother respects, we will affirm the judgment of the District\\nCourt.\\n\\n III. Juror Misconduct and Dismissal of Juror 12 10\\n Defendant Fattah challenges the District Court’s\\ndecision to conduct an in camera inquiry into alleged juror\\nmisconduct and the ultimate dismissal of Juror 12. 11 We\\nreject both challenges. The record reveals credible\\nallegations of juror misconduct and a sufficient basis to\\nsupport the finding that Juror 12 violated his oath.\\n\\n A. Investigation of Alleged Juror Misconduct\\n We first consider whether the District Court erred in\\nits handling of the two notes from jurors. A trial court’s\\nresponse to allegations of juror misconduct is reviewed\\nunder an abuse of discretion standard. United States v.\\nBoone, 458 F.3d 321, 326 (3d Cir. 2006) (citing United\\nStates v. Resko, 3 F.3d 684, 690 (3d Cir. 1993)). We\\nconclude that the District Court did not abuse its discretion\\n\\n\\n10\\n The District Court had jurisdiction under 18 U.S.C.\\n§ 3231. We have jurisdiction under 28 U.S.C. § 1291 and\\n18 U.S.C. § 3742(a).\\n11\\n Vederman, Nicholas, and Brand adopt Fattah’s claim of\\nreversible error concerning the dismissal of Juror 12.\\n 58\\n\\fin addressing the issues raised in the jurors’ notes to the\\nCourt.\\n Trial courts are afforded discretion in responding to\\nallegations of juror misconduct. This is so because “the\\ntrial court is in a superior position to observe the ‘mood at\\ntrial and the predilections of the jury.’ ” Resko, 3 F.3d at\\n690 (quoting United States v. Chiantese, 582 F.2d 974,\\n980 (5th Cir. 1978)). But this discretion is not unlimited.\\nOnce the jury retires to deliberate, the confidentiality of its\\ndeliberations must be closely guarded. An accused is\\nconstitutionally entitled to be tried before a jury of his\\npeers. As ordinary citizens, jurors are “expected to speak,\\ndebate, argue, and make decisions the way ordinary people\\ndo in their daily lives.” Pena-Rodriguez v. Colorado, 137\\nS. Ct. 855, 874 (2017) (Alito, J., dissenting). To protect\\nagainst intrusion into a defendant’s right to be judged only\\nby fellow citizens, “the door to the jury room [is] locked.”\\nId. at 875.\\n In Boone, this Court considered the threshold for\\nintervention by a trial judge who is presented with\\nallegations of juror misconduct during the course of\\ndeliberations. 458 F.3d at 327. We recognized that “[i]t is\\nbeyond question that the secrecy of deliberations is critical\\nto the success of the jury system.” Id. at 329. But that\\nsecrecy abuts a competing interest—the jury’s proper\\nexecution of its duties. That is, “a juror who refuses to\\ndeliberate or who commits jury nullification violates the\\nsworn jury oath and prevents the jury from fulfilling its\\n\\n 59\\n\\fconstitutional role.” Id. Recognizing these competing\\ninterests, we declined in Boone to adopt a sweeping\\nlimitation on a trial court’s ability to investigate\\nallegations of misconduct during jury deliberations. See id.\\nConsistent with the standard applied at other stages of\\ncriminal proceedings, Boone teaches that “where\\nsubstantial evidence of jury misconduct—including\\ncredible allegations of jury nullification or of a refusal to\\ndeliberate—arises during deliberations, a district court\\nmay, within its sound discretion, investigate the\\nallegations through juror questioning or other appropriate\\nmeans.” Id.\\n Fattah argues that the District Court had no basis to\\nquestion any of the jurors. Fattah Br. 20. We disagree. In\\nBoone, notes from the jury presented substantial credible\\nevidence of misconduct. 458 F.3d at 330. Here, the initial\\nnote from the foreperson alleged that Juror 12 “refuse[d]\\nto vote by the letter of the law,” would “not listen or reason\\nwith anybody,” and that he had “an agenda or ax to grind”\\nwith the Government. JA5916. The note contained\\nallegations of both a refusal to deliberate and a suggestion\\nof nullification. A refusal to deliberate is a violation of a\\njuror’s oath. Boone, 458 F.3d at 329 (citing United States\\nv. Baker, 262 F.3d 124, 130 (2d Cir. 2001) (“It is well-\\nsettled that jurors have a duty to deliberate.”)). Moreover,\\nnullification—a juror’s refusal to follow the law—is a\\nviolation of the juror’s sworn oath to render a verdict\\naccording to the law and evidence. See United States v.\\nThomas, 116 F.3d 606, 614–18 (2d Cir. 1997) (discussing\\n 60\\n\\fboth “benevolent” and “shameful” examples of juror\\nnullification, but “categorically reject[ing] the idea that, in\\na society committed to the rule of law, jury nullification is\\ndesirable or that courts may permit it to occur when it is\\nwithin their authority to prevent”). The second jury note,\\nsigned by nine jurors, supported the claim of misconduct\\nby asserting that Juror 12 was “incapable of making\\ndecision[s]” and was “constantly scream[ing]” at the other\\njurors. JA5916–17. We conclude that the District Court\\ndid not abuse its discretion in deciding to initially question\\nJuror 2, and subsequently, Jurors 12, 3, 6 and 1.\\n\\n Fattah also challenges the scope of the District\\nCourt’s questioning. He argues that the rights to an\\nimpartial jury and to a unanimous verdict “would be\\nrendered toothless if trial courts had free rein to question\\njurors during deliberations.” Fattah Br. 36. Indeed, we\\nacknowledged the legitimacy of such a concern in Boone.\\nDespite adopting a modest “credible allegations” standard\\nfor investigating misconduct, we “ke[pt] in mind the\\nimportance of maintaining deliberative secrecy.” Boone,\\n458 F.3d at 329. Fattah asserts that the trial court’s\\nquestions to the five jurors were “intrusive and pointed”\\nand “nothing like the questioning . . . approved in Boone.”\\nFattah Br. 38. But Fattah does not elaborate on how, in his\\nview, the questions posed by Judge Bartle specifically\\nintruded into deliberative secrecy.\\n\\n To be sure, Judge Bartle’s questioning of each juror\\nwas more extemporaneous than the juror questioning in\\n\\n 61\\n\\fBoone. There, the district court asked a single juror four\\n“concise and carefully-worded” questions. 458 F.3d at\\n330. Judge Bartle’s voir dire of each of the five jurors took\\non a more conversational tone. We take no issue with that\\napproach. The substance of the judge’s questions was\\nlimited and mirrored that of questions we deemed\\nappropriate in Kemp. There, the court conducted three\\nrounds of questioning. In the first round, each juror was\\nasked:\\n (1) “Are you personally experiencing any\\n problems with how the deliberations are\\n proceeding without telling us anything about\\n the votes as to guilt or innocence? If yes,\\n describe the problem.” (2) “Are all the jurors\\n discussing the evidence or lack of evidence?”\\n (3) “Are all the jurors following the court’s\\n instructions on the law?”\\n\\nKemp, 500 F.3d at 273. In the second and third rounds,\\neach juror was asked:\\n (1) “Is there any juror or jurors who are\\n refusing to deliberate?” (2) “Is there any juror\\n who is refusing to discuss the evidence or\\n lack of evidence?” (3) “Is there any juror who\\n is refusing to follow the Court’s\\n instructions?”\\nId. at 274. Here, Judge Bartle began his voir dire of each\\njuror by stating that he did not wish for the juror to discuss\\n 62\\n\\fthe merits of the case or to reveal the content of the\\ndeliberations that had taken place. He asked the jurors\\nwhether screaming was occurring, whether the jurors were\\ndiscussing the evidence, whether Juror 12 was placing his\\nhands on other jurors, and whether Juror 12 was unwilling\\nto follow his instructions.\\n Fattah points to no specific question posed or topic\\ndiscussed that was inappropriate, and we see little to no\\nsubstantive difference between the questions here and\\nthose asked by the trial judge in Kemp. As in Kemp, “the\\nDistrict Court took care to limit its questions to appropriate\\nmatters that did not touch on the merits of the jury’s\\ndeliberation, and expressly informed each juror on\\nmultiple occasions that he or she should not reveal the\\nsubstance of the deliberations.” Id. at 302 (citing United\\nStates v. Edwards, 303 F.3d 606, 634 n.16 (5th Cir. 2002)).\\n Fattah also argues that once the remarks of Juror 2\\nand Juror 12 revealed no further evidence of misconduct,\\nthe court had no basis to question other jurors. Fattah\\nReply 19. Yet, our cases make clear that a trial court may,\\nin its discretion, examine each juror. Kemp, 500 F.3d at\\n302 (“We have recognized that there are times in which\\nindividual questioning is the optimal way in which to root\\nout misconduct.”). Indeed, “the District Court must utilize\\nprocedures that will ‘provide a reasonable assurance for\\nthe discovery of prejudice.’ ” Id. (quoting Martin v.\\n\\n\\n\\n 63\\n\\fWarden, Huntingdon State Corr. Inst., 653 F.2d 799, 807\\n(3d Cir. 1981)). 12\\n\\n Judge Bartle, a very able and experienced district\\njudge, was in the best position to determine what type of\\ninquiry was warranted under the circumstances. We\\nconclude that his questioning of the five jurors was not an\\nabuse of discretion. See id. at 302.\\n\\n B. Dismissal of Juror 12\\n Fattah, joined by Vederman, Brand, and Nicholas,\\nstrongly contends that the District Court committed\\nreversible error by dismissing Juror 12. “We review the\\ndismissal of a juror for cause for abuse of discretion.”\\n\\n12\\n Our cases do not suggest that a trial judge confronted\\nwith allegations that a jury’s deliberations are being\\nobstructed by one of its members should always resort to\\ninterviewing jurors. Reinstructing the jury on its duty to\\ndeliberate will often be the better course at the first sign of\\ntrouble. Mere disagreement among jurors—even spirited\\ndisagreement—is no ground for intervention.\\nFurthermore, intrusive or leading questions about the\\ndeliberative process may work against the twin goals of\\nprotecting that process and ensuring that jurors remain\\nfaithful to their oaths. We share the Eleventh Circuit’s\\npreference of “err[ing] on the side of too little inquiry as\\nopposed to too much.” United States v. Oscar, 877 F.3d\\n1270, 1287 (11th Cir. 2017) (quoting United States v.\\nAugustin, 661 F.3d 1105, 1133 (11th Cir. 2011)).\\n 64\\n\\fKemp, 500 F.3d at 303. That deferential standard compels\\nus to affirm.\\n Rule 23(b) of the Federal Rules of Criminal\\nProcedure permits a trial court to excuse a deliberating\\njuror for good cause. See id. (citing Fed. R. Crim. P.\\n23(b)). Good cause exists where a juror refuses to apply\\nthe law, refuses to follow the court’s instructions, refuses\\nto deliberate with his or her fellow jurors, or demonstrates\\nbias. See Kemp, 500 F.3d at 305–06; United States v.\\nOscar, 877 F.3d 1270, 1287 (11th Cir. 2017); Thomas, 116\\nF.3d at 617. Good cause does not exist when there is\\nreasonable but sustained disagreement about how a juror\\nviews the evidence. The courts of appeals are emphatic\\nthat trial courts “may not dismiss a juror during\\ndeliberations if the request for discharge stems from\\ndoubts the juror harbors about the sufficiency of the\\ngovernment’s evidence.” Kemp, 500 F.3d at 303 (quoting\\nUnited States v. Brown, 823 F.2d 591, 596 (D.C. Cir.\\n1987)); see also Oscar, 877 F.3d at 1287 (same); United\\nStates v. Symington, 195 F.3d 1080, 1087 (9th Cir. 1999);\\nThomas, 116 F.3d at 622.\\n\\n To reinforce a defendant’s right to a unanimous\\njury, we have adopted a high standard for juror dismissal.\\nKemp, 500 F.3d at 304 & n.26. “[D]istrict courts may\\ndischarge a juror for bias, failure to deliberate, failure to\\nfollow the district court’s instructions, or jury nullification\\nwhen there is no reasonable possibility that the allegations\\nof misconduct stem from the juror’s view of the evidence.”\\n\\n 65\\n\\fId. at 304 (emphasis added). This “no reasonable\\npossibility” standard is “by no means lax.” Id. Rather, “[i]t\\ncorresponds with the burden for establishing guilt in a\\ncriminal trial.” Id.\\n\\n We first applied this standard in Kemp, but have not\\nhad occasion to do so since. There, the evidence\\nsupporting the district court’s removal decision was\\n“overwhelming.” 500 F.3d at 304. Ten jurors separately\\nand consistently reported that a juror was improperly\\nbiased, and did so only after three rounds of questioning\\nand careful and correct instructions from the district court\\nas to the distinction between appropriate skepticism and\\nimpermissible bias. Id. at 304–05; see id. at 275–76\\n(district court’s instruction). The testimony also showed\\nthat the juror in question refused to deliberate or to discuss\\nthe evidence with her fellow jurors. Id. at 305.\\n Whether the evidence of misconduct in this case is\\nas strong as that in Kemp is beside the point. After only\\nfour hours of deliberations, Juror 12 stated unequivocally\\nto the courtroom deputy that he was “going to hang” the\\njury, and that it would be “11 to 1 no matter what.”\\nJA5981–82 (emphasis added). These statements, coupled\\nwith the District Court’s finding that Juror 12 lacked\\ncredibility, provided a sufficient basis for Juror 12’s\\ndismissal.\\n\\n As grounds for excusing Juror 12, the District Court\\nfound that he refused to deliberate in good faith, “delayed,\\ndisrupted, impeded, and obstructed the deliberative\\n 66\\n\\fprocess and had the intent to do so,” JA5995, and that he\\nwas “intent on . . . hanging this jury no matter what the law\\nis, no matter what the evidence is.” Id. The District Court\\ndetermined from this that Juror 12 had violated his oath as\\na juror and that no further instructions or admonitions\\ncould rehabilitate the juror. Id. The District Court based\\nthese findings on personal observation, including Juror\\n12’s words and demeanor, and making the specific finding\\nthat Juror 12 was not credible. That finding is amply\\nsupported by the record.\\n\\n In United States v. Abbell, 271 F.3d 1286, 1303 (9th\\nCir. 2001), the Ninth Circuit recognized that “the\\ndemeanor of the pertinent juror is important to juror\\nmisconduct determinations” because the “juror’s\\nmotivations and intentions are at issue.” That court\\nemphasized, as we do, that a district judge is best situated\\nto assess the demeanor of a juror. Id. Here, Juror 12 stated\\nhe could not recall putting his hand on another juror’s\\nshoulder, while his fellow jurors’ testimony was consistent\\non this point. Juror 12 also failed, at first, to recall his\\ntroubling statements to the courtroom deputy despite\\nhaving made those statements only the previous afternoon.\\nWhen questioned a second time and asked directly about\\nthe statements, he admitted to saying that he would hang\\nthe jury but claimed he could not “really remember”\\nsaying “no matter what” the day before. JA5989–90. Juror\\n12’s spotty recollection of the previous day’s events\\nfurther supports the District Court’s finding that he was\\nnot credible.\\n 67\\n\\f Fattah argues that the credibility determination was\\nnot, by itself, a sufficient reason to dismiss the juror\\nbecause the record demonstrates more than a reasonable\\npossibility that the complaints about his conduct stemmed\\nfrom Juror 12’s own view of the Government’s case.\\nFattah Reply Br. 11; Fattah Br. 25, 28. Fattah claims that\\nthe District Court abused its discretion by dismissing Juror\\n12 “on the basis of, in effect, six words the juror\\npurportedly said to the court’s deputy after he was verbally\\nattacked by other jurors.” Fattah Br. 24. According to\\nFattah, the questioning of the other jurors “confirmed that\\nthere were no legitimate grounds for removing juror 12.”\\nId. at 26. We conclude otherwise.\\n “A district court’s finding on the question whether\\na juror has impermissibly refused to participate in the\\ndeliberation process is a finding of fact to which\\nappropriate deference is due.” Baker, 262 F.3d at 130.\\nWhile district courts must apply a high standard for juror\\ndismissal, their underlying findings are afforded\\nconsiderable deference on appeal. Kemp, 500 F.3d at 304\\n(citing Abbell, 271 F.3d at 1302–03). We will reverse only\\nif the decision to dismiss a juror was “without factual\\nsupport, or for a legally irrelevant reason.” Abbell, 271\\nF.3d at 1302 (citation omitted).\\n Here, the District Court had a legitimate reason for\\nremoving Juror 12. Refusal to deliberate constitutes good\\ncause for dismissal. Although the judge did not expressly\\narticulate the Kemp standard when he announced that he\\n\\n 68\\n\\fwould dismiss Juror 12, he did acknowledge the “no\\nreasonable possibility” standard in his discussion with\\ncounsel. The unmistakable import of the District Court’s\\nstatement from the bench is that there was no reasonable\\npossibility that Juror 12’s intransigence was based on his\\nview of the evidence. See Oscar, 877 F.3d at 1288 n.16.\\n Fattah contends that there is no record support for\\nthe finding that Juror 12 said “he was going to hang this\\njury no matter what.” Fattah Br. 29. To be sure, the\\ncourtroom deputy’s testimony is not that Juror 12 used the\\nwords “hang this jury” and “no matter what” in the same\\nsentence. She testified that Juror 12 first stated “I am going\\nto hang this jury,” then later stated “it is going to be 11 to\\n1 no matter what.” JA5981–82. This is a distinction\\nwithout a difference. Likewise, Fattah challenges the\\nDistrict Court’s finding that Juror 12 was determined to\\nhang the jury “no matter what the law is” and “no matter\\nwhat the evidence is.” Fattah Br. 29. Although there is no\\nevidence that Juror 12 uttered the phrases “no matter what\\nthe law is” or “no matter what the evidence is,” the District\\nCourt was describing the import of Juror 12’s statements.\\nThis was not error.\\n Fattah expresses the concern that “[i]f jurors are\\nasked the right questions or interrogated long enough, it\\nwould not be difficult for a trial court to elicit testimony\\nfrom [a] majority [of] jurors that can be held up as\\nevidence of a dissenting juror’s bias or refusal to\\ndeliberate.” Fattah Br. 22. He also worries that a group of\\n\\n 69\\n\\fjurors might have an incentive to rid themselves of a juror\\nwho holds a different view. Id. These are valid concerns—\\nbut no basis existed for such concerns in this case. Juror\\n12’s own words provided most of the support for his\\neventual dismissal. Furthermore, his statements were\\nmade early in the deliberations, in a complex case, before\\nany juror could reasonably be expected to have reached\\nfinal verdicts on the twenty-nine counts before the jury.\\n\\n The able District Judge did not err in finding that\\nJuror 12 refused to deliberate and therefore violated his\\noath.\\n\\n IV. The District Court’s Instructions Under\\n McDonnell\\n On appeal, Fattah and Vederman renew their\\nchallenge to the jury instructions given on Counts 3, 16,\\n17, 18, 22, and 23, concerning the meaning of the term\\n“official act” as used in the bribery statute (pursuant to\\nwhich both were convicted) and the honest services fraud\\nstatute (pursuant to which Fattah alone was convicted).\\n\\n In light of the Supreme Court’s opinion in\\nMcDonnell v. United States, 136 S. Ct. 2355 (2016),\\nreleased the week after the jury verdict, the District Court\\nconceded that its instructions were incomplete and\\nerroneous, at least as to Counts 16–18. Nevertheless, the\\nDistrict Court held that the erroneous jury instructions had\\nnot influenced the verdict on the bribery counts, and\\ndeclined to set aside Fattah and Vederman’s convictions.\\n 70\\n\\fAs to Counts 16–18 and 22–23, we disagree, and will\\nreverse the District Court’s judgment. The District Court’s\\njudgment with respect to Count 3, which did not involve\\nVederman, will be affirmed. JA78–79.\\n\\n A. The McDonnell Framework\\n In McDonnell, the Supreme Court interpreted the\\nterm “official act” as defined in 18 U.S.C. § 201(a)(3). 136\\nS. Ct. at 2368. The statute defines an “official act” as “any\\ndecision or action on any question, matter, cause, suit,\\nproceeding or controversy, which may at any time be\\npending, or which may by law be brought before any\\npublic official, in such official’s official capacity, or in\\nsuch official’s place of trust or profit.” 18 U.S.C.\\n§ 201(a)(3). The McDonnell Court distilled this definition\\ninto two requirements:\\n First, the Government must identify a\\n “question, matter, cause, suit, proceeding or\\n controversy” that “may at any time be\\n pending” or “may by law be brought” before\\n a public official. Second, the Government\\n must prove that the public official made a\\n decision or took an action “on” that question,\\n matter, cause, suit, proceeding, or\\n controversy, or agreed to do so.\\n\\n136 S. Ct. at 2368. Applying this two-step test to Governor\\nRobert McDonnell’s convictions, the Supreme Court\\nconcluded that “the jury was not correctly instructed on\\n 71\\n\\fthe meaning of ‘official act,’ ” and as a result, “may have\\nconvicted Governor McDonnell for conduct that is not\\nunlawful.” Id. at 2375. Given that uncertainty, the Court\\n“[could not] conclude that the errors in the jury\\ninstructions were ‘harmless beyond a reasonable doubt.’ ”\\nId. (quoting Neder v. United States, 527 U.S. 1, 16 (1999)).\\nThe Supreme Court, therefore, vacated Governor\\nMcDonnell’s convictions. Id.\\n\\n McDonnell lays out a clear path for the Government\\nto follow in proving that an accused has performed an\\n“official act.” First, the Government must “identify a\\n‘question, matter, cause, suit, proceeding or controversy’\\nthat ‘may at any time be pending’ or ‘may by law be\\nbrought’ before a public official.” 136 S. Ct. at 2368\\n(quoting 18 U.S.C. § 201(a)(3)). This first step is divided\\ninto two sub-components. In Step 1(A), the Government\\nmust “identify a ‘question, matter, cause, suit, proceeding\\nor controversy.’ ” Id. Step 1(B) then clarifies that the\\nidentified “question, matter, cause, suit, proceeding or\\ncontroversy” be one that “ ‘may at any time be pending’ or\\n‘may by law be brought’ before a public official.” Id.\\n\\n Under Step 1(A), a “question, matter, cause, suit,\\nproceeding or controversy” must be “a formal exercise of\\ngovernmental power that is similar in nature to a lawsuit\\nbefore a court, a determination before an agency, or a\\nhearing before a committee.” Id. at 2372. Importantly, “a\\ntypical meeting, telephone call, or event arranged by a\\n\\n\\n 72\\n\\fpublic official” does not qualify as such a formal exercise\\nof governmental power. Id. at 2368.\\n Step 1(B) then requires us to ask whether the\\nqualifying “question, matter, cause, suit, proceeding or\\ncontroversy” was one that “ ‘may at any time be pending’\\nor ‘may by law be brought’ before a public official.” Id.\\nAs the McDonnell Court clarified, “ ‘[p]ending’ and ‘may\\nby law be brought’ suggest something that is relatively\\ncircumscribed—the kind of thing that can be put on an\\nagenda, tracked for progress, and then checked off as\\ncomplete.” Id. at 2369; accord United States v. Repak, 852\\nF.3d 230, 252 (3d Cir. 2017) (quoting McDonnell, 136 S.\\nCt. at 2369). By contrast, matters described at a high level\\nof generality—for example, “[e]conomic development,”\\n“justice,” and “national security”—are not sufficiently\\n“focused and concrete.” McDonnell, 136 S. Ct. at 2369.\\n\\n In McDonnell, the Court concluded that at least\\nthree questions or matters identified by the Fourth Circuit\\nwere sufficiently focused:\\n (1) whether researchers at any of Virginia’s\\n state universities would initiate a study of [a\\n drug]; (2) whether the state-created Tobacco\\n Indemnification and Community\\n Revitalization Commission would allocate\\n grant money for the study of [a chemical\\n compound]; and (3) whether the health\\n insurance plan for state employees in\\n\\n 73\\n\\f Virginia would include [a specific drug] as a\\n covered drug.\\nId. at 2370 (internal quotations omitted) (quoting United\\nStates v. McDonnell, 792 F.3d 478, 515–16 (4th Cir.\\n2015)). We provided guidance in the form of a fourth\\nexample in Repak, when we held that a redevelopment\\nauthority’s awarding of contracts was “a concrete\\ndetermination made by the [redevelopment authority’s]\\nBoard of Directors.” 852 F.3d at 253.\\n\\n Step 2 requires the Government to prove that the\\npublic official made a “decision” or took “an action” on\\nthe identified “question, matter, cause, suit, proceeding or\\ncontroversy.” McDonnell, 136 S. Ct. at 2368. The\\nMcDonnell Court explained:\\n Setting up a meeting, hosting an event, or\\n calling an official (or agreeing to do so)\\n merely to talk about a research study or to\\n gather additional information . . . does not\\n qualify as a decision or action on the pending\\n question of whether to initiate the study.\\n Simply expressing support for the research\\n study at a meeting, event, or call—or sending\\n a subordinate to such a meeting, event, or\\n call—similarly does not qualify as a decision\\n or action on the study, as long as the public\\n official does not intend to exert pressure on\\n another official or provide advice, knowing\\n\\n 74\\n\\f or intending such advice to form the basis for\\n an “official act.”\\nId. at 2371. The Court further clarified:\\n\\n If an official sets up a meeting, hosts an\\n event, or makes a phone call on a question or\\n matter that is or could be pending before\\n another official, that could serve as evidence\\n of an agreement to take an official act. A jury\\n could conclude, for example, that the official\\n was attempting to pressure or advise another\\n official on a pending matter. And if the\\n official agreed to exert that pressure or give\\n that advice in exchange for a thing of value,\\n that would be illegal.\\nId.\\n Here, Fattah was charged with engaging in three\\ncategories of official acts, which we analyze in accordance\\nwith the McDonnell framework. In Counts 16–18 and 22–\\n23, Fattah is alleged to have set up a meeting between\\nVederman and the U.S. Trade Representative, attempted\\nto secure Vederman an ambassadorship, and hired\\nVederman’s girlfriend, all in return for a course of conduct\\nwherein Vederman provided things of value to Fattah.\\n\\n In this case, as in McDonnell, the jury instructions\\nwere erroneous. We conclude that the first category of the\\ncharged acts—setting up a meeting between Vederman\\n 75\\n\\fand the U.S. Trade Representative—is not unlawful, and\\nthat the second category—attempting to secure Vederman\\nan ambassadorship—requires reconsideration by a\\nproperly instructed jury. The third charged act—hiring\\nVederman’s girlfriend—is clearly an official act. But\\nbecause we cannot isolate the jury’s consideration of the\\nhiring from the first two categories of charged acts, we\\nmust reverse and remand the judgment of the District\\nCourt.\\n\\n B. The Kirk Meeting\\n We turn first to Fattah’s scheduling of a meeting\\nbetween Vederman and the U.S. Trade Representative,\\nRon Kirk. Under McDonnell, “setting up a meeting . . .\\ndoes not, standing alone, qualify as an ‘official act.’ ” 136\\nS. Ct. at 2368. Fattah’s setting up the meeting between\\nVederman and Kirk was therefore not an official act, a\\nconcession implicit in the Government’s opening brief.\\nSee Gov’t Br. 32 (failing to mention the Kirk meeting as\\none of the “two categories” of allegedly “official acts”).\\nBut the jury was not properly instructed on this point.\\nWithout the benefit of the principles laid down in\\nMcDonnell, the jury was free to conclude that arranging\\nthe Kirk meeting was an official act—and it may have\\ndone so. The District Court’s erroneous jury instructions,\\ntherefore, cannot survive harmless error review.\\n\\n In a footnote in its brief to this Court, the\\nGovernment argues that evidence about the Kirk meeting\\nwas offered only “because it established the strength of\\n 76\\n\\fVederman’s desire to be an ambassador” and not because\\nthe Government was attempting to establish the meeting\\nas an independent official act. Id. at79–80 n.6. But the\\nrecord undercuts the Government’s post hoc justification.\\n\\n The indictment, provided to the jury in redacted\\nform for use in its deliberations, lists Fattah’s setting up\\nthe Kirk meeting as an official act under the heading\\n“FATTAH’s Official Acts for VEDERMAN.” JA494.\\nUnder this heading are three distinct subheadings:\\n(1) “The Pursuit of an Ambassadorship,” (2) “The Pursuit\\nof Another Executive Branch Position,” and (3) “Hiring\\nthe Lobbyist’s Girlfriend to the Congressional Staff.”\\nJA494–95. The second subheading, “The Pursuit of\\nAnother Executive Branch Position,” describes the\\narrangement of the Kirk meeting. Quite clearly, then, this\\nthree-part structure demonstrates that setting up the Kirk\\nmeeting was one of three distinct categories of official acts\\nalleged by the Government.\\n\\n Although there is some support for the\\nGovernment’s argument that evidence of the Kirk meeting\\nwas presented at trial only to establish the extent of\\nVederman’s interest in becoming an ambassador, JA827,\\n852–53 (mentioning the Kirk meeting in close proximity\\nto references to Fattah’s attempts to secure Vederman an\\nambassadorship), it is undermined by language in the\\nredacted indictment itself, and by the way in which the\\nGovernment presented its case at trial as a “pattern” of\\nconnected acts.\\n\\n 77\\n\\f The redacted indictment, for example, refers to the\\nKirk meeting as “The Pursuit of Another Executive\\nBranch Position.” JA495 (emphasis added). The use of the\\nword “Another” strongly suggests that evidence about the\\nKirk meeting was not merely evidence of Fattah’s attempt\\nto secure Vederman an ambassadorship, but was also\\nevidence of a separate and distinct attempt to secure\\nVederman a position on a federal trade-related\\ncommission. The redacted indictment also notes that “[i]n\\nor around May 2011, with little progress made on securing\\nan ambassadorship for VEDERMAN, FATTAH turned\\ntowards obtaining for VEDERMAN an appointment in the\\nExecutive Branch to a federal trade commission.” Id.\\n(emphasis added). The words “turned towards,” taken\\nliterally, clearly convey that arranging the Kirk meeting\\nwas presented as distinct from Fattah’s efforts to secure\\nVederman an ambassadorship.\\n\\n The District Court denied Fattah and Vederman a\\nnew trial on Counts 17 and 18, referring to evidence of the\\nKirk meeting as “de minimis” and noting that “Kirk’s\\ntestimony during this lengthy trial lasted a mere sixteen\\nminutes.” JA97 n.14. In the District Court’s view,\\nevidence of the Kirk meeting “played no role in the\\noutcome” of the case. Id. Considering the record in light\\nof McDonnell, we are not so sure.\\n\\n Although it is possible that evidence of the Kirk\\nmeeting played a minor role at trial when compared to the\\nother acts on which the Government presented evidence,\\n\\n 78\\n\\fthe redacted indictment suggests that the Kirk meeting was\\na significant part of the Government’s case. The\\nindictment dedicates five paragraphs to describing the\\nKirk meeting, but just three paragraphs to describing the\\nhiring of Vederman’s girlfriend—a hiring that, as we\\nexplain below, is clearly an official act. JA495–96. While\\nneither the number of minutes used at trial nor the number\\nof paragraphs contained in an indictment is a dispositive\\nunit of measurement for determining the significance of\\nevidence, we conclude that the District Court’s erroneous\\njury instructions pertaining to the Kirk meeting were not\\nharmless.\\n We conclude, in accordance with McDonnell, that\\nFattah’s arranging a meeting between Vederman and the\\nU.S. Trade Representative was not itself an official act.\\nBecause the jury may have convicted Fattah for conduct\\nthat is not unlawful, we cannot conclude that the error in\\nthe jury instruction was harmless beyond a reasonable\\ndoubt, and we must vacate and remand the convictions of\\nFattah and Vederman as to Counts 16, 17, 18, 22 and 23.\\n\\n C. Fattah’s Efforts to Secure Vederman an\\n Ambassadorship\\n The nature of Fattah’s efforts to secure Vederman\\nan ambassadorship is less clear, and presents a closer\\nquestion than the Kirk meeting. We ultimately conclude\\nthat the question warrants remand so that it may be\\nanswered by a properly instructed jury. On remand, the\\njury must decide whether Fattah’s conduct constituted a\\n 79\\n\\f“decision” or “action” under Step 2 of the McDonnell\\nanalysis.\\n At the outset, it is clear to us that, under Steps 1(A)\\nand 1(B), a formal appointment of Vederman as an\\nambassador would qualify as a “matter” that “may at any\\ntime be pending” before a public official. The formal\\nappointment of a particular person (Vederman), to a\\nspecific position (an ambassadorship), constitutes a matter\\nthat is sufficiently focused and concrete. The formal\\nappointment of an ambassador is a matter that is “pending”\\nbefore the President—the constitutional actor charged\\nwith nominating ambassadors—as well Senators, who are\\ncharged with confirming the President’s ambassadorial\\nnominations. U.S. Const. art. II § 2 (“[H]e shall nominate,\\nand by and with the Advice and Consent of the Senate,\\nshall appoint Ambassadors . . . .”). It is beyond cavil that\\nthe formal appointment of an ambassador satisfies both\\nsub-components of McDonnell’s Step 1.\\n Turning to Step 2, we consider whether Fattah’s\\nefforts to secure Vederman an ambassadorship qualify as\\nmaking a “decision” or taking “an action” on the identified\\n“matter” of appointment. McDonnell, 136 S. Ct. at 2368.\\nAlthough those efforts—three emails, two letters, and one\\nphone call—do not themselves qualify as a “question,\\nmatter, cause, suit, proceeding, or controversy” under\\nMcDonnell’s Step 1, they may nonetheless qualify as the\\nmaking of a “decision” or taking “an action” on the\\nidentified matter of appointment. Id.\\n\\n 80\\n\\f McDonnell’s Step 2 requires us to determine\\nwhether Fattah’s efforts qualify as permissible attempts to\\n“express[] support,” or impermissible attempts “to\\npressure or advise another official on a pending matter.”\\nId. at 2371. At trial, the jury was not instructed that they\\nhad to place Fattah’s efforts on one side or the other of this\\ndivide. The jury might even have thought they were\\npermitted to find Fattah’s efforts—three emails, two\\nletters, and one phone call—to themselves be official acts,\\nrather than a “decision” or “action” on the properly\\nidentified matter of appointment. Such a determination\\nwould have been contrary to the dictates of McDonnell.\\n Faced with such uncertainty, we cannot assume the\\njury verdict was proper. Although the jury might not have\\nconcluded that Fattah’s efforts were themselves official\\nacts, and although the jury might not have concluded that\\nthose efforts crossed the line into impermissible attempts\\n“to pressure or advise,” we are unable to conclude that the\\njury necessarily did so. Nor can we, on the cold record\\nbefore us, determine whether Fattah’s efforts to secure\\nVederman an ambassadorship crossed the line.\\nDetermining, for example, just how forceful a strongly\\nworded letter of recommendation must be before it\\nbecomes impermissible “pressure or advice” is a fact-\\nintensive inquiry that falls within the domain of a properly\\ninstructed jury. Should the Government elect to retry these\\ncounts after remand, the finder of fact will need to decide\\nwhether Fattah’s efforts constituted permissible attempts\\nto “express[] support,” or impermissible attempts “to\\n 81\\n\\fpressure or advise another official on a pending matter.”\\nId.\\n\\n D. The Zionts Hiring\\n The third group of acts charged in the Fattah–\\nVederman scheme involves Fattah’s decision to hire\\nVederman’s girlfriend, Alexandra Zionts, as a\\ncongressional staffer. We conclude that the hiring was an\\nofficial act. A brief analysis of McDonnell’s two steps\\nsuffices to show why this is so.\\n Here, under McDonnell’s Step 1(A), the relevant\\n“matter” is the decision to hire Zionts. Step 1(B) of the\\nanalysis is satisfied because the hiring decision was\\n“pending” before Fattah himself. And that hiring was\\n“focused and concrete,” “within the specific duties of an\\nofficial’s position—the function conferred by the\\nauthority of his office.” Id. at 2369. Finally, McDonnell’s\\nStep 2 requires that the “Government . . . prove that the\\npublic official made a decision or took an action ‘on’ [the\\nidentified] question, matter, cause, suit, proceeding, or\\ncontroversy, or agreed to do so.” Id. at 2368. Fattah’s\\ndecision to hire Zionts clearly satisfies that requirement.\\nWe therefore conclude that the hiring of Zionts was an\\nofficial act under McDonnell.\\n\\n Vederman concedes that the Zionts hiring was an\\nofficial act. Oral Argument Transcript at 5–6. Fattah, for\\nhis part, maintains that “hiring someone for a routine, part-\\ntime, short-term position falls well outside [the] definition\\n 82\\n\\f[of ‘official act’] and is nothing like a lawsuit, agency\\ndetermination, or committee hearing, even if each shares\\nthe happenstance that federal funds will be used.” Fattah\\nReply Br. 25.\\n\\n Fattah’s argument lacks traction. Official acts need\\nnot be momentous decisions—or even notable ones.\\nJudges, for example, make “routine” evidentiary rulings\\nevery day, and yet it is beyond question that those rulings\\nare official acts. In the realm of official acts, it is of no\\nmoment that Zionts provided only “part-time, short term”\\nlabor. When a public official hires an employee to work in\\nhis government office, he has engaged in an official act.\\n * * *\\n If we could conclude that the Zionts hiring was the\\nonly category of actions that the jury relied on when it\\nfound that Fattah performed an official act under Counts\\n16–18 and 22–23, remand would not be necessary. But, as\\nwe have explained, we cannot rule out that the jury\\nerroneously convicted Fattah and Vederman based on\\nother actions that were not official acts under\\nMcDonnell.13\\n\\n\\n13\\n More specifically, the incomplete, and therefore\\nerroneous, instructions could have led the jury to commit\\nat least one of three mistakes. First, the jury could have\\nimproperly convicted Vederman and Fattah based on the\\nKirk meeting alone, or misunderstood the Kirk meeting to\\n 83\\n\\f The Government argues that because the Zionts\\nhiring was an official act, the effect of the erroneous jury\\ninstructions could be no more than harmless. The jury’s\\nverdict, the Government contends, permits us to deduce\\nthat the jury necessarily concluded the Zionts hiring was\\nan official act, and that this conclusion alone supported\\nFattah’s and Vederman’s convictions as to Counts 16–18\\nand 22–23—regardless of whether the jury erroneously\\nfound any unofficial acts to be official acts. We disagree.\\n Fattah and Vederman objected to the definition of\\n“official act” at trial. We thus apply the harmless error\\nstandard of review. McDonnell, 136 S. Ct. at 2375. The\\nGovernment argues that because the jury convicted Fattah\\nand Vederman of illegally laundering the proceeds of a\\n“scheme to commit bribery” under Count 23, the jury\\nfound that the scheme must have encompassed only the\\nZionts hiring. JA531.That would mean that the jury did not\\nconclude that the “scheme to commit bribery” included\\n\\nbe a necessary component of an impermissible “pattern”\\nof official acts. Second, the jury might have concluded that\\nFattah’s efforts to secure Vederman an ambassadorship\\nwere themselves official acts. Third, the jury might have\\nconcluded that Fattah’s efforts to secure Vederman an\\nambassadorship were merely attempts to “express[]\\nsupport,” rather than to “exert pressure . . . or provide\\nadvice,” but nonetheless erroneously concluded that those\\nexpressions of support were official acts. McDonnell, 136\\nS. Ct. at 2371.\\n 84\\n\\fany acts that McDonnell now makes clear were unofficial.\\nYet the redacted indictment, jury instructions, and the fact\\nthat the Government presented its case under a “pattern”\\ntheory at trial compel us to reject the Government’s\\nargument.\\n\\n The very first sentence under Count 23 of the\\nredacted indictment incorporates all three categories of\\n“Overt Acts” contained within paragraphs “58 through 95\\nof Count One.” 14 All three of these categories fall under a\\ngeneral heading within the redacted indictment titled “The\\nBribery and Fraud Scheme [redacted].” JA494. The jury\\nhad before it instructions for Count 23 which referred to\\n“the alleged bribery scheme involving an $18,000\\npayment,” JA448 (emphasis added), and the redacted\\nindictment which referred to “a scheme to commit\\nbribery,” JA531 (emphasis added). The parallel language\\ncould well lead a rational jury to conclude that the relevant\\n“scheme” included all three categories of acts listed under\\nthe general heading: “The Bribery and Fraud Scheme\\n[redacted].” JA494 (emphasis added).\\n\\n\\n\\n14\\n JA531. Paragraphs 58 through 95 of Count 1 refer to the\\nthree categories of allegedly official acts discussed above:\\n(1) “The Pursuit of an Ambassadorship,” (2) “The Pursuit\\nof Another Executive Branch Position,” and (3) the\\n“Hiring of the Lobbyist’s Girlfriend to the Congressional\\nStaff.” JA494–95.\\n 85\\n\\f Like the redacted indictment and jury instructions,\\nthe Government’s trial arguments referred to patterns and\\na course of conduct, and stressed that the jury need not\\nconnect specific payments to particular official acts. In its\\nclosing argument to the jury, the Government stated that\\nthe alleged “scheme took place over a period of several\\nyears. Over and over again you’re going to see the same\\npattern.” JA5383 (emphasis added). Then, in its rebuttal\\nargument, the Government went out of its way to\\nexplicitly distinguish its “pattern” theory from an\\nalternative theory that would have directly connected\\nindividual payments to individual acts. As the prosecutor\\nargued to the jury:\\n Ms. Recker appears to argue that each thing\\n of value must coincide with some specific\\n official act, but that is not the law and that is\\n not what Judge Bartle is going to instruct you.\\n Instead what he will tell you is that the\\n government is not required to prove that\\n Vederman intended to influence Fattah to\\n perform a set number of official acts in return\\n for things of value so long as the evidence\\n shows a course of conduct of giving things of\\n value, things of value to Fattah in exchange\\n for a pattern of official acts favorable to\\n Vederman. In other words a stream of\\n benefits. These for those, not this for that.\\n\\n\\n\\n 86\\n\\fJA5715–16 (emphases added). In closing to the jury, the\\nGovernment made several other references to this\\n“pattern” theory, 15 and the District Court referred to this\\n“pattern” theory in its instructions to the jury. As Judge\\nBartle instructed:\\n\\n [I]t is not necessary for the government to\\n prove that a defendant intended to induce a\\n public official to perform a number of official\\n acts in return for things of value.\\n So as long as the evidence shows a\\n course of conduct of giving things of value to\\n a public official in exchange for a pattern of\\n official acts favorable to the giver.\\n\\nJA5833–34 (emphasis added). On appeal, the Government\\nchanges course, asking us to assume that the jury ignored\\nthese repeated references to a “pattern of official acts” and\\n\\n15\\n See, e.g., JA5389 (“And the exchange of an official act\\nfor a thing of value is called a bribe. There’s the pattern.\\nFattah needs money, Vederman gets an official act.”); JA\\n5393 (“That’s why you see the pattern over and over again.\\nFattah needs money, Vederman gets an official act.”);\\nJA5400 (“The same pattern we saw over and over again.\\nFattah needs money, Vederman gets an official act.”);\\nJA5409 (“[Y]ou know that these were bribes because of\\nthe pattern you saw over and over and over again. Fattah\\nneeds money, Vederman gets an official act, that makes\\nthese things a bribe.”).\\n 87\\n\\finstead considered the Zionts hiring and Vederman’s\\n$18,000 payment to Fattah as an isolated quid pro quo.\\nThis is an invitation to speculate, and we decline to do so.16\\nThe jury began its deliberations accompanied by a copy of\\nthe redacted indictment which alleged a pattern of official\\nacts, consisting of any combination of three categories of\\nacts: pursuing an ambassadorship, arranging the Kirk\\nmeeting, and hiring Zionts. In light of the erroneous\\ninstructions, and because only one category clearly\\n\\n16\\n Providing some support to the Government’s ultimately\\nunconvincing argument that the jury considered the Zionts\\nhiring and $18,000 payment in isolation, we note that the\\nredacted indictment does mention those two events side-\\nby-side in paragraph 78 of the indictment’s Part V. JA497\\n(“On January 13, 2012, VEDERMAN wired $18,000 to\\nFATTAH, and six days later, on January 19, 2012,\\nBOWSER emailed VEDERMAN’s girlfriend, A.Z.,\\nwelcoming her as a new employee to FATTAH’s\\nCongressional Staff.”). But although paragraph 78\\nmentions the $18,000 wire transfer and the Zionts hiring\\nin the same breath, paragraph 78 does not instruct the jury\\nto connect these two events apart from the rest of the\\nevidence presented at trial. In light of the other instructions\\nand arguments indicating that the jury should not consider\\nthe Zionts hiring in isolation, but instead should consider\\nthe hiring as one part of a three-part scheme, paragraph 78\\nis not sufficient to avoid a reversal and remand on the\\nconvictions of Fattah and Vederman as to Counts 16–18\\nand 22–23.\\n 88\\n\\fqualifies as an “official act,” the jury’s deliberations were\\nfraught with the potential for McDonnell error. We will\\nvacate the convictions of Fattah and Vederman as to\\nCounts 16, 17, 18, 22, and 23, and remand to the District\\nCourt.\\n\\nE. Vederman’s Sufficiency Challenge to Counts 16–18\\n and 22–23\\n Vederman argues that there is insufficient evidence\\nto support a conviction, even if a jury were properly\\ninstructed under McDonnell. Specifically, Vederman\\nargues that there is insufficient evidence to convict him\\nand Fattah, after remand, on Counts 16–18 and 22–23\\nbecause “[a]t least seven of the eight alleged ‘official acts’\\nwere, as a matter of law, not official at all.” Vederman Br.\\n35. As to the single act that Vederman implicitly concedes\\nto be an official act—the Zionts hiring—Vederman argues\\nthat “[t]he only thing that even arguably associates” the\\nZionts hiring with Vederman was its timing in relation to\\nVederman’s sham purchase of the Fattahs’ Porsche. Id.\\nAccording to Vederman, “the undisputed chronology\\nprecludes any inference that Vederman conferred this\\nbenefit on his friend as an illegal bribe.” Id. (emphasis\\nomitted). Vederman is wrong. Sufficient evidence was\\nproduced at trial to have allowed a properly-instructed jury\\nto convict Fattah and Vederman of Counts 16–18 and 22–\\n23.\\n To begin with, even if the Zionts hiring had been the\\nsole official act to survive this Court’s interpretation of\\n 89\\n\\fMcDonnell, there would still be sufficient evidence to\\nconvict Fattah and Vederman. Zionts did not receive\\nwritten notice of her official hiring until six days after the\\nsham Porsche purchase. Moreover, the jury would not be\\nrestricted to considering the chronology of the sham\\npurchase alone. It would be free to consider Vederman’s\\nentire course of conduct. Under the general heading\\n“VEDERMAN’S Payments and Things of Value to\\nFATTAH,” the redacted indictment not only refers to the\\n$18,000 wire transaction from Vederman to Fattah as part\\nof the sham Porsche purchase, but also to Vederman’s\\n$3,000 payment for the college tuition of Simone Muller,\\nFattah’s live-in au pair, as well as thousands of dollars in\\npayments made by Vederman for Chip Fattah’s college\\ntuition. JA496–97.\\n And the Zionts hiring is not the only act to survive\\nour application of McDonnell. As we explained, a jury\\ncould find that Fattah’s efforts to secure Vederman an\\nambassadorship—three emails, two letters, and a phone\\ncall—were an impermissible attempt to “pressure or\\nadvise” President Obama, Senator Casey, or both men.17\\n\\n17\\n Although Fattah’s efforts to secure Vederman an\\nambassadorship present a jury question that is not for us to\\nanswer on appeal, we note that not one of these efforts\\nalone could qualify as an official act itself. See McDonnell,\\n136 S. Ct. at 2372 (“Setting up a meeting, talking to\\nanother official, or organizing an event (or agreeing to do\\nso)—without more—does not fit that definition of ‘official\\n 90\\n\\fThis means that a properly instructed jury on remand,\\npresented with evidence of Fattah’s efforts to secure an\\nambassadorship for Vederman and evidence of the Zionts\\nhiring, could find more than a single official act.\\n\\n F. Blue Guardians\\n In addition to the charges arising from his dealings\\nwith Vederman, Fattah was charged in Count 3 with\\n\\n\\nact.’ ”). The relevant question for a jury to consider on\\nremand, then, is whether these actions constituted “a\\n‘decision or action’ on a different question or matter”—to\\nwit, the formal appointment of an ambassador. Id. at 2369\\n(emphasis omitted).\\n Even though the emails, letters, and phone call are\\nnot, individually, official acts, it will be for a jury to decide\\nif Fattah’s efforts to secure an ambassadorship for\\nVederman crossed the line from permissible “support” to\\nimpermissible “pressure or advice.” While we express\\ndoubt that some of Fattah’s efforts concerning the\\nambassadorship are, when considered in isolation, enough\\nto cross that line, a properly instructed jury considering all\\nof the facts in context might nonetheless conclude that\\nother efforts—such as a hand-delivered letter to the\\nPresident of the United States—indeed crossed that line.\\nFurther, a jury might find that in the aggregate, three\\nemails, two letters, and a phone call crossed the line and\\ntherefore constituted a “decision or action” on the\\nidentified matter of appointment.\\n 91\\n\\fparticipating in a scheme with Lindenfeld to funnel money\\nto a fraudulent nonprofit organization. In connection with\\nthis scheme, Fattah was convicted of conspiring to commit\\nhonest services fraud.\\n\\n Fattah owed Lindenfeld nearly $100,000 for work\\nperformed on Fattah’s 2007 mayoral campaign. In lieu of\\nrepayment, Fattah suggested that Lindenfeld create an\\nentity, later named Blue Guardians, to which Fattah would\\ndirect $15,000,000 in public funds by using his position as\\na member of the House Committee on Appropriations.\\nNothing in McDonnell requires us to upset Fattah’s\\nconviction on Count 3.\\n Step 1(A) of our McDonnell analysis requires the\\nGovernment to “identify a ‘question, matter, cause, suit,\\nproceeding or controversy.’ ” 136 S. Ct. at 2368. Here, the\\n“matter” is the appropriation of millions of dollars in\\npublic funds. See Repak, 852 F.3d at 253–54 (holding the\\nawarding of redevelopment funds to be an official act). In\\nparticular, it was Fattah’s promise to perform this official\\nact that was unlawful. As McDonnell makes clear:\\n\\n [A] public official is not required to actually\\n make a decision or take an action on a\\n “question, matter, cause, suit, proceeding or\\n controversy”; it is enough that the official\\n agree to do so. The agreement need not be\\n explicit, and the public official need not\\n specify the means that he will use to perform\\n his end of the bargain.\\n 92\\n\\f136 S. Ct. at 2370–71 (internal citations omitted). That\\nFattah took steps to actually carry out his promise (e.g., by\\ndrafting and sending a formal appropriations request on\\nofficial congressional letterhead) is evidence of his illegal\\npromise. See id. at 2371.\\n\\n Step 1(B) requires the Government to establish that\\nthe “ ‘question, matter, cause, suit, proceeding or\\ncontroversy’ . . . ‘may at any time be pending’ or ‘may by\\nlaw be brought’ before a public official.” McDonnell, 136\\nS. Ct. at 2368. Appropriating public funds was not only a\\nmatter that was pending before Fattah as a member of the\\nAppropriations Committee, it was also a matter that was\\npending before the Chairman and Ranking Member of an\\nAppropriations Subcommittee to whom Fattah ultimately\\nsent a formal written request. See id. at 2369 (“[T]he\\nmatter may be pending either before the public official\\nwho is performing the official act, or before another public\\nofficial.”). Appropriating millions of dollars in response to\\nthe Blue Guardians request is “focused and concrete,” and\\n“the kind of thing that can be put on an agenda, tracked for\\nprogress, and then checked off as complete.” Id.\\n\\n Given Fattah’s membership on the Appropriations\\nCommittee, this was “something within the specific duties\\nof an official’s position—the function conferred by the\\nauthority of his office.” Id. Even if we were to assume,\\nagainst all reason, that an appropriation is not “something\\nwithin the specific duties” of either Fattah or the Chairman\\nor Ranking Member of an Appropriations Subcommittee,\\n\\n 93\\n\\fFattah’s formal request for an appropriation was\\nsomething that Fattah had the authority to do. Like the\\nExecutive Director in Repak, who lacked authority himself\\nto award redevelopment funds but could request such\\nfunds from the Board, Fattah used his position as a\\nCongressman to formally request appropriations for the\\nBlue Guardians. 852 F.3d at 254 (“Repak had the power\\nto, and indeed did, make recommendations to the\\n[redevelopment authority.\\n Step 2 of McDonnell requires the Government to\\n“prove that the public official made a decision or took an\\naction ‘on’ that question, matter, cause, suit, proceeding,\\nor controversy, or agreed to do so.” 136 S. Ct. at 2368\\n(emphasis added). Here, Fattah agreed to request an\\nappropriation for a bogus purpose. Unlike Fattah’s letters,\\nemails, and phone call seeking an ambassadorship for\\nVederman, there is no potential for the jury to have made\\na mistake when it found Fattah’s Blue Guardians promise\\nunlawful.\\n Fattah argues that the Government presented “[n]o\\nevidence . . . that would have allowed [the jury] to\\nconclude that [he] made a decision or took an action, or\\ncould have done so, on the question whether Blue\\nGuardians would receive a $15 million federal grant.”\\nFattah Br. 46. This argument misses the point. It was\\nFattah’s agreement to engage in the official act of formally\\nrequesting the appropriation that was illegal. See\\nMcDonnell, 136 S. Ct. at 2371.\\n\\n 94\\n\\f Lindenfeld’s trial testimony provided sufficient\\nevidence of Fattah’s illegal agreement. JA1694–96, 1954.\\nFattah’s letter provided additional evidence from which\\nthe jury could have concluded that Fattah illegally agreed\\nto perform an official act. 18 In short, the agreement itself\\nwas illegal, and the Government provided sufficient\\nevidence for the jury to conclude that the illegal agreement\\ntook place.\\n\\n The Government’s evidence in support of the Blue\\nGuardians scheme meets the requirements of McDonnell,\\nand the Count 3 verdict will stand.\\n\\n V. Sufficiency of the Evidence for the RICO\\n Conspiracy Conviction\\n The jury found Fattah, Vederman, Brand, and\\nNicholas guilty of the RICO conspiracy charged in Count\\n1 of the indictment, but acquitted Bowser. Vederman filed\\na post-verdict motion, and the District Court overturned\\nhis RICO conspiracy conviction.\\n\\n\\n\\n18\\n Despite Fattah’s protestation to the contrary, there is\\nevidence that Fattah took steps to carry out his official act.\\nJA6432–33 (Letter from Congressman Fattah to House\\nAppropriations Subcommittee members “request[ing]\\nfunding and support for the following projects and\\nprograms of critical importance,” including $3,000,000\\nfor “Blue Guardians”).\\n 95\\n\\f On appeal, Fattah, Brand, and Nicholas challenge\\nthe sufficiency of the evidence supporting their RICO\\nconspiracy convictions. We “review[] the sufficiency of\\nthe evidence in the light most favorable to the government\\nand must credit all available inferences in favor of the\\ngovernment.” United States v. Riddick, 156 F.3d 505, 509\\n(3d Cir. 1998). If a rational juror could have found the\\nelements of the crime beyond a reasonable doubt, we must\\nsustain the verdict. United States v. Cartwright, 359 F.3d\\n281, 286 (3d Cir. 2004), abrogated on other grounds by\\nUnited States v. Caraballo-Rodriguez, 726 F.3d 418 (3d\\nCir. 2013) (en banc).\\n The indictment charged a RICO conspiracy in\\nviolation of 18 U.S.C. § 1962(d), which makes it\\n“unlawful for any person to conspire to violate” § 1962(c).\\nSection 1962(c) provides:\\n It shall be unlawful for any person . . .\\n associated with any enterprise engaged in, or\\n the activities of which affect, interstate . . .\\n commerce, to conduct or participate, directly\\n or indirectly, in the conduct of such\\n enterprise’s affairs through a pattern of\\n racketeering activity . . . .\\n\\n18 U.S.C. § 1962(c).\\n\\n In Salinas v. United States, 522 U.S. 52 (1997), the\\ndefendant was convicted of a § 1962(d) RICO conspiracy,\\nbut a jury acquitted him of the substantive RICO offense\\n 96\\n\\funder § 1962(c). Id. at 55. The Supreme Court rejected\\nSalinas’s contention that his conviction had to be set aside\\nbecause he had neither committed nor agreed to commit\\nthe two predicate acts required for the § 1962(c) offense.\\nId. at 66. The Court declared that liability for a RICO\\nconspiracy under § 1962(d), “unlike the general\\nconspiracy provision applicable to federal crimes,” does\\nnot require proof of an overt act. Id. at 63. A conspiracy\\nmay be found, the Court explained, “even if a conspirator\\ndoes not agree to commit or facilitate each and every part\\nof the substantive offense. The partners in the criminal\\nplan must agree to pursue the same criminal objective and\\nmay divide up the work, yet each is responsible for the acts\\nof each other.” Id. at 63–64 (citations omitted). This means\\nthat, if a plan “calls for some conspirators to perpetrate the\\ncrime and others to provide support, the supporters are as\\nguilty as the perpetrators.” Id. at 64. Thus, opting into and\\nparticipating in a conspiracy may result in criminal\\nliability for the acts of one’s co-conspirators. Smith v.\\nBerg, 247 F.3d 532, 537 (3d Cir. 2001).\\n Accordingly, liability for a RICO conspiracy may\\nbe found where the conspirator intended to “further an\\nendeavor which, if completed, would satisfy all of the\\nelements of a substantive criminal offense, but it suffices\\nthat he adopt the goal of furthering or facilitating the\\ncriminal endeavor.” Salinas, 522 U.S. at 65. Because the\\nsubstantive criminal offense here was conducting a\\n§ 1962(c) enterprise, the government had to prove:\\n\\n 97\\n\\f (1) that two or more persons agreed to\\n conduct or to participate, directly or\\n indirectly, in the conduct of an enterprise’s\\n affairs through a pattern of racketeering\\n activity; (2) that the defendant was a party to\\n or member of that agreement; and (3) that the\\n defendant joined the agreement or conspiracy\\n knowing of its objective to conduct or\\n participate, directly or indirectly, in the\\n conduct of an enterprise’s affairs through a\\n pattern of racketeering activity.\\n\\nUnited States v. John-Baptiste, 747 F.3d 186, 207 (3d Cir.\\n2014).\\n In United States v. Turkette, 452 U.S. 576 (1981),\\nthe Supreme Court instructed that an enterprise is a “group\\nof persons associated together for a common purpose of\\nengaging in a course of conduct.” Id. at 583. The\\ngovernment can prove an enterprise “by evidence of an\\nongoing organization, formal or informal, and by evidence\\nthat the various associates function as a continuing unit.”\\nId. In Boyle v. United States, 556 U.S. 938 (2009), the\\nSupreme Court established that an “association-in-fact\\nenterprise must have at least three structural features: a\\npurpose, relationships among those associated with the\\nenterprise, and longevity sufficient to permit these\\nassociates to pursue the enterprise’s purpose.” Id. at 946.\\nThe structure necessary for a § 1962(c) enterprise is not\\ncomplex. Boyle explained that an enterprise\\n\\n 98\\n\\f need not have a hierarchical structure or a\\n “chain of command”; decisions may be made\\n on an ad hoc basis and by any number of\\n methods—by majority vote, consensus, a\\n show of strength, etc. Members of the group\\n need not have fixed roles; different members\\n may perform different roles at different\\n times. The group need not have a name,\\n regular meetings, dues, [or] established rules\\n and regulations . . . .While the group must\\n function as a continuing unit and remain in\\n existence long enough to pursue a course of\\n conduct, nothing in RICO exempts an\\n enterprise whose associates engage in spurts\\n of activity punctuated by periods of\\n quiescence.\\n\\nId. at 948.\\n\\n Another element of a substantive § 1962(c) RICO\\nenterprise is that the enterprise must conduct its affairs\\nthrough a pattern of racketeering activity. Section 1961\\ndefines racketeering activity to include various criminal\\noffenses, including wire fraud, 18 U.S.C. § 1344, and\\nobstruction of justice, 18 U.S.C. § 1511. See 18 U.S.C.\\n§ 1961(1). A pattern of such activity “requires at least two\\nacts of racketeering activity.” Id. § 1961(5). The\\nracketeering predicates may establish a pattern if they\\n“related and . . . amounted to, or threatened the likelihood\\n\\n\\n 99\\n\\fof, continued criminal activity.” H.J. Inc. v. Nw. Bell Tel.\\nCo., 492 U.S. 229, 237 (1989).\\n Here, the District Court denied the post-trial\\nsufficiency arguments raised by Fattah, Brand, and\\nNicholas. It reasoned:\\n For a RICO conspiracy to exist, the\\n conspirators must agree to participate in an\\n enterprise with a unity of purpose as well as\\n relationships among those involved. The\\n evidence demonstrates that an agreement\\n among Fattah, Brand, Nicholas, Lindenfeld,\\n and Naylor existed for the overall purpose of\\n maintaining and enhancing Fattah as a\\n political figure and of preventing his standing\\n from being weakened by the failure to be able\\n to pay or write down his campaign debts.\\n These five persons agreed to work together as\\n a continuing unit, albeit with different roles.\\n The Government established that\\n Fattah, Brand, and Nicholas conspired along\\n with Naylor and Lindenfeld to conceal and\\n repay the 2007 illegal $1,000,000 loan to the\\n Fattah for Mayor campaign.\\n\\nJA128–29. The District Court further determined that\\n [w]hile each member may not have been\\n involved in every aspect of the enterprise, its\\n activities were sufficiently structured and\\n 100\\n\\f coordinated to achieve the purpose of\\n maintaining and enhancing Fattah’s political\\n standing and of preventing him from being\\n weakened politically because of his\\n campaign debts.\\n A RICO conspiracy also requires an\\n agreement to participate in an enterprise with\\n longevity sufficient to pursue its purpose.\\n This was established. In May 2007 the illegal\\n loan was obtained and continued through its\\n repayment in January 2008 and into at least\\n 2014 when the last campaign report reducing\\n a fake campaign debt to Naylor’s consulting\\n firm was filed by Fattah.\\nJA131.\\n\\n The defendants argue that the evidence is\\ninsufficient to show either an enterprise for purposes of\\n§ 1962(c) or an agreement as required for a § 1962(d)\\nconspiracy. We disagree, and conclude that the District\\nCourt’s analysis is on the mark.\\n\\n We begin by considering whether there was an\\nagreement. The evidence showed that Fattah knew each\\nmember involved in the scheme to conceal the unlawful\\ncampaign loan. When Lindenfeld learned of the $1 million\\nloan, he informed Fattah that it exceeded campaign\\nfinance limits. In short, the transaction was unlawful, and\\nthe two knew it. The transaction nonetheless went\\nforward, disguised as a loan, with Lindenfeld executing\\n 101\\n\\fthe promissory note as Strategies’ officer and obligating\\nStrategies to repay Lord $1 million. The concealment\\nefforts continued as Lindenfeld funneled a substantial\\nportion of the loan proceeds to Naylor for get-out-the-vote\\nefforts. After the losing campaign, Lindenfeld spoke with\\nFattah and Naylor about accounting for the funds that had\\nbeen spent. They decided not to include the amounts in the\\nFFM campaign reports. Fattah instructed Naylor to\\nprepare a fictitious invoice, and Naylor complied. The\\nFFM campaign reports filed from 2008 to 2014 disclosed\\nnothing about the unlawful $1 million loan. Instead, they\\nfalsely showed that Naylor’s consulting firm made yearly\\nin-kind contributions of $20,000 in debt forgiveness, when\\nin reality there was no debt to forgive.\\n As Lindenfeld fretted over repaying the $600,000\\nbalance of the Lord loan, Naylor assured him that Fattah\\nhad promised to take care of the repayment. And the\\nevidence supports an inference that Fattah recruited both\\nNicholas and Brand in doing so. As EAA’s director,\\nNicholas could fund the repayment. Brand, through his\\ncompany, Solutions, acted as the middleman: he received\\nthe payment from EAA pursuant to a fictitious contract,\\nand then forwarded the balance due to Strategies pursuant\\nto yet another fictitious contract. Nicholas and Brand\\ncontinued in the spring and summer of 2008 to hide the\\nfictitious agreement and the $600,000 payment to\\nLindenfeld to satisfy the Lord loan.\\n\\n\\n\\n 102\\n\\f In short, this evidence shows that Fattah,\\nLindenfeld, Naylor, Brand, and Nicholas all agreed to\\nparticipate in Fattah’s plan to conceal the unlawful\\ncampaign loan to maintain his political stature. Nicholas\\nand Brand claim that they had no knowledge of the false\\ncampaign reporting aspect of the plan. But as Salinas\\ninstructs, conspirators need not “agree to commit or\\nfacilitate each and every part of the” conspiracy. 522 U.S.\\nat 63. Rather, they “must agree to pursue the same criminal\\nobjective and may divide up the work, yet each [be]\\nresponsible for the acts of each other.” Id. at 63–64. Thus,\\na conspirator may agree to “facilitate only some of the acts\\nleading to the substantive offense” yet still be criminally\\nliable. Id. at 65.\\n The evidence showed that a substantial amount of\\nmoney was needed to repay Lord, and that the source of\\nthe repayment was EAA, a non-profit organization whose\\nfunds could be spent only for purposes consistent with the\\nterms of the grants it received. It also showed that Nicholas\\nwas presented with a sham contract to legitimize the\\nEAA–Solutions transaction. We conclude that the\\nevidence is sufficient to support an inference that Nicholas\\nknew at the start that the plan was unlawful. Yet she still\\nagreed to provide the requisite funds and to play a role in\\nconcealing the illegal campaign loan so that Fattah could\\nmaintain his political stature.\\n\\n As to Brand, even if he did not know that false\\ncampaign reports were being filed, the evidence is\\n\\n 103\\n\\fsufficient to show he played a key role in the enterprise.\\nFrom the outset, Brand worked to disguise the repayment\\nof the Lord loan as the consideration in a sham contract\\nbetween EAA and Solutions. He then arranged for the\\ntransfer of funds to Strategies in satisfaction of a\\ncontractual term in another purported business agreement\\nbetween Solutions and Strategies. The evidence reveals\\nthat Brand was the point man in the effort to meet the\\nJanuary 31, 2008 deadline to repay the Lord loan, and it\\namply shows that Brand also agreed to participate in the\\nplan to hide the illegal campaign loan and its repayment to\\nbenefit Fattah politically.\\n Fattah, Brand, and Nicholas attack their RICO\\nconspiracy convictions on another front. They argue that\\nthose verdicts should be set aside because the evidence\\nfails to show that the various schemes alleged in the\\nindictment as part of the RICO conspiracy are connected.\\nThe RICO count, they assert, charges a hub-and-spoke\\nconspiracy that is unconnected by a rim. In their view,\\nFattah is the hub, and the spokes consist of a series of\\nindependent schemes: the Vederman bribery scheme, the\\npayment of the outstanding tuition debt of Fattah’s son\\nChip, the Blue Guardians plan, and the repayment of the\\nillegal Lord loan to maintain Fattah’s political stature.\\nThey argue that, without a unifying rim, their actions\\ncannot constitute an enterprise. Again, we disagree.\\n\\n In In re Insurance Brokerage Antitrust Litigation,\\n618 F.3d 300 (3d Cir. 2010), we concluded, in analyzing\\n\\n 104\\n\\fone of plaintiffs’ RICO claims, that the alleged hub-and-\\nspoke enterprise—comprised of broker hubs and insurer\\nspokes—could not withstand a motion to dismiss because\\nit did not have a unifying rim. Id. at 374. We explained\\nthat the allegations did “not plausibly imply concerted\\naction—as opposed to merely parallel conduct—by the\\ninsurers, and therefore cannot provide a ‘rim’ enclosing\\nthe ‘spokes’ of these alleged ‘hub-and-spoke’\\nenterprises.” Id. Thus, the allegations did not “adequately\\nplead an association-in-fact enterprise” because the hub-\\nand-spoke conspiracy failed to “function as a unit.” Id.\\n\\n That is not the case here. The evidence showed that\\nFattah, Brand, and Nicholas agreed to conceal the illegal\\nLord loan. Each acted for the common purpose of\\nfurthering Fattah’s political interests. In short, they\\nengaged in concerted activity and functioned as a unit. The\\njury convicted Fattah, Brand, and Nicholas of the RICO\\nconspiracy based on the racketeering activity of wire fraud\\nand obstruction of justice to conceal the unlawful\\ntransaction. Because the evidence shows that Fattah,\\nLindenfeld, Naylor, Brand, and Nicholas agreed to protect\\nFattah’s political status by acting to maintain the secrecy\\nof the unlawful Lord loan, the alleged lack of a unifying\\n“rim” is not fatal to this RICO enterprise. What matters in\\nanalyzing the structure of this enterprise is that it\\nfunctioned as a unit. Boyle, 556 U.S. at 945; In re Ins.\\nBrokerage Antitrust Litig., 618 F.3d at 374. That “basic\\nrequirement” was met. Id.\\n\\n 105\\n\\f We turn next to the contention that the evidence\\nfails to establish other components of an enterprise. We\\nconclude that much of the evidence supporting the\\nexistence of an agreement also shows that there was an\\nassociation-in-fact enterprise.\\n\\n Boyle made clear that an association-in-fact\\nenterprise must have “a purpose, relationships among\\nthose associated with the enterprise, and longevity\\nsufficient to permit these associates to pursue the\\nenterprise’s purpose.” 556 U.S. at 946. The purpose, as we\\nhave repeatedly observed, was to maintain and preserve\\nFattah’s political stature by concealing the illegal loan and\\nits repayment. Though informal, there were relationships\\namong those associated with the enterprise. Fattah was at\\nthe center of this association and he directed its activity.\\nHe knew each of the association’s members, and the\\nmembers knew each other (except, perhaps, for Nicholas,\\nwho may not have known Lindenfeld).19\\n\\n\\n19\\n Nicholas’s lack of familiarity with Lindenfeld does not\\nundermine her membership in this association-in-fact\\nenterprise. We have previously explained that “[i]t is well-\\nestablished that one conspirator need not know the\\nidentities of all his co-conspirators, nor be aware of all the\\ndetails of the conspiracy in order to be found to have\\nagreed to participate in it.” United States v. Riccobene, 709\\nF.2d 214, 225 (3d Cir. 1983), abrogated on other grounds\\nby Griffin v. United States, 502 U.S. 46 (1991).\\n 106\\n\\f The Government also adduced sufficient proof of\\nthe longevity component required for an enterprise. The\\nscheme began in mid-2007, when Lord made the\\ncampaign loan, directing the proceeds of the loan to\\nStrategies. From the outset, Fattah, Lindenfeld, and Naylor\\nall knew they needed to conceal this illegal transaction.\\nThey began by fabricating an explanation for the source of\\nthe funds they spent on election day. SLA created a fake\\ninvoice for the campaign, showing a fictitious debt that\\nNaylor could later forgive by fictitious in-kind\\ncontributions existing only on Fattah’s campaign finance\\nreports.\\n The effort to disguise the Lord loan was not limited\\nto filing false campaign reports. Nicholas and Brand, who\\njoined the conspiracy a few months later than the other\\nmembers, understood that they too had to make the\\nfraudulent $600,000 payment by EAA to Solutions appear\\nlegitimate. Nicholas and Brand tried to disguise the sham\\ncontract as an ordinary transaction (even though it called\\nfor a six-figure upfront payment simply to support\\nSolutions’ various projects), and they succeeded in\\nkeeping it out of the DOJ auditors’ view until August\\n2008. The ruse continued as Solutions funneled the\\n$600,000 payment to Strategies under the guise of another\\nsham contract (which also required an upfront six-figure\\npayment). The scheme then continued as Fattah submitted\\nfalse FFM campaign reports from 2008 through 2014.\\n\\n\\n\\n 107\\n\\f Finally, we consider whether the enterprise\\nconducted its affairs through a pattern of racketeering\\nactivity, as required for a § 1962(c) enterprise. Wire fraud\\nand obstruction of justice may constitute “racketeering\\nactivity” under § 1961(1). As the Supreme Court\\ninstructed in H.J. Inc., the “multiple predicates within a\\nsingle scheme” must be related and “amount[] to, or\\nthreaten[] the likelihood of, continued criminal activity.”\\n492 U.S. at 237. Here, the amount of the illegal loan to be\\nconcealed was substantial. The enterprise needed to write\\noff the fictitious debt to Naylor’s consulting firm, and it\\nwas urgent that both the EAA–Solutions contract and the\\nSolutions–Strategies contract be legitimized. We conclude\\nthe evidence was sufficient to establish that this enterprise\\nconducted its affairs through a pattern of racketeering\\nactivity and that the predicate acts of wire fraud and\\nobstruction of justice were related. The racketeering\\nactivity furthered the goals of maintaining the secrecy of\\nthis $1 million illicit campaign loan and of preserving\\nFattah’s political stature.\\n Nicholas contends that the evidence fails to\\nestablish a pattern of racketeering activity because the\\nactions to which she agreed did not “extend[] over a\\nsubstantial period of time” as H.J. Inc. requires. 492 U.S.\\nat 242. That case indeed instructs that the continuity\\nrequirement of a pattern is a “temporal concept,” and that\\n“[p]redicate acts extending over a few weeks or months”\\ndo not satisfy the continuity concept. Id. But the Supreme\\nCourt explained that continuity may also be established by\\n 108\\n\\fshowing that there is a “threat of continued racketeering\\nactivity.” Id. Here, the course of fraudulent conduct\\nundertaken to secure and to conceal the $1 million Lord\\nloan consisted of the creation of sham debts, fictitious\\ncontracts, and false accounting entries over the course of\\nabout a year. But because Fattah needed to appear able to\\nretire his campaign debt, the enterprise needed to continue\\nfiling false campaign reports for several years, allowing\\nthe annual $20,000 in-kind debt forgiveness contributions\\nto appear to satisfy Naylor’s fake $193,000 invoice. That\\nevidence was sufficient to establish the requisite threat of\\ncontinued criminal activity. See H.J. Inc., 492 U.S. at 242–\\n43.\\n We conclude that the Government met its burden in\\nproving that Fattah, Brand, and Nicholas 20 engaged in a\\nRICO conspiracy in violation of § 1962(d).\\n\\n\\n20\\n Nicholas also asserts, in passing, that that her conviction\\nunder § 1962(d) should be set aside because that statutory\\nprovision is unconstitutionally vague as applied to her.\\nAccording to Nicholas, a person of ordinary intelligence\\nwould not know that her actions constituted an agreement\\nto participate in a RICO enterprise. See United States v.\\nPungitore, 910 F.2d 1084, 1104–05 (3d Cir. 1990). To the\\ncontrary, a person of ordinary intelligence, who had been\\nemployed by a prominent politician and then became the\\nCEO of a nonprofit organization which that politician had\\nfounded (and, to some extent, continued to direct), would\\n 109\\n\\f VI. Variance from the Indictment and Sufficiency of\\n the Evidence for Count 2\\n Brand and Nicholas challenge their convictions for\\nconspiracy to commit wire fraud by arguing that the\\nGovernment’s evidence at trial impermissibly varied from\\nthe indictment. Nicholas also challenges the sufficiency of\\nthe evidence to support her conviction for conspiracy to\\ncommit wire fraud. We address these contentions\\ntogether. 21\\n\\n Count 2 of the indictment alleged a single\\nconspiracy. JA277–79. Brand and Nicholas assert that the\\nGovernment’s evidence at trial did not support the\\nexistence of a single conspiracy but instead showed two\\nindependent conspiracies, only one of which involved the\\ntwo of them. According to Brand and Nicholas, the only\\nconspiracy with which they were involved ended more\\nthan five years before the Government charged them. That\\nwould mean that all their conduct falls outside the five-\\nyear limitations period for wire fraud conspiracy under 18\\nU.S.C. § 3282.\\n\\n\\nrealize that agreeing to participate with others in hiding an\\nunlawful campaign loan of $1 million could constitute an\\nunlawful RICO conspiracy.\\n21\\n In her briefing, Nicholas discusses variance in far less\\ndetail than Brand, so we refer primarily to Brand’s\\narguments. See Nicholas Br. 54–56. Her variance\\narguments fail for the same reasons that Brand’s fail.\\n 110\\n\\f “A conviction must be vacated when (1) there is a\\nvariance between the indictment and the proof presented\\nat trial and (2) the variance prejudices a substantial right\\nof the defendant.” Kemp, 500 F.3d at 287 (quoting United\\nStates v. Kelly, 892 F.2d 255, 258 (3d Cir. 1989)). We see\\nno variance, and will affirm the District Court.\\n A variance exists “if the indictment charges a single\\nconspiracy while the evidence presented at trial proves\\nonly the existence of multiple conspiracies.” Id. “We must\\ndetermine ‘whether there was sufficient evidence from\\nwhich the jury could have concluded that the government\\nproved the single conspiracy alleged in the indictment.’ ”\\nId. (quoting Kelly, 892 F.2d at 258). Viewing the record in\\nthe light most favorable to the Government, we consider\\nthree factors: (1) “whether there was a common goal\\namong the conspirators”; (2) “whether the agreement\\ncontemplated bringing to pass a continuous result that will\\nnot continue without the continuous cooperation of the\\nconspirators”; and (3) “the extent to which the participants\\noverlap in the various dealings.” Id. (quoting Kelly, 892\\nF.2d at 259).\\n\\n Brand argues that the Government failed to\\nestablish a common goal among the conspirators. To\\ndetermine whether the conspirators shared a common\\ngoal, “we look to the underlying purpose of the alleged\\ncriminal activity” in a fairly broad sense. United States v.\\nRigas, 605 F.3d 194, 214 (3d Cir. 2010) (en banc). In\\nRigas, we described the common goal of the defendants as\\n\\n 111\\n\\f“enriching [themselves] through the plunder of [their\\ncorporate employer],” id., and we have similarly\\narticulated the common goal in fairly general terms\\nelsewhere. See United States v. Greenidge, 495 F.3d 85,\\n93 (3d Cir. 2007) (“There was certainly evidence of a\\ncommon goal among these co-conspirators: to make\\nmoney by depositing stolen and altered corporate checks\\ninto business accounts.”); Kelly, 892 F.2d at 259 (“[T]he\\ncommon goal of all the participants was simply to make\\nmoney selling ‘speed.’ ”). Importantly, a common goal\\nmay exist even when “conspirators individually or in\\ngroups perform different tasks in pursuing the common\\ngoal,” and a single conspiracy may “attract[] different\\nmembers at different times” or “involve[] different sub-\\ngroups committing acts in furtherance of the overall plan.”\\nUnited States v. Boyd, 595 F.2d 120, 123 (3d Cir. 1978).\\n\\n Here, the indictment described the purpose of the\\nunified conspiracy in Count 2 at length:\\n\\n It was a purpose of the conspiracy to obtain\\n an illegal campaign loan and to fraudulently\\n repay that loan with hundreds of thousands of\\n dollars of misappropriated charitable funds\\n from Sallie Mae and federal grant funds from\\n NASA which were intended for educational\\n purposes.\\n\\n . . . . It was further a purpose of the\\n conspiracy to present FATTAH to the public\\n as a perennially viable candidate for public\\n 112\\n\\f office who honored his obligations to his\\n creditors and was able to retire his publicly\\n reported campaign debts.\\n . . . . It was further a purpose of the\\n conspiracy to promote FATTAH’s political\\n and financial goals through deception by\\n concealing and protecting the conspirators’\\n activities from detection and prosecution by\\n law enforcement officials and the federal\\n judiciary, as well as from exposure by the\\n news media, through means that included\\n obstruction of justice and the falsification of\\n documents, including Campaign Finance\\n Reports, false invoices, contracts, and other\\n documents and records.\\n\\nJA277–78, ¶¶ 3–5.\\n Brand characterizes the evidence at trial as\\nestablishing two distinct conspiracies. The first he labels\\nthe “diversion of funds scheme,” covering the\\nmisappropriation of funds by Nicholas, Brand,\\nLindenfeld, and Fattah to repay the Lord loan. Brand Br.\\n34. Brand calls the second conspiracy the “CFR scheme,”\\nin which Fattah and Naylor filed the false campaign\\nfinance reports showing Naylor gradually forgiving a non-\\nexistent debt. Id.\\n Brand argues that the only goal of the CFR scheme\\nwas to cover up how the funds from the illegal campaign\\n 113\\n\\floan were spent, a goal he distinguishes from that of the\\ndiversion of funds scheme, which he characterizes as a\\nplan to cover up the repayment of the loan with stolen\\nfunds. He also argues that the evidence does not establish\\nhe was involved in, or even aware of, the false campaign\\nfinance reports filed by Fattah. In Brand’s view, that\\nnecessarily means the evidence showed two separate\\nconspiracies.\\n\\n In considering these arguments, we begin by noting\\nthat one conspiracy can involve multiple subsidiary\\nschemes. Rigas, 605 F.3d at 214. It is true that the false\\ncampaign finance reports, in the narrowest sense, had the\\nspecific purpose of covering up how the illegal loan funds\\nwere used during the election. But the false campaign\\nfinance reports were also filed in furtherance of a broader\\ngoal shared by the conspirators involved in repayment of\\nthe Lord loan. They sought to promote Fattah’s political\\nand financial goals by preserving his image as a viable\\ncandidate and making him appear able to repay or\\notherwise service his campaign debts without resorting to\\nillegal means in doing so. The two subsidiary schemes\\nworked in concert in furtherance of this overarching goal,\\nand both were directed at covering up how the loan was\\ntruly repaid. The “diversion of funds scheme” hid the\\nillegal (but real) loan repayment through the use of fake\\ncontracts; the “CFR scheme” showed the seemingly legal\\n(but fake) loan forgiveness installments through the\\ncreation of fake invoices and campaign finance reports.\\nThe existence of two concealment schemes acting in\\n 114\\n\\fconcert does not undermine the unity of the conspiracy of\\nwhich they were both a part. We have no difficulty\\nconcluding that the false campaign finance reports and the\\nconcealed use of stolen funds to repay the Lord loan\\noperated together in furtherance of a common goal.\\n\\n As for Brand’s argument that he was unaware of the\\nfalse campaign finance reports and therefore could not be\\na part of any conspiracy involving them, it is well-settled\\nthat “each member of the charged conspiracy is liable for\\nthe substantive crimes his coconspirators commit in\\nfurtherance of the conspiracy even if he neither\\nparticipates in his co-conspirators’ crimes nor has any\\nknowledge of them.” United States v. Bailey, 840 F.3d 99,\\n112 (3d Cir. 2016) (citing Pinkerton v. United States, 328\\nU.S. 640 (1946)). The exceptions to that rule allow a\\ndefendant to escape liability for a co-conspirator’s crime\\nif: (1) “the substantive offense committed by one of the\\nconspirators was not in fact done in furtherance of the\\nconspiracy,” (2) “the substantive offense committed by\\none of the conspirators ‘did not fall within the scope of the\\nunlawful project,’ ” or (3) “the substantive offense\\ncommitted by one of the conspirators ‘could not be\\nreasonably foreseen as a necessary or natural consequence\\nof the unlawful agreement.’ ” Id. (quoting Pinkerton, 328\\nU.S. at 647–48). There was, as we have concluded, a unity\\nof purpose between the co-conspirators to further Fattah’s\\npolitical and financial goals by secretly obtaining and\\nrepaying an illegal campaign loan with stolen funds. The\\nfiling of false campaign reports does not fit within any of\\n 115\\n\\fthe recognized exceptions to co-conspirator liability, as it\\nwas in furtherance of the conspiracy’s shared goal, within\\nthe scope of the agreement to conceal the loan, and\\nforeseeable to Brand and Nicholas.\\n\\n Neither Brand nor Nicholas briefed the other two\\nfactors we consider when determining whether the\\nevidence impermissibly varied from the evidence,\\n“whether the agreement contemplated bringing to pass a\\ncontinuous result that will not continue without the\\ncontinuous cooperation of the conspirators,” and “the\\nextent to which the participants overlap in the various\\ndealings.” Kemp, 500 F.3d at 287 (quoting Kelly, 892 F.2d\\nat 258). The unified goal of promoting Fattah’s political\\ncareer and maintaining secrecy surrounding the illegal\\nloan and the misappropriated funds used to repay it\\nrequired the continuous cooperation of the conspirators.\\nIndeed, the efforts of several of them overlapped in every\\naspect of the scheme. And Lindenfeld and Fattah were, at\\na minimum, involved in some way in nearly every aspect\\nof the origination of the loan, the false campaign finance\\nreports, and the use of misappropriated funds to repay the\\nloan. For his part, Naylor was involved in the use of the\\nfunds, the false campaign finance reports, and to a lesser\\nextent, the repayment of the loan.\\n Brand (as part of his variance argument) and\\nNicholas (as part of her sufficiency argument) argue that\\nthe Government did not prove they agreed to conceal their\\nactions, and thus the false campaign reports would not be\\n\\n 116\\n\\fsufficient to extend the duration of the conspiracy so that\\nit fell within the statute of limitations. Acts of\\nconcealment, such as the false campaign reports, are not\\nautomatically “in furtherance” of a conspiracy. We must\\ndetermine whether there was “an express original\\nagreement among the conspirators to continue to act in\\nconcert in order to cover up, for their own self-protection,\\ntraces of the crime after its commission,” as opposed to “a\\nconspiracy to conceal . . . being implied from elements\\nwhich will be present in virtually every conspiracy case,\\nthat is, secrecy plus overt acts of concealment.”\\nGrunewald v. United States, 353 U.S. 391, 404 (1957). If\\nthe indictment “specifically alleges a continuing\\nconspiracy” to conceal the crime after the completion of\\nthe wire fraud, and such a conspiracy can be proven, the\\nstatute of limitations does not begin to run until the last\\novert act of concealment. United States v. Moses, 148 F.3d\\n277, 282 (3d Cir. 1998).\\n\\n Here, the evidence shows that the conspirators\\nexpressly agreed to conceal the loan and its repayment. As\\nan initial matter, Brand’s only role in the conspiracy was\\nto cover up the use of stolen funds by (1) serving as an\\nintermediary between Nicholas and Lindenfeld; and\\n(2) agreeing to create false documentation (the contracts)\\nwith both EAA and Strategies for the sole purpose of\\ndisguising the payments and covering up the wire fraud\\nconspiracy. Nicholas could simply have paid Lindenfeld\\nherself (or paid Lord) if she and Brand had not agreed to\\nconceal the crime from the start. Additionally, and as\\n 117\\n\\fBrand acknowledges, the false campaign finance reports\\nbegan before the loan was repaid, proving that\\nconcealment of the crime was contemplated and begun as\\na direct purpose of the conspiracy before Brand and\\nNicholas became involved in the repayment. Nicholas too\\nagreed to conceal the repayment, as she implicitly\\nacknowledged in her emails with Brand and Fattah. GSA2.\\nFinally, when Lindenfeld briefly strayed from the\\nconspiracy’s commitment to secrecy by mentioning the\\nrepayment in front of others who did not know of the\\nscheme, Brand became “angry,” “took [Lindenfeld] out in\\nthe hallway,” and chastised him, saying that “[Lindenfeld]\\ncouldn’t say that sort of []thing” in front of other people.\\nJA1670–71. We conclude that the evidence is consistent\\nwith the allegations in the indictment, which charge a\\nsingle conspiracy consisting of an original agreement to\\nconceal the illegal loan and its subsequent illegal\\nrepayment to further Fattah’s political career.\\n\\n Nicholas makes several arguments in passing. She\\nsuggests that the District Court upheld the conviction after\\ntrial “on a theory not submitted to the jury.” Nicholas Br.\\n51. This argument is, essentially, that the indictment and\\nthe District Court’s post-trial ruling described the\\nconspiracy one way, but that the jury charge described the\\nconspiracy differently. Nicholas argues that the jury was\\npresented with the theory that the sole purpose of the false\\ncampaign reports under Count 2 was to “conceal[] the\\nalleged scheme to defraud,” JA5849, rather than to support\\n\\n 118\\n\\fFattah’s political career, as the District Court described the\\npurpose after trial, see JA74.\\n Nicholas ignores that part of the jury charge which\\ninstructed that Count 2 required a finding “[t]hat two or\\nmore persons agreed to commit wire fraud as charged in\\nthe indictment.” JA5845 (emphasis added). The jury had\\naccess to the indictment, and as Nicholas points out,\\nNicholas Br. 45–46, the indictment outlines the offense in\\nthe same way the District Court later described it in its\\npost-trial ruling. The District Court consistently described\\nthe count, and we see no reversible error.\\n Nicholas also argues that the conspiracy charged in\\nCount 2 has an objective—“to ‘present Fattah’ as\\n‘perennially viable’ ”—and that such an objective is not\\nillegal. Nicholas Br. 53. But, of course, the jury was not\\ninstructed that it was illegal to be a Fattah supporter, or\\neven to work on his campaign. The jury was charged\\nspecifically on the crime of wire fraud.\\n\\n We conclude that there was no impermissible\\nvariance between the indictment and the Government’s\\nevidence at trial, and that there was sufficient evidence to\\nsupport the convictions. We will affirm the convictions of\\nBrand and Nicholas for conspiracy to commit wire fraud\\nunder Count 2.\\n\\n\\n\\n\\n 119\\n\\f VII. The District Court’s Instruction to the Jury on\\n the Meaning of Intent\\n Nicholas contends that the District Court\\nimproperly instructed the jury by using the disjunctive\\nrather than the conjunctive at one point in its definition of\\nintent. When providing its final charge to the jury, the\\nDistrict Court explained:\\n Certain of the offenses charged in the\\n indictment require that the government prove\\n that the charged defendant acted intentionally\\n or with intent. This means that the\\n government must prove either that (1), it was\\n the defendant’s conscious desire or purpose\\n to act in a certain way or to cause a certain\\n result; or (2), the defendant knew that he or\\n she was acting in that way or it would be\\n practically certain to cause that result.\\n\\nJA5787 (emphasis added). According to Nicholas, an\\naccurate definition of intent required that the final “or” be\\nan “and.” Nicholas argues that this was an error so\\ngrievous as to “effectively eliminate[] the intent element\\nfrom each offense of conviction.” 22 Nicholas Br. 26.\\n\\n\\n22\\n The Comment to Third Circuit Model Criminal Jury\\nInstruction 5.03 makes clear that the definition of intent\\nencapsulates both “specific intent” (acting “purposely” or\\nwith “conscious object”) and “general intent” (acting\\n 120\\n\\f Our review of whether a jury instruction stated the\\nproper legal standard is plenary. United States v. Petersen,\\n622 F.3d 196, 207 n.7 (3d Cir. 2010). At trial, Nicholas\\nfailed to object to this portion of the jury charge.\\nAccordingly, our review must be for plain error. See\\nUnited States v. Flores-Mejia, 759 F.3d 253, 258 (3d Cir.\\n2014) (en banc).\\n\\n To prevail on plain error review, Nicholas must\\nestablish that there was an error, that it was plain (i.e., clear\\nunder current law), and that it affected her substantial\\nrights (i.e., whether there is a reasonable likelihood that\\nthe jury applied the challenged instruction in an\\nimpermissible manner). United States v. Olano, 507 U.S.\\n\\n“knowingly” or “with awareness”). Although Nicholas\\ndescribes the alleged error as “essentially eliminating” the\\nelement of intent, we think Nicholas’s argument is better\\nunderstood as a claim that the instruction given could have\\npermitted a jury to conclude that she acted with only\\ngeneral intent (that she was aware of what she was doing),\\nwhen her crimes require specific intent (that she had an\\nillegal purpose). As her brief states, “[p]lainly she\\n‘knowingly’ wrote checks from EAA to [Solutions] and\\nmade record entries about them; the question was whether\\nshe intended to defraud EAA and NASA, or to obstruct\\njustice, by doing so.” Nicholas Br. 24. We cannot agree\\nwith her characterization that the instruction resulted in the\\n“effective omission” of the intent element from the jury\\ninstructions.\\n 121\\n\\f725, 733–34 (1993); United States v. Dobson, 419 F.3d\\n231, 239–40 (3d Cir. 2005). If these requirements are met,\\nwe may then exercise our discretion to address the error,\\nbut only if we conclude that the error seriously affected the\\nfairness, integrity, or public reputation of the judicial\\nproceeding. United States v. Andrews, 681 F.3d 509, 517\\n(3d Cir. 2012) (quoting Johnson v. United States, 520 U.S.\\n461, 467 (1997)). A failure to instruct the jury on a\\nnecessary element of an offense ordinarily constitutes\\nplain error, unless the instructions as a whole otherwise\\nmake clear to the jury all the necessary elements of the\\noffense. United States v. Stimler, 864 F.3d 253, 270 (3d\\nCir. 2017).\\n Nicholas acknowledges, as she must, that the\\ninstruction given was a verbatim recitation of Instruction\\n5.03 of the Third Circuit’s Model Criminal Jury\\nInstructions. She nonetheless contends that our Model\\nInstruction is erroneous. Even if we were to accept\\nNicholas’s contention that the instruction is incorrect, a\\nproposition we consider as highly doubtful, see Petersen,\\n622 F.3d at 208 (“We have a hard time concluding that the\\nuse of our own model jury instruction can constitute error\\n. . . .”), we conclude that, considering the instructions as a\\nwhole, the District Court clearly and specifically\\ninstructed the jury on the intent element as it applied to\\neach of Nicholas’s charged crimes.\\n\\n The disputed intent instruction was given at the\\nbeginning of the final charge, explaining the general\\n\\n 122\\n\\fmeaning of the intent applicable to “[c]ertain of the\\noffenses charged.”23 JA5787. The District Court went on\\nto instruct the jury in specific detail on the elements of\\neach of the crimes of which Nicholas was accused,\\n\\n\\n\\n\\n23\\n The introductory definition did not end with the\\nlanguage Nicholas cites. The District Court elaborated that\\nacting in good faith is a complete defense to the charges:\\n\\n The offenses charged in the indictment\\n require proof that the charged defendants\\n acted with criminal intent. If you find that a\\n defendant acted in good faith that would be a\\n complete defense to such a charge, because\\n good faith on the part of the defendant would\\n be inconsistent with his or her acting\\n knowingly, willfully, corruptly, or with intent\\n to defraud or intent to impede, obstruct, or\\n wrongfully influence.\\n\\nJA5788–89 (emphasis added). This instruction\\nundermines Nicholas’s claim that the jury could have\\nreasonably concluded that she “ ‘knowingly’ wrote\\nchecks” but did not “intend[] to defraud . . . or to obstruct\\njustice[] by doing so,” Nicholas Br. 24, as this instruction\\nleaves little room for doubt that good faith is at odds with\\n“criminal intent.”\\n\\n 123\\n\\fexplaining also the intent element of each. 24 See JA5791\\n(describing the third element of the RICO conspiracy\\ncharge as: “the particular defendant and at least one other\\nalleged conspirator shared a unity of purpose and the intent\\nto achieve the objective of conducting or participating in\\nthe conduct of an enterprise’s affairs through a pattern of\\nracketeering activity”); JA5823 (regarding wire fraud,\\ninstructing that the government must prove “[t]hat the\\ndefendant under consideration acted with the intent to\\ndefraud”); JA5838–39 (regarding obstruction of justice,\\ninstructing that the defendant must have acted “with the\\nintent to impair the record, document, or object’s integrity\\nor availability for use in an official proceeding,” and must\\nhave acted corruptly “with the purpose of wrongfully\\nimpeding the due administration of justice”); JA5860\\n(explaining that falsification of records requires that “the\\ndefendant under consideration acted with the intent to\\nimpede, obstruct or influence the investigation or proper\\nadministration of a matter”). These instructions are\\nconsistent with both our Model Jury Instructions and our\\ncase law concerning the elements of these crimes. See\\nThird Circuit Model Criminal Jury Instruction 6.18.1962D\\n(RICO), 6.18.1343 (wire fraud), 6.18.1512A2 (obstruction\\nof justice); United States v. Sussman, 709 F.3d 155, 168\\n(3d Cir. 2013) (obstruction of justice); United States v.\\n\\n24\\n Nicholas did not object to the knowledge and intent\\ninstructions when the District Court discussed each of the\\nindividual charges, and does not identify a disagreement\\nwith any specific instruction on any particular charge.\\n 124\\n\\fMoyer, 674 F.3d 192, 208–09 (3d Cir. 2012) (falsification\\nof records); United States v. Pelullo (Pelullo I), 964 F.2d\\n193, 216 (3d Cir. 1992) (wire fraud).\\n The District Court also provided a separate\\ndefinition of the knowledge element of each charge,\\nillustrating the difference between knowledge and intent.\\nSee JA5793 (explaining that the evidence must show that\\na RICO defendant “knowingly agreed to facilitate or\\nfurther a course of conduct, which if completed would\\ninclude a pattern of racketeering activity”); JA5823 (wire\\nfraud means that the defendant “knowingly devised a\\nscheme to defraud a victim . . . by materially false or\\nfraudulent pretenses”); JA5860 (falsification of records\\nhas as an element “[t]hat the defendant under\\nconsideration knowingly concealed, covered up, falsified\\nor made false entries in a document or record”). These\\ninstructions made clear that knowledge and intent are\\nseparate considerations, undermining Nicholas’s\\ncontention that the jury was led to believe that “knowledge\\nis sufficient to prove intent.” Nicholas Br. 24.\\n The District Court provided each member of the\\njury with more than 100 pages of instructions before\\ndeliberations began. Viewing those instructions as a\\nwhole, we are satisfied that the jury was apprised of the\\ncorrect meaning of intent as an element of the crimes with\\nwhich Nicholas was charged, as well as the distinction\\nbetween knowledge and intent. We perceive no error,\\n\\n\\n 125\\n\\fmuch less error that is plain, in the District Court’s\\ninstructions to the jury. 25\\n\\n VIII. Sending the Indictment to the Jury\\n At trial, Vederman, Nicholas, and Brand objected to\\nthe District Court’s decision to give the jury a redacted\\ncopy of the indictment to use during its deliberations. Only\\nNicholas and Brand raise this issue on appeal. In\\nNicholas’s view, sending the indictment to the jury\\nunfairly prejudiced her because it contained unsupported\\nallegations that she had obstructed federal agencies and\\nreferred to a nonexistent certification requirement for\\nSallie Mae funds. Brand argues that he was prejudiced by\\nthe indictment’s references to “schemes” and “fake”\\ncontracts, and because it mentioned Brand’s spouse and\\nthat she was a former member of Fattah’s congressional\\nstaff. Nicholas and Brand together assert that the\\nindictment included legal theories on which the jury was\\nnot instructed. They contend that the indictment’s\\nnarrative of the Government’s case set out a roadmap that\\nomitted any averments relating to the defense theory and\\nallowed the Government to yet again present its case. To\\nbuttress that argument, Nicholas and Brand cite the\\ntestimony of Juror 12, who described the jury’s initial\\n\\n\\n\\n25\\n Accordingly, we need not consider the merits of\\nNicholas’s argument that Model Criminal Jury Instruction\\n5.03 is erroneous.\\n 126\\n\\fdeliberations and alleged that the jurors viewed the\\nindictment as evidence.\\n In United States v. Todaro, 448 F.2d 64, 66 (3d Cir.\\n1971), we held that the decision to allow “jurors to have a\\ncopy of the indictment with them during their\\ndeliberations . . . is a matter within the discretion of the\\nDistrict Judge, subject to a limiting instruction that the\\nindictment does not constitute evidence, but is an\\naccusation only.” Subsequently, in United States v.\\nPungitore, 910 F.2d 1084, 1142 n.83 (3d Cir. 1990), we\\nacknowledged that the District Court has the power to\\nredact the indictment if doing so would be appropriate to\\navoid prejudice to the defendant. See also United States v.\\nRoy, 473 F.3d 1232, 1237 n.2 (D.C. Cir. 2007) (noting that\\ncourt may redact an indictment before submitting it to the\\njury).\\n\\n While both Nicholas and Brand objected in general\\nterms to the District Court’s decision to provide the\\nindictment to the jury, they have not directed us to any\\nspecific request to redact the information they now claim\\nis prejudicial. And the District Court provided a limiting\\ninstruction on four occasions during its charge, repeatedly\\nemphasizing that the indictment was not evidence.\\nJA5765, 5767, 5782, 5880. The Court instructed the jury\\non its duty to base its verdict “solely upon the evidence in\\nthe case.” JA5764. Just before the jury retired to\\ndeliberate, the Court reiterated that the purpose of the\\n\\n\\n 127\\n\\findictment is to set forth the charges, and that it is “merely\\nan accusation.” JA5909.\\n “[J]uries are presumed to follow their instructions\\n. . . .” Richardson v. Marsh, 481 U.S. 200, 211 (1987). In\\nour view, Juror 12’s assertion that the indictment was\\nbeing considered evidence does not, standing alone,\\nestablish that his fellow jurors actually did so. We reject\\nthe notion that the jury, after hearing weeks of testimony\\nand having viewed substantial documentary evidence,\\nwent on to ignore the Court’s limiting instruction\\nconcerning the indictment. 26 Accordingly, we conclude\\n\\n\\n26\\n We acknowledge that our case law provides minimal\\nguidance to district courts concerning the practice of\\nsending an indictment to the jury for their use during\\ndeliberations. We are also aware that some courts have\\ndisapproved the practice of sending the indictment out\\nwith the jury. See United States v. Esso, 684 F.3d 347, 352\\nn.5 (2d Cir. 2012); Roy, 473 F.3d at 1237 n.2. We\\nemphasize that this practice is committed to the sound\\ndiscretion of the district judge. Todaro, 448 F.2d at 66. In\\nour view, such an exercise of a judge’s discretion should\\nbe informed by considering the nature of the case, the\\nnumber of defendants, the length of the indictment, the\\nextent of the factual recitation supporting the criminal\\ncharges, and most importantly, whether the indictment\\n(especially if lengthy and fact-laden) will be useful to the\\njury, in light of the judge’s own carefully tailored jury\\n 128\\n\\fthat the District Court did not abuse its discretion in\\nsending the indictment out to the jury.\\n\\n IX. The District Court’s Evidentiary Rulings\\n Vederman, Nicholas, and Brand each challenge\\nevidentiary rulings by the District Court. We conclude that\\nnone of these contentions warrants setting aside their\\nconvictions.\\n\\n A. The District Court’s Application of Rule 404(b)\\n Vederman argues that the District Court misapplied\\nFederal Rule of Evidence 404(b) when it excluded\\nevidence of Vederman’s prior gift-giving. 27 This Court\\nreviews a district court’s application of Rule 404(b) for\\nabuse of discretion. United States v. Daraio, 445 F.3d 253,\\n\\ninstruction, as supplemented by a verdict slip. See Esso,\\n684 F.3d at 352 n.5.\\n27\\n Although Rule 404(b) determinations are usually in\\nresponse to attempts to introduce “bad” acts evidence,\\nVederman’s attempt to introduce “good” acts of gift-\\ngiving is properly analyzed under the same rule. Ansell v.\\nGreen Acres Contracting Co., 347 F.3d 515, 520 (3d Cir.\\n2003) (“The evidence admitted in this case differs from\\ngarden variety Rule 404(b) matter because it is evidence,\\nnot of a prior bad act in a criminal case, but of a subsequent\\ngood act in a civil case. Nonetheless, this evidence is\\nencompassed by the plain text of Rule 404(b) which\\naddresses ‘other . . . acts,’ not just prior bad acts.”).\\n 129\\n\\f259 (3d Cir. 2006); Ansell v. Green Acres Contracting Co.,\\n347 F.3d 515, 519 (3d Cir. 2003). A trial court commits\\n“[a]n abuse of discretion . . . when [the] district court’s\\ndecision rests upon a clearly erroneous finding of fact, an\\nerrant conclusion of law or an improper application of law\\nto fact.” Pardini v. Allegheny Intermediate Unit, 524 F.3d\\n419, 422 (3d Cir. 2008) (quoting P.N. v. Clementon Bd. of\\nEduc., 442 F.3d 848, 852 (3d Cir. 2006)).\\n\\n Federal Rule of Evidence 404(b) provides in part:\\n (b) Crimes, Wrongs, or Other Acts.\\n\\n (1) Prohibited Uses. Evidence of a\\n crime, wrong, or other act is not\\n admissible to prove a person’s\\n character in order to show that on a\\n particular occasion the person\\n acted in accordance with the\\n character.\\n\\n (2) Permitted Uses; Notice in a\\n Criminal Case. This evidence may\\n be admissible for another purpose,\\n such as proving motive,\\n opportunity, intent, preparation,\\n plan, knowledge, identity, absence\\n of mistake, or lack of accident.\\nFed. R. Evid. 404(b)(1)–(2).\\n\\n 130\\n\\f At trial, Vederman sought to present a witness from\\nAmerican University who would have testified that\\n“Vederman agreed, on more than fifty instances, to\\nfinancially assist students [at American] who needed help\\nwith tuition, book money, or travel funds to visit their\\nfamilies.” Vederman Br. 42 (emphasis omitted).\\nAccording to Vederman, the testimony was relevant to\\nrefuting the Government’s argument that he agreed to\\nguarantee the tuition expenses of Fattah’s au pair as a way\\nof bribing the congressman. In excluding this evidence\\nunder Rule 404(b), the District Court stated at sidebar:\\n\\n I sustain the government’s objection to\\n calling a representative of American\\n University to testify on behalf of Herbert\\n Vederman.\\n\\n In my view the testimony runs afoul of\\n Rule 404(b)(1) of the Federal Rules of\\n Evidence. I find it to be propensity evidence.\\n He or she would be testifying about Mr.\\n Vederman’s financial generosity with respect\\n to students of American University.\\n The issue here is payment of partial\\n tuition of a student at the Philadelphia\\n University. I see no connection between the\\n generosity at American University and the\\n situation with Philadelphia University.\\n\\n\\n 131\\n\\fJA4459–60. Vederman argues that because the proposed\\nevidence related to Vederman’s intent, and not solely his\\npropensity to perform good acts, we should conclude that\\nthe District Court abused its discretion. We see no error in\\nthe District Court’s ruling.\\n\\n Vederman challenges as arbitrary the District\\nCourt’s “assertion that support for American University\\nstudents is too remote from support for Philadelphia\\nUniversity students” such that it constitutes inadmissible\\nevidence. Vederman Reply Br. 23. This distinction was far\\nfrom arbitrary. Vederman may well have financially\\nsupported American University students because of\\nconnections he had to that school or to the D.C.\\ncommunity at large—connections Vederman did not have\\nto Philadelphia University. And the excluded testimony\\nappears to have described support for students Vederman\\ndid not previously know. By supporting Fattah’s au pair,\\nVederman was helping an employee of a man whom he\\nknew quite well. JA889 (“[Fattah and Vederman] spent a\\nlot of time together traveling back and forth to\\nWashington, in the case of a death in the family attending\\ncertain ceremonies that were important, and above all\\nspending time with each other and their families\\ntogether.”). Vederman’s decision to help Fattah’s au pair,\\nwho wished to attend Philadelphia University, seems more\\nlike a departure from, rather than a continuation of, his\\npattern of support for American University students.\\n\\n\\n\\n 132\\n\\f As the party seeking admission of evidence under\\nRule 404(b), Vederman bore “the burden of demonstrating\\nits applicability” and “identifying a proper purpose.”\\nUnited States v. Caldwell, 760 F.3d 267, 276 (3d Cir.\\n2014). By failing to explain sufficiently why the factual\\ndistinctions discussed above were not material, Vederman\\nfailed to meet his burden. In particular, although\\nVederman argues that he offered evidence of his prior gift-\\ngiving to prove intent—“a proper non-propensity\\npurpose”—he failed to show why the proposed testimony\\nwas “relevant to that identified purpose.” Id. at 277. 28 As\\nwe noted in Ansell v. Green Acres Contracting, an\\nemployment discrimination case on which Vederman\\nheavily relies, “[t]here is. . . no bright line rule for\\ndetermining when evidence is too remote to be relevant.”\\n347 F.3d at 525. As such, a district court’s determination\\nunder Rule 404(b) “will not be disturbed on appeal unless\\nit amounts to an abuse of discretion.” Id. The District\\n\\n\\n\\n28\\n Under Rule 404(b), “prior act evidence is inadmissible\\nunless the evidence is (1) offered for a proper non-\\npropensity purpose that is at issue in the case; (2) relevant\\nto that identified purpose; (3) sufficiently probative under\\nRule 403 such that its probative value is not outweighed\\nby any inherent danger of unfair prejudice; and\\n(4) accompanied by a limiting instruction, if requested.”\\nUnited States v. Caldwell, 760 F.3d 267, 277–78 (3d Cir.\\n2014).\\n 133\\n\\fCourt did not abuse its discretion in excluding evidence of\\nVederman’s support for students at American University.\\n\\nB. Evidentiary Rulings Regarding Nicholas’s Defense\\n Nicholas argues that the District Court rendered\\nthree erroneous evidentiary rulings that prejudiced her\\ndefense. We do not find any of her arguments convincing.\\n\\n 1. The EAA Board Minutes\\n In support of its theory that Nicholas defrauded\\nEAA, the Government introduced minutes from EAA’s\\nBoard. Minutes from 2005 revealed that the Board limited\\nNicholas’s signing authority to $100,000. Minutes from\\nDecember 2007, February 2008, and May 2008 failed to\\nreference either the EAA–Solutions contract or the checks,\\ndrawn from EAA’s account for $500,000 and $100,000,\\nthat were purportedly paid pursuant to the contract.\\nNicholas contends that the Board minutes were\\nerroneously admitted because they constituted improper\\nhearsay which failed to satisfy either the exception for\\nbusiness records under Federal Rule of Evidence 803(6)\\nor the absence of records exception under Federal Rule of\\nEvidence 803(7). “We review the District Court’s\\nevidentiary ruling[s] for abuse of discretion, but also\\n‘exercise plenary review . . . to the extent [the rulings] are\\nbased on a legal interpretation of the Federal Rules of\\nEvidence.’ ” Repak, 852 F.3d at 240 (citations omitted)\\n(second alteration in original).\\n\\n 134\\n\\f Applying those standards here,29 we conclude there\\nwas sufficient basis to admit exhibit EAA-48 under\\nFederal Rule of Evidence 803(6) as a business record.\\nAlthough allowing the prosecution to inquire over\\nNicholas’s earlier objection based on Federal Rule of\\nEvidence 803(7) to the absence of any mention of the\\n$500,000 check in the 2008 Board Minutes was error, it\\nwas not reversible error. Other evidence in the record\\noverwhelmingly showed that Nicholas made the $500,000\\nand $100,000 payments to Solutions with the requisite\\nfraudulent intent. That evidence included the 2005 policy\\nlimiting Nicholas’s authority to approve expenditures to\\n$100,000, the accountant’s testimony about the\\ndisbursement policy requiring the completion of a check\\nrequest form for the issuance of a check, and Jones’\\ntestimony that he never saw a request for the $500,000\\ncheck. That evidence, coupled with Nicholas’s tendering\\nof the upfront half-million dollar payment before the terms\\nof the purported agreement had been finalized or executed,\\nher failure to mention the $600,000 in payments to\\nSolutions during her interview with FBI Agent\\n\\n29\\n We note that the argument section of Nicholas’s brief on\\nthis issue specifically cited to the page in the record where\\nexhibit EAA-48 was admitted without objection by any\\ndefense counsel. See Appellant’s Br. at 57 (citing JA4381-\\n82). Nonetheless, there was an earlier objection to the\\nadmission of exhibit EAA-48 that was preserved and that\\nwas referenced in a string citation elsewhere in Nicholas’s\\nbrief.\\n 135\\n\\fDieffenbach, and her alteration of EAA’s general ledger\\nto conceal the $100,000 payment, makes it “highly\\nprobable” that the jury would have reached the same\\nresult. See United States v. Friedman, 658 F.3d 342, 352\\n(3d Cir. 2011).\\n\\n Nicholas also asserts that the Board minutes were\\nunfairly prejudicial. We disagree. Any possible prejudice\\nwas minimized by the fact that the Board minutes make no\\nreference to either the EAA–Solutions contract or to any\\nfinancial matters whatsoever. Indeed, given these lacunae\\nin the Government’s proof, a reasonable factfinder might\\nwell have concluded that the Board’s intention to limit\\nNicholas’s signing authority had not been implemented\\nand that Nicholas had not concealed the contract from the\\nBoard.\\n\\n 2. Jones’ Memory Regarding Other Contracts\\n Nicholas next asserts that the District Court erred\\nduring her cross-examination of Board Chairman Jones by\\nsustaining the prosecution’s objection to her inquiry into\\nwhether he remembered other contracts in excess of\\n$100,000 being brought to the Board. See JA1386–87. The\\nbasis of the prosecution’s objection seemed to be that\\nNicholas’s line of inquiry was beyond the scope of the\\ndirect testimony. JA1387 (“I showed checks concerning\\nwhat’s going on, not other programs.”); see Fed. R. Evid.\\n611(b). The District Court sustained the objection,\\ndeclaring that “it has absolutely nothing to do with this\\ncase.” JA1387. Nicholas contends that if Jones did not\\n 136\\n\\frecall whether other large contracts had been presented to\\nthe Board, his inability to recall the EAA–Solutions\\ncontract would have been “unremarkable rather than\\nevidence of fraud or concealment.” Nicholas Br. 61.\\n\\n We acknowledge that whether Jones remembered\\nother large contracts requiring Board approval had some\\nrelevance under Rule 401. Yet any error by the District\\nCourt in prohibiting Nicholas’s counsel from pursuing this\\nline of inquiry is harmless. Jones admitted that he did not\\nknow if the Board ever implemented the policy requiring\\nits approval of contracts exceeding $100,000. He also\\nconceded that the EAA Board focused less on the financial\\nside of EAA than on its programs. JA1383–85. Nicholas\\ncould not have been prejudiced by the District Court’s\\nruling.\\n\\n 3. Exclusion of NOAA Evidence\\n Nicholas defended against the criminal charges\\narising out of the non-existent October 2012 conference\\nby asserting that she acted in “good faith in spending the\\nNOAA funds on EAA expenses,” Nicholas Br. 64, that the\\ndifference in the dates in the paperwork was not material,\\nand that NOAA had received the benefits of the\\nsponsorship because its logo was displayed on the signage\\nused at the February conference. Nicholas succeeded in\\npresenting testimony and introducing photographs that\\nshowed NOAA’s logo on the February 2012 annual\\nconference bags, padfolios, and name tags. The Court\\nexcluded a photograph of a NOAA intern at the February\\n 137\\n\\f2012 conference, other photographs of the February\\nconference signage, and some checks that pertained to the\\nFebruary conference. Nicholas claims that her inability to\\nintroduce those exhibits frustrated her ability to present\\nher good faith defense. We are not persuaded.\\n\\n The photographs were excluded as cumulative, the\\nsort of ruling to which we afford trial judges very broad\\ndiscretion. See Fed. R. Evid. 403; United States v.\\nDalfonso, 707 F.2d 757, 762 (3d Cir. 1983). It was not\\nerror to exclude the student intern’s photograph. The\\nconference brochure included photographs from previous\\nconferences, and the witness from NOAA was unable to\\ntestify to the year the student served as an intern. Finally,\\nthe checks tendered for the travel expenses incurred for the\\nFebruary conference were excluded as irrelevant to\\nwhether Nicholas had a good faith belief that NOAA\\nsponsored the October conference.\\n\\nC. The Cooperating Witness’s Mental Health Records\\n During discovery, Brand learned that a cooperating\\nwitness was diagnosed with bipolar II disorder and was\\ntaking medication to treat that condition. Brand\\nsubpoenaed mental health records kept by the witness’s\\ncurrent and former psychiatrists in hopes of using those\\nrecords to attack the witness’s memory, truthfulness, and\\ncredibility. The witness and the Government both filed\\nmotions to quash the subpoena, arguing that the witness’s\\nmental health records were protected by the\\npsychotherapist–patient privilege recognized by the\\n 138\\n\\fSupreme Court in Jaffee v. Redmond, 518 U.S. 1 (1996).\\nThe Government also filed a motion in limine seeking to\\nrestrict the scope of cross-examination to prevent Brand\\nfrom questioning the witness about his mental health.\\n\\n Alongside his motion to quash, the witness\\nvoluntarily produced for the Court his mental health\\nrecords. The Court concluded that the psychotherapist–\\npatient privilege would ordinarily apply to the mental\\nhealth records, but that the privilege was not absolute,\\nespecially when invoked in response to a criminal\\ndefendant’s efforts to obtain through discovery evidence\\nthat is favorable to his case. Following the procedure set\\nforth in Pennsylvania v. Ritchie, 480 U.S. 39 (1987), the\\nDistrict Court conducted an in camera review of the\\nmental health records to determine if they contained\\nmaterial evidence—that is, evidence that would “give[]\\nrise to a reasonable probability that it [would] affect the\\noutcome of the case.” JA149. The District Court found\\n“nothing in the mental health records of the [witness] . . .\\nmaterial for this criminal action,” noting that “[t]he\\nrecords reveal nothing that calls into question [the\\nwitness’s] memory, perception, competence, or veracity.”\\nJA150. Accordingly, the Court entered an order granting\\nthe motions to quash the subpoena.\\n The District Court also granted the Government’s\\nmotion in limine and restricted the scope of cross-\\nexamination, ruling that “no reference may be made to [the\\nwitness’s] bipolar disorder or the medications he takes to\\n\\n 139\\n\\fmanage it.” JA142, 156. The Court reasoned that bipolar\\ndisorder varied in its effects from person to person, and\\nconcluded that Brand had not shown that the effects of the\\ndisorder had any bearing on the witness’s credibility. The\\nDistrict Court ruled that cross-examination would not\\nserve any valid impeachment purpose.\\n Brand claims that the District Court’s order ran\\nafoul of the Due Process Clause of the Fifth Amendment\\nand the Confrontation Clause of the Sixth Amendment.\\nWe review a district court’s rulings to quash a subpoena\\nand to limit the scope of cross-examination for abuse of\\ndiscretion. United States v. Tykarsky, 446 F.3d 458, 475\\n(3d Cir. 2006); NLRB v. Frazier, 966 F.2d 812, 815 (3d\\nCir. 1992). Here, the District Court did not abuse that\\ndiscretion.\\n\\n1. The District Court’s Denial of Access to the Mental\\n Health Records\\n In claiming that the District Court’s decision to\\nreview the mental health records in camera before ruling\\non their admissibility violated his rights under both the\\nFifth and Sixth Amendments, Brand specifically argues\\nthat his right to confront the witness was impeded because\\nhe was denied access to records he could have used to\\nimpeach the witness. This very argument was considered\\nand rejected by a plurality of the Supreme Court in Ritchie,\\nwhich noted that “the effect [of the argument] would be to\\ntransform the Confrontation Clause into a constitutionally\\ncompelled rule of pretrial discovery. . . . [T]he right to\\n 140\\n\\fconfrontation is a trial right, designed to prevent improper\\nrestrictions on the types of questions that defense counsel\\nmay ask during cross-examination.” 480 U.S. at 52. We\\nfollow the Ritchie plurality, and conclude that the\\nConfrontation Clause did not require the District Court to\\ngrant Brand access to the witness’s mental health records.\\n Brand next challenges the District Court’s decision\\nto quash the subpoena as a violation of the Fifth\\nAmendment’s Due Process Clause. He concedes that\\nRitchie’s Due Process holding allowed the District Court\\nto review the mental health records in camera without\\ndisclosing them to him. See id. at 59–60 (“A defendant’s\\nright to discover exculpatory evidence does not include the\\nunsupervised authority to search through [the\\nGovernment’s] files. . . . We find that [the defendant’s]\\ninterest . . . in ensuring a fair trial can be protected fully by\\nrequiring that the [privileged] files be submitted only to\\nthe trial court for in camera review.”). Brand instead\\nargues that the District Court abused its discretion by\\nfocusing on “irrelevant facts and spurious symptoms. . . .\\nsuch as ‘hallucinations,’ ” and by “refus[ing] to consider\\nevidence of cognitive impairment and memory issues.”\\nBrand Br. 30. The record reveals, however, that the\\nDistrict Court reviewed the mental health records and\\ndetermined that they “reveal[ed] nothing that calls into\\nquestion [the witness’s] memory, perception, competence,\\nor veracity.” JA150. This hardly amounts to a refusal to\\nconsider evidence of cognitive impairment or memory\\nissues.\\n 141\\n\\f Brand also challenges the legal standard applied by\\nthe District Court, arguing that the court “focused solely\\non whether disclosure would ‘change the outcome’ of\\nBrand’s trial,” Brand Br. 29 (quoting JA148), rather than\\nconsidering “whether the ultimate verdict is one ‘worthy\\nof confidence.’ ” Id. (quoting United States v. Robinson,\\n583 F.3d 1265, 1270 (10th Cir. 2009)). Brand\\nmisleadingly quotes from the District Court’s opinion. The\\nDistrict Court considered, in accordance with Ritchie,\\n“whether there is a reasonable probability that disclosure\\nwould change the outcome” of Brand’s trial, JA148\\n(emphasis added), not whether disclosure would\\nnecessarily change the outcome. As articulated in Ritchie,\\na “ ‘reasonable probability’ is a probability sufficient to\\nundermine confidence in the outcome.” 480 U.S. at 57\\n(quoting United States v. Bagley, 473 U.S. 667, 682 (1985)\\n(Blackmun, J.)). The District Court applied the correct\\nstandard.\\n\\n2. The District Court’s Grant of the Motion in Limine\\n In granting the Government’s motion in limine, the\\nDistrict Court ruled that Brand could not “reference . . .\\n[the witness’s] bipolar disorder or the medications he takes\\nto manage it.” JA156. Yet that ruling placed no restriction\\non Brand’s ability to cross-examine the witness with\\nrespect to “his memory, competence, or truthfulness.” Id.\\nBrand argues, nevertheless, that his Sixth Amendment\\nright “to be confronted with the witnesses against him”\\nwas violated. U.S. Const. amend. VI.\\n\\n 142\\n\\f The Confrontation Clause protects a defendant’s\\nright to cross-examine a witness with respect to any\\ntestimonial statements made by that witness. United States\\nv. Berrios, 676 F.3d 118, 125–26 (3d Cir. 2012) (citing\\nCrawford v. Washington, 541 U.S. 36, 51 (2004), and\\nDavis v. Washington, 547 U.S. 813, 823–24 (2006)). But\\nthe scope of cross-examination is not unlimited, and “[a]\\ndistrict court retains ‘wide latitude insofar as the\\nConfrontation Clause is concerned to impose reasonable\\nlimits on such cross-examination based on concerns about\\n. . . harassment, prejudice, confusion of the issues, the\\nwitness’ safety, or interrogation that is repetitive or only\\nmarginally relevant.’ ” John-Baptiste, 747 F.3d at 211\\n(quoting United States v. Mussare, 405 F.3d 161, 169 (3d\\nCir. 2005)). We review limitations on cross-examination\\nfor abuse of discretion, and reverse “only when the\\nrestriction ‘is so severe as to constitute a denial of the\\ndefendant’s right to confront witnesses against him and . . .\\nis prejudicial to [his] substantial rights.’ ” Id. (alternation\\nin original) (quoting United States v. Conley, 92 F.3d 157,\\n169 (3d Cir. 1996)).\\n In United States v. Chandler, 326 F.3d 210, 219 (3d\\nCir. 2003), we analyzed whether a district court’s decision\\nto limit cross-examination with respect to a witness’s\\nmotivation for testifying violated the Confrontation\\nClause. See also Mussare, 405 F.3d at 169; John-Baptiste,\\n747 F.3d at 211–12. Consistent with Delaware v. Van\\nArsdall, 475 U.S. 673 (1986), we first concluded that “the\\nexposure of a witness’ motivation in testifying is a proper\\n 143\\n\\fand important function of the constitutionally protected\\nright of cross-examination.” Chandler, 326 F.3d at 219–\\n20 (quoting Van Arsdall, 475 U.S. at 678–79). We also\\nnoted that the Confrontation Clause does not prevent a trial\\njudge from imposing reasonable limits on cross-\\nexamination. Id. In reviewing a district judge’s imposition\\nof such limitations, we apply a two-part analysis. As we\\nhave since described, “we inquire into: ‘(1) whether the\\nlimitation significantly limited the defendant’s right to\\ninquire into a witness’s motivation for testifying; and\\n(2) whether the constraints imposed fell within the\\nreasonable limits that a district court has the authority to\\nimpose.’ ” John-Baptiste, 747 F.3d at 211–12 (quoting\\nMussare, 405 F.3d at 169).\\n The same analytical framework is appropriate when\\ndetermining whether a restriction on the cross-\\nexamination of a witness with respect to his memory and\\nperception violates the Confrontation Clause. See Davis v.\\nAlaska, 415 U.S. 308, 316 (1974); Greene v. McElroy, 360\\nU.S. 474, 496 (1959); United States v. Segal, 534 F.2d\\n578, 582 (3d Cir. 1976). Memory and perception, like\\nmotivation for testifying, are central issues affecting the\\ncredibility of any witness, and unreasonable limitations on\\nthe right to cross-examine on those subjects cannot be\\ncountenanced. We therefore ask, paraphrasing Chandler:\\n(1) whether the District Court’s decision to put the\\nwitness’s diagnosis and medications off limits\\nsignificantly impaired Brand’s right to inquire into the\\nwitness’s memory and perception; and (2) whether the\\n 144\\n\\fruling fell within the reasonable limits that the District\\nCourt has the authority to impose.\\n We conclude that the District Court did not err. As\\nan initial matter, the District Court permitted Brand to\\ncross-examine the witness about his memory and\\nperception, and limited cross-examination only with\\nrespect to the witness’s bipolar disorder and the\\nmedications he was taking to treat that condition. Brand\\nwas free to question the witness about his memory and\\nperception, and indeed did so. The restriction on asking\\nthe witness about his bipolar disorder was not a significant\\nlimitation of Brand’s right to inquire into the witness’s\\nmemory or perception. Moreover, as the District Court\\npointed out, Brand failed to show how inquiry into the\\nwitness’s bipolar disorder would be useful for\\nimpeachment purposes. See JA154.\\n\\n Given that failure, the District Court’s limits on\\ncross-examination were reasonable. The Court concluded,\\nafter reviewing the evidence submitted by Brand and the\\nwitness’s mental health records, that any mention of the\\nwitness’s bipolar disorder would “only be designed to\\nconfuse the jury or to stigmatize him unfairly because of a\\n‘mental problem’ without any countervailing probative\\nvalue.” JA155. The District Court did not abuse its\\ndiscretion in limiting Brand’s cross-examination on a topic\\nthat would be far more prejudicial than probative. See\\nTykarsky, 446 F.3d at 476–77 (“[T]he District Court acted\\n\\n\\n 145\\n\\fwell within its discretion to restrict irrelevant and\\nconfusing testimony.”).\\n All of this is not to suggest that a witness’s mental\\nhealth is always off limits. The appropriate course in any\\ngiven case must be determined from the facts and\\ncircumstances surrounding that case and the witness’s\\nparticular condition. See United States v. George, 532 F.3d\\n933, 937 (D.C. Cir. 2008) (“The days are long past when\\nany mental illness was presumed to undermine a witness’s\\ncompetence to testify. . . . [M]ental illness [is] potentially\\nrelevant in a broad[] range of circumstances . . . . [But]\\nsome indication is needed that a particular witness’s\\nmedical history throws some doubt on the witness’s\\ncompetence or credibility.”). Here, Brand failed to show,\\nthrough mental health records or otherwise, any\\nparticularized reason to doubt the credibility of the witness\\nfor medical reasons.\\n\\n Brand states that the witness provided “the only\\nevidence offered” on the intent element of his conspiracy\\nconviction and that he should therefore be entitled to\\nunrestricted cross-examination. Brand Br. 12 n.3. Yet no\\nmatter the importance of a witness to any party, a district\\ncourt may always place reasonable limits on cross-\\nexamination to avoid “harassment, prejudice, confusion of\\nthe issues, the witness’ safety, or interrogation that is\\nrepetitive or only marginally relevant.” John-Baptiste, 747\\nF.3d at 211 (citation omitted).\\n\\n\\n 146\\n\\f We conclude that the District Court did not abuse\\nits discretion in restricting the scope of Brand’s cross-\\nexamination of the cooperating witness.\\n\\n X. The Government’s Cross-Appeal\\n The jury convicted Fattah, Vederman, and Bowser\\nof bank fraud, 18 U.S.C. § 134430 (Count 19) and making\\nfalse statements to a financial institution, 18 U.S.C.\\n§ 1014 31 (Count 20). In response to post-trial motions, the\\nDistrict Court granted a judgment of acquittal on both\\ncounts under Fed. R. Crim. P. 29, concluding that the\\n\\n30\\n “Whoever knowingly executes, or attempts to execute,\\na scheme or artifice . . . to defraud a financial institution\\n. . . shall be fined not more than $1,000,000 or imprisoned\\nnot more than 30 years, or both.” The definition of\\n“financial institution” for purposes of § 1344 is set forth at\\n18 U.S.C. § 20, and includes “a credit union with accounts\\ninsured by the National Credit Union Share Insurance\\nFund” and “a mortgage lending business (as defined in\\nsection 27 of this Title).” 18 U.S.C. §§ 20(2), (10).\\n31\\n “Whoever knowingly makes any false statement or\\nreport, or willfully overvalues any land, property or\\nsecurity, for the purpose of influencing in any way the\\naction of . . . a Federal credit union . . . any institution the\\naccounts of which are insured by . . . the National Credit\\nUnion Administration Board . . . or a mortgage lending\\nbusiness . . . shall be fined not more than $1,000,000 or\\nimprisoned not more than 30 years, or both.”\\n 147\\n\\fevidence was insufficient to establish that the Credit\\nUnion Mortgage Association (CUMA), the entity to whom\\nFattah, Vederman, and Bowser made the false statements,\\nis a “financial institution,” or, more specifically, a\\n“mortgage lending business” as defined in 18 U.S.C. § 27.\\nThe Government claims that, viewing the evidence in the\\nlight most favorable to it, the District Court erred and that\\nCUMA is, indeed, a “mortgage lending business.” We\\nagree. Because the evidence is sufficient to support the\\njury’s verdict, we will remand so Fattah and Vederman\\nmay be resentenced on these charges.32\\n\\n A. CUMA is a Mortgage Lending Business\\n In reviewing the District Court’s post-verdict\\njudgment of acquittal under Rule 29 of the Federal Rules\\nof Civil Procedure, we consider whether the evidence,\\nwhen viewed in a light most favorable to the government,\\nsupports the jury’s verdict. United States v. Dixon, 658\\nF.2d 181, 188 (3d Cir. 1981). Our standard of review is the\\nsame as that applied by the District Court, and we must\\nuphold the jury’s verdict unless no reasonable juror could\\naccept the evidence as sufficient to support the defendant’s\\nguilt beyond a reasonable doubt. United States v.\\nColeman, 811 F.2d 804, 807 (3d Cir. 1987).\\n\\n32\\n Because the Government did not file an appeal as to\\nBowser, the cross-appeal is limited to Fattah and\\nVederman. The judgment of acquittal as to Bowser is\\ntherefore unaffected by our ruling today.\\n 148\\n\\f Initially, the grand jury’s indictment alleged that\\nCUMA is a financial institution because it is federally\\ninsured. JA302–03. At trial, however, the jury was\\ninstructed that CUMA could qualify as a financial\\ninstitution either because it is federally insured or because\\nit is a “mortgage lending business.” See JA111, 401–02. A\\n“mortgage lending business” is “an organization which\\nfinances or refinances any debt secured by an interest in\\nreal estate, including private mortgage companies and any\\nsubsidiaries of such organizations, and whose activities\\naffect interstate or foreign commerce.” 18 U.S.C. § 27.\\n\\n At trial, CUMA’s president and CEO, Eddie Scott\\nToler, testified that CUMA is not federally insured.\\nJA4235. The Government therefore attempted to prove\\nthat CUMA is a “mortgage lending business” by\\npresenting evidence that CUMA funds mortgages and then\\nsells them in a secondary market.\\n\\n Toler also testified that CUMA is a “credit union\\nservice organization”—a for-profit company owned by 48\\ncredit unions, which serves small credit unions that do not\\nhave the infrastructure or in-house expertise to handle\\nmortgage loans themselves. JA4235. According to Toler,\\n“[CUMA] exclusively provide[s] First Trust Residential\\nMortgage loaning [sic] services, all the way from the\\norigination of the mortgage loan through processing,\\nunderwriting, closing and access to the secondary market\\nwhere—and we’re selling the mortgage loan on the\\nsecondary market.” JA4236–37. In jurisdictions in which\\n\\n 149\\n\\fCUMA is licensed, 33 CUMA holds the mortgage for a\\nlimited period, generally from two to thirty days, and then\\nsells the mortgage either to a partner credit union or on the\\nsecondary market. JA4240.\\n\\n The District Court concluded that CUMA is not a\\n“mortgage lending business” because “[t]he record is\\ndevoid of any evidence that CUMA finances or refinances\\nany debt.” JA113. Concluding that CUMA “simply is a\\nloan processor for various credit unions which do the\\nfinancing or refinancing,” id., the District Court ruled that\\nCUMA’s “activity does not constitute the financing or\\nrefinancing of any debt. CUMA is not the mortgagee. It is\\nmerely selling the debt instrument to a third party.” JA114.\\n We cannot agree with the District Court’s view of\\nthe evidence. Toler testified that in “Maryland, D.C., and\\nVirginia . . . all of the loans are closed in the name of\\nCUMA.” JA4238–39. As Toler described it, CUMA\\nborrows on a line of credit to fund the loan, and when the\\nloan is sold, CUMA pays off its line of credit. JA4239–40.\\nSo contrary to the District Court’s assessment, the\\nevidence, viewed in a light most favorable to the\\nGovernment, shows that CUMA is indeed the\\nmortgagee—at least during the time from closing until the\\nloan is sold to a partner credit union or on the secondary\\nmarket. The fact that CUMA funds the closing and then\\n\\n33\\n CUMA is licensed in Maryland, Washington, D.C., and\\nVirginia. JA4238.\\n 150\\n\\fholds the mortgage, even for a brief time, is sufficient to\\nsupport a conclusion that CUMA is “an organization\\nwhich finances or refinances any debt secured by an\\ninterest in real estate.” 18 U.S.C. § 27.\\n\\n Fattah and Vederman attempt to refute the argument\\nthat CUMA engages in financing mortgages by focusing\\non Toler’s testimony that CUMA “doesn’t actually have\\nany money to fund these mortgage loans.” JA4239; see\\nFattah Reply Br. 38, Vederman Reply Br. 36. But Toler\\ntestified that CUMA employs a credit line to borrow the\\nfunds necessary to close on mortgages. See JA4239. That\\nCUMA incurs debt to finance mortgages hardly\\nundermines a conclusion that CUMA finances mortgages.\\nIndeed, it is the very nature of modern banking that\\nfinancial institutions do not hold cash reserves equal to the\\nfull amount of their liabilities. See, e.g., Timothy C.\\nHarker, Bailment Ailment: An Analysis of the Legal Status\\nof Ordinary Demand Deposits in the Shadow of the\\nFinancial Crisis of 2008, 19 Fordham J. Corp. & Fin. L.\\n543, 561 (2014) (“[F]ractional reserve banking . . . is the\\nde facto standard for all modern banks.”).\\n\\n Vederman also argues that, even if CUMA acts as a\\nmortgage lending business in some transactions, it was not\\nacting as a mortgage lending business in this transaction.\\nVederman points to Toler’s testimony that, in a state in\\nwhich CUMA is not licensed, the mortgage is closed in the\\nname of a credit union. In such cases, the credit union, and\\nnot CUMA, owns the mortgage for the short period before\\n\\n 151\\n\\fthe loan is sold on the secondary market. JA4241. CUMA\\nis not licensed in the Commonwealth of Pennsylvania. See\\nid. Thus, according to Vederman, CUMA was acting in its\\ncapacity as a mortgage servicing company for Fattah’s\\nvacation home purchase and did not—and could not—\\nfinance Fattah’s mortgage. That would mean that CUMA\\ncould not have been a victim of a crime against a financial\\ninstitution in this instance: “When an entity is not\\nfunctioning as a mortgage lender, the ‘pertinent federal\\ninterest’ behind the statutes is not implicated.” Vederman\\nReply Br. 38 (citation omitted).\\n\\n The Government responds that neither of the\\nstatutes of conviction requires that the fraud or false\\nstatement occur in connection with the same transaction\\nthat places the entity within the definition of “financial\\ninstitution.” Gov’t Fourth Step Br. 4. We agree with the\\nGovernment.\\n\\n Both § 1344 and § 1014 protect entities that fall\\nwithin the definition of “financial institution” and are\\notherwise quite broad in their application. See Loughrin v.\\nUnited States, 134 S. Ct. 2384, 2389 (2014) (interpreting\\n§ 1344 as not requiring specific intent to defraud a bank);\\nUnited States v. Boren, 278 F.3d 911, 914 (9th Cir. 2002)\\n(“[Section 1014’s] reach is not limited to false statements\\nmade with regard to loans, but extends to any application,\\ncommitment or other specified transaction.”). Neither\\nstatute is expressly limited in the manner that Vederman\\nsuggests. Williams v. United States, 458 U.S. 279, 284\\n\\n 152\\n\\f(1982) (“To obtain a conviction under § 1014, the\\nGovernment must establish two propositions: it must\\ndemonstrate (1) that the defendant made a ‘false statement\\nor report,’ . . . and (2) that he did so ‘for the purpose of\\ninfluencing in any way the action of [a described financial\\ninstitution] upon any application, advance, . . .\\ncommitment, or loan.’ ”); United States v. Leahy, 445 F.3d\\n634, 646 (3d Cir. 2006) (“The purpose of the bank fraud\\nstatute is to protect the ‘financial integrity of [banking]\\ninstitutions.’ ”) (citing S. Rep. No. 98-225, at 377 (1983),\\nas reprinted in 1984 U.S.C.C.A.N. 3517), abrogated on\\nother grounds by Loughrin, 134 S. Ct. at 2389.\\n In support of his position, Vederman relies on\\nUnited States v. Devoll, 39 F.3d 575 (5th Cir. 1994), in\\nwhich the Fifth Circuit concluded that § 1014 (false\\nstatements to a financial institution) is not intended to\\ncapture fraud unrelated to an entity’s lending activities,\\nand therefore held that it “applies only to actions involving\\nlending transactions.” Id. at 580. The Fifth Circuit stated:\\n [W]e are not persuaded that the statute\\n imposes liability whenever a defendant’s\\n false statement was intended to interfere with\\n any activity of a financial institution; such a\\n broad interpretation of section 1014\\n presumably would encompass fraud or false\\n representations having nothing to do with\\n financial transactions, such as fraud in an\\n employment contract or, for example, in a\\n\\n 153\\n\\f contract to provide goods or services for\\n custodial care, premises repair, or renovation.\\nId.\\n\\n Yet a majority of circuits, including our own, have\\ndeclined to follow Devoll’s suggestion that § 1014 is\\nrestricted to lending transactions. As the Ninth Circuit has\\nheld, “we join at least six of our sister circuits—the First,\\nThird, Fourth, Sixth, Seventh, and Tenth—in holding that\\n18 U.S.C. § 1014 is not limited to lending transactions,\\nand reject the minority rule to the contrary.” Boren, 278\\nF.3d at 915. And even if we were to adopt Devoll’s narrow\\nconstruction of § 1014 to lending transactions, that would\\nnot resolve the more specific question of whether the\\ndefrauded entity must be defined as a “mortgage lending\\nbusiness” by virtue of the specific transaction in which the\\nfalse statements arose.\\n Recently, the Eighth Circuit addressed precisely\\nthis issue. In United States v. Springer, 866 F.3d 949 (8th\\nCir. 2017), that Court considered the defendant’s appeal\\nfrom the district court’s denial of a Rule 29 motion on\\ngrounds that GMAC, the entity defrauded, was not a\\n“financial institution.” The Court upheld the district\\ncourt’s determination that the evidence was sufficient to\\nestablish that GMAC is in the mortgage lending business\\nbecause there was testimony that “it had made hundreds or\\nthousands of loans secured by mortgages in 2010 and 2011\\nin states all across the country,” which established that its\\nactivities affect interstate commerce. Id. at 953. It was not\\n 154\\n\\fdeterminative that GMAC did not own the specific loan at\\nissue in the case: “we discern no requirement in the\\ndefinition of ‘mortgage lending business’ that the business\\nown the particular loan in question; it need only finance or\\nrefinance any debt secured by an interest in real estate, or,\\nin other words, be in the interstate mortgage lending\\nbusiness in general.” Id.\\n\\n In our view, the Eighth Circuit’s analysis is correct.\\nWe therefore adopt that Court’s reasoning in Springer and\\nconclude that it is of no moment that CUMA did not\\nfinance the mortgage at issue in Fattah’s case. CUMA is a\\n“mortgage lending business,” and that alone suffices to\\nsupport the convictions under §§ 1014 and 1344.\\n\\n B. Sufficiency of the Evidence\\n Finally, Vederman argues that, even if CUMA is a\\nfinancial institution, the judgment of acquittal should\\nstand because the Government did not put forth any\\nevidence that he made a false representation to CUMA.34\\nSpecifically, Vederman argues that the title to the Porsche\\nwas actually changed to his name, making it a “true sale”\\nas a matter of law, without regard to whether Fattah’s wife\\n\\n34\\n Although Vederman presented this argument in his Rule\\n29 motion, the District Court did not need to reach it in the\\ncontext of Counts 19 and 20 because the Court granted the\\nmotion on the ground that CUMA is not a financial\\ninstitution. The District Court rejected the argument as to\\nCounts 16, 17, and 18. See JA100–02.\\n 155\\n\\fcontinued to retain possession. See United States v.\\nCastro, 704 F.3d 125, 139 (3d Cir. 2013) (holding in\\nanother context that “the government must be able to show\\nthat [the defendant] made a statement to government\\nagents that was untrue, and the government cannot satisfy\\nthat burden by showing that the defendant intended to\\ndeceive, if in fact he told the literal truth”); see also 75 Pa.\\nCons. Stat. § 102 (defining “owner” as “[a] person, other\\nthan a lienholder, having the property right in or title to a\\nvehicle”).\\n\\n The Government responds that, regardless of\\nwhether it is legally possible for one person to hold a title\\nwhile a different person possesses the vehicle, the jury was\\npermitted to consider all the circumstances in deciding\\nwhether the Porsche sale was a sham. We agree.\\n\\n First, as the District Court observed, it was unclear\\nas to whether the title had been properly executed under\\nPennsylvania law. For instance, Fattah’s wife never\\nappeared before a notary. 35 JA101. In addition, title 75,\\nsection 1111(a) of the Pennsylvania Consolidated Statutes\\nrequires that, “[i]n the event of the sale or transfer of the\\nownership of a vehicle within this Commonwealth, the\\nowner shall . . . deliver the certificate to the transferee at\\n\\n35\\n Vederman argues that it is of no significance that the\\nparties did not appear before a notary as the statute\\nrequires, but he offers cases only from states other than\\nPennsylvania to support this proposition.\\n 156\\n\\fthe time of the delivery of the vehicle.” And, the transferee\\nmust, within twenty days of the assignment of the vehicle,\\napply for a new title. See 75 Pa. Cons. Stat. § 1111(b).\\nNeither of these requirements was fulfilled. Finally,\\nVederman never registered the Porsche in his name with\\nthe Department of Motor Vehicles. See id.; JA4254.\\n Second, and more importantly, even if the title had\\nbeen properly transferred to Vederman, the title provisions\\nof the Pennsylvania Motor Vehicle Code “were [not]\\ndesigned to establish conclusively the ownership of an\\nautomobile.” Weigelt v. Factors Credit Corp., 101 A.2d\\n404, 404 (Pa. Super. Ct. 1953). Indeed, “[t]he purpose of\\na certificate of title is not to conclusively establish\\nownership in a motor vehicle, but rather to establish the\\nperson entitled to possession.” Speck Cadillac-Olds, Inc.\\nv. Goodman, 95 A.2d 191, 193 (Pa. 1953). Thus, a title\\nprovides evidence of ownership; it is not dispositive of the\\nissue. Wasilko v. Home Mut. Cas. Co., 232 A.2d 60, 61\\n(Pa. Super. Ct. 1967).\\n Vederman’s argument that the title in his name\\nconstitutes conclusive evidence of ownership rests upon\\nan erroneous conclusion that the jury was prohibited from\\nconsidering all the circumstances of the transfer. As the\\nDistrict Court observed, though, Pennsylvania’s\\nCommonwealth Court has held that “[w]hether a\\ntransferor has transferred ownership of a motor vehicle to\\na transferee is a factual determination to be made by the\\ncourt below.” Dep’t. of Transp. v. Walker, 584 A.2d 1080,\\n\\n 157\\n\\f1082 (Pa. Commw. Ct. 1990). Thus, the signed certificate\\nof title was appropriately treated as one piece of evidence\\nfor the jury to consider in assessing the validity of the\\nvehicle transfer. Considered in the light most favorable to\\nthe Government, the totality of the evidence is sufficient\\nto support the jury’s conclusion that the Porsche sale was\\na sham.\\n\\n XI. Prejudicial Spillover\\n Finally, Fattah, Vederman, Nicholas, and Brand\\neach contend that their convictions on various counts\\nresulted from prejudicial spillover. We are not persuaded.\\n We exercise plenary review over a district court’s\\ndenial of a claim of prejudicial spillover, United States v.\\nLee, 612 F.3d 170, 178–79 (3d Cir. 2010), and we apply a\\ntwo-step test when reviewing such a claim. United States\\nv. Wright, 665 F.3d 560, 575 (3d Cir. 2002). First, a court\\nmust consider “whether the jury heard evidence that would\\nhave been inadmissible at a trial limited to the remaining\\nvalid count[s].” Id. (quoting United States v. Cross, 308\\nF.3d 308, 317 (3d Cir. 2002)). The second step requires\\nthat we “ask whether that evidence (the ‘spillover\\nevidence’) was prejudicial.” Id. We consider four factors:\\n“whether (1) the charges are intertwined with each other;\\n(2) the evidence for the remaining counts is sufficiently\\ndistinct to support the verdict on these counts; (3) the\\nelimination of the invalid count [will] significantly\\nchange[] the strategy of the trial; and (4) the prosecution\\nused language of the sort to arouse a jury.” Id. (quoting\\n 158\\n\\fUnited States v. Murphy, 323 F.3d 102, 118 (3d Cir.\\n2003)); see also United States v. Pelullo (Pellulo II), 14\\nF.3d 881, 898–99 (3d. Cir. 1994). These four factors are\\nconsidered in a light “somewhat favorable to the\\ndefendant.” Wright, 665 F.3d at 575 (quoting Murphy, 323\\nF.3d at 122); see also Gov’t Br. 198 (same).\\n\\n A. Fattah’s Claim of Prejudicial Spillover\\n Fattah argues that he suffered prejudicial spillover\\non the remaining counts of conviction in light of (1)\\nevidence pertinent to the alleged Vederman bribery\\nschemes that is now arguably inadmissible under\\nMcDonnell; and (2) “the government’s flawed RICO\\nconspiracy theory.” Fattah Br. 50, 64. Fattah’s argument\\nis undercut substantially because of our determination that\\nMcDonnell requires a new trial for Counts 16, 17, 22, and\\n23 and our decision to affirm the RICO conspiracy\\nconviction. The only possible spillover left to consider is\\nthe evidence pertaining to Fattah’s arranging a meeting\\nbetween Vederman and the U.S. Trade Representative,\\nRon Kirk, which in light of McDonnell is now arguably\\ninadmissible.36\\n\\n The evidence of the Kirk meeting admitted during\\nthis five-week trial was limited. Although this evidence\\n\\n36\\n Nothing in this opinion is intended to foreclose the\\npossibility that evidence of the Kirk meeting may be\\nadmissible on retrial for some purpose other than as proof\\nof an official act.\\n 159\\n\\fwas part of the Government’s proof as to both the RICO\\nand the bribery related charges, there is more than\\nsufficient—and distinct —evidence to support Fattah’s\\nconviction on all the other counts. In our view, eliminating\\nany evidence of the Kirk meeting would not have altered\\nthe strategy of the trial, nor should it significantly change\\nthe strategy for any new trial that may be held. Because\\nFattah has not pointed us to any argument by the\\nprosecution relating to this meeting that could have\\ninflamed the jury, we conclude that Fattah’s prejudicial\\nspillover claim fails. Like the District Court, we presume\\nthat the jury followed the Court’s instructions to consider\\nand weigh separately the evidence on each count as to each\\ndefendant and not to be swayed by evidence pertaining to\\nother defendants. 37\\n\\n B. Vederman’s Assertion of Prejudicial Spillover\\n Because the District Court acquitted Vederman of\\nthe RICO charge, Vederman argues that he was “severely\\nprejudiced by the presentation to the jury of a legally\\nflawed racketeering conspiracy charge,” and as a\\nconsequence his bribery and money laundering\\n\\n37\\n We likewise reject Brand’s prejudicial spillover\\narguments. See Brand Br. 6 (“Brand adopts the significant\\nissue advanced by his co-appellant pursuant to Fed. R.\\nApp. P. 28(i) that improper jury instructions and the\\nresulting spillover of related improperly admitted\\nevidence and argument unfairly prejudiced Brand.”).\\n 160\\n\\fconvictions should be overturned. Vederman Br. 46. In\\nresponse to the Government’s appeal of the District\\nCourt’s Rule 29 acquittal on Counts 19–20 involving\\nCUMA, Vederman asserts that these two counts also were\\naffected by spillover evidence because the Government’s\\ntheory tied the bribery charges to the actions taken to\\ndefraud CUMA. In that we are vacating Vederman’s\\nconvictions of Counts 16–18 and 22–23 based on\\nMcDonnell and remanding for further proceedings, we\\nneed address only Vederman’s argument of prejudicial\\nspillover as it relates to the charges involving CUMA in\\nCounts 19–20, charges that we will reinstate.\\n The District Court’s acquittal of Vederman on the\\nRICO count establishes that step one of the Wright\\nspillover test has been met. “[T]he jury heard evidence that\\nwould have been inadmissible at a trial limited” to the\\nbribery and CUMA-related counts. Wright, 665 F.3d at\\n575 (quoting Cross, 308 F.3d at 317).\\n\\n Wright’s second step requires “ask[ing] whether\\nthat evidence (the ‘spillover evidence’) was prejudicial.”\\nId. Vederman submits that the RICO, bribery, and CUMA-\\nrelated charges were intertwined “in that the acts relating\\nto the alleged bribery scheme were also charged as\\n‘predicates’ under RICO.” Vederman Br. 49. We disagree.\\n\\n To be sure, the RICO, bribery, and CUMA Counts\\nare related to one another. But in this instance, mere\\nrelatedness is not enough to demonstrate the foundation\\nnecessary for spillover. This is so because the bribery\\n 161\\n\\fcharges were a predicate to the RICO charge. In other\\nwords, the jury had to determine if Vederman was guilty\\nof bribery, and the jury then used that “predicate” to\\nconsider whether he was also guilty of the RICO\\nconspiracy. Thus, the necessarily tiered structure of the\\nquestions presented to the jury refute Vederman’s\\nargument that the counts were intertwined.\\n\\n That the bribery charges were predicates for the\\nRICO conspiracy further demonstrates that the “evidence\\nfor the different counts was sufficiently distinct to support\\nthe verdict on other separate counts.” Pelullo II, 14 F.3d at\\n898. Regardless of the evidence pertaining solely to the\\nRICO conviction, the evidence supporting both the bribery\\ncharges and the charges involving CUMA in Counts 19–\\n20 would have remained the same.\\n\\n The next factor we address is “whether the\\nelimination of the count on which the defendant was\\ninvalidly convicted would have significantly changed the\\n[defendant’s] strategy of the trial.” Id. As Vederman\\nargues, “the RICO charge interfered with Vederman’s\\ncentral defense to the bribery charge—that his gestures\\ntoward Fattah ‘were motivated purely by friendship.’ ”\\nVederman Reply Br. 28 (citing Gov’t Br. 200). In other\\nwords, the “RICO count made it dangerous to unduly\\nemphasize [Vederman’s] close friendship” with Fattah. Id.\\nFrom Vederman’s perspective, “a bribery-only trial would\\nhave reduced this danger and allowed a freer presentation\\nof the defense.” Id.\\n\\n 162\\n\\f It is quite likely that Vederman’s claim of friendship\\nwould have been less risky as a litigation strategy if he had\\nnot been facing a RICO charge. But Vederman\\nnevertheless chose to take that risk and fully presented his\\nfriendship argument to the jury. Moreover, while\\nVederman’s reliance on friendship might have helped him\\ndefend against the bribery charges, that friendship would\\nnot have altered the evidence pertaining to Counts 19–20\\ninvolving CUMA. Whether done for friendship or some\\nother reason, submitting fraudulent information to a\\nfinancial institution is unlawful.\\n\\n Finally, we “examine the charges, the language that\\nthe government used, and the evidence introduced during\\nthe trial to see whether they are ‘of the sort to arouse a\\njury.’ ” Pelullo II, 14 F.3d at 899 (quoting United States v.\\nIvic, 700 F.2d 51, 65 (2d Cir. 1983)). Vederman points out\\nthat Fattah was presented as “a backslapping, corrupt party\\nboss,” with “predictable spillover to his friend and\\nassociate, Vederman.” Vederman Br. 50 (quoting United\\nStates v. Murphy, 323 F.3d 102, 118 (3d Cir. 2003)). But\\nthis description was of Fattah, not Vederman. Vederman\\ncites other examples of prejudicial, pejorative language in\\nthe Government’s closing arguments. At one point, the\\nGovernment referred to “conspirators engaged in what can\\nonly be described as a white collar crime spree from\\nPhiladelphia all the way to Washington, D.C.” and\\npromised “to untangle the webs of lies and deception that\\nthese conspirators spun.” Vederman Br. 51 (quoting\\nJA5295, 5297). Whatever rhetorical flair these words\\n 163\\n\\fcontained, they did not obscure the evidence which\\nindependently supported the convictions for bank fraud at\\nCount 19 and for making false statements to CUMA at\\nCount 20. Accordingly, because we presume that the jury\\nfollowed the District Court’s instruction to consider and to\\nweigh separately the evidence on each count and as to each\\ndefendant, and because the evidence supporting the\\nCUMA-related charges in Counts 19–20 is sufficiently\\ndistinct from the RICO conspiracy, we conclude that\\nVederman’s spillover argument is unavailing.38\\n\\n XII. Conclusion\\n We will vacate the convictions of Chaka Fattah, Sr.\\nand Herbert Vederman as to Counts 16, 17, 18, 22, and 23.\\n\\n38\\n Nicholas adopted “pertinent portions” of the prejudicial\\nspillover arguments advanced by Vederman and Fattah.\\nNicholas Br. 65. Her spillover claim has no more merit\\nthan theirs. Nicholas’s involvement in the RICO\\nconspiracy was distinct from the bribery charges, which\\ndid not unfairly influence the other counts. As to\\nNicholas’s assertion that the NOAA charges did not\\nbelong in the indictment and should have been tried\\nseparately, we fail to see how this relates to a claim of\\nprejudicial spillover. To the extent it challenges the\\nDistrict Court’s denial of Nicholas’s motion for a\\nseverance, Nicholas has failed to provide legal support for\\nsuch a contention. See Fed. R. App. P. 28(a)(8)(A); United\\nStates v. Irizarry, 341 F.3d 273, 305 (3d Cir. 2003).\\n 164\\n\\fFattah and Vederman may be retried on these counts\\nbefore a properly instructed jury. We will also reverse the\\nDistrict Court’s judgment of acquittal on Counts 19 and\\n20. The convictions of Chaka Fattah, Sr. and Herbert\\nVederman will be reinstated, and the case will be\\nremanded for sentencing on those counts. In all other\\nrespects, the judgments of the District Court will be\\naffirmed.\\n\\n\\n\\n\\n 165\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4359254/\", \"author_raw\": \"SMITH, Chief Judge\"}]}"},"judge1":{"kind":"string","value":"SMITH"},"judge2":{"kind":"string","value":"GREENAWAY"},"judge3":{"kind":"string","value":"KRAUSE"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4582001/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Appellant in 17-1346 v. Chaka FATTAH, Sr., Appellant in 16-4397 Karen Nicholas, Appellant in 16-4410 Robert Brand, Appellant in 16-4411 Herbert Vederman, Appellant in 16-4427\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-16\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n Nos. 16-4397, 16-4410, 16-4411,\n 16-4427, 17-1346\n _____________\n\n UNITED STATES OF AMERICA\n Appellant in 17-1346\n\n v.\n\n CHAKA FATTAH, SR.,\n Appellant in 16-4397\n\n KAREN NICHOLAS,\n Appellant in 16-4410\n\n ROBERT BRAND,\n Appellant in 16-4411\n\n HERBERT VEDERMAN,\n Appellant in 16-4427\n _____________\n\nOn Appeal from the United States District Court\n for the Eastern District of Pennsylvania\n District Court Nos. 2-15-cr-00346-001,\n\f 2-15-cr-00346-002, 2-15-cr-00346-003,\n 2-15-cr-00346-004\n District Judge: The Honorable Harvey Bartle III\n\n Argued January 18, 2018\n\nBefore: SMITH, Chief Judge, GREENAWAY, JR., and\n KRAUSE, Circuit Judges\n\n (Filed: January 16, 2019)\n\nAndrea G. Foulkes\nEric L. Gibson\nPaul L. Gray\nRobert A. Zauzmer\nOffice of United States Attorney\n615 Chestnut Street\nSuite 1250\nPhiladelphia, PA 19106\n\nJonathan Ian Kravis [ARGUED]\nUnited States Department of Justice\nCriminal Division, Public Integrity Section\n1400 New York Avenue, N.W.\nWashington, DC 20005\n Counsel for the United States\n\nMark M. Lee\nBruce P. Merenstein [ARGUED]\nSamuel W. Silver\n 2\n\fSchnader Harrison Segal & Lewis\n1600 Market Street\nSuite 3600\nPhiladelphia, PA 19103\n Counsel for Appellant Fattah\n\nAnn C. Flannery [ARGUED]\nSuite 2700\n1835 Market Street\nPhiladelphia, PA 19103\n\nLisa A. Mathewson\nSuite 810\n123 South Broad Street\nPhiladelphia, PA 19109\n Counsel for Appellant Nicholas\n\nAlan Silber\nPashman Stein Walder Hayden\n21 Main Street\nSuite 200\nHackensack, NJ 07601\n Counsel for National Association of Criminal\n Defense Lawyers, Amicus Appellant Nicholas\n\nMira E. Baylson\nBarry Gross [ARGUED]\nMeredith C. Slawe\nDrinker Biddle & Reath\nOne Logan Square\n 3\n\fSuite 2000\nPhiladelphia, PA 19103\n Counsel for Appellant Brand\n\nHenry W. Asbill\nBuckley Sandler\n1250 24th Street, N.W.\nSuite 700\nWashington, DC 20037\n\nGlen D. Nager [ARGUED]\nJacob M. Roth\nJulia W. M. F. Sheketoff\nJones Day\n51 Louisiana Avenue, N.W.\nWashington, DC 20001\n Counsel for Appellant Vederman\n\n ________________\n\n OPINION\n ________________\n\n\nSMITH, Chief Judge.\n\n\n\n\n 4\n\f Table of Contents\nI. Introduction ................................................................... 8\nII. Background .................................................................. 9\n A. The Fattah for Mayor Scheme ................................. 9\n 1. The Lord Loan and Its Repayment ..................... 10\n 2. The College Tuition Component of the FFM\n Scheme ................................................................ 27\n 3. The NOAA Grant and the Phantom Conference 28\n B. The Blue Guardians Scheme.................................. 31\n C. The Fattah–Vederman Bribery Scheme................. 33\n D. The Indictment and Trial ....................................... 39\nIII. Juror Misconduct and Dismissal of Juror 12 ........... 58\n A. Investigation of Alleged Juror Misconduct ........... 58\n B. Dismissal of Juror 12 ............................................. 64\nIV. The District Court’s Instructions Under McDonnell 70\n A. The McDonnell Framework................................... 71\n B. The Kirk Meeting ................................................... 76\n C. Fattah’s Efforts to Secure Vederman an\n Ambassadorship.......................................................... 79\n D. The Zionts Hiring .................................................. 82\n E. Vederman’s Sufficiency Challenge to Counts 16–18\n and 22–23.................................................................... 89\n F. Blue Guardians ....................................................... 91\n\n 5\n\fV. Sufficiency of the Evidence for the RICO Conspiracy\nConviction ...................................................................... 95\nVI. Variance from the Indictment and Sufficiency of the\nEvidence for Count 2.................................................... 110\nVII. The District Court’s Instruction to the Jury on the\nMeaning of Intent ......................................................... 120\nVIII. Sending the Indictment to the Jury ...................... 126\nIX. The District Court’s Evidentiary Rulings .............. 129\n A. The District Court’s Application of Rule 404(b) 129\n B. Evidentiary Rulings Regarding Nicholas’s\n Defense ..................................................................... 134\n 1. The EAA Board Minutes .................................. 134\n 2. Jones’ Memory Regarding Other Contracts ..... 136\n 3. Exclusion of NOAA Evidence.......................... 137\n C. The Cooperating Witness’s Mental Health\n Records ..................................................................... 138\n 1. The District Court’s Denial of Access to the\n Mental Health Records ..................................... 140\n 2. The District Court’s Grant of the Motion in\n Limine ............................................................... 142\nX. The Government’s Cross-Appeal ............................ 147\n A. CUMA is a Mortgage Lending Business............. 148\n B. Sufficiency of the Evidence ................................. 155\nXI. Prejudicial Spillover ............................................... 158\n A. Fattah’s Claim of Prejudicial Spillover ............... 159\n 6\n\f B. Vederman’s Assertion of Prejudicial Spillover ... 160\nXII. Conclusion ............................................................ 164\n\n\n\n\n 7\n\f I. Introduction\n Chaka Fattah, Sr., a powerful and prominent fixture\nin Philadelphia politics, financially overextended himself\nin both his personal life and his professional career during\nan ultimately unsuccessful run for mayor. Fattah received\na substantial illicit loan to his mayoral campaign and used\nhis political influence and personal connections to engage\nfriends, employees, and others in an elaborate series of\nschemes aimed at preserving his political status by hiding\nthe source of the illicit loan and its repayment. In so doing,\nFattah and his allies engaged in shady and, at times, illegal\nbehavior, including the misuse of federal grant money and\nfederal appropriations, the siphoning of money from\nnonprofit organizations to pay campaign debts, and the\nmisappropriation of campaign funds to pay personal\nobligations.\n Based upon their actions, Fattah and four of his\nassociates—Herbert Vederman, Robert Brand, Bonnie\nBowser, and Karen Nicholas—were charged with\nnumerous criminal acts in a twenty-nine count indictment.\nAfter a jury trial, each was convicted on multiple counts.\nAll but Bowser appealed. As we explain below, the\nDistrict Court’s judgment will be affirmed in part and\nreversed in part.\n\n\n\n\n 8\n\f II. Background1\n During the 1980s and ’90s, Fattah served in both\nhouses of the Pennsylvania General Assembly, first as a\nmember of the House of Representatives and later as a\nSenator. In 1995, Fattah was elected to the United States\nHouse of Representatives for Pennsylvania’s Second\nCongressional District. In 2006, Fattah launched an\nunsuccessful run for Mayor of Philadelphia, setting in\nmotion the events that would lead to his criminal\nconviction and resignation from Congress ten years later.\n\n A. The Fattah for Mayor Scheme\n Fattah declared his candidacy for mayor in\nNovember of 2006. Thomas Lindenfeld, a political\nconsultant on Fattah’s exploratory committee, believed\nthat “[a]t the beginning of the campaign, [Fattah] was a\nconsiderable . . . candidate and somebody who had a very\nlikely chance of success.” JA1618. But Fattah’s campaign\nsoon began to experience difficulties, particularly with\nfundraising. Philadelphia had adopted its first-ever\ncampaign contribution limits, which limited contributions\nto $2,500 from individuals and $10,000 from political\naction committees and certain types of business\norganizations. Fattah’s fundraising difficulties led him to\n\n\n\n1\n The facts are drawn from the trial record unless otherwise\nnoted.\n 9\n\fseek a substantial loan, far in excess of the new\ncontribution limits.\n\n 1. The Lord Loan and Its Repayment\n While serving in Congress, Fattah became\nacquainted with Albert Lord, II. The two first met around\n1998, when Lord was a member of the Board of Directors\nof Sallie Mae.\n As the May 15, 2007 primary date for the\nPhiladelphia mayoral race approached, Fattah met Lord to\nask for assistance, telling Lord that the Fattah for Mayor\n(FFM) campaign was running low on funds. Fattah asked\nLord to meet with Thomas Lindenfeld, a political\nconsultant in Washington, D.C., and part-owner of LSG\nStrategies, Inc. (Strategies), a company that was working\nwith the FFM campaign and that specialized in direct voter\ncontact initiatives. Lindenfeld had been part of the\nexploratory group that initially considered Fattah’s\nviability as a candidate for mayor. Lindenfeld had known\nFattah since 1999, when Fattah endorsed Philadelphia\nMayor John Street. Through Fattah, Lindenfeld had also\ngotten to know several of Fattah’s associates, including\nHerbert Vederman, Robert Brand, and Bonnie Bowser.\nHerbert Vederman, a businessman and former state\nofficial, was the finance director for the FFM campaign.\nRobert Brand owned Solutions for Progress (Solutions), a\n“Philadelphia-based public policy technology company,\nwhose mission [was] to deliver technology that directly\nassists low and middle income families [in obtaining]\n 10\n\fpublic benefits.” JA6551. Bowser was Fattah’s Chief of\nStaff and campaign treasurer, and served in his district\noffice in Philadelphia.\n Lord’s assistant contacted Lindenfeld to arrange a\nmeeting, and Lindenfeld informed Fattah that he would be\nmeeting with Lord. Lindenfeld, along with his partner,\nMichael Matthews, met with Lord and discussed Fattah’s\nneed for funds to mount an intensive media campaign.\nAfter that meeting, Lindenfeld reported to Fattah that Lord\nwanted to help, but that they had not discussed a specific\ndollar amount. Approximately a week later, Fattah\ninstructed Lindenfeld to meet with Lord a second time.\nLord “wanted to know if he could give a substantial\namount of money, a million dollars” to Fattah’s campaign.\nJA1630. That prompted Lindenfeld to reply that the\namount “would be beyond the campaign finance limits.”\nId.\n\n Lord proposed a solution: he offered to instead give\na million dollars to Strategies in the form of a loan. To that\nend, Lindenfeld had a promissory note drafted which\nspecified that Lord was lending Strategies $1 million, and\nthat Strategies promised to repay the $1 million at 9.25%\ninterest, with repayment to commence January 31, 2008.\nLindenfeld later acknowledged that the promissory note\nwould make it appear as though Lord’s $1 million was not\na contribution directly to the Congressman, although he\nknew that it was actually a loan to the FFM campaign.\nIndeed, Lindenfeld confirmed with Fattah that neither\n\n 11\n\fLindenfeld nor Strategies would be responsible for\nrepayment. With that understanding, Lindenfeld executed\nboth the note and a security agreement purporting to\nencumber Strategies’ accounts receivable and all its assets.\n\n On May 1, shortly before the primary election, Lord\nwired $1 million to Lindenfeld. Lindenfeld held the money\nin Strategies’ operating account until Fattah told him how\nit was to be spent. Some of the money was eventually used\nfor print materials mailed directly to voters. And, at\nFattah’s direction, Lindenfeld wired a substantial sum to\nSydney Lei and Associates (SLA), a company owned by\nGregory Naylor which specialized in “get out the vote”\nefforts.\n Naylor had known Fattah for more than 30 years.2\nDuring the campaign, Naylor worked as the field director\nand was in charge of getting out the vote on election day.\n\n2\n Naylor first worked with Fattah when he was in the state\nlegislature. When Fattah was elected to Congress, Naylor\nworked in his Philadelphia office. Naylor met Nicholas\nwhen she joined Fattah’s staff at some point in the 1990s.\nAfter concluding her employment with Fattah’s office,\nNicholas worked with the Educational Advancement\nAlliance (EAA), an education nonprofit entity founded by\nFattah. This entity helped to recruit underrepresented\nstudents for scholarship and college opportunities. Around\n2009, Naylor left Fattah’s office to work exclusively with\nSLA. Naylor also knew Brand.\n 12\n\fOn the final day of the campaign, Naylor worked with\nVederman, who allowed Naylor to use his credit card to\nrent vans that would transport Fattah voters to the polls.\n As the primary date neared, Fattah and Naylor knew\nthe campaign was running out of money. The campaign\nwas unable to finance “media buys,” and Naylor needed\nmoney for field operations to cover Philadelphia’s more\nthan one thousand polling places. In early May,\nLindenfeld called Naylor to say that Lindenfeld “would be\nsending some money [Naylor’s] way.” JA3057. Within\ndays, SLA received a six-figure sum for Naylor to use in\nthe campaign and on election day. Naylor used the money\nto pay some outstanding bills, including salaries for FFM\nemployees, and allocated $200,000 to field operations for\nelection day.\n\n Fattah lost the mayoral primary on May 15, 2007.\nAfterward, Lindenfeld spoke with Fattah, Naylor and\nBowser about accounting for the FFM campaign money\nfrom Lord that had been spent. They decided that the\namounts should not appear in the FFM campaign finance\nreports, and Fattah instructed Naylor to have his firm,\nSLA, create an invoice. Naylor did so, creating an invoice\ndated June 1, 2007 from SLA to FFM, seeking payment of\n$193,580.19. Naylor later acknowledged that the FFM\ncampaign did not actually owe money to SLA, and that the\nfalse invoice was created to “hide the transaction that took\nplace earlier” and “make it look like [SLA] was owed\nmoney.” JA3075–76. Although FFM did not owe SLA\n\n 13\n\fanything for the election day expenses, the FFM campaign\nfinance reports from 2009 through 2013 listed a $20,000\nin-kind contribution from SLA for each year, thereby\nlowering FFM’s alleged outstanding debt to SLA.\n\n Of the total $1 million Lord loan, $400,000 had not\nbeen spent. Lindenfeld returned that sum to Lord on June\n3, 2007. He included a cover letter which stated: “As it\nturns out the business opportunities we had contemplated\ndo not seem to be as fruitful as previously expected.”\nJA1254. Lindenfeld later admitted that there were no such\n“business opportunities” and that the letter was simply an\neffort to conceal the loan.\n In late 2007, faced with financial pressures, Lord\nasked his son, Albert Lord, III, to collect the outstanding\n$600,000 balance on the loan to Strategies. Lord III\ncontacted Lindenfeld about repayment and expressed a\nwillingness to forgive the interest owed if the principal\nwas paid. Lindenfeld immediately called Fattah and\ninformed him that repayment could not be put off any\nlonger. Fattah told Lindenfeld more than once that “[h]e\nwould take care of it,” JA1652, but Fattah did not act.\nNeeding someone who might have Fattah’s ear,\nLindenfeld reached out to Naylor and Bowser. Naylor\ntalked to Fattah on several occasions and told him that\nLindenfeld was under considerable pressure to repay the\nloan. Fattah told Naylor more than once that he was\n“working on it.” JA3082–83.\n\n\n 14\n\f During his political career, Fattah had focused on\neducation, especially for the underprivileged. Indeed,\nFattah founded two nonprofit organizations: College\nOpportunity Resources for Education (CORE), and the\nEducational Advancement Alliance (EAA).\n\n EAA held the annual Fattah Conference on Higher\nEducation (the “annual conference”) to acquaint high\nschool students with higher education options. JA3079.\nSallie Mae regularly sponsored the conference. According\nto Raymond Jones, EAA’s chairman of the board from\n2004 through 2007, EAA offered a variety of programs to\nprovide “marginalized students with educational\nopportunities so they could continue and go to college.”\nJA1360. EAA was funded with federal grant money which\ncould only be spent for the purposes described in the\nparticular grant. Karen Nicholas served as EAA’s\nexecutive director, handling the organization’s day-to-day\nadministrative responsibilities. Nicholas had previously\nbeen a staffer for Fattah when he was a member of\nPennsylvania’s House of Representatives.\n CORE was an organization that awarded\nscholarships to graduating high school students in\nPhiladelphia who had gained admission to a state\nuniversity or the Community College of Philadelphia.\nCORE received funding from a variety of sources,\nincluding Sallie Mae. Because CORE also received\nfederal funds, and because EAA had experience working\nwith federal grants, EAA received and handled the federal\n\n 15\n\ffunds awarded to CORE. In short, EAA functioned as a\nfiduciary for CORE. When money became a problem for\nthe FFM campaign, Fattah’s involvement with EAA and\nCORE soon became less about helping underprivileged\nstudents, and more about providing an avenue for\ndisguising efforts to repay the illicit campaign funds from\nLord.\n\n On January 7, 2008, Robert Brand contacted Fattah\nby telephone. Shortly thereafter, Lindenfeld received an\nunexpected call from Brand proposing an arrangement for\nBrand’s company, Solutions, to work with Strategies.\nSolutions had developed a software tool called “The\nBenefit Bank,” which was designed to “assist low and\nmoderate income families to have enhanced access to\nbenefits and taxes.” JA1993. During the telephone call,\nBrand referred to The Benefit Bank and suggested a\ncontract under which Strategies would be paid $600,000\nupfront. JA1666. Shortly thereafter, on January 9, 2008,\nBrand followed up on his call to Lindenfeld with an email\nabout “develop[ing] a working relationship where you\ncould help us to grow The Benefit Bank and our process\nof civic engagement. While I know this is not your core\nbusiness I would like to try to convince you to take us on\nas a client.” JA6427. Lindenfeld responded that he was\ninterested. To Lindenfeld, “this was the way that\nCongressman Fattah was going to repay the debt to Al\nLord.” JA1654. When Lindenfeld called Fattah and told\nhim of the contact from Brand, Fattah simply replied that\nLindenfeld “should just proceed.” JA1666–67.\n 16\n\f A few days later, Brand emailed Nicholas at EAA a\nproposal from Solutions concerning The Benefit Bank,\nwhich sought EAA’s support in developing an education\nedition of The Benefit Bank and a $900,000 upfront\npayment.\n\n As the January 31 date for repayment of the balance\nof the $1 million Lord loan approached, a flurry of activity\ntook place. On January 24, both Raymond Jones, chair of\nthe EAA Board, and Nicholas signed a check from EAA\nmade out to Solutions in the amount of $500,000.\nAlthough no contract existed between EAA and Solutions,\nthe memo line of the check indicated that it was for a\ncontract, and Nicholas entered it into EAA’s ledger.3\n\n That same day, Ivy Butts, an employee of\nStrategies, emailed Lindenfeld the instructions Brand\nwould need to wire the $600,000 balance on the Lord loan.\n\n3\n Raymond Jones, who was EAA’s Chairman of the Board\nfrom 2004 through 2007, recalled at trial that the Board\nhad a limit on the amount that Nicholas could spend\nwithout board approval. JA1358, 1369. Nicholas was\nauthorized to sign contracts on behalf of EAA for no more\nthan $100,000. JA1369–71. Jones did not recall the\ncontract between EAA and Solutions, nor did the EAA\nboard minutes for December 2007, February 2008, or May\n2008 refer to the EAA–Solutions contract or to the\nsubstantial upfront payment of half a million dollars upon\nexecution of the agreement. JA6358–63; 6567.\n 17\n\fWithin minutes, Lindenfeld forwarded that email to Brand\nat Solutions. Brand then made two telephone calls to\nFattah. By late afternoon, Brand emailed Nicholas,\ninforming her that he had “met with all the people I need\nto meet with and have a pretty clear schedule of what\nworks best for us. I am also seeing what line of credit we\nhave to stretch out the payments until you get your line of\ncredit in place.” JA6558. Brand asked if they could talk\nand “finalize this effort.” JA6558. On January 25 and 26,\nthere were a number of calls between Fattah, Brand, and\nNicholas.\n\n On Sunday January 27, at 5:46 pm, Brand\ntelephoned Fattah. At 10:59 pm, Brand emailed Nicholas\na revised contract between EAA and Solutions for the\nengagement of services. Brand indicated he would send\nsomeone to pick up the check at about 1:00 pm the\nfollowing day. The revised contract called for the same\n$900,000 payment from EAA to Solutions, yet specified\nthat $500,000 was to be paid on signing, with $100,000\ndue three weeks later, and another $100,000 to be paid six\nweeks out. No due date for the $200,000 balance was\nspecified. The terms of the contract called for EAA to\nassist Solutions with further developing The Benefit Bank.\nIn addition, under the contract, EAA would receive certain\n\n\n\n\n 18\n\ffunds from the Commonwealth of Pennsylvania for a\nprogram relating to FAFSA applications. 4\n\n The same evening, Brand sent Lindenfeld a contract\nentitled “Cooperative Development Agreement to Provide\nServices to Solutions for Progress, Inc. for Growth of The\nBenefit Bank.” JA6569. The agreement proposed a\nworking partnership in which Strategies would work with\nSolutions to identify and secure a Benefit Bank affiliate in\nthe District of Columbia and two other states, and to\nfacilitate introductions to key officials in other states\nwhere The Benefit Bank might expand. The terms of the\nagreement provided that Solutions would pay $600,000 to\nStrategies by January 31, 2008, which would “enable\n[Strategies’] team to assess opportunities and develop\ndetailed work plans for each area.” JA6572. Brand copied\nSolutions’ Chief Financial Officer, Michael Golden.\nLindenfeld responded to Brand’s email within a minute,\nasking if Brand had received the wiring instructions.\nBrand immediately confirmed that he had.\n\n Concerned that Solutions did not have $600,000 to\npay Strategies, Golden talked to Brand, who informed him\nthat Solutions would be receiving a check for $500,000\nfrom EAA. Early the next morning, Nicholas responded to\nBrand’s email from the night before. She advised Brand\nthat he could pick up the check, “but as I stated I am not\n\n4\n FAFSA is an acronym for Free Application for Federal\nStudent Aid.\n 19\n\fin a position to sign a contract committing funds that I am\nnot sure that I will have.” Gov’t Supp. App. (GSA) 1. That\nsame day, a $540,000 transfer was made from the\nconference account, which EAA handled, into EAA’s\nchecking account. The conference account was maintained\nto handle expenses for Fattah’s annual higher education\nconference. Prior to this transfer, EAA had only\n$23,170.95 in its account. EAA then tendered a $500,000\ncheck to Solutions, which promptly deposited the check\nbefore the close of that day’s business. EAA never\nreplenished the $540,000 withdrawal from the conference\naccount.\n Brand received the executed contract between\nSolutions and Strategies on January 28. Even though the\ncontract called for Strategies to perform services in\nexchange for the $600,000 payment, Lindenfeld neither\nexpected to do any work for the $600,000, nor did he in\nfact do any work.\n\n In sum, by January 28, Solutions had received\n$500,000 from EAA, but it still had to come up with\n$100,000 to provide Strategies with the entire amount\nneeded to repay the Lord loan. Golden obtained the needed\nfunds the following day by drawing $150,000 on a line of\ncredit held by Brand’s wife. Brand and Fattah spoke four\nmore times on the telephone on January 29. Trial evidence\nlater showed that, during the month of January 2008,\nneither the FFM campaign bank account nor Fattah’s\n\n\n 20\n\fpersonal account had a sufficient balance to fund a\n$600,000 payment.\n On the morning of January 30, frustrated by the\ndelay, Lindenfeld sent Brand an email with a subject line\n“You are killing me.” JA6430. Lindenfeld stated that he\nhad “made a commitment based on yours to me. Please\ndon’t drag this out. I have a lot on the line.” Id. Brand\nresponded late in the afternoon, stating: “just met with\nMichael. He does the transfer at 8 AM tomorrow. It should\nbe in your account ($600K) early tomorrow morning.” Id.\nLindenfeld replied: “The earlier the better.” Id. The\nfollowing morning, Golden wired $600,000 from\nSolutions’ Pennsylvania bank account into Strategies’\nWashington D.C. bank account. JA2745, 2874. Strategies\nin turn, wired the same amount from its Washington D.C.\nbank account to Lord’s bank account in Virginia. JA2874,\n6549. Around noon, Brand telephoned Lindenfeld.\n\n In the days following the exhaustive efforts to meet\nthe January 31 loan repayment deadline, four more\ntelephone calls took place between Brand and Fattah.5\nNaylor learned at some point that the loan had been paid\noff. When Naylor asked Fattah about details of the\nrepayment, Fattah simply replied “[t]hat it went through\nEAA to Solutions and it was done.” JA3088.\n\n5\n By contrast, between October to December 2007, Brand\nand Fattah spoke by telephone only “once or twice [a]\nmonth.” JA2734.\n 21\n\f Meanwhile, at some point in January, EAA received\nnotice that the Department of Justice Office of the\nInspector General (DOJ) intended to audit its books.6 DOJ\nauditors told EAA to provide, at the “entrance\nconference,” documentation containing budgetary and\naccounting information. EAA failed to produce any\naccounting information.\n Although Lindenfeld was no longer making\ndemands of Brand, Brand was still owed the remaining\n$100,000 that Solutions had paid to satisfy the Lord loan.\nOn March 23, 2008, Brand sent Nicholas an email\noutlining his efforts to contact her over the previous two\nweeks about documentation on the CORE work, how to\nproceed with the paperwork for the Commonwealth of\nPennsylvania, and “how we can get our proposed contract\nsigned and the outstanding payments made.” JA2749.\nNicholas responded that evening, writing:\n\n I can appreciate your urgency however I do\n have EAA work that I continue to do,\n including the [usual] facilitation of programs,\n our financial audit, the start-up of two new\n programs[,] and of course the DOJ audit. I am\n still trying to obtain a line of credit without a\n completed 2007 audit and things are getting a\n\n\n\n6\n One of the terms and conditions of a federal grant is that\nthe recipient “be readily prepared for an audit.” JA2314.\n 22\n\f little uncomfortable now as I try to keep us\n afloat.\nJA6576. Nicholas told Brand that the DOJ auditors were\nmaking demands and would soon be on site. She noted that\n“[t]hey are still very uncomfortable with your contract\namongst other things and depending on their findings\nsome of the funding received may have to be returned.” Id.\nNicholas said that she had submitted the paperwork to the\nstate, and she told Brand that “in the future . . . as a result\nof the DOJ audit I will not be in a position to do another\ncontract such as this.” Id.\n Shortly after Nicholas’s reply to Brand, Nicholas\nforwarded the Brand–Nicholas email chain to Fattah. The\nbody of the email stated, in its entirety: “I really don’t\nappreciate the tone of Bob’s email. I can appreciate that he\nhas some things going on however I am doing my best to\nassist him. Some other things are a priority. He needs to\nback off.” GSA2. Later that night, Bowser sent Fattah an\nemail with a subject line that read “Karen N” and a\ntelephone number. JA2752.\n\n As the audit continued, the auditors found other\ndeficiencies. During April of 2008, DOJ issued a notice of\nirregularity to EAA, which resulted in the audit being\nreferred to DOJ’s Investigations Division for a more\ncomprehensive review.\n\n On April 24, 2008, Brand emailed Nicholas asking\nfor a time to update her on The Benefit Bank. In early May,\n 23\n\fBrand sent another email to Nicholas attaching a revised\nEAA–Solutions contract proposal, which decreased the\ninitial upfront cost from $900,000 to $700,000.\n Although Solutions and EAA had still not signed a\ncontract, EAA paid Solutions another $100,000 in May.\nThat money was obtained via a loan to EAA from CORE.\nThomas Butler, who had worked for Fattah both when\nFattah was in Congress and when he was in the General\nAssembly, was CORE’s executive director. Butler had\nbeen contacted in mid-May by Jackie Barnett, a member\nof CORE’s Board who had also worked with\nCongressman Fattah. Barnett informed Butler that\nNicholas had requested a loan from CORE to EAA, and\nthat Fattah, as Chairman of CORE’s Board, had approved\nit. Butler and Barnett withdrew funds from two CORE\nbank accounts and obtained a cashier’s check, dated May\n19, in the amount of $225,000 and made payable to EAA.\nThe withdrawals were from accounts used for Sallie Mae\nfunds and other scholarship money.\n After EAA received the $225,000 check, EAA\ntendered a $100,000 check to Solutions. The check bore\nthe notation “Commonwealth of Pennsylvania.” EAA\nrepaid CORE the following month. Because EAA lacked\nsufficient funds of its own to cover this payment, EAA\ndrew on grant money that it had received from NASA.\n\n Brand and Lindenfeld continued to communicate\nconcerning The Benefit Bank. In July of 2008, a meeting\nwas held at Solutions with Brand, Lindenfeld, Golden, and\n 24\n\fother Solutions employees to discuss “an enormous\namount of work” that Brand wanted Strategies to do.\nJA1670. Lindenfeld said in response “we’d be glad to do\nthat, but . . . we would have to be paid.” Id. At that point,\nsomeone in the meeting stated that Strategies “had already\nbeen paid” $600,000. Id. Lindenfeld replied: “well, that\nwas for Congressman Fattah, . . . that’s not for us. So if\nyou want us to do work, we have to get paid for it\nseparately.” Id. Brand became upset with Lindenfeld over\nhis comment about being paid because his colleagues at\nSolutions were not aware of the reason for the $600,000\npayment.\n Meanwhile, EAA was attempting to meet the\ndemands of the DOJ auditors, who were focused on the\nrelationship between EAA and CORE. DOJ served a\nsubpoena upon Solutions to produce “[a]ny and all\ndocuments including, but not limited to, contract\ndocuments, invoices, correspondence, timesheets,\ndeliverables and proof of payment related to any services\nprovided to or payments received” from CORE or EAA.\nJA2350.\n\n Special Agent Dieffenbach, from the DOJ,\ninterviewed Nicholas on July 14, 2008. During that\ninterview, Nicholas discussed the relationship between\nEAA and CORE, how invoices were paid, and how\nconsultants were handled. Nicholas also answered\nquestions about EAA’s relationship with Solutions,\nincluding the payment of invoices. She did not inform\n\n 25\n\fAgent Dieffenbach of the $500,000 payment in January or\nthe subsequent $100,000 payment in May. Nor did the\ninterview address the EAA–Solutions contract that\npurportedly required those payments, because the contract\nhad yet to be produced.\n\n Solutions failed to comply with the subpoena,\nprompting an email from Agent Dieffenbach on August 26\nasking for an update concerning Solutions’ reply to the\nDOJ subpoena. Solutions then produced an undated\nversion of the EAA–Solutions contract that required the\n$600,000 upfront payment. Neither Brand nor Nicholas\nprovided the auditors with the January and May checks\nfrom EAA to Solutions.\n Efforts to conceal the repayment of the Lord loan\nand to promote the political and financial interests of\nFattah continued. The FFM campaign reports indicated in-\nkind contributions of debt forgiveness by SLA even\nthough there had been no actual debt. In September of\n2009, with EAA’s ledgers still under scrutiny, Nicholas\naltered the description of the entry for the $100,000 check\nto Solutions from “professional fees consulting” to\n“CORE Philly.” JA2546. Other FFM campaign debt was\nreduced further after Vederman negotiated with creditors.\n\n EAA never fully recovered from its payment of the\n$600,000 balance on the Lord loan and the audits that took\nplace in 2008. It began laying off employees in 2011, and\nby June of 2012, only four employees remained. JA3659.\nEAA ceased operations at some point in 2012. JA1530.\n 26\n\f 2. The College Tuition Component of the FFM\n Scheme\n Although the FFM campaign was close to insolvent,\nit nevertheless made tuition payments for Fattah’s son,\nChaka Fattah Jr., also known as Chip. Chip attended\nDrexel University, but had yet to complete his coursework\nbecause he had failed to pay an outstanding tuition\nbalance. As the FFM campaign got underway in 2007,\nFattah wanted Chip to re-enroll in classes at Drexel and\nget a degree. Fattah asked Naylor to help financially, and\nhe did so by writing checks from SLA to Drexel toward\nChip’s outstanding tuition. By October of 2007, Chip was\npermitted to re-enroll in classes.\n Although Naylor never directly addressed the issue\nwith Fattah, he agreed to assist with Chip’s outstanding\ntuition with the expectation that SLA would be repaid. The\nfirst check to Drexel in the amount of $5,000 was sent in\nAugust of 2007, with $400 payments in the months that\nfollowed until August of 2008. At some point, Chip\ninformed Naylor that the payee was no longer Drexel, but\nSallie Mae. Naylor then began sending monthly checks\nfrom SLA to Sallie Mae. Those payments, in the amount\nof $525.52, began in March of 2009 and continued until\nApril of 2011, after which Fattah told Naylor he no longer\nneeded to make them. SLA’s payments to Drexel and\nSallie Mae totaled $23,063.52.\n\n Naylor’s expectation of repayment was eventually\nrealized. Beginning in January of 2008 and continuing\n 27\n\funtil November 2010, Bowser sporadically sent SLA\nreimbursement checks from the FFM campaign with a\nnotation that payment was for “election day operation\nexpenses.” JA3136. The FFM funds had been transferred\nfrom the Fattah for Congress campaign. These\nreimbursement checks totaled $25,400. In an effort to\nconceal the source of the payments to Drexel and Sallie\nMae, and to make it appear that the younger Fattah had\nperformed services for SLA, Naylor created false tax\nforms for Chip. Chip, however, had never performed\nservices for SLA.\n\n 3. The NOAA Grant and the Phantom Conference\n In mid-December 2011, when EAA was\nexperiencing serious financial difficulties, Nicholas\nsubmitted an email request to the educational partnership\nprogram of the National Oceanic & Atmospheric\nAdministration (NOAA) for a grant “designed to provide\ntraining opportunities and funding to students at minority\nserving institutions” interested in science, technology,\nengineering, and math fields related to NOAA’s mission.\nJA3354–55. The request sought $409,000 to fund EAA’s\nannual conference scheduled for February 17–19, 2012.\nJacqueline Rousseau, a supervisory program manager at\nNOAA, participated in a conference call with Nicholas\nshortly thereafter and advised Nicholas that the agency\ncould not afford the $409,000 request but would consider\na smaller grant. Rousseau advised Nicholas that EAA\n\n\n 28\n\fwould need to submit an application if it wished to be\nconsidered for a grant.\n Before submitting a grant application, Nicholas\nemailed Rousseau about sponsoring the conference. On\nJanuary 11, 2012, Rousseau informed Nicholas that the\n“NOAA Office of Education, Scholarship Programs has\nagreed to participate and provide sponsorship funds of\n$50K to support the referenced conference.” JA6453.\nRousseau also informed Nicholas that Chantell Haskins,\nwho also worked with the student scholarship program,\nwould be the point of contact for NOAA.\n In February 2012, EAA held its annual conference\nat the Sheraton Hotel in downtown Philadelphia. The\nconference had been held at the same location each year\nsince 2008.\n\n Nicholas contacted Haskins at some point in early\n2012, inquiring about the $50,000 grant. On May 8, 2012,\nHaskins sent Nicholas an e-mail which included\ninformation about submitting proposals to fund a\nconference for students. EAA then submitted a grant\napplication, which Haskins reviewed. She advised\nNicholas on June 28, 2012 that the grant could not be used\nto provide meals, and that the date of the conference would\nhave to be pushed back, with the new date included in a\nmodified application. When Nicholas asked if expenses\nfrom a previous conference could be paid from the new\ngrant, Haskins informed her that this was not allowed.\n\n 29\n\f In early July 2012, Nicholas sent a modified grant\nproposal to Haskins. It eliminated the budget item for food\nand changed the date of the 2012 conference to October\n19–21, 2012 at the same Sheraton Hotel in Philadelphia\nwhere EAA’s annual conference had taken place earlier in\nthe year. NOAA approved a $50,000 grant for the October\n2012 conference—a conference that would never be held.\n\n Unaware that no October 2012 conference had\ntaken place, NOAA allowed Nicholas access to the\n$50,000 grant in March of 2013. She then transferred the\nentire amount from NOAA to EAA’s bank account a few\ndays later. Naylor had performed services for EAA for\nwhich he was still owed $116,590. JA3119. In discussions\nwith Naylor, Nicholas had informed him that the\nlikelihood of EAA’s being able to pay him was “[n]ot very\ngood.” JA3120. Yet several days after EAA had received\nthe $50,000 from NOAA, Nicholas sent Naylor a check\nfor $20,000. JA3120, 4283.\n\n On April 3, 2013, Nicholas submitted a final report\nto NOAA concerning EAA’s use of the grant. Notably,\npage 4 of the report stated the conference had been held in\nFebruary 2012, while page 17 stated that the conference\nhad been held from October 19 to 21, 2012. NOAA issued\na notice asking for clarification and for a list of students\nwho had been supported at the conference. Nicholas failed\nto file either a clarifying report regarding the date of the\nconference or a timely report regarding the disbursement\nof the grant. Finally, in November of 2013, Nicholas\n\n 30\n\fsubmitted the final Federal Financial Report in which she\ncertified, falsely, that the $50,000 had been used for a\nproject during the period from August 1, 2012 to\nDecember 30, 2012.\n\n B. The Blue Guardians Scheme\n In addition to functioning as the conduit for Lord’s\n$1 million loan to Fattah’s campaign, Lindenfeld’s\ncompany, Strategies, also performed services for the\ncampaign. The work resulted in indebtedness from FFM\nto Strategies of approximately $95,000. Fattah made\nseveral small payments, but failed to pay the full amount\ndue. Although Lindenfeld spoke to Fattah, Naylor and\nBowser about the debt, no payments were forthcoming.\nDuring a meeting in Fattah’s D.C. office, Fattah told\nLindenfeld “that [repayment] really wasn’t going to be\npossible because the campaign had been over for a long\ntime” and the funds were not available. JA1693. Fattah\nthen asked Lindenfeld if he could write off the debt on his\nFFM campaign finance reports. Id. Lindenfeld told Fattah\nthat as long as he was paid, it was not his business how\nFattah disclosed it on the campaign finance reports.\nJA1694.\n In lieu of repayment, Fattah suggested that\nStrategies could claim to be interested in setting up an\nentity to address environmental issues and ocean pollution\nalong the coastline and in the Caribbean. Fattah explained\nthat creating such an entity would make it possible to\nobtain an appropriation from the government. Hearing\n 31\n\fthis, Lindenfeld knew he was not going to be paid by the\nFFM campaign, and was amenable to receiving money\nfrom an appropriation instead. At a later meeting,\nLindenfeld told Fattah that the name of the entity would\nbe “Blue Guardians.” Lindenfeld consulted with an\nattorney about creating Blue Guardians as an entity to\nreceive the federal grant. He emailed Fattah, asking\nquestions about how to complete an application to the\nHouse Appropriations Committee. Fattah provided\nsuggestions, and an application was eventually completed.\nIt indicated that Blue Guardians would be “in operation for\na minimum of ten years,” and, in accordance with Fattah’s\nguidance, requested $15 million in federal funds. JA1711–\n13.\n Lindenfeld submitted the application to Fattah’s\noffice in April of 2009. Afterward, a Fattah staffer\ncontacted Lindenfeld to suggest that he change his\nWashington, D.C., address to Philadelphia because that\nwas the location of Fattah’s district. Fattah later suggested\nto Lindenfeld that Brand might allow the use of his\nPhiladelphia office address, a plan to which Brand agreed.\n\n In February 2010, Lindenfeld submitted a second\napplication to the Appropriations Committee. In March,\nFattah submitted a project request using his congressional\nletterhead and seeking $3,000,000 for the “Blue\nGuardians, Coastal Environmental Education Outreach\nProgram.” JA6432. Within a month, Blue Guardians had\nboth articles of incorporation and a bank account. Around\n\n 32\n\fthat time, a news reporter contacted Lindenfeld to discuss\nthe new Blue Guardians entity. The inquiry made\nLindenfeld uncomfortable, and he ultimately decided to\nabandon the Blue Guardians project. He continued to seek\npayment from Fattah, to no avail.\n\n Nonetheless, having obtained Lindenfeld’s\nacquiescence to writing off the campaign’s debt to\nStrategies, Fattah started falsifying FFM’s campaign\nreports. Beginning in 2009 and extending through 2013,\nthe FFM campaign reports executed by Fattah and Bowser\nstated that Strategies made in-kind contributions of\n$20,000, until the debt appeared to have been paid in full.\n\n C. The Fattah–Vederman Bribery Scheme\n Vederman and Fattah were personal friends.\nVederman was a successful businessman who had also\nserved in prominent roles in the administrations of Ed\nRendell when he was Mayor of Philadelphia and Governor\nof Pennsylvania. In November of 2008, Vederman was a\nsenior consultant in the government and public affairs\npractice group of a Philadelphia law firm. His assistance\nto the FFM campaign included paying for rented vans used\nin the get-out-the-vote effort.\n\n After Fattah’s electoral defeat, the campaign still\nowed more than $84,000 to a different law firm for\nservices performed for the campaign. Vederman\napproached that firm in the summer of 2008 asking if it\nwould forgive FFM’s debt. Negotiations resulted in a\n 33\n\fcommitment from FFM to pay the firm $30,000 by the end\nof 2008 in exchange for forgiveness of $20,000, all of\nwhich would appear on the FFM campaign finance report.\nVederman’s efforts also led to payment by Fattah of an\nadditional $10,000 in 2009 to the law firm, in exchange\nfor additional forgiveness of $20,000 of debt. It was not\nlong after Vederman’s successful efforts to lower Fattah’s\ncampaign debt, that Fattah wrote a letter to U.S. Senator\nRobert P. Casey recommending Vederman for an\nambassadorship.\n\n At some point in 2010, Vederman again intervened\non behalf of the FFM campaign. FFM remained in debt to\nan advertising and public relations firm owned by Robert\nDilella. By late 2011, Vederman and Dilella had worked\nout a settlement to resolve the outstanding debt. Pursuant\nto that settlement, Dilella received partial payment from\nthe FFM campaign: $25,000 in satisfaction of a $55,000\ndebt. Dilella testified at trial that he would not have agreed\nto retire a portion of the debt had he known the FFM\ncampaign was paying college tuition for Fattah’s son.\n Vederman helped Fattah financially in other ways.\nBefore the 2006 FFM campaign, Fattah and his wife,\nRenee Chenault-Fattah, sponsored a young woman named\nSimone Muller to live with them as an au pair exchange\nvisitor. Muller was from South Africa, and her J-1 visa\nallowed her to serve as a nanny and to study in the United\nStates. Muller later applied for and received a second visa,\nan F-1 student visa that indicated she had been accepted as\n\n 34\n\fan international student at the Community College of\nPhiladelphia. The application indicated that Muller would\nagain be residing with the Fattahs. Notwithstanding this\nliving arrangement, Fattah identified Vederman as the\nperson who would be paying for Muller’s trip to the\nUnited States.\n By the beginning of 2010, Muller wished to transfer\nto Philadelphia University. This required her to submit\nverification that funds were available to pay for her study.\nAlthough the Fattahs were Muller’s sponsors, Fattah\nexplained to the University’s Dean of Enrollment Services\nthat he was submitting a letter of secondary support from\nVederman. JA3754, 3763–65, 6504. Without Vederman’s\nJanuary 2010 letter of support, the University would not\nhave admitted Muller. In addition to this pledge of support,\nVederman paid $3,000 of Muller’s tuition. Shortly\nthereafter, Fattah resumed his efforts to secure an\nambassadorship for Vederman.\n\n In February of 2010, Fattah staffer Maisha Leek\ncontacted Katherine Kochman, a scheduler for White\nHouse Chief of Staff Rahm Emanuel. Leek requested a\ntelephone conference with Emanuel, Rendell, and Fattah\nto discuss Vederman’s “serving his country in an\ninternational capacity.” JA2893. In a follow-up email on\nMarch 26, Leek sent documents to Kristin Sheehy, a\nsecretary to White House Deputy Chief of Staff James\nMessina. The documents included Fattah’s 2008 letter to\nSenator Casey and Vederman’s biography. After\n\n 35\n\fparticipating in a telephone conference about Vederman\nwith Fattah and Rendell, Messina sent Vederman’s\nbiography to the White House personnel office for\nconsideration.\n\n As the April 2010 tax deadline approached, Fattah\nstill owed the City of Philadelphia earned income tax in\nthe amount of $2,381. Just days before the filing deadline,\nVederman gave a check to Chip Fattah for $3,500. The\nyounger Fattah quickly deposited $2,310 into his father’s\nbank account. Fattah paid his tax bill on April 15. Without\nChip’s deposit into his father’s bank account, the older\nFattah would not have had sufficient funds to pay his tax\nbill.\n On October 30, 2010, Vederman gave Chip another\ncheck, this one for $2,800. That same day, Fattah hand-\ndelivered a letter to President Obama recommending\nVederman for an ambassadorship. A few weeks later,\nFattah’s staffer, Leek, sent the letter that Fattah had given\nto President Obama to Messina’s office. That letter\npointed out that both Rendell and Fattah had sent letters\non behalf of Vederman, and that he was an\n“unquestionably exceptional candidate for an\nambassadorship.” JA6291–92.\n\n Fattah’s efforts to secure Vederman an\nambassadorship were unsuccessful. Fattah then shifted\ngears and sought to secure Vederman a position on a\nfederal trade committee. Fattah approached Ron Kirk, who\nserved as U.S. Trade Representative, and asked him to\n 36\n\fspeak with a constituent. In May of 2011, Leek followed\nup on that discussion by emailing Kirk and asking him to\nmeet with Vederman. Kirk met with Vederman on June 5,\n2011 and explained to him the role of the trade advisory\ncommittees. Although the two men “had a very nice\nconversation,” JA 3566, it soon became “pretty apparent\nto [Kirk and his staff] that [serving on a trade advisory\ncommittee was] not what Mr. Vederman was interested\nin.” JA3567. As Kirk put it, “it was obvious that\n[Vederman] was looking for something perhaps more\nrobust in his mind or . . . higher profile than one of our\nadvisory committees.” Id. Given Vederman’s lukewarm\ninterest, no appointment to an advisory committee was\nforthcoming.\n In late December 2011, the Fattahs applied for a\nmortgage so they could purchase a second home in the\nPoconos. Shortly after applying for the mortgage, Fattah\nemailed Vederman, offering to sell him his wife’s 1989\nPorsche for $18,000. Vederman accepted the offer. The\nnext day, Vederman wired $18,000 to Fattah’s Wright\nPatman Federal Credit Union account.\n\n The Credit Union Mortgage Association (CUMA)\nacted as the loan processing organization for the home\nmortgage. Because CUMA is required to verify the source\nof any large deposits, CUMA’s mortgage loan processor,\nVictoria Souza, contacted Fattah on January 17, 2012, to\nconfirm the source of the $18,000. Fattah informed Souza\nthat the $18,000 represented the proceeds of the Porsche\n\n 37\n\fsale. Souza requested documentation, including a signed\nbill of sale and title.\n That same day, Bowser emailed Vederman a blank\nbill of sale for the Porsche. After Vederman signed the bill\nof sale, Fattah forwarded it to Souza. The bill of sale was\ndated January 16, 2012, which was the day before Souza\nhad requested the documentation. It bore the signatures of\nRenee Chenault-Fattah and Herbert Vederman, with\nBonnie Bowser as a witness.\n\n Fattah also provided Souza with a copy of the\nPorsche’s title. It was dated the same day it was sent to\nSouza, and bore signatures of Chenault-Fattah as the seller\nand Vederman as buyer, along with a notary’s stamp.\nNeither Vederman nor Chenault-Fattah actually appeared\nbefore the notary.\n\n Vederman never took possession of the Porsche.\nRenee Chenault-Fattah continued to have the Porsche\nserviced and insured long after the purported sale had\ntaken place. Moreover, the Porsche remained registered in\nChenault-Fattah’s name, and was never registered to\nHerbert Vederman. When FBI agents searched the\nFattahs’ home in 2014, the Porsche was discovered in the\nFattahs’ garage.\n\n On January 24, 2012, the Fattahs wired $25,000 to\nthe attorney handling the escrow account for the purchase\nof the vacation home. Without the $18,000 transfer from\n\n 38\n\fVederman, the Fattahs would not have had sufficient funds\nin their bank accounts to close on the home.\n Around the same time that the Fattahs were\npurchasing the house in the Poconos, Fattah’s Philadelphia\noffice hired Vederman’s longtime girlfriend, Alexandra\nZionts. Zionts had long worked for a federal magistrate\njudge in Florida. Near the end of 2011, the magistrate\njudge retired, leaving Zionts ten months shy of obtaining\nthe necessary service required to receive retirement\nbenefits. If Zionts could find another job in the federal\ngovernment, her benefits and pension would not be\nadversely affected. Vederman assisted Zionts in her job\nsearch, which included calling Fattah. Fattah hired her, a\nmove that put his congressional office overbudget. Zionts\nworked in Fattah’s office for only about two months,\nleaving to work for a congressman from Florida.\n\n Tia Watson, who performed constituent services for\nFattah and worked on the same floor as Zionts in Fattah’s\ndistrict office, testified she had no idea what work Zionts\nperformed. Although Zionts contacted Temple University\nabout archiving Fattah’s papers from his career in both the\nstate and federal government, an employee from Temple\nUniversity observed that Zionts’ work contributed nothing\nof value to the papers project.\n\n D. The Indictment and Trial\n Fattah’s schemes eventually unraveled. On July 29,\n2015, a federal grand jury in the Eastern District of\n 39\n\fPennsylvania returned a twenty-nine count indictment\nalleging that Fattah and his associates had engaged in a\nvariety of criminal acts. Fattah, Vederman, Nicholas,\nBrand, and Bowser were charged with unlawfully\nconspiring to violate the Racketeer Influenced and Corrupt\nOrganizations Act (RICO), 18 U.S.C. § 1962(d). In\naddition to the RICO charge, the indictment alleged that\nFattah and certain co-defendants had unlawfully conspired\nto commit wire fraud, 18 U.S.C. §§ 1343, 1349; honest\nservices fraud, 18 U.S.C. §§ 1343, 1346, 1349; mail fraud,\n18 U.S.C. §§ 1341, 1349; money laundering, 18 U.S.C.\n§ 1956; and to defraud the United States, 18 U.S.C. § 371.\nSeveral defendants were also charged with making false\nstatements to banks, 18 U.S.C. § 1014; falsifying records,\n18 U.S.C. § 1519; laundering money, 18 U.S.C. § 1957;\nand engaging in mail, wire, and bank fraud, 18 U.S.C.\n§§ 1341, 1343, and 1344.\n\n The RICO charge alleged that the defendants and\nother co-conspirators constituted an enterprise aimed at\nsupporting and promoting Fattah’s political and financial\ninterests. The efforts to conceal the $1 million Lord loan\nand its repayment are at the heart of the RICO conspiracy\nand the Fattah for Mayor scheme. The indictment further\nalleged that the RICO enterprise involved: (1) the scheme\nto satisfy an outstanding campaign debt by creating the\nfake “Blue Guardians” nonprofit; and (2) the bribery\nscheme to obtain payments and things of value from\nVederman in exchange for Fattah’s efforts to secure\nVederman an appointment as a United States Ambassador.\n 40\n\f A jury trial, before the Honorable Harvey Bartle III\nof the Eastern District of Pennsylvania, began on May 16,\n2016, and lasted about a month. 7 Judge Bartle charged the\njury on Wednesday, June 15, 2016, and deliberations\nbegan late that afternoon. The following day, after\ndeliberating for only four hours, the jury sent a note to the\njudge. Written by the foreperson, the note read:\n Juror Number 12 refuses to vote by the letter\n of the law. He will not, after proof, still\n change his vote. His answer will not change.\n He has the 11 of us a total wreck knowing that\n we are not getting anywhere in the hour of\n deliberation yesterday and the three hours\n today. We have zero verdicts at this time all\n due to Juror Number 12. He will not listen or\n reason with anybody. He is killing every\n other juror’s experience. We showed him all\n the proof. He doesn’t care. Juror Number 12\n has an agenda or ax to grind w/govt.\nJA5916.\n\n Shortly after receiving the foreperson’s note, the\nCourt received a second communication—a note signed\n\n\n\n 7\n The District Court dismissed one charge prior to\ntrial: an individual money laundering count against\nNicholas.\n 41\n\fby nine jurors, including the foreperson. The second note\nread:\n We feel that [Juror 12] is argumentative,\n incapable of making decision. He constantly\n scream [sic] at all of us.\nId.\n Judge Bartle met with counsel in his chambers and\nadvised them of his intention to voir dire both the\nforeperson and Juror 12 in an effort to determine whether\nthe juror was deliberating as required by his oath. The\nJudge also indicated that he would “stay away from the\nmerits of the case,” and that whether he would voir dire\nmore jurors “remain[ed] to be seen.” JA5917.\n Counsel for the defendants objected to the Court’s\nproposed inquiry. As a group, they indicated that while the\nnote could be read as suggesting “a flat refusal to\ndeliberate,” they were of the opinion that it sounded “more\nin the manner of a disagreement over the evidence.”\nJA5918. Nicholas’s counsel specifically argued that\nquestioning the jurors so quickly after the start of\ndeliberations would send a message that differences of\nopinion among a block of jurors could be resolved by\ncomplaining to the Court. Defense counsel acknowledged\nthat the case law gave Judge Bartle wide discretion on how\nto proceed, but suggested that a “less intrusive” course of\naction was preferred. JA5918–19. They collectively urged\n\n 42\n\fthe Court to do nothing more than remind the jurors of\ntheir duty to deliberate.\n The Government agreed with Judge Bartle’s\nproposed voir dire. In the prosecution’s view, the Court\nhad already given proper instructions to the jury on their\nduty to deliberate. The Government further argued that if\nJuror 12 had exhibited bias, as suggested in the notes, he\nwould have lied during the voir dire process and his\nrefusal to deliberate would be “further evidence of that and\nhis unsuitability as a juror.” JA5921.\n\n With all counsel present, and over defense counsel’s\nobjections, Judge Bartle ultimately questioned five jurors\nin chambers. He questioned Juror 2 (the foreperson), Juror\n12 (the subject of the complaints), Juror 3, Juror 6, and\nJuror 1.\n\n Judge Bartle began each voir dire by informing the\njuror that he would ask a series of questions, but would not\ninquire into the merits of the case or how any juror was\nvoting. Each juror was placed under oath, and Judge Bartle\nasked, among other questions, whether screaming was\noccurring; whether the jurors were discussing the\nevidence; whether Juror 12 was placing his hands on other\njurors; and whether Juror 12 was unwilling to follow his\ninstructions.\n The foreperson acknowledged that he had written\nthe initial note during lunch earlier that day. He stated that\nJuror 12 was not willing to follow the law, but instead\n 43\n\f“want[ed] to add his own piece of the law . . . which has\nnothing to do with it.” JA5927–28. The foreperson further\ntestified that Juror 12 “was standing up screaming” and\nthat “[i]t was everybody pretty much against [Juror 12].”\nJA5929. He testified that Juror 12 “has his own agenda,”\nand that Juror 12 put his hand on another juror. JA5930.\nThe foreperson also stated that the jury had discussed only\na single count since the day before, and that they were still\ndiscussing it. When the District Court responded that the\njurors should understand that they could take as much time\nas they needed, the foreperson responded: “I understand\nthat. . . . [W]e all understand it. But we feel that he’s just—\nhe’s got another agenda.” JA5934.\n Judge Bartle advised counsel that he considered this\n“a very serious situation” and that he would proceed to\nvoir dire Juror 12. JA5937. Fattah’s counsel renewed his\nobjection to questioning Juror 12, which the Court\noverruled. Brand’s counsel argued that because the Court\nhad decided to voir dire Juror 12, it should also voir dire\nan additional juror. The Court agreed to do so.\n When the Court questioned Juror 12, he admitted to\nhaving “yelled back” at others, but only when they raised\ntheir voices to him. JA5939. Juror 12 contended that he, in\nfact, was “the only one” deliberating. Id. When an initial\nvote was taken the previous afternoon, his vote “was\ndifferent than everybody else’s.” Id. Juror 12 explained to\nthe other jurors why his vote was different, bringing up\nspecific evidence. In response, the other jurors said “that\n\n 44\n\fdoesn’t mean anything” and “pointed to the indictment.”\nJA5940. Juror 12 told the other jurors that the indictment\nis not evidence. Id. In response, the others “threatened to\nhave [him] thrown off.” Id.\n\n Juror 12 testified that a similar sequence of events\nhad taken place that morning. After a brief period of\ndeliberations, another vote was taken, and with the same\nresult as the previous afternoon. A discussion ensued, and\nthe other jurors again “point[ed] to the indictment.” Id.\nJuror 12 told them to “read the charge,” “[t]he indictment\nis not evidence.” Id. They read the charge, and Juror 12\nagain attempted to explain his view, but the other jurors\npaid little attention. Accordingly, Juror 12 told the others\nthat if they did not want him there, he “[didn’t] want to be\n[there]”—he would be “[o]kay with it” if they wanted him\ntaken off the jury. JA5941.\n Upon hearing this testimony, Judge Bartle again\nasked about the tone of deliberations. Juror 12 repeated\nthat he raised his voice only in response to others who did\nso—he did “not want to yell at anybody.” JA5942. Judge\nBartle then asked whether he had touched other jurors.\nJuror 12 replied that he had not hurt anyone. When asked\nif he had put his hand on anybody’s shoulder, Juror 12\nanswered: “I couldn’t remember to be honest with you.”\nJA5946.\n\n Following Juror 12’s voir dire, the Court summoned\nJuror 3 to chambers. Juror 3 testified that, after discussion\nof a particular count, there was one juror at odds with the\n 45\n\fothers. According to Juror 3, “the rest of the jurors\npounced on the gentleman with the . . . dissenting\nopinion.” JA5948. Juror 3 testified that Juror 12 “got very\ndefensive and just a little bit [] impatient” and that “the\nother jurors were very impatient with him.” Id. Juror 3 did\nnot recall witnessing Juror 12 putting his hand on any\nother jurors.\n\n The Government requested that the Court voir dire\nanother juror. Defense counsel objected, claiming that the\nquestioning “threaten[ed] . . . the entire deliberative\nprocess.” JA5949–50. Judge Bartle reminded counsel that\nhe had the authority to question each juror, and called for\nvoir dire of Juror 6.\n Juror 6 testified that the jury had been discussing the\ncase and reviewing the evidence, but that Juror 12 “wants\nto be seen” and was “being obstinate.” JA5951–52.\nAccording to Juror 6, Juror 12 “may not agree” with the\nconclusion of other jurors but “doesn’t give valid reasons\nas to why he may disagree with the charge.” JA5952. Juror\n6 also revealed that Juror 12 was the first to raise his voice,\nand that he may have touched her and another juror. When\nasked to clarify what she meant by Juror 12 disagreeing\nwith “the charge,” Juror 6 testified that Juror 12 was\n“reading maybe too deeply into it and putting his own\nemotions into it instead of just looking at what it says [and]\nwhat the facts are.” JA5952, 5955. According to Juror 6,\nJuror 12 “just continues to read past that into his own mind\nof what he feels it should be.” JA5955. Juror 6 testified\n\n 46\n\fthat Juror 12’s “justification for some of his responses [did\nnot] seem to relate to what the matter [was] before\n[them].” JA5957.\n Judge Bartle chose to hear from yet another juror.\nJuror 1 was called and informed the Court and counsel that\nthe jury “really [hadn’t] been able to even start the\ndeliberation process” in light of the disruptive behavior of\n“one particular individual.” JA5958–59. The particular\nindividual, according to Juror 1, was “very opinionated”\nand “[came] into the process with his view already\nestablished, refusing to even listen to any of the evidence\n. . . [being] very forceful . . . standing up, yelling, pointing\nhis finger.” JA5959. When asked if this individual was\nwilling to follow the Court’s instructions, Juror 1 testified\nthat he “pours [sic] over the documents very well” but that\nhe was adding other factors to answer the question on the\nverdict form, such as “what did this person feel.” JA5961.\nWhen Judge Bartle advised that intent was an appropriate\nconsideration, Juror 1 agreed but said that Juror 12 was\n“trying to investigate . . . going way beyond the scope” of\nthe evidence before them. JA5961–62. Juror 12, he said,\n“has an opinion and that opinion is established.” JA5962.\nHe stated that Juror 12 was “not willing to listen to any\nsort of reason or any sort of what everyone else is saying”\nbut instead, was “trying to force everyone else to get to his\npoint of view.” Id. “[I]f he feels like he’s not getting there,\nhe gets louder and louder and points and puts his hand on\nyour shoulder . . . .” Id.\n\n 47\n\f After questioning the five jurors (Jurors 1, 2, 3, 6,\nand 12), Judge Bartle heard argument from counsel. The\nattorney for the Government pointed out that the Court\nwould have to make a credibility determination because\nJuror 12 stated that he did not recall touching anyone. In\nthe Government’s view, Juror 12 was disrupting the\nprocess and should be removed. Defense counsel\ndisagreed. They argued that Juror 12 was conscientious\nand was engaging with the evidence. They pointed out that\ndespite the testimony that Juror 12 was reading too deeply\ninto the instructions or introducing new factors for the jury\nto consider, Juror 6 had testified that the jurors “talked it\nthrough” and resolved the concern. JA5965. Defense\ncounsel argued that the jury was discussing intent, an issue\nthat was at the heart of the case. Defense counsel perceived\nno breakdown in deliberations and argued that dismissal\nwould be premature. They suggested, instead, that the\nCourt provide a supplemental instruction.\n\n Judge Bartle decided to adjourn for the afternoon.\nBut before he left the courtroom, defense counsel brought\ntwo matters to his attention. First, in light of testimony\nduring the voir dire, they asked that the jury be\nreinstructed that the verdict form and indictment were not\nevidence. Second, they apprised the Judge of the standard\nfor juror dismissal set forth in United States v. Kemp, 500\nF.3d 257 (3d Cir. 2007). Defense counsel stated that under\nKemp, a request to discharge a juror must be denied if there\nis a possibility that the request stems from the juror’s view\nof the evidence. Judge Bartle expressed hesitation on\n 48\n\freinstructing the jury, but agreed that Kemp would control\nhis determination as to whether dismissal was appropriate.\n With the following morning came a new revelation.\nWith counsel in chambers, the Judge informed them that\n“additional significant evidence” had come to light since\nthe previous day’s recess. JA5980. He placed his\ncourtroom deputy under oath, and she proceeded to testify\nto an exchange that had occurred the previous day as she\nwas escorting Juror 12 back to the jury room after he had\nbeen voir dired. According to the deputy, Juror 12 stopped\nher in the hallway, placed his hand on her shoulder, and\nlooked her “straight in the eye.” JA5981. He then said:\n“I’m going to hang this jury.” Id. The deputy then related\nthat before any further conversation could take place\nbetween Juror 12 and the deputy, Judge Bartle summoned\nJuror 12 back to his chambers. Later that day, however,\nJuror 12 and the courtroom deputy had another exchange.\nShe testified that after all five jurors had been questioned,\nJuror 12 emerged from the jury room and told her “I really\nneed to talk to you.” JA5982. She informed Judge Bartle\nand counsel that Juror 12 “said more about how they’re\ntreating him and what he’s saying to them.” Id. He flatly\nstated that “it’s going to be 11 to 1 no matter what.” Id.\n\n There were no follow-up questions for the deputy.\nInstead, defense counsel suggested that what Juror 12 may\nhave meant was that he was willing to hang the jury\nbecause of a lack of evidence. They requested that Juror\n12 be asked about his comments to the deputy.\n\n 49\n\f After once again summoning Juror 12 to his\nchambers, the Judge advised him that “[s]ome questions\nhave arisen” about what he may have done after being voir\ndired the previous day. JA5985. Juror 12 acknowledged\nhaving conversations with the courtroom deputy. When\nasked “what happened” and “[w]hat occurred,” Juror 12\nresponded: “Basically, I said that there was a lot of name\ncalling going on.” JA5985. He said comments had been\nmade by other jurors about his service in the military. He\nspecifically referred to other jurors’ suggesting that he had\npossibly “hit [his] head . . . hard a few times” while\nserving in a parachute regiment. JA5986. He testified he\nhad conveyed these comments to the deputy and that he\nfound them offensive. When asked if he said anything else\nto the deputy, Juror 12 responded: “I may have. I really\ncan’t recall.” JA5987. And when Judge Bartle followed up\nby asking if he could recall anything else that he said to\nthe deputy, Juror 12 simply replied: “No. To me, that was\nthe most important thing.” Id. Juror 12 was then excused\nfrom chambers.\n Defense counsel next requested that the juror be\nasked directly whether he told the courtroom deputy that\nhe was going to “hang this jury.” JA5988. Juror 12 was\nrecalled to chambers, and the following back and forth\ntook place:\n\n The Court: You may be seated. And, of\n course, [Juror 12], you know you’re under\n oath here from yesterday?\n\n 50\n\f Juror 12: Yes, sir.\n The Court: . . . Did you say to [the courtroom\n deputy] that you’re going to hang this jury?\n Juror 12: I said I would.\n The Court: You did?\n Juror 12: I did. I said—I told her—I said, we\n don’t agree; I’m not just going to say guilty\n because everybody wants me to, and if that\n hangs this jury, so be it.\n ....\n Juror 12: I did say that, sir.\n The Court: You didn’t remember that before?\n Juror 12: I’m more concerned about people\n spitting on my military record.\n The Court: Did you say that you’d hang the\n jury no matter what?\n Juror 12: If they do—if we cannot come to—\n The Court: No. The question is what you said\n to her. Did you say to her you would hang the\n jury no matter what?\n Juror 12: I can’t really remember that. I did\n say that if we didn’t—a person—no matter\n what, I can’t recall that exactly.\n The Court: All right. Thank you very much.\n You can wait just out there in the anteroom.\nJA5989–90.\n\n Defense counsel continued to oppose Juror 12’s\ndismissal. They argued that the juror’s concern was about\n\n 51\n\fthe evidence, and that his comments to the courtroom\ndeputy reflected a conviction that “he’s not going to agree\njust because others want him to agree.” JA5991. They also\nargued that nothing should be made of Juror 12’s failure\nto mention the comments when initially questioned by the\nCourt, and that a supplemental instruction was all that was\nwarranted given the early stage of the deliberations.\n\n The Government strongly disagreed. The Assistant\nUnited States Attorney argued that Juror 12 “should\nabsolutely be removed” because “his demeanor ha[d]\ndemonstrated a hostility . . . both to the other jurors and to\nthe court.” JA5993. The Government also suggested that\nJuror 12’s comments that he would hang the jury meant\nthat he was not participating in the deliberations and was\nignoring the evidence and the law.\n\n Ruling from the bench, Judge Bartle announced:\n I find [the deputy clerk] to be credible. I find\n [Juror 12], not to be credible. I find that [Juror\n 12] did tell [the deputy clerk] that he was\n going to hang this jury no matter what.\n There have been only approximately\n four hours of deliberation. There’s no way in\n the world he could have reviewed and\n considered all of the evidence in the case and\n my instructions on the law.\n I instructed the jury to deliberate,\n meaning to discuss the evidence; obviously,\n to hold onto your honestly held beliefs, but at\n 52\n\f least you have to be willing to discuss the\n evidence and participate in the discussion\n with other jurors.\n Juror number 12 has delayed,\n disrupted, impeded, and obstructed the\n deliberative process and had the intent to do\n so. I base that having observed him, based on\n his words and his demeanor before me.\n He wants only to have his own voice\n heard. He has preconceived notions about the\n case. He has violated his oath as a juror.\n And I do not believe that any further\n instructions or admonitions would do any\n good. I think he’s intent on, as he said,\n hanging this jury no matter what the law is,\n no matter what the evidence is.\n Therefore, he will be excused, and I\n will replace him with the next alternate . . . .\n\nJA5994–95.\n In response, defense counsel moved for a mistrial,\nwhich the judge promptly denied. He then informed the\nreconstituted jury that deliberations would need to start\nover, and reinstructed them on certain points of law,\nincluding that the verdict slip does not constitute evidence.\n\n Judge Bartle elaborated upon his decision to remove\nJuror 12 in two post-trial memorandum opinions. In the\nfirst, ruling on a media request for the sealed transcripts,\nhe explained:\n 53\n\f Here, there is no doubt that Juror 12\n intentionally refused to deliberate when he\n declared so early in the process that he would\n hang the jury no matter what. This finding\n was predicated on the admission of Juror 12\n as reported by the court’s deputy clerk. The\n facts became clear to the court after hearing\n the credible testimony of the deputy clerk and\n the less credible testimony of Juror 12. The\n demeanor of Juror 12 before the court\n confirmed the court’s findings.\n\nGSA23–24. The second opinion addressed motions for\nbail pending appeal from Nicholas and Brand. GSA25.\nThere, Judge Bartle explained:\n\n The law is well-settled that the court has\n discretion to act as it did under these\n circumstances. See United States v. Kemp,\n 500 F.3d 257, 304 (3d Cir. 2007). The court,\n after taking testimony, specifically found that\n the juror, following only a few hours of\n deliberation, stated to the court’s courtroom\n deputy clerk that he would hang this jury no\n matter what. He could not possibly have\n reviewed all of the law and evidence of this\n five-week trial at the time he made his\n remark. The court examined the deputy clerk\n and the juror under oath in the presence of\n counsel for all parties. The undersigned\n\n 54\n\f found the deputy clerk to be credible and the\n juror not to be credible. Based on the juror’s\n demeanor, it was clear he would not change\n his attitude and that his intent had been and\n would continue to be to refuse to deliberate\n in good faith concerning the law and the\n evidence.\n\nGSA32.\n After deliberating for approximately 15 hours, the\njury returned with its verdicts on June 21, 2016, finding\nthe defendants guilty on most counts. Fattah, Vederman,\nand Brand were convicted on all counts. The jury acquitted\nBowser on sixteen counts, but found her guilty of the\nbribery conspiracy and the associated charges of bank\nfraud, making false statements to a financial institution,\nfalsifying records, and money laundering (Counts 16, 19,\n20, 21 and 22). The jury also acquitted Nicholas of wire\nfraud (Count 24). See Nicholas Supp. App. (NSA) 36.\n The following week, on June 27, the Supreme Court\nissued its opinion in McDonnell v. United States, 136 S.\nCt. 2355 (2016). McDonnell provided new limitations on\nthe definition of “official acts” as used in the honest\nservices fraud and bribery statutes under which Fattah and\nVederman had been convicted. Id. at 2369–72. Fattah and\nVederman both moved to set aside their convictions. The\nDistrict Court “acknowledge[d] that under McDonnell our\ninstructions to the jury on the meaning of official act\nturned out to be incomplete and thus erroneous.” JA103.\n 55\n\fBut the Court held that “the incomplete and thus erroneous\njury instruction on the meaning of official acts did not\ninfluence the verdict on the bribery counts” and upheld the\nverdict on Counts 16–18 and 22–23. JA107, 121.\n\n Fattah, Vederman, and Bowser had more success\nwith their other post-verdict motions. The District Court,\nin a thoughtful opinion, granted relief under Federal Rule\nof Criminal Procedure 29, acquitting Vederman of the\nRICO conspiracy (Count 1) and Fattah, Vederman, and\nBowser of bank fraud, making false statements to a\nfinancial institution, and falsifying records (Counts 19, 20,\nand 21). JA37–139.\n This appeal followed. 8 The defendants raise a\nvariety of challenges to their convictions. All defendants\nbut Bowser challenge the District Court’s decision to\ndismiss Juror 12. Fattah and Vederman argue that the\nDistrict Court erred in upholding the jury’s verdict on the\nbribery and honest services fraud counts in light of the\nSupreme Court’s decision in McDonnell. Fattah, Brand\nand Nicholas challenge the sufficiency of the evidence\nunderlying the RICO conviction. Several of the defendants\ncontend the District Court erred in its instruction on intent\nand by sending the indictment out to the jury. There are\n\n\n\n8\n Fattah, Brand, Vederman, and Nicholas each filed a\ntimely notice of appeal, but Bowser did not challenge her\nconvictions.\n 56\n\falso several evidentiary challenges.9 The Government\ncross-appeals from the District Court’s judgment\nacquitting Fattah and Vederman on Counts 19 and 20,\narguing that the District Court erred in interpreting the\ndefinition of a “mortgage lending business” under 18\nU.S.C. § 27. We address these arguments in turn.\n\n We hold that the District Court erred in upholding\nthe jury verdict in light of McDonnell, and we will\ntherefore reverse and remand for retrial on Counts 16, 17,\n18, 22, and 23. We also hold that the District Court erred\n\n9\n Pursuant to Rule 28(i), “Fattah joins in the arguments of\nHerbert Vederman, Robert Brand, and Karen Nicholas to\nthe extent their arguments on appeal apply to Mr. Fattah.”\nFattah Br. 19 n.69. Federal Rule of Appellate Procedure\n28(i) provides that a defendant, “[i]n a case involving\nmore than one appellant . . . may adopt by reference a part\nof another’s brief.” Here, Fattah’s decision to join fails to\nspecify which of the many issues of his codefendants he\nbelieves worthy of our consideration. Rather, it appears\nthat he presumes we will scour the record and make that\ndetermination for him. This type of blanket request fails to\nsatisfy Rule 28(a)(5)’s directive requiring that the\n“appellant’s brief must contain . . . a statement of the\nissues presented for review.” Fed. R. App. P. 28(a)(5). We\nconclude that expecting the appellate court to identify the\nissues to be adopted simply results in the abandonment and\nwaiver of the unspecified issues. See Kost v. Kozakiewicz,\n1 F.3d 176, 182 (3d Cir. 1993).\n 57\n\fin acquitting Fattah and Vederman on Counts 19 and 20.\nBecause the jury’s verdict was supported by the evidence,\nwe will reinstate the convictions as to those counts. In all\nother respects, we will affirm the judgment of the District\nCourt.\n\n III. Juror Misconduct and Dismissal of Juror 12 10\n Defendant Fattah challenges the District Court’s\ndecision to conduct an in camera inquiry into alleged juror\nmisconduct and the ultimate dismissal of Juror 12. 11 We\nreject both challenges. The record reveals credible\nallegations of juror misconduct and a sufficient basis to\nsupport the finding that Juror 12 violated his oath.\n\n A. Investigation of Alleged Juror Misconduct\n We first consider whether the District Court erred in\nits handling of the two notes from jurors. A trial court’s\nresponse to allegations of juror misconduct is reviewed\nunder an abuse of discretion standard. United States v.\nBoone, 458 F.3d 321, 326 (3d Cir. 2006) (citing United\nStates v. Resko, 3 F.3d 684, 690 (3d Cir. 1993)). We\nconclude that the District Court did not abuse its discretion\n\n\n10\n The District Court had jurisdiction under 18 U.S.C.\n§ 3231. We have jurisdiction under 28 U.S.C. § 1291 and\n18 U.S.C. § 3742(a).\n11\n Vederman, Nicholas, and Brand adopt Fattah’s claim of\nreversible error concerning the dismissal of Juror 12.\n 58\n\fin addressing the issues raised in the jurors’ notes to the\nCourt.\n Trial courts are afforded discretion in responding to\nallegations of juror misconduct. This is so because “the\ntrial court is in a superior position to observe the ‘mood at\ntrial and the predilections of the jury.’ ” Resko, 3 F.3d at\n690 (quoting United States v. Chiantese, 582 F.2d 974,\n980 (5th Cir. 1978)). But this discretion is not unlimited.\nOnce the jury retires to deliberate, the confidentiality of its\ndeliberations must be closely guarded. An accused is\nconstitutionally entitled to be tried before a jury of his\npeers. As ordinary citizens, jurors are “expected to speak,\ndebate, argue, and make decisions the way ordinary people\ndo in their daily lives.” Pena-Rodriguez v. Colorado, 137\nS. Ct. 855, 874 (2017) (Alito, J., dissenting). To protect\nagainst intrusion into a defendant’s right to be judged only\nby fellow citizens, “the door to the jury room [is] locked.”\nId. at 875.\n In Boone, this Court considered the threshold for\nintervention by a trial judge who is presented with\nallegations of juror misconduct during the course of\ndeliberations. 458 F.3d at 327. We recognized that “[i]t is\nbeyond question that the secrecy of deliberations is critical\nto the success of the jury system.” Id. at 329. But that\nsecrecy abuts a competing interest—the jury’s proper\nexecution of its duties. That is, “a juror who refuses to\ndeliberate or who commits jury nullification violates the\nsworn jury oath and prevents the jury from fulfilling its\n\n 59\n\fconstitutional role.” Id. Recognizing these competing\ninterests, we declined in Boone to adopt a sweeping\nlimitation on a trial court’s ability to investigate\nallegations of misconduct during jury deliberations. See id.\nConsistent with the standard applied at other stages of\ncriminal proceedings, Boone teaches that “where\nsubstantial evidence of jury misconduct—including\ncredible allegations of jury nullification or of a refusal to\ndeliberate—arises during deliberations, a district court\nmay, within its sound discretion, investigate the\nallegations through juror questioning or other appropriate\nmeans.” Id.\n Fattah argues that the District Court had no basis to\nquestion any of the jurors. Fattah Br. 20. We disagree. In\nBoone, notes from the jury presented substantial credible\nevidence of misconduct. 458 F.3d at 330. Here, the initial\nnote from the foreperson alleged that Juror 12 “refuse[d]\nto vote by the letter of the law,” would “not listen or reason\nwith anybody,” and that he had “an agenda or ax to grind”\nwith the Government. JA5916. The note contained\nallegations of both a refusal to deliberate and a suggestion\nof nullification. A refusal to deliberate is a violation of a\njuror’s oath. Boone, 458 F.3d at 329 (citing United States\nv. Baker, 262 F.3d 124, 130 (2d Cir. 2001) (“It is well-\nsettled that jurors have a duty to deliberate.”)). Moreover,\nnullification—a juror’s refusal to follow the law—is a\nviolation of the juror’s sworn oath to render a verdict\naccording to the law and evidence. See United States v.\nThomas, 116 F.3d 606, 614–18 (2d Cir. 1997) (discussing\n 60\n\fboth “benevolent” and “shameful” examples of juror\nnullification, but “categorically reject[ing] the idea that, in\na society committed to the rule of law, jury nullification is\ndesirable or that courts may permit it to occur when it is\nwithin their authority to prevent”). The second jury note,\nsigned by nine jurors, supported the claim of misconduct\nby asserting that Juror 12 was “incapable of making\ndecision[s]” and was “constantly scream[ing]” at the other\njurors. JA5916–17. We conclude that the District Court\ndid not abuse its discretion in deciding to initially question\nJuror 2, and subsequently, Jurors 12, 3, 6 and 1.\n\n Fattah also challenges the scope of the District\nCourt’s questioning. He argues that the rights to an\nimpartial jury and to a unanimous verdict “would be\nrendered toothless if trial courts had free rein to question\njurors during deliberations.” Fattah Br. 36. Indeed, we\nacknowledged the legitimacy of such a concern in Boone.\nDespite adopting a modest “credible allegations” standard\nfor investigating misconduct, we “ke[pt] in mind the\nimportance of maintaining deliberative secrecy.” Boone,\n458 F.3d at 329. Fattah asserts that the trial court’s\nquestions to the five jurors were “intrusive and pointed”\nand “nothing like the questioning . . . approved in Boone.”\nFattah Br. 38. But Fattah does not elaborate on how, in his\nview, the questions posed by Judge Bartle specifically\nintruded into deliberative secrecy.\n\n To be sure, Judge Bartle’s questioning of each juror\nwas more extemporaneous than the juror questioning in\n\n 61\n\fBoone. There, the district court asked a single juror four\n“concise and carefully-worded” questions. 458 F.3d at\n330. Judge Bartle’s voir dire of each of the five jurors took\non a more conversational tone. We take no issue with that\napproach. The substance of the judge’s questions was\nlimited and mirrored that of questions we deemed\nappropriate in Kemp. There, the court conducted three\nrounds of questioning. In the first round, each juror was\nasked:\n (1) “Are you personally experiencing any\n problems with how the deliberations are\n proceeding without telling us anything about\n the votes as to guilt or innocence? If yes,\n describe the problem.” (2) “Are all the jurors\n discussing the evidence or lack of evidence?”\n (3) “Are all the jurors following the court’s\n instructions on the law?”\n\nKemp, 500 F.3d at 273. In the second and third rounds,\neach juror was asked:\n (1) “Is there any juror or jurors who are\n refusing to deliberate?” (2) “Is there any juror\n who is refusing to discuss the evidence or\n lack of evidence?” (3) “Is there any juror who\n is refusing to follow the Court’s\n instructions?”\nId. at 274. Here, Judge Bartle began his voir dire of each\njuror by stating that he did not wish for the juror to discuss\n 62\n\fthe merits of the case or to reveal the content of the\ndeliberations that had taken place. He asked the jurors\nwhether screaming was occurring, whether the jurors were\ndiscussing the evidence, whether Juror 12 was placing his\nhands on other jurors, and whether Juror 12 was unwilling\nto follow his instructions.\n Fattah points to no specific question posed or topic\ndiscussed that was inappropriate, and we see little to no\nsubstantive difference between the questions here and\nthose asked by the trial judge in Kemp. As in Kemp, “the\nDistrict Court took care to limit its questions to appropriate\nmatters that did not touch on the merits of the jury’s\ndeliberation, and expressly informed each juror on\nmultiple occasions that he or she should not reveal the\nsubstance of the deliberations.” Id. at 302 (citing United\nStates v. Edwards, 303 F.3d 606, 634 n.16 (5th Cir. 2002)).\n Fattah also argues that once the remarks of Juror 2\nand Juror 12 revealed no further evidence of misconduct,\nthe court had no basis to question other jurors. Fattah\nReply 19. Yet, our cases make clear that a trial court may,\nin its discretion, examine each juror. Kemp, 500 F.3d at\n302 (“We have recognized that there are times in which\nindividual questioning is the optimal way in which to root\nout misconduct.”). Indeed, “the District Court must utilize\nprocedures that will ‘provide a reasonable assurance for\nthe discovery of prejudice.’ ” Id. (quoting Martin v.\n\n\n\n 63\n\fWarden, Huntingdon State Corr. Inst., 653 F.2d 799, 807\n(3d Cir. 1981)). 12\n\n Judge Bartle, a very able and experienced district\njudge, was in the best position to determine what type of\ninquiry was warranted under the circumstances. We\nconclude that his questioning of the five jurors was not an\nabuse of discretion. See id. at 302.\n\n B. Dismissal of Juror 12\n Fattah, joined by Vederman, Brand, and Nicholas,\nstrongly contends that the District Court committed\nreversible error by dismissing Juror 12. “We review the\ndismissal of a juror for cause for abuse of discretion.”\n\n12\n Our cases do not suggest that a trial judge confronted\nwith allegations that a jury’s deliberations are being\nobstructed by one of its members should always resort to\ninterviewing jurors. Reinstructing the jury on its duty to\ndeliberate will often be the better course at the first sign of\ntrouble. Mere disagreement among jurors—even spirited\ndisagreement—is no ground for intervention.\nFurthermore, intrusive or leading questions about the\ndeliberative process may work against the twin goals of\nprotecting that process and ensuring that jurors remain\nfaithful to their oaths. We share the Eleventh Circuit’s\npreference of “err[ing] on the side of too little inquiry as\nopposed to too much.” United States v. Oscar, 877 F.3d\n1270, 1287 (11th Cir. 2017) (quoting United States v.\nAugustin, 661 F.3d 1105, 1133 (11th Cir. 2011)).\n 64\n\fKemp, 500 F.3d at 303. That deferential standard compels\nus to affirm.\n Rule 23(b) of the Federal Rules of Criminal\nProcedure permits a trial court to excuse a deliberating\njuror for good cause. See id. (citing Fed. R. Crim. P.\n23(b)). Good cause exists where a juror refuses to apply\nthe law, refuses to follow the court’s instructions, refuses\nto deliberate with his or her fellow jurors, or demonstrates\nbias. See Kemp, 500 F.3d at 305–06; United States v.\nOscar, 877 F.3d 1270, 1287 (11th Cir. 2017); Thomas, 116\nF.3d at 617. Good cause does not exist when there is\nreasonable but sustained disagreement about how a juror\nviews the evidence. The courts of appeals are emphatic\nthat trial courts “may not dismiss a juror during\ndeliberations if the request for discharge stems from\ndoubts the juror harbors about the sufficiency of the\ngovernment’s evidence.” Kemp, 500 F.3d at 303 (quoting\nUnited States v. Brown, 823 F.2d 591, 596 (D.C. Cir.\n1987)); see also Oscar, 877 F.3d at 1287 (same); United\nStates v. Symington, 195 F.3d 1080, 1087 (9th Cir. 1999);\nThomas, 116 F.3d at 622.\n\n To reinforce a defendant’s right to a unanimous\njury, we have adopted a high standard for juror dismissal.\nKemp, 500 F.3d at 304 & n.26. “[D]istrict courts may\ndischarge a juror for bias, failure to deliberate, failure to\nfollow the district court’s instructions, or jury nullification\nwhen there is no reasonable possibility that the allegations\nof misconduct stem from the juror’s view of the evidence.”\n\n 65\n\fId. at 304 (emphasis added). This “no reasonable\npossibility” standard is “by no means lax.” Id. Rather, “[i]t\ncorresponds with the burden for establishing guilt in a\ncriminal trial.” Id.\n\n We first applied this standard in Kemp, but have not\nhad occasion to do so since. There, the evidence\nsupporting the district court’s removal decision was\n“overwhelming.” 500 F.3d at 304. Ten jurors separately\nand consistently reported that a juror was improperly\nbiased, and did so only after three rounds of questioning\nand careful and correct instructions from the district court\nas to the distinction between appropriate skepticism and\nimpermissible bias. Id. at 304–05; see id. at 275–76\n(district court’s instruction). The testimony also showed\nthat the juror in question refused to deliberate or to discuss\nthe evidence with her fellow jurors. Id. at 305.\n Whether the evidence of misconduct in this case is\nas strong as that in Kemp is beside the point. After only\nfour hours of deliberations, Juror 12 stated unequivocally\nto the courtroom deputy that he was “going to hang” the\njury, and that it would be “11 to 1 no matter what.”\nJA5981–82 (emphasis added). These statements, coupled\nwith the District Court’s finding that Juror 12 lacked\ncredibility, provided a sufficient basis for Juror 12’s\ndismissal.\n\n As grounds for excusing Juror 12, the District Court\nfound that he refused to deliberate in good faith, “delayed,\ndisrupted, impeded, and obstructed the deliberative\n 66\n\fprocess and had the intent to do so,” JA5995, and that he\nwas “intent on . . . hanging this jury no matter what the law\nis, no matter what the evidence is.” Id. The District Court\ndetermined from this that Juror 12 had violated his oath as\na juror and that no further instructions or admonitions\ncould rehabilitate the juror. Id. The District Court based\nthese findings on personal observation, including Juror\n12’s words and demeanor, and making the specific finding\nthat Juror 12 was not credible. That finding is amply\nsupported by the record.\n\n In United States v. Abbell, 271 F.3d 1286, 1303 (9th\nCir. 2001), the Ninth Circuit recognized that “the\ndemeanor of the pertinent juror is important to juror\nmisconduct determinations” because the “juror’s\nmotivations and intentions are at issue.” That court\nemphasized, as we do, that a district judge is best situated\nto assess the demeanor of a juror. Id. Here, Juror 12 stated\nhe could not recall putting his hand on another juror’s\nshoulder, while his fellow jurors’ testimony was consistent\non this point. Juror 12 also failed, at first, to recall his\ntroubling statements to the courtroom deputy despite\nhaving made those statements only the previous afternoon.\nWhen questioned a second time and asked directly about\nthe statements, he admitted to saying that he would hang\nthe jury but claimed he could not “really remember”\nsaying “no matter what” the day before. JA5989–90. Juror\n12’s spotty recollection of the previous day’s events\nfurther supports the District Court’s finding that he was\nnot credible.\n 67\n\f Fattah argues that the credibility determination was\nnot, by itself, a sufficient reason to dismiss the juror\nbecause the record demonstrates more than a reasonable\npossibility that the complaints about his conduct stemmed\nfrom Juror 12’s own view of the Government’s case.\nFattah Reply Br. 11; Fattah Br. 25, 28. Fattah claims that\nthe District Court abused its discretion by dismissing Juror\n12 “on the basis of, in effect, six words the juror\npurportedly said to the court’s deputy after he was verbally\nattacked by other jurors.” Fattah Br. 24. According to\nFattah, the questioning of the other jurors “confirmed that\nthere were no legitimate grounds for removing juror 12.”\nId. at 26. We conclude otherwise.\n “A district court’s finding on the question whether\na juror has impermissibly refused to participate in the\ndeliberation process is a finding of fact to which\nappropriate deference is due.” Baker, 262 F.3d at 130.\nWhile district courts must apply a high standard for juror\ndismissal, their underlying findings are afforded\nconsiderable deference on appeal. Kemp, 500 F.3d at 304\n(citing Abbell, 271 F.3d at 1302–03). We will reverse only\nif the decision to dismiss a juror was “without factual\nsupport, or for a legally irrelevant reason.” Abbell, 271\nF.3d at 1302 (citation omitted).\n Here, the District Court had a legitimate reason for\nremoving Juror 12. Refusal to deliberate constitutes good\ncause for dismissal. Although the judge did not expressly\narticulate the Kemp standard when he announced that he\n\n 68\n\fwould dismiss Juror 12, he did acknowledge the “no\nreasonable possibility” standard in his discussion with\ncounsel. The unmistakable import of the District Court’s\nstatement from the bench is that there was no reasonable\npossibility that Juror 12’s intransigence was based on his\nview of the evidence. See Oscar, 877 F.3d at 1288 n.16.\n Fattah contends that there is no record support for\nthe finding that Juror 12 said “he was going to hang this\njury no matter what.” Fattah Br. 29. To be sure, the\ncourtroom deputy’s testimony is not that Juror 12 used the\nwords “hang this jury” and “no matter what” in the same\nsentence. She testified that Juror 12 first stated “I am going\nto hang this jury,” then later stated “it is going to be 11 to\n1 no matter what.” JA5981–82. This is a distinction\nwithout a difference. Likewise, Fattah challenges the\nDistrict Court’s finding that Juror 12 was determined to\nhang the jury “no matter what the law is” and “no matter\nwhat the evidence is.” Fattah Br. 29. Although there is no\nevidence that Juror 12 uttered the phrases “no matter what\nthe law is” or “no matter what the evidence is,” the District\nCourt was describing the import of Juror 12’s statements.\nThis was not error.\n Fattah expresses the concern that “[i]f jurors are\nasked the right questions or interrogated long enough, it\nwould not be difficult for a trial court to elicit testimony\nfrom [a] majority [of] jurors that can be held up as\nevidence of a dissenting juror’s bias or refusal to\ndeliberate.” Fattah Br. 22. He also worries that a group of\n\n 69\n\fjurors might have an incentive to rid themselves of a juror\nwho holds a different view. Id. These are valid concerns—\nbut no basis existed for such concerns in this case. Juror\n12’s own words provided most of the support for his\neventual dismissal. Furthermore, his statements were\nmade early in the deliberations, in a complex case, before\nany juror could reasonably be expected to have reached\nfinal verdicts on the twenty-nine counts before the jury.\n\n The able District Judge did not err in finding that\nJuror 12 refused to deliberate and therefore violated his\noath.\n\n IV. The District Court’s Instructions Under\n McDonnell\n On appeal, Fattah and Vederman renew their\nchallenge to the jury instructions given on Counts 3, 16,\n17, 18, 22, and 23, concerning the meaning of the term\n“official act” as used in the bribery statute (pursuant to\nwhich both were convicted) and the honest services fraud\nstatute (pursuant to which Fattah alone was convicted).\n\n In light of the Supreme Court’s opinion in\nMcDonnell v. United States, 136 S. Ct. 2355 (2016),\nreleased the week after the jury verdict, the District Court\nconceded that its instructions were incomplete and\nerroneous, at least as to Counts 16–18. Nevertheless, the\nDistrict Court held that the erroneous jury instructions had\nnot influenced the verdict on the bribery counts, and\ndeclined to set aside Fattah and Vederman’s convictions.\n 70\n\fAs to Counts 16–18 and 22–23, we disagree, and will\nreverse the District Court’s judgment. The District Court’s\njudgment with respect to Count 3, which did not involve\nVederman, will be affirmed. JA78–79.\n\n A. The McDonnell Framework\n In McDonnell, the Supreme Court interpreted the\nterm “official act” as defined in 18 U.S.C. § 201(a)(3). 136\nS. Ct. at 2368. The statute defines an “official act” as “any\ndecision or action on any question, matter, cause, suit,\nproceeding or controversy, which may at any time be\npending, or which may by law be brought before any\npublic official, in such official’s official capacity, or in\nsuch official’s place of trust or profit.” 18 U.S.C.\n§ 201(a)(3). The McDonnell Court distilled this definition\ninto two requirements:\n First, the Government must identify a\n “question, matter, cause, suit, proceeding or\n controversy” that “may at any time be\n pending” or “may by law be brought” before\n a public official. Second, the Government\n must prove that the public official made a\n decision or took an action “on” that question,\n matter, cause, suit, proceeding, or\n controversy, or agreed to do so.\n\n136 S. Ct. at 2368. Applying this two-step test to Governor\nRobert McDonnell’s convictions, the Supreme Court\nconcluded that “the jury was not correctly instructed on\n 71\n\fthe meaning of ‘official act,’ ” and as a result, “may have\nconvicted Governor McDonnell for conduct that is not\nunlawful.” Id. at 2375. Given that uncertainty, the Court\n“[could not] conclude that the errors in the jury\ninstructions were ‘harmless beyond a reasonable doubt.’ ”\nId. (quoting Neder v. United States, 527 U.S. 1, 16 (1999)).\nThe Supreme Court, therefore, vacated Governor\nMcDonnell’s convictions. Id.\n\n McDonnell lays out a clear path for the Government\nto follow in proving that an accused has performed an\n“official act.” First, the Government must “identify a\n‘question, matter, cause, suit, proceeding or controversy’\nthat ‘may at any time be pending’ or ‘may by law be\nbrought’ before a public official.” 136 S. Ct. at 2368\n(quoting 18 U.S.C. § 201(a)(3)). This first step is divided\ninto two sub-components. In Step 1(A), the Government\nmust “identify a ‘question, matter, cause, suit, proceeding\nor controversy.’ ” Id. Step 1(B) then clarifies that the\nidentified “question, matter, cause, suit, proceeding or\ncontroversy” be one that “ ‘may at any time be pending’ or\n‘may by law be brought’ before a public official.” Id.\n\n Under Step 1(A), a “question, matter, cause, suit,\nproceeding or controversy” must be “a formal exercise of\ngovernmental power that is similar in nature to a lawsuit\nbefore a court, a determination before an agency, or a\nhearing before a committee.” Id. at 2372. Importantly, “a\ntypical meeting, telephone call, or event arranged by a\n\n\n 72\n\fpublic official” does not qualify as such a formal exercise\nof governmental power. Id. at 2368.\n Step 1(B) then requires us to ask whether the\nqualifying “question, matter, cause, suit, proceeding or\ncontroversy” was one that “ ‘may at any time be pending’\nor ‘may by law be brought’ before a public official.” Id.\nAs the McDonnell Court clarified, “ ‘[p]ending’ and ‘may\nby law be brought’ suggest something that is relatively\ncircumscribed—the kind of thing that can be put on an\nagenda, tracked for progress, and then checked off as\ncomplete.” Id. at 2369; accord United States v. Repak, 852\nF.3d 230, 252 (3d Cir. 2017) (quoting McDonnell, 136 S.\nCt. at 2369). By contrast, matters described at a high level\nof generality—for example, “[e]conomic development,”\n“justice,” and “national security”—are not sufficiently\n“focused and concrete.” McDonnell, 136 S. Ct. at 2369.\n\n In McDonnell, the Court concluded that at least\nthree questions or matters identified by the Fourth Circuit\nwere sufficiently focused:\n (1) whether researchers at any of Virginia’s\n state universities would initiate a study of [a\n drug]; (2) whether the state-created Tobacco\n Indemnification and Community\n Revitalization Commission would allocate\n grant money for the study of [a chemical\n compound]; and (3) whether the health\n insurance plan for state employees in\n\n 73\n\f Virginia would include [a specific drug] as a\n covered drug.\nId. at 2370 (internal quotations omitted) (quoting United\nStates v. McDonnell, 792 F.3d 478, 515–16 (4th Cir.\n2015)). We provided guidance in the form of a fourth\nexample in Repak, when we held that a redevelopment\nauthority’s awarding of contracts was “a concrete\ndetermination made by the [redevelopment authority’s]\nBoard of Directors.” 852 F.3d at 253.\n\n Step 2 requires the Government to prove that the\npublic official made a “decision” or took “an action” on\nthe identified “question, matter, cause, suit, proceeding or\ncontroversy.” McDonnell, 136 S. Ct. at 2368. The\nMcDonnell Court explained:\n Setting up a meeting, hosting an event, or\n calling an official (or agreeing to do so)\n merely to talk about a research study or to\n gather additional information . . . does not\n qualify as a decision or action on the pending\n question of whether to initiate the study.\n Simply expressing support for the research\n study at a meeting, event, or call—or sending\n a subordinate to such a meeting, event, or\n call—similarly does not qualify as a decision\n or action on the study, as long as the public\n official does not intend to exert pressure on\n another official or provide advice, knowing\n\n 74\n\f or intending such advice to form the basis for\n an “official act.”\nId. at 2371. The Court further clarified:\n\n If an official sets up a meeting, hosts an\n event, or makes a phone call on a question or\n matter that is or could be pending before\n another official, that could serve as evidence\n of an agreement to take an official act. A jury\n could conclude, for example, that the official\n was attempting to pressure or advise another\n official on a pending matter. And if the\n official agreed to exert that pressure or give\n that advice in exchange for a thing of value,\n that would be illegal.\nId.\n Here, Fattah was charged with engaging in three\ncategories of official acts, which we analyze in accordance\nwith the McDonnell framework. In Counts 16–18 and 22–\n23, Fattah is alleged to have set up a meeting between\nVederman and the U.S. Trade Representative, attempted\nto secure Vederman an ambassadorship, and hired\nVederman’s girlfriend, all in return for a course of conduct\nwherein Vederman provided things of value to Fattah.\n\n In this case, as in McDonnell, the jury instructions\nwere erroneous. We conclude that the first category of the\ncharged acts—setting up a meeting between Vederman\n 75\n\fand the U.S. Trade Representative—is not unlawful, and\nthat the second category—attempting to secure Vederman\nan ambassadorship—requires reconsideration by a\nproperly instructed jury. The third charged act—hiring\nVederman’s girlfriend—is clearly an official act. But\nbecause we cannot isolate the jury’s consideration of the\nhiring from the first two categories of charged acts, we\nmust reverse and remand the judgment of the District\nCourt.\n\n B. The Kirk Meeting\n We turn first to Fattah’s scheduling of a meeting\nbetween Vederman and the U.S. Trade Representative,\nRon Kirk. Under McDonnell, “setting up a meeting . . .\ndoes not, standing alone, qualify as an ‘official act.’ ” 136\nS. Ct. at 2368. Fattah’s setting up the meeting between\nVederman and Kirk was therefore not an official act, a\nconcession implicit in the Government’s opening brief.\nSee Gov’t Br. 32 (failing to mention the Kirk meeting as\none of the “two categories” of allegedly “official acts”).\nBut the jury was not properly instructed on this point.\nWithout the benefit of the principles laid down in\nMcDonnell, the jury was free to conclude that arranging\nthe Kirk meeting was an official act—and it may have\ndone so. The District Court’s erroneous jury instructions,\ntherefore, cannot survive harmless error review.\n\n In a footnote in its brief to this Court, the\nGovernment argues that evidence about the Kirk meeting\nwas offered only “because it established the strength of\n 76\n\fVederman’s desire to be an ambassador” and not because\nthe Government was attempting to establish the meeting\nas an independent official act. Id. at79–80 n.6. But the\nrecord undercuts the Government’s post hoc justification.\n\n The indictment, provided to the jury in redacted\nform for use in its deliberations, lists Fattah’s setting up\nthe Kirk meeting as an official act under the heading\n“FATTAH’s Official Acts for VEDERMAN.” JA494.\nUnder this heading are three distinct subheadings:\n(1) “The Pursuit of an Ambassadorship,” (2) “The Pursuit\nof Another Executive Branch Position,” and (3) “Hiring\nthe Lobbyist’s Girlfriend to the Congressional Staff.”\nJA494–95. The second subheading, “The Pursuit of\nAnother Executive Branch Position,” describes the\narrangement of the Kirk meeting. Quite clearly, then, this\nthree-part structure demonstrates that setting up the Kirk\nmeeting was one of three distinct categories of official acts\nalleged by the Government.\n\n Although there is some support for the\nGovernment’s argument that evidence of the Kirk meeting\nwas presented at trial only to establish the extent of\nVederman’s interest in becoming an ambassador, JA827,\n852–53 (mentioning the Kirk meeting in close proximity\nto references to Fattah’s attempts to secure Vederman an\nambassadorship), it is undermined by language in the\nredacted indictment itself, and by the way in which the\nGovernment presented its case at trial as a “pattern” of\nconnected acts.\n\n 77\n\f The redacted indictment, for example, refers to the\nKirk meeting as “The Pursuit of Another Executive\nBranch Position.” JA495 (emphasis added). The use of the\nword “Another” strongly suggests that evidence about the\nKirk meeting was not merely evidence of Fattah’s attempt\nto secure Vederman an ambassadorship, but was also\nevidence of a separate and distinct attempt to secure\nVederman a position on a federal trade-related\ncommission. The redacted indictment also notes that “[i]n\nor around May 2011, with little progress made on securing\nan ambassadorship for VEDERMAN, FATTAH turned\ntowards obtaining for VEDERMAN an appointment in the\nExecutive Branch to a federal trade commission.” Id.\n(emphasis added). The words “turned towards,” taken\nliterally, clearly convey that arranging the Kirk meeting\nwas presented as distinct from Fattah’s efforts to secure\nVederman an ambassadorship.\n\n The District Court denied Fattah and Vederman a\nnew trial on Counts 17 and 18, referring to evidence of the\nKirk meeting as “de minimis” and noting that “Kirk’s\ntestimony during this lengthy trial lasted a mere sixteen\nminutes.” JA97 n.14. In the District Court’s view,\nevidence of the Kirk meeting “played no role in the\noutcome” of the case. Id. Considering the record in light\nof McDonnell, we are not so sure.\n\n Although it is possible that evidence of the Kirk\nmeeting played a minor role at trial when compared to the\nother acts on which the Government presented evidence,\n\n 78\n\fthe redacted indictment suggests that the Kirk meeting was\na significant part of the Government’s case. The\nindictment dedicates five paragraphs to describing the\nKirk meeting, but just three paragraphs to describing the\nhiring of Vederman’s girlfriend—a hiring that, as we\nexplain below, is clearly an official act. JA495–96. While\nneither the number of minutes used at trial nor the number\nof paragraphs contained in an indictment is a dispositive\nunit of measurement for determining the significance of\nevidence, we conclude that the District Court’s erroneous\njury instructions pertaining to the Kirk meeting were not\nharmless.\n We conclude, in accordance with McDonnell, that\nFattah’s arranging a meeting between Vederman and the\nU.S. Trade Representative was not itself an official act.\nBecause the jury may have convicted Fattah for conduct\nthat is not unlawful, we cannot conclude that the error in\nthe jury instruction was harmless beyond a reasonable\ndoubt, and we must vacate and remand the convictions of\nFattah and Vederman as to Counts 16, 17, 18, 22 and 23.\n\n C. Fattah’s Efforts to Secure Vederman an\n Ambassadorship\n The nature of Fattah’s efforts to secure Vederman\nan ambassadorship is less clear, and presents a closer\nquestion than the Kirk meeting. We ultimately conclude\nthat the question warrants remand so that it may be\nanswered by a properly instructed jury. On remand, the\njury must decide whether Fattah’s conduct constituted a\n 79\n\f“decision” or “action” under Step 2 of the McDonnell\nanalysis.\n At the outset, it is clear to us that, under Steps 1(A)\nand 1(B), a formal appointment of Vederman as an\nambassador would qualify as a “matter” that “may at any\ntime be pending” before a public official. The formal\nappointment of a particular person (Vederman), to a\nspecific position (an ambassadorship), constitutes a matter\nthat is sufficiently focused and concrete. The formal\nappointment of an ambassador is a matter that is “pending”\nbefore the President—the constitutional actor charged\nwith nominating ambassadors—as well Senators, who are\ncharged with confirming the President’s ambassadorial\nnominations. U.S. Const. art. II § 2 (“[H]e shall nominate,\nand by and with the Advice and Consent of the Senate,\nshall appoint Ambassadors . . . .”). It is beyond cavil that\nthe formal appointment of an ambassador satisfies both\nsub-components of McDonnell’s Step 1.\n Turning to Step 2, we consider whether Fattah’s\nefforts to secure Vederman an ambassadorship qualify as\nmaking a “decision” or taking “an action” on the identified\n“matter” of appointment. McDonnell, 136 S. Ct. at 2368.\nAlthough those efforts—three emails, two letters, and one\nphone call—do not themselves qualify as a “question,\nmatter, cause, suit, proceeding, or controversy” under\nMcDonnell’s Step 1, they may nonetheless qualify as the\nmaking of a “decision” or taking “an action” on the\nidentified matter of appointment. Id.\n\n 80\n\f McDonnell’s Step 2 requires us to determine\nwhether Fattah’s efforts qualify as permissible attempts to\n“express[] support,” or impermissible attempts “to\npressure or advise another official on a pending matter.”\nId. at 2371. At trial, the jury was not instructed that they\nhad to place Fattah’s efforts on one side or the other of this\ndivide. The jury might even have thought they were\npermitted to find Fattah’s efforts—three emails, two\nletters, and one phone call—to themselves be official acts,\nrather than a “decision” or “action” on the properly\nidentified matter of appointment. Such a determination\nwould have been contrary to the dictates of McDonnell.\n Faced with such uncertainty, we cannot assume the\njury verdict was proper. Although the jury might not have\nconcluded that Fattah’s efforts were themselves official\nacts, and although the jury might not have concluded that\nthose efforts crossed the line into impermissible attempts\n“to pressure or advise,” we are unable to conclude that the\njury necessarily did so. Nor can we, on the cold record\nbefore us, determine whether Fattah’s efforts to secure\nVederman an ambassadorship crossed the line.\nDetermining, for example, just how forceful a strongly\nworded letter of recommendation must be before it\nbecomes impermissible “pressure or advice” is a fact-\nintensive inquiry that falls within the domain of a properly\ninstructed jury. Should the Government elect to retry these\ncounts after remand, the finder of fact will need to decide\nwhether Fattah’s efforts constituted permissible attempts\nto “express[] support,” or impermissible attempts “to\n 81\n\fpressure or advise another official on a pending matter.”\nId.\n\n D. The Zionts Hiring\n The third group of acts charged in the Fattah–\nVederman scheme involves Fattah’s decision to hire\nVederman’s girlfriend, Alexandra Zionts, as a\ncongressional staffer. We conclude that the hiring was an\nofficial act. A brief analysis of McDonnell’s two steps\nsuffices to show why this is so.\n Here, under McDonnell’s Step 1(A), the relevant\n“matter” is the decision to hire Zionts. Step 1(B) of the\nanalysis is satisfied because the hiring decision was\n“pending” before Fattah himself. And that hiring was\n“focused and concrete,” “within the specific duties of an\nofficial’s position—the function conferred by the\nauthority of his office.” Id. at 2369. Finally, McDonnell’s\nStep 2 requires that the “Government . . . prove that the\npublic official made a decision or took an action ‘on’ [the\nidentified] question, matter, cause, suit, proceeding, or\ncontroversy, or agreed to do so.” Id. at 2368. Fattah’s\ndecision to hire Zionts clearly satisfies that requirement.\nWe therefore conclude that the hiring of Zionts was an\nofficial act under McDonnell.\n\n Vederman concedes that the Zionts hiring was an\nofficial act. Oral Argument Transcript at 5–6. Fattah, for\nhis part, maintains that “hiring someone for a routine, part-\ntime, short-term position falls well outside [the] definition\n 82\n\f[of ‘official act’] and is nothing like a lawsuit, agency\ndetermination, or committee hearing, even if each shares\nthe happenstance that federal funds will be used.” Fattah\nReply Br. 25.\n\n Fattah’s argument lacks traction. Official acts need\nnot be momentous decisions—or even notable ones.\nJudges, for example, make “routine” evidentiary rulings\nevery day, and yet it is beyond question that those rulings\nare official acts. In the realm of official acts, it is of no\nmoment that Zionts provided only “part-time, short term”\nlabor. When a public official hires an employee to work in\nhis government office, he has engaged in an official act.\n * * *\n If we could conclude that the Zionts hiring was the\nonly category of actions that the jury relied on when it\nfound that Fattah performed an official act under Counts\n16–18 and 22–23, remand would not be necessary. But, as\nwe have explained, we cannot rule out that the jury\nerroneously convicted Fattah and Vederman based on\nother actions that were not official acts under\nMcDonnell.13\n\n\n13\n More specifically, the incomplete, and therefore\nerroneous, instructions could have led the jury to commit\nat least one of three mistakes. First, the jury could have\nimproperly convicted Vederman and Fattah based on the\nKirk meeting alone, or misunderstood the Kirk meeting to\n 83\n\f The Government argues that because the Zionts\nhiring was an official act, the effect of the erroneous jury\ninstructions could be no more than harmless. The jury’s\nverdict, the Government contends, permits us to deduce\nthat the jury necessarily concluded the Zionts hiring was\nan official act, and that this conclusion alone supported\nFattah’s and Vederman’s convictions as to Counts 16–18\nand 22–23—regardless of whether the jury erroneously\nfound any unofficial acts to be official acts. We disagree.\n Fattah and Vederman objected to the definition of\n“official act” at trial. We thus apply the harmless error\nstandard of review. McDonnell, 136 S. Ct. at 2375. The\nGovernment argues that because the jury convicted Fattah\nand Vederman of illegally laundering the proceeds of a\n“scheme to commit bribery” under Count 23, the jury\nfound that the scheme must have encompassed only the\nZionts hiring. JA531.That would mean that the jury did not\nconclude that the “scheme to commit bribery” included\n\nbe a necessary component of an impermissible “pattern”\nof official acts. Second, the jury might have concluded that\nFattah’s efforts to secure Vederman an ambassadorship\nwere themselves official acts. Third, the jury might have\nconcluded that Fattah’s efforts to secure Vederman an\nambassadorship were merely attempts to “express[]\nsupport,” rather than to “exert pressure . . . or provide\nadvice,” but nonetheless erroneously concluded that those\nexpressions of support were official acts. McDonnell, 136\nS. Ct. at 2371.\n 84\n\fany acts that McDonnell now makes clear were unofficial.\nYet the redacted indictment, jury instructions, and the fact\nthat the Government presented its case under a “pattern”\ntheory at trial compel us to reject the Government’s\nargument.\n\n The very first sentence under Count 23 of the\nredacted indictment incorporates all three categories of\n“Overt Acts” contained within paragraphs “58 through 95\nof Count One.” 14 All three of these categories fall under a\ngeneral heading within the redacted indictment titled “The\nBribery and Fraud Scheme [redacted].” JA494. The jury\nhad before it instructions for Count 23 which referred to\n“the alleged bribery scheme involving an $18,000\npayment,” JA448 (emphasis added), and the redacted\nindictment which referred to “a scheme to commit\nbribery,” JA531 (emphasis added). The parallel language\ncould well lead a rational jury to conclude that the relevant\n“scheme” included all three categories of acts listed under\nthe general heading: “The Bribery and Fraud Scheme\n[redacted].” JA494 (emphasis added).\n\n\n\n14\n JA531. Paragraphs 58 through 95 of Count 1 refer to the\nthree categories of allegedly official acts discussed above:\n(1) “The Pursuit of an Ambassadorship,” (2) “The Pursuit\nof Another Executive Branch Position,” and (3) the\n“Hiring of the Lobbyist’s Girlfriend to the Congressional\nStaff.” JA494–95.\n 85\n\f Like the redacted indictment and jury instructions,\nthe Government’s trial arguments referred to patterns and\na course of conduct, and stressed that the jury need not\nconnect specific payments to particular official acts. In its\nclosing argument to the jury, the Government stated that\nthe alleged “scheme took place over a period of several\nyears. Over and over again you’re going to see the same\npattern.” JA5383 (emphasis added). Then, in its rebuttal\nargument, the Government went out of its way to\nexplicitly distinguish its “pattern” theory from an\nalternative theory that would have directly connected\nindividual payments to individual acts. As the prosecutor\nargued to the jury:\n Ms. Recker appears to argue that each thing\n of value must coincide with some specific\n official act, but that is not the law and that is\n not what Judge Bartle is going to instruct you.\n Instead what he will tell you is that the\n government is not required to prove that\n Vederman intended to influence Fattah to\n perform a set number of official acts in return\n for things of value so long as the evidence\n shows a course of conduct of giving things of\n value, things of value to Fattah in exchange\n for a pattern of official acts favorable to\n Vederman. In other words a stream of\n benefits. These for those, not this for that.\n\n\n\n 86\n\fJA5715–16 (emphases added). In closing to the jury, the\nGovernment made several other references to this\n“pattern” theory, 15 and the District Court referred to this\n“pattern” theory in its instructions to the jury. As Judge\nBartle instructed:\n\n [I]t is not necessary for the government to\n prove that a defendant intended to induce a\n public official to perform a number of official\n acts in return for things of value.\n So as long as the evidence shows a\n course of conduct of giving things of value to\n a public official in exchange for a pattern of\n official acts favorable to the giver.\n\nJA5833–34 (emphasis added). On appeal, the Government\nchanges course, asking us to assume that the jury ignored\nthese repeated references to a “pattern of official acts” and\n\n15\n See, e.g., JA5389 (“And the exchange of an official act\nfor a thing of value is called a bribe. There’s the pattern.\nFattah needs money, Vederman gets an official act.”); JA\n5393 (“That’s why you see the pattern over and over again.\nFattah needs money, Vederman gets an official act.”);\nJA5400 (“The same pattern we saw over and over again.\nFattah needs money, Vederman gets an official act.”);\nJA5409 (“[Y]ou know that these were bribes because of\nthe pattern you saw over and over and over again. Fattah\nneeds money, Vederman gets an official act, that makes\nthese things a bribe.”).\n 87\n\finstead considered the Zionts hiring and Vederman’s\n$18,000 payment to Fattah as an isolated quid pro quo.\nThis is an invitation to speculate, and we decline to do so.16\nThe jury began its deliberations accompanied by a copy of\nthe redacted indictment which alleged a pattern of official\nacts, consisting of any combination of three categories of\nacts: pursuing an ambassadorship, arranging the Kirk\nmeeting, and hiring Zionts. In light of the erroneous\ninstructions, and because only one category clearly\n\n16\n Providing some support to the Government’s ultimately\nunconvincing argument that the jury considered the Zionts\nhiring and $18,000 payment in isolation, we note that the\nredacted indictment does mention those two events side-\nby-side in paragraph 78 of the indictment’s Part V. JA497\n(“On January 13, 2012, VEDERMAN wired $18,000 to\nFATTAH, and six days later, on January 19, 2012,\nBOWSER emailed VEDERMAN’s girlfriend, A.Z.,\nwelcoming her as a new employee to FATTAH’s\nCongressional Staff.”). But although paragraph 78\nmentions the $18,000 wire transfer and the Zionts hiring\nin the same breath, paragraph 78 does not instruct the jury\nto connect these two events apart from the rest of the\nevidence presented at trial. In light of the other instructions\nand arguments indicating that the jury should not consider\nthe Zionts hiring in isolation, but instead should consider\nthe hiring as one part of a three-part scheme, paragraph 78\nis not sufficient to avoid a reversal and remand on the\nconvictions of Fattah and Vederman as to Counts 16–18\nand 22–23.\n 88\n\fqualifies as an “official act,” the jury’s deliberations were\nfraught with the potential for McDonnell error. We will\nvacate the convictions of Fattah and Vederman as to\nCounts 16, 17, 18, 22, and 23, and remand to the District\nCourt.\n\nE. Vederman’s Sufficiency Challenge to Counts 16–18\n and 22–23\n Vederman argues that there is insufficient evidence\nto support a conviction, even if a jury were properly\ninstructed under McDonnell. Specifically, Vederman\nargues that there is insufficient evidence to convict him\nand Fattah, after remand, on Counts 16–18 and 22–23\nbecause “[a]t least seven of the eight alleged ‘official acts’\nwere, as a matter of law, not official at all.” Vederman Br.\n35. As to the single act that Vederman implicitly concedes\nto be an official act—the Zionts hiring—Vederman argues\nthat “[t]he only thing that even arguably associates” the\nZionts hiring with Vederman was its timing in relation to\nVederman’s sham purchase of the Fattahs’ Porsche. Id.\nAccording to Vederman, “the undisputed chronology\nprecludes any inference that Vederman conferred this\nbenefit on his friend as an illegal bribe.” Id. (emphasis\nomitted). Vederman is wrong. Sufficient evidence was\nproduced at trial to have allowed a properly-instructed jury\nto convict Fattah and Vederman of Counts 16–18 and 22–\n23.\n To begin with, even if the Zionts hiring had been the\nsole official act to survive this Court’s interpretation of\n 89\n\fMcDonnell, there would still be sufficient evidence to\nconvict Fattah and Vederman. Zionts did not receive\nwritten notice of her official hiring until six days after the\nsham Porsche purchase. Moreover, the jury would not be\nrestricted to considering the chronology of the sham\npurchase alone. It would be free to consider Vederman’s\nentire course of conduct. Under the general heading\n“VEDERMAN’S Payments and Things of Value to\nFATTAH,” the redacted indictment not only refers to the\n$18,000 wire transaction from Vederman to Fattah as part\nof the sham Porsche purchase, but also to Vederman’s\n$3,000 payment for the college tuition of Simone Muller,\nFattah’s live-in au pair, as well as thousands of dollars in\npayments made by Vederman for Chip Fattah’s college\ntuition. JA496–97.\n And the Zionts hiring is not the only act to survive\nour application of McDonnell. As we explained, a jury\ncould find that Fattah’s efforts to secure Vederman an\nambassadorship—three emails, two letters, and a phone\ncall—were an impermissible attempt to “pressure or\nadvise” President Obama, Senator Casey, or both men.17\n\n17\n Although Fattah’s efforts to secure Vederman an\nambassadorship present a jury question that is not for us to\nanswer on appeal, we note that not one of these efforts\nalone could qualify as an official act itself. See McDonnell,\n136 S. Ct. at 2372 (“Setting up a meeting, talking to\nanother official, or organizing an event (or agreeing to do\nso)—without more—does not fit that definition of ‘official\n 90\n\fThis means that a properly instructed jury on remand,\npresented with evidence of Fattah’s efforts to secure an\nambassadorship for Vederman and evidence of the Zionts\nhiring, could find more than a single official act.\n\n F. Blue Guardians\n In addition to the charges arising from his dealings\nwith Vederman, Fattah was charged in Count 3 with\n\n\nact.’ ”). The relevant question for a jury to consider on\nremand, then, is whether these actions constituted “a\n‘decision or action’ on a different question or matter”—to\nwit, the formal appointment of an ambassador. Id. at 2369\n(emphasis omitted).\n Even though the emails, letters, and phone call are\nnot, individually, official acts, it will be for a jury to decide\nif Fattah’s efforts to secure an ambassadorship for\nVederman crossed the line from permissible “support” to\nimpermissible “pressure or advice.” While we express\ndoubt that some of Fattah’s efforts concerning the\nambassadorship are, when considered in isolation, enough\nto cross that line, a properly instructed jury considering all\nof the facts in context might nonetheless conclude that\nother efforts—such as a hand-delivered letter to the\nPresident of the United States—indeed crossed that line.\nFurther, a jury might find that in the aggregate, three\nemails, two letters, and a phone call crossed the line and\ntherefore constituted a “decision or action” on the\nidentified matter of appointment.\n 91\n\fparticipating in a scheme with Lindenfeld to funnel money\nto a fraudulent nonprofit organization. In connection with\nthis scheme, Fattah was convicted of conspiring to commit\nhonest services fraud.\n\n Fattah owed Lindenfeld nearly $100,000 for work\nperformed on Fattah’s 2007 mayoral campaign. In lieu of\nrepayment, Fattah suggested that Lindenfeld create an\nentity, later named Blue Guardians, to which Fattah would\ndirect $15,000,000 in public funds by using his position as\na member of the House Committee on Appropriations.\nNothing in McDonnell requires us to upset Fattah’s\nconviction on Count 3.\n Step 1(A) of our McDonnell analysis requires the\nGovernment to “identify a ‘question, matter, cause, suit,\nproceeding or controversy.’ ” 136 S. Ct. at 2368. Here, the\n“matter” is the appropriation of millions of dollars in\npublic funds. See Repak, 852 F.3d at 253–54 (holding the\nawarding of redevelopment funds to be an official act). In\nparticular, it was Fattah’s promise to perform this official\nact that was unlawful. As McDonnell makes clear:\n\n [A] public official is not required to actually\n make a decision or take an action on a\n “question, matter, cause, suit, proceeding or\n controversy”; it is enough that the official\n agree to do so. The agreement need not be\n explicit, and the public official need not\n specify the means that he will use to perform\n his end of the bargain.\n 92\n\f136 S. Ct. at 2370–71 (internal citations omitted). That\nFattah took steps to actually carry out his promise (e.g., by\ndrafting and sending a formal appropriations request on\nofficial congressional letterhead) is evidence of his illegal\npromise. See id. at 2371.\n\n Step 1(B) requires the Government to establish that\nthe “ ‘question, matter, cause, suit, proceeding or\ncontroversy’ . . . ‘may at any time be pending’ or ‘may by\nlaw be brought’ before a public official.” McDonnell, 136\nS. Ct. at 2368. Appropriating public funds was not only a\nmatter that was pending before Fattah as a member of the\nAppropriations Committee, it was also a matter that was\npending before the Chairman and Ranking Member of an\nAppropriations Subcommittee to whom Fattah ultimately\nsent a formal written request. See id. at 2369 (“[T]he\nmatter may be pending either before the public official\nwho is performing the official act, or before another public\nofficial.”). Appropriating millions of dollars in response to\nthe Blue Guardians request is “focused and concrete,” and\n“the kind of thing that can be put on an agenda, tracked for\nprogress, and then checked off as complete.” Id.\n\n Given Fattah’s membership on the Appropriations\nCommittee, this was “something within the specific duties\nof an official’s position—the function conferred by the\nauthority of his office.” Id. Even if we were to assume,\nagainst all reason, that an appropriation is not “something\nwithin the specific duties” of either Fattah or the Chairman\nor Ranking Member of an Appropriations Subcommittee,\n\n 93\n\fFattah’s formal request for an appropriation was\nsomething that Fattah had the authority to do. Like the\nExecutive Director in Repak, who lacked authority himself\nto award redevelopment funds but could request such\nfunds from the Board, Fattah used his position as a\nCongressman to formally request appropriations for the\nBlue Guardians. 852 F.3d at 254 (“Repak had the power\nto, and indeed did, make recommendations to the\n[redevelopment authority.\n Step 2 of McDonnell requires the Government to\n“prove that the public official made a decision or took an\naction ‘on’ that question, matter, cause, suit, proceeding,\nor controversy, or agreed to do so.” 136 S. Ct. at 2368\n(emphasis added). Here, Fattah agreed to request an\nappropriation for a bogus purpose. Unlike Fattah’s letters,\nemails, and phone call seeking an ambassadorship for\nVederman, there is no potential for the jury to have made\na mistake when it found Fattah’s Blue Guardians promise\nunlawful.\n Fattah argues that the Government presented “[n]o\nevidence . . . that would have allowed [the jury] to\nconclude that [he] made a decision or took an action, or\ncould have done so, on the question whether Blue\nGuardians would receive a $15 million federal grant.”\nFattah Br. 46. This argument misses the point. It was\nFattah’s agreement to engage in the official act of formally\nrequesting the appropriation that was illegal. See\nMcDonnell, 136 S. Ct. at 2371.\n\n 94\n\f Lindenfeld’s trial testimony provided sufficient\nevidence of Fattah’s illegal agreement. JA1694–96, 1954.\nFattah’s letter provided additional evidence from which\nthe jury could have concluded that Fattah illegally agreed\nto perform an official act. 18 In short, the agreement itself\nwas illegal, and the Government provided sufficient\nevidence for the jury to conclude that the illegal agreement\ntook place.\n\n The Government’s evidence in support of the Blue\nGuardians scheme meets the requirements of McDonnell,\nand the Count 3 verdict will stand.\n\n V. Sufficiency of the Evidence for the RICO\n Conspiracy Conviction\n The jury found Fattah, Vederman, Brand, and\nNicholas guilty of the RICO conspiracy charged in Count\n1 of the indictment, but acquitted Bowser. Vederman filed\na post-verdict motion, and the District Court overturned\nhis RICO conspiracy conviction.\n\n\n\n18\n Despite Fattah’s protestation to the contrary, there is\nevidence that Fattah took steps to carry out his official act.\nJA6432–33 (Letter from Congressman Fattah to House\nAppropriations Subcommittee members “request[ing]\nfunding and support for the following projects and\nprograms of critical importance,” including $3,000,000\nfor “Blue Guardians”).\n 95\n\f On appeal, Fattah, Brand, and Nicholas challenge\nthe sufficiency of the evidence supporting their RICO\nconspiracy convictions. We “review[] the sufficiency of\nthe evidence in the light most favorable to the government\nand must credit all available inferences in favor of the\ngovernment.” United States v. Riddick, 156 F.3d 505, 509\n(3d Cir. 1998). If a rational juror could have found the\nelements of the crime beyond a reasonable doubt, we must\nsustain the verdict. United States v. Cartwright, 359 F.3d\n281, 286 (3d Cir. 2004), abrogated on other grounds by\nUnited States v. Caraballo-Rodriguez, 726 F.3d 418 (3d\nCir. 2013) (en banc).\n The indictment charged a RICO conspiracy in\nviolation of 18 U.S.C. § 1962(d), which makes it\n“unlawful for any person to conspire to violate” § 1962(c).\nSection 1962(c) provides:\n It shall be unlawful for any person . . .\n associated with any enterprise engaged in, or\n the activities of which affect, interstate . . .\n commerce, to conduct or participate, directly\n or indirectly, in the conduct of such\n enterprise’s affairs through a pattern of\n racketeering activity . . . .\n\n18 U.S.C. § 1962(c).\n\n In Salinas v. United States, 522 U.S. 52 (1997), the\ndefendant was convicted of a § 1962(d) RICO conspiracy,\nbut a jury acquitted him of the substantive RICO offense\n 96\n\funder § 1962(c). Id. at 55. The Supreme Court rejected\nSalinas’s contention that his conviction had to be set aside\nbecause he had neither committed nor agreed to commit\nthe two predicate acts required for the § 1962(c) offense.\nId. at 66. The Court declared that liability for a RICO\nconspiracy under § 1962(d), “unlike the general\nconspiracy provision applicable to federal crimes,” does\nnot require proof of an overt act. Id. at 63. A conspiracy\nmay be found, the Court explained, “even if a conspirator\ndoes not agree to commit or facilitate each and every part\nof the substantive offense. The partners in the criminal\nplan must agree to pursue the same criminal objective and\nmay divide up the work, yet each is responsible for the acts\nof each other.” Id. at 63–64 (citations omitted). This means\nthat, if a plan “calls for some conspirators to perpetrate the\ncrime and others to provide support, the supporters are as\nguilty as the perpetrators.” Id. at 64. Thus, opting into and\nparticipating in a conspiracy may result in criminal\nliability for the acts of one’s co-conspirators. Smith v.\nBerg, 247 F.3d 532, 537 (3d Cir. 2001).\n Accordingly, liability for a RICO conspiracy may\nbe found where the conspirator intended to “further an\nendeavor which, if completed, would satisfy all of the\nelements of a substantive criminal offense, but it suffices\nthat he adopt the goal of furthering or facilitating the\ncriminal endeavor.” Salinas, 522 U.S. at 65. Because the\nsubstantive criminal offense here was conducting a\n§ 1962(c) enterprise, the government had to prove:\n\n 97\n\f (1) that two or more persons agreed to\n conduct or to participate, directly or\n indirectly, in the conduct of an enterprise’s\n affairs through a pattern of racketeering\n activity; (2) that the defendant was a party to\n or member of that agreement; and (3) that the\n defendant joined the agreement or conspiracy\n knowing of its objective to conduct or\n participate, directly or indirectly, in the\n conduct of an enterprise’s affairs through a\n pattern of racketeering activity.\n\nUnited States v. John-Baptiste, 747 F.3d 186, 207 (3d Cir.\n2014).\n In United States v. Turkette, 452 U.S. 576 (1981),\nthe Supreme Court instructed that an enterprise is a “group\nof persons associated together for a common purpose of\nengaging in a course of conduct.” Id. at 583. The\ngovernment can prove an enterprise “by evidence of an\nongoing organization, formal or informal, and by evidence\nthat the various associates function as a continuing unit.”\nId. In Boyle v. United States, 556 U.S. 938 (2009), the\nSupreme Court established that an “association-in-fact\nenterprise must have at least three structural features: a\npurpose, relationships among those associated with the\nenterprise, and longevity sufficient to permit these\nassociates to pursue the enterprise’s purpose.” Id. at 946.\nThe structure necessary for a § 1962(c) enterprise is not\ncomplex. Boyle explained that an enterprise\n\n 98\n\f need not have a hierarchical structure or a\n “chain of command”; decisions may be made\n on an ad hoc basis and by any number of\n methods—by majority vote, consensus, a\n show of strength, etc. Members of the group\n need not have fixed roles; different members\n may perform different roles at different\n times. The group need not have a name,\n regular meetings, dues, [or] established rules\n and regulations . . . .While the group must\n function as a continuing unit and remain in\n existence long enough to pursue a course of\n conduct, nothing in RICO exempts an\n enterprise whose associates engage in spurts\n of activity punctuated by periods of\n quiescence.\n\nId. at 948.\n\n Another element of a substantive § 1962(c) RICO\nenterprise is that the enterprise must conduct its affairs\nthrough a pattern of racketeering activity. Section 1961\ndefines racketeering activity to include various criminal\noffenses, including wire fraud, 18 U.S.C. § 1344, and\nobstruction of justice, 18 U.S.C. § 1511. See 18 U.S.C.\n§ 1961(1). A pattern of such activity “requires at least two\nacts of racketeering activity.” Id. § 1961(5). The\nracketeering predicates may establish a pattern if they\n“related and . . . amounted to, or threatened the likelihood\n\n\n 99\n\fof, continued criminal activity.” H.J. Inc. v. Nw. Bell Tel.\nCo., 492 U.S. 229, 237 (1989).\n Here, the District Court denied the post-trial\nsufficiency arguments raised by Fattah, Brand, and\nNicholas. It reasoned:\n For a RICO conspiracy to exist, the\n conspirators must agree to participate in an\n enterprise with a unity of purpose as well as\n relationships among those involved. The\n evidence demonstrates that an agreement\n among Fattah, Brand, Nicholas, Lindenfeld,\n and Naylor existed for the overall purpose of\n maintaining and enhancing Fattah as a\n political figure and of preventing his standing\n from being weakened by the failure to be able\n to pay or write down his campaign debts.\n These five persons agreed to work together as\n a continuing unit, albeit with different roles.\n The Government established that\n Fattah, Brand, and Nicholas conspired along\n with Naylor and Lindenfeld to conceal and\n repay the 2007 illegal $1,000,000 loan to the\n Fattah for Mayor campaign.\n\nJA128–29. The District Court further determined that\n [w]hile each member may not have been\n involved in every aspect of the enterprise, its\n activities were sufficiently structured and\n 100\n\f coordinated to achieve the purpose of\n maintaining and enhancing Fattah’s political\n standing and of preventing him from being\n weakened politically because of his\n campaign debts.\n A RICO conspiracy also requires an\n agreement to participate in an enterprise with\n longevity sufficient to pursue its purpose.\n This was established. In May 2007 the illegal\n loan was obtained and continued through its\n repayment in January 2008 and into at least\n 2014 when the last campaign report reducing\n a fake campaign debt to Naylor’s consulting\n firm was filed by Fattah.\nJA131.\n\n The defendants argue that the evidence is\ninsufficient to show either an enterprise for purposes of\n§ 1962(c) or an agreement as required for a § 1962(d)\nconspiracy. We disagree, and conclude that the District\nCourt’s analysis is on the mark.\n\n We begin by considering whether there was an\nagreement. The evidence showed that Fattah knew each\nmember involved in the scheme to conceal the unlawful\ncampaign loan. When Lindenfeld learned of the $1 million\nloan, he informed Fattah that it exceeded campaign\nfinance limits. In short, the transaction was unlawful, and\nthe two knew it. The transaction nonetheless went\nforward, disguised as a loan, with Lindenfeld executing\n 101\n\fthe promissory note as Strategies’ officer and obligating\nStrategies to repay Lord $1 million. The concealment\nefforts continued as Lindenfeld funneled a substantial\nportion of the loan proceeds to Naylor for get-out-the-vote\nefforts. After the losing campaign, Lindenfeld spoke with\nFattah and Naylor about accounting for the funds that had\nbeen spent. They decided not to include the amounts in the\nFFM campaign reports. Fattah instructed Naylor to\nprepare a fictitious invoice, and Naylor complied. The\nFFM campaign reports filed from 2008 to 2014 disclosed\nnothing about the unlawful $1 million loan. Instead, they\nfalsely showed that Naylor’s consulting firm made yearly\nin-kind contributions of $20,000 in debt forgiveness, when\nin reality there was no debt to forgive.\n As Lindenfeld fretted over repaying the $600,000\nbalance of the Lord loan, Naylor assured him that Fattah\nhad promised to take care of the repayment. And the\nevidence supports an inference that Fattah recruited both\nNicholas and Brand in doing so. As EAA’s director,\nNicholas could fund the repayment. Brand, through his\ncompany, Solutions, acted as the middleman: he received\nthe payment from EAA pursuant to a fictitious contract,\nand then forwarded the balance due to Strategies pursuant\nto yet another fictitious contract. Nicholas and Brand\ncontinued in the spring and summer of 2008 to hide the\nfictitious agreement and the $600,000 payment to\nLindenfeld to satisfy the Lord loan.\n\n\n\n 102\n\f In short, this evidence shows that Fattah,\nLindenfeld, Naylor, Brand, and Nicholas all agreed to\nparticipate in Fattah’s plan to conceal the unlawful\ncampaign loan to maintain his political stature. Nicholas\nand Brand claim that they had no knowledge of the false\ncampaign reporting aspect of the plan. But as Salinas\ninstructs, conspirators need not “agree to commit or\nfacilitate each and every part of the” conspiracy. 522 U.S.\nat 63. Rather, they “must agree to pursue the same criminal\nobjective and may divide up the work, yet each [be]\nresponsible for the acts of each other.” Id. at 63–64. Thus,\na conspirator may agree to “facilitate only some of the acts\nleading to the substantive offense” yet still be criminally\nliable. Id. at 65.\n The evidence showed that a substantial amount of\nmoney was needed to repay Lord, and that the source of\nthe repayment was EAA, a non-profit organization whose\nfunds could be spent only for purposes consistent with the\nterms of the grants it received. It also showed that Nicholas\nwas presented with a sham contract to legitimize the\nEAA–Solutions transaction. We conclude that the\nevidence is sufficient to support an inference that Nicholas\nknew at the start that the plan was unlawful. Yet she still\nagreed to provide the requisite funds and to play a role in\nconcealing the illegal campaign loan so that Fattah could\nmaintain his political stature.\n\n As to Brand, even if he did not know that false\ncampaign reports were being filed, the evidence is\n\n 103\n\fsufficient to show he played a key role in the enterprise.\nFrom the outset, Brand worked to disguise the repayment\nof the Lord loan as the consideration in a sham contract\nbetween EAA and Solutions. He then arranged for the\ntransfer of funds to Strategies in satisfaction of a\ncontractual term in another purported business agreement\nbetween Solutions and Strategies. The evidence reveals\nthat Brand was the point man in the effort to meet the\nJanuary 31, 2008 deadline to repay the Lord loan, and it\namply shows that Brand also agreed to participate in the\nplan to hide the illegal campaign loan and its repayment to\nbenefit Fattah politically.\n Fattah, Brand, and Nicholas attack their RICO\nconspiracy convictions on another front. They argue that\nthose verdicts should be set aside because the evidence\nfails to show that the various schemes alleged in the\nindictment as part of the RICO conspiracy are connected.\nThe RICO count, they assert, charges a hub-and-spoke\nconspiracy that is unconnected by a rim. In their view,\nFattah is the hub, and the spokes consist of a series of\nindependent schemes: the Vederman bribery scheme, the\npayment of the outstanding tuition debt of Fattah’s son\nChip, the Blue Guardians plan, and the repayment of the\nillegal Lord loan to maintain Fattah’s political stature.\nThey argue that, without a unifying rim, their actions\ncannot constitute an enterprise. Again, we disagree.\n\n In In re Insurance Brokerage Antitrust Litigation,\n618 F.3d 300 (3d Cir. 2010), we concluded, in analyzing\n\n 104\n\fone of plaintiffs’ RICO claims, that the alleged hub-and-\nspoke enterprise—comprised of broker hubs and insurer\nspokes—could not withstand a motion to dismiss because\nit did not have a unifying rim. Id. at 374. We explained\nthat the allegations did “not plausibly imply concerted\naction—as opposed to merely parallel conduct—by the\ninsurers, and therefore cannot provide a ‘rim’ enclosing\nthe ‘spokes’ of these alleged ‘hub-and-spoke’\nenterprises.” Id. Thus, the allegations did not “adequately\nplead an association-in-fact enterprise” because the hub-\nand-spoke conspiracy failed to “function as a unit.” Id.\n\n That is not the case here. The evidence showed that\nFattah, Brand, and Nicholas agreed to conceal the illegal\nLord loan. Each acted for the common purpose of\nfurthering Fattah’s political interests. In short, they\nengaged in concerted activity and functioned as a unit. The\njury convicted Fattah, Brand, and Nicholas of the RICO\nconspiracy based on the racketeering activity of wire fraud\nand obstruction of justice to conceal the unlawful\ntransaction. Because the evidence shows that Fattah,\nLindenfeld, Naylor, Brand, and Nicholas agreed to protect\nFattah’s political status by acting to maintain the secrecy\nof the unlawful Lord loan, the alleged lack of a unifying\n“rim” is not fatal to this RICO enterprise. What matters in\nanalyzing the structure of this enterprise is that it\nfunctioned as a unit. Boyle, 556 U.S. at 945; In re Ins.\nBrokerage Antitrust Litig., 618 F.3d at 374. That “basic\nrequirement” was met. Id.\n\n 105\n\f We turn next to the contention that the evidence\nfails to establish other components of an enterprise. We\nconclude that much of the evidence supporting the\nexistence of an agreement also shows that there was an\nassociation-in-fact enterprise.\n\n Boyle made clear that an association-in-fact\nenterprise must have “a purpose, relationships among\nthose associated with the enterprise, and longevity\nsufficient to permit these associates to pursue the\nenterprise’s purpose.” 556 U.S. at 946. The purpose, as we\nhave repeatedly observed, was to maintain and preserve\nFattah’s political stature by concealing the illegal loan and\nits repayment. Though informal, there were relationships\namong those associated with the enterprise. Fattah was at\nthe center of this association and he directed its activity.\nHe knew each of the association’s members, and the\nmembers knew each other (except, perhaps, for Nicholas,\nwho may not have known Lindenfeld).19\n\n\n19\n Nicholas’s lack of familiarity with Lindenfeld does not\nundermine her membership in this association-in-fact\nenterprise. We have previously explained that “[i]t is well-\nestablished that one conspirator need not know the\nidentities of all his co-conspirators, nor be aware of all the\ndetails of the conspiracy in order to be found to have\nagreed to participate in it.” United States v. Riccobene, 709\nF.2d 214, 225 (3d Cir. 1983), abrogated on other grounds\nby Griffin v. United States, 502 U.S. 46 (1991).\n 106\n\f The Government also adduced sufficient proof of\nthe longevity component required for an enterprise. The\nscheme began in mid-2007, when Lord made the\ncampaign loan, directing the proceeds of the loan to\nStrategies. From the outset, Fattah, Lindenfeld, and Naylor\nall knew they needed to conceal this illegal transaction.\nThey began by fabricating an explanation for the source of\nthe funds they spent on election day. SLA created a fake\ninvoice for the campaign, showing a fictitious debt that\nNaylor could later forgive by fictitious in-kind\ncontributions existing only on Fattah’s campaign finance\nreports.\n The effort to disguise the Lord loan was not limited\nto filing false campaign reports. Nicholas and Brand, who\njoined the conspiracy a few months later than the other\nmembers, understood that they too had to make the\nfraudulent $600,000 payment by EAA to Solutions appear\nlegitimate. Nicholas and Brand tried to disguise the sham\ncontract as an ordinary transaction (even though it called\nfor a six-figure upfront payment simply to support\nSolutions’ various projects), and they succeeded in\nkeeping it out of the DOJ auditors’ view until August\n2008. The ruse continued as Solutions funneled the\n$600,000 payment to Strategies under the guise of another\nsham contract (which also required an upfront six-figure\npayment). The scheme then continued as Fattah submitted\nfalse FFM campaign reports from 2008 through 2014.\n\n\n\n 107\n\f Finally, we consider whether the enterprise\nconducted its affairs through a pattern of racketeering\nactivity, as required for a § 1962(c) enterprise. Wire fraud\nand obstruction of justice may constitute “racketeering\nactivity” under § 1961(1). As the Supreme Court\ninstructed in H.J. Inc., the “multiple predicates within a\nsingle scheme” must be related and “amount[] to, or\nthreaten[] the likelihood of, continued criminal activity.”\n492 U.S. at 237. Here, the amount of the illegal loan to be\nconcealed was substantial. The enterprise needed to write\noff the fictitious debt to Naylor’s consulting firm, and it\nwas urgent that both the EAA–Solutions contract and the\nSolutions–Strategies contract be legitimized. We conclude\nthe evidence was sufficient to establish that this enterprise\nconducted its affairs through a pattern of racketeering\nactivity and that the predicate acts of wire fraud and\nobstruction of justice were related. The racketeering\nactivity furthered the goals of maintaining the secrecy of\nthis $1 million illicit campaign loan and of preserving\nFattah’s political stature.\n Nicholas contends that the evidence fails to\nestablish a pattern of racketeering activity because the\nactions to which she agreed did not “extend[] over a\nsubstantial period of time” as H.J. Inc. requires. 492 U.S.\nat 242. That case indeed instructs that the continuity\nrequirement of a pattern is a “temporal concept,” and that\n“[p]redicate acts extending over a few weeks or months”\ndo not satisfy the continuity concept. Id. But the Supreme\nCourt explained that continuity may also be established by\n 108\n\fshowing that there is a “threat of continued racketeering\nactivity.” Id. Here, the course of fraudulent conduct\nundertaken to secure and to conceal the $1 million Lord\nloan consisted of the creation of sham debts, fictitious\ncontracts, and false accounting entries over the course of\nabout a year. But because Fattah needed to appear able to\nretire his campaign debt, the enterprise needed to continue\nfiling false campaign reports for several years, allowing\nthe annual $20,000 in-kind debt forgiveness contributions\nto appear to satisfy Naylor’s fake $193,000 invoice. That\nevidence was sufficient to establish the requisite threat of\ncontinued criminal activity. See H.J. Inc., 492 U.S. at 242–\n43.\n We conclude that the Government met its burden in\nproving that Fattah, Brand, and Nicholas 20 engaged in a\nRICO conspiracy in violation of § 1962(d).\n\n\n20\n Nicholas also asserts, in passing, that that her conviction\nunder § 1962(d) should be set aside because that statutory\nprovision is unconstitutionally vague as applied to her.\nAccording to Nicholas, a person of ordinary intelligence\nwould not know that her actions constituted an agreement\nto participate in a RICO enterprise. See United States v.\nPungitore, 910 F.2d 1084, 1104–05 (3d Cir. 1990). To the\ncontrary, a person of ordinary intelligence, who had been\nemployed by a prominent politician and then became the\nCEO of a nonprofit organization which that politician had\nfounded (and, to some extent, continued to direct), would\n 109\n\f VI. Variance from the Indictment and Sufficiency of\n the Evidence for Count 2\n Brand and Nicholas challenge their convictions for\nconspiracy to commit wire fraud by arguing that the\nGovernment’s evidence at trial impermissibly varied from\nthe indictment. Nicholas also challenges the sufficiency of\nthe evidence to support her conviction for conspiracy to\ncommit wire fraud. We address these contentions\ntogether. 21\n\n Count 2 of the indictment alleged a single\nconspiracy. JA277–79. Brand and Nicholas assert that the\nGovernment’s evidence at trial did not support the\nexistence of a single conspiracy but instead showed two\nindependent conspiracies, only one of which involved the\ntwo of them. According to Brand and Nicholas, the only\nconspiracy with which they were involved ended more\nthan five years before the Government charged them. That\nwould mean that all their conduct falls outside the five-\nyear limitations period for wire fraud conspiracy under 18\nU.S.C. § 3282.\n\n\nrealize that agreeing to participate with others in hiding an\nunlawful campaign loan of $1 million could constitute an\nunlawful RICO conspiracy.\n21\n In her briefing, Nicholas discusses variance in far less\ndetail than Brand, so we refer primarily to Brand’s\narguments. See Nicholas Br. 54–56. Her variance\narguments fail for the same reasons that Brand’s fail.\n 110\n\f “A conviction must be vacated when (1) there is a\nvariance between the indictment and the proof presented\nat trial and (2) the variance prejudices a substantial right\nof the defendant.” Kemp, 500 F.3d at 287 (quoting United\nStates v. Kelly, 892 F.2d 255, 258 (3d Cir. 1989)). We see\nno variance, and will affirm the District Court.\n A variance exists “if the indictment charges a single\nconspiracy while the evidence presented at trial proves\nonly the existence of multiple conspiracies.” Id. “We must\ndetermine ‘whether there was sufficient evidence from\nwhich the jury could have concluded that the government\nproved the single conspiracy alleged in the indictment.’ ”\nId. (quoting Kelly, 892 F.2d at 258). Viewing the record in\nthe light most favorable to the Government, we consider\nthree factors: (1) “whether there was a common goal\namong the conspirators”; (2) “whether the agreement\ncontemplated bringing to pass a continuous result that will\nnot continue without the continuous cooperation of the\nconspirators”; and (3) “the extent to which the participants\noverlap in the various dealings.” Id. (quoting Kelly, 892\nF.2d at 259).\n\n Brand argues that the Government failed to\nestablish a common goal among the conspirators. To\ndetermine whether the conspirators shared a common\ngoal, “we look to the underlying purpose of the alleged\ncriminal activity” in a fairly broad sense. United States v.\nRigas, 605 F.3d 194, 214 (3d Cir. 2010) (en banc). In\nRigas, we described the common goal of the defendants as\n\n 111\n\f“enriching [themselves] through the plunder of [their\ncorporate employer],” id., and we have similarly\narticulated the common goal in fairly general terms\nelsewhere. See United States v. Greenidge, 495 F.3d 85,\n93 (3d Cir. 2007) (“There was certainly evidence of a\ncommon goal among these co-conspirators: to make\nmoney by depositing stolen and altered corporate checks\ninto business accounts.”); Kelly, 892 F.2d at 259 (“[T]he\ncommon goal of all the participants was simply to make\nmoney selling ‘speed.’ ”). Importantly, a common goal\nmay exist even when “conspirators individually or in\ngroups perform different tasks in pursuing the common\ngoal,” and a single conspiracy may “attract[] different\nmembers at different times” or “involve[] different sub-\ngroups committing acts in furtherance of the overall plan.”\nUnited States v. Boyd, 595 F.2d 120, 123 (3d Cir. 1978).\n\n Here, the indictment described the purpose of the\nunified conspiracy in Count 2 at length:\n\n It was a purpose of the conspiracy to obtain\n an illegal campaign loan and to fraudulently\n repay that loan with hundreds of thousands of\n dollars of misappropriated charitable funds\n from Sallie Mae and federal grant funds from\n NASA which were intended for educational\n purposes.\n\n . . . . It was further a purpose of the\n conspiracy to present FATTAH to the public\n as a perennially viable candidate for public\n 112\n\f office who honored his obligations to his\n creditors and was able to retire his publicly\n reported campaign debts.\n . . . . It was further a purpose of the\n conspiracy to promote FATTAH’s political\n and financial goals through deception by\n concealing and protecting the conspirators’\n activities from detection and prosecution by\n law enforcement officials and the federal\n judiciary, as well as from exposure by the\n news media, through means that included\n obstruction of justice and the falsification of\n documents, including Campaign Finance\n Reports, false invoices, contracts, and other\n documents and records.\n\nJA277–78, ¶¶ 3–5.\n Brand characterizes the evidence at trial as\nestablishing two distinct conspiracies. The first he labels\nthe “diversion of funds scheme,” covering the\nmisappropriation of funds by Nicholas, Brand,\nLindenfeld, and Fattah to repay the Lord loan. Brand Br.\n34. Brand calls the second conspiracy the “CFR scheme,”\nin which Fattah and Naylor filed the false campaign\nfinance reports showing Naylor gradually forgiving a non-\nexistent debt. Id.\n Brand argues that the only goal of the CFR scheme\nwas to cover up how the funds from the illegal campaign\n 113\n\floan were spent, a goal he distinguishes from that of the\ndiversion of funds scheme, which he characterizes as a\nplan to cover up the repayment of the loan with stolen\nfunds. He also argues that the evidence does not establish\nhe was involved in, or even aware of, the false campaign\nfinance reports filed by Fattah. In Brand’s view, that\nnecessarily means the evidence showed two separate\nconspiracies.\n\n In considering these arguments, we begin by noting\nthat one conspiracy can involve multiple subsidiary\nschemes. Rigas, 605 F.3d at 214. It is true that the false\ncampaign finance reports, in the narrowest sense, had the\nspecific purpose of covering up how the illegal loan funds\nwere used during the election. But the false campaign\nfinance reports were also filed in furtherance of a broader\ngoal shared by the conspirators involved in repayment of\nthe Lord loan. They sought to promote Fattah’s political\nand financial goals by preserving his image as a viable\ncandidate and making him appear able to repay or\notherwise service his campaign debts without resorting to\nillegal means in doing so. The two subsidiary schemes\nworked in concert in furtherance of this overarching goal,\nand both were directed at covering up how the loan was\ntruly repaid. The “diversion of funds scheme” hid the\nillegal (but real) loan repayment through the use of fake\ncontracts; the “CFR scheme” showed the seemingly legal\n(but fake) loan forgiveness installments through the\ncreation of fake invoices and campaign finance reports.\nThe existence of two concealment schemes acting in\n 114\n\fconcert does not undermine the unity of the conspiracy of\nwhich they were both a part. We have no difficulty\nconcluding that the false campaign finance reports and the\nconcealed use of stolen funds to repay the Lord loan\noperated together in furtherance of a common goal.\n\n As for Brand’s argument that he was unaware of the\nfalse campaign finance reports and therefore could not be\na part of any conspiracy involving them, it is well-settled\nthat “each member of the charged conspiracy is liable for\nthe substantive crimes his coconspirators commit in\nfurtherance of the conspiracy even if he neither\nparticipates in his co-conspirators’ crimes nor has any\nknowledge of them.” United States v. Bailey, 840 F.3d 99,\n112 (3d Cir. 2016) (citing Pinkerton v. United States, 328\nU.S. 640 (1946)). The exceptions to that rule allow a\ndefendant to escape liability for a co-conspirator’s crime\nif: (1) “the substantive offense committed by one of the\nconspirators was not in fact done in furtherance of the\nconspiracy,” (2) “the substantive offense committed by\none of the conspirators ‘did not fall within the scope of the\nunlawful project,’ ” or (3) “the substantive offense\ncommitted by one of the conspirators ‘could not be\nreasonably foreseen as a necessary or natural consequence\nof the unlawful agreement.’ ” Id. (quoting Pinkerton, 328\nU.S. at 647–48). There was, as we have concluded, a unity\nof purpose between the co-conspirators to further Fattah’s\npolitical and financial goals by secretly obtaining and\nrepaying an illegal campaign loan with stolen funds. The\nfiling of false campaign reports does not fit within any of\n 115\n\fthe recognized exceptions to co-conspirator liability, as it\nwas in furtherance of the conspiracy’s shared goal, within\nthe scope of the agreement to conceal the loan, and\nforeseeable to Brand and Nicholas.\n\n Neither Brand nor Nicholas briefed the other two\nfactors we consider when determining whether the\nevidence impermissibly varied from the evidence,\n“whether the agreement contemplated bringing to pass a\ncontinuous result that will not continue without the\ncontinuous cooperation of the conspirators,” and “the\nextent to which the participants overlap in the various\ndealings.” Kemp, 500 F.3d at 287 (quoting Kelly, 892 F.2d\nat 258). The unified goal of promoting Fattah’s political\ncareer and maintaining secrecy surrounding the illegal\nloan and the misappropriated funds used to repay it\nrequired the continuous cooperation of the conspirators.\nIndeed, the efforts of several of them overlapped in every\naspect of the scheme. And Lindenfeld and Fattah were, at\na minimum, involved in some way in nearly every aspect\nof the origination of the loan, the false campaign finance\nreports, and the use of misappropriated funds to repay the\nloan. For his part, Naylor was involved in the use of the\nfunds, the false campaign finance reports, and to a lesser\nextent, the repayment of the loan.\n Brand (as part of his variance argument) and\nNicholas (as part of her sufficiency argument) argue that\nthe Government did not prove they agreed to conceal their\nactions, and thus the false campaign reports would not be\n\n 116\n\fsufficient to extend the duration of the conspiracy so that\nit fell within the statute of limitations. Acts of\nconcealment, such as the false campaign reports, are not\nautomatically “in furtherance” of a conspiracy. We must\ndetermine whether there was “an express original\nagreement among the conspirators to continue to act in\nconcert in order to cover up, for their own self-protection,\ntraces of the crime after its commission,” as opposed to “a\nconspiracy to conceal . . . being implied from elements\nwhich will be present in virtually every conspiracy case,\nthat is, secrecy plus overt acts of concealment.”\nGrunewald v. United States, 353 U.S. 391, 404 (1957). If\nthe indictment “specifically alleges a continuing\nconspiracy” to conceal the crime after the completion of\nthe wire fraud, and such a conspiracy can be proven, the\nstatute of limitations does not begin to run until the last\novert act of concealment. United States v. Moses, 148 F.3d\n277, 282 (3d Cir. 1998).\n\n Here, the evidence shows that the conspirators\nexpressly agreed to conceal the loan and its repayment. As\nan initial matter, Brand’s only role in the conspiracy was\nto cover up the use of stolen funds by (1) serving as an\nintermediary between Nicholas and Lindenfeld; and\n(2) agreeing to create false documentation (the contracts)\nwith both EAA and Strategies for the sole purpose of\ndisguising the payments and covering up the wire fraud\nconspiracy. Nicholas could simply have paid Lindenfeld\nherself (or paid Lord) if she and Brand had not agreed to\nconceal the crime from the start. Additionally, and as\n 117\n\fBrand acknowledges, the false campaign finance reports\nbegan before the loan was repaid, proving that\nconcealment of the crime was contemplated and begun as\na direct purpose of the conspiracy before Brand and\nNicholas became involved in the repayment. Nicholas too\nagreed to conceal the repayment, as she implicitly\nacknowledged in her emails with Brand and Fattah. GSA2.\nFinally, when Lindenfeld briefly strayed from the\nconspiracy’s commitment to secrecy by mentioning the\nrepayment in front of others who did not know of the\nscheme, Brand became “angry,” “took [Lindenfeld] out in\nthe hallway,” and chastised him, saying that “[Lindenfeld]\ncouldn’t say that sort of []thing” in front of other people.\nJA1670–71. We conclude that the evidence is consistent\nwith the allegations in the indictment, which charge a\nsingle conspiracy consisting of an original agreement to\nconceal the illegal loan and its subsequent illegal\nrepayment to further Fattah’s political career.\n\n Nicholas makes several arguments in passing. She\nsuggests that the District Court upheld the conviction after\ntrial “on a theory not submitted to the jury.” Nicholas Br.\n51. This argument is, essentially, that the indictment and\nthe District Court’s post-trial ruling described the\nconspiracy one way, but that the jury charge described the\nconspiracy differently. Nicholas argues that the jury was\npresented with the theory that the sole purpose of the false\ncampaign reports under Count 2 was to “conceal[] the\nalleged scheme to defraud,” JA5849, rather than to support\n\n 118\n\fFattah’s political career, as the District Court described the\npurpose after trial, see JA74.\n Nicholas ignores that part of the jury charge which\ninstructed that Count 2 required a finding “[t]hat two or\nmore persons agreed to commit wire fraud as charged in\nthe indictment.” JA5845 (emphasis added). The jury had\naccess to the indictment, and as Nicholas points out,\nNicholas Br. 45–46, the indictment outlines the offense in\nthe same way the District Court later described it in its\npost-trial ruling. The District Court consistently described\nthe count, and we see no reversible error.\n Nicholas also argues that the conspiracy charged in\nCount 2 has an objective—“to ‘present Fattah’ as\n‘perennially viable’ ”—and that such an objective is not\nillegal. Nicholas Br. 53. But, of course, the jury was not\ninstructed that it was illegal to be a Fattah supporter, or\neven to work on his campaign. The jury was charged\nspecifically on the crime of wire fraud.\n\n We conclude that there was no impermissible\nvariance between the indictment and the Government’s\nevidence at trial, and that there was sufficient evidence to\nsupport the convictions. We will affirm the convictions of\nBrand and Nicholas for conspiracy to commit wire fraud\nunder Count 2.\n\n\n\n\n 119\n\f VII. The District Court’s Instruction to the Jury on\n the Meaning of Intent\n Nicholas contends that the District Court\nimproperly instructed the jury by using the disjunctive\nrather than the conjunctive at one point in its definition of\nintent. When providing its final charge to the jury, the\nDistrict Court explained:\n Certain of the offenses charged in the\n indictment require that the government prove\n that the charged defendant acted intentionally\n or with intent. This means that the\n government must prove either that (1), it was\n the defendant’s conscious desire or purpose\n to act in a certain way or to cause a certain\n result; or (2), the defendant knew that he or\n she was acting in that way or it would be\n practically certain to cause that result.\n\nJA5787 (emphasis added). According to Nicholas, an\naccurate definition of intent required that the final “or” be\nan “and.” Nicholas argues that this was an error so\ngrievous as to “effectively eliminate[] the intent element\nfrom each offense of conviction.” 22 Nicholas Br. 26.\n\n\n22\n The Comment to Third Circuit Model Criminal Jury\nInstruction 5.03 makes clear that the definition of intent\nencapsulates both “specific intent” (acting “purposely” or\nwith “conscious object”) and “general intent” (acting\n 120\n\f Our review of whether a jury instruction stated the\nproper legal standard is plenary. United States v. Petersen,\n622 F.3d 196, 207 n.7 (3d Cir. 2010). At trial, Nicholas\nfailed to object to this portion of the jury charge.\nAccordingly, our review must be for plain error. See\nUnited States v. Flores-Mejia, 759 F.3d 253, 258 (3d Cir.\n2014) (en banc).\n\n To prevail on plain error review, Nicholas must\nestablish that there was an error, that it was plain (i.e., clear\nunder current law), and that it affected her substantial\nrights (i.e., whether there is a reasonable likelihood that\nthe jury applied the challenged instruction in an\nimpermissible manner). United States v. Olano, 507 U.S.\n\n“knowingly” or “with awareness”). Although Nicholas\ndescribes the alleged error as “essentially eliminating” the\nelement of intent, we think Nicholas’s argument is better\nunderstood as a claim that the instruction given could have\npermitted a jury to conclude that she acted with only\ngeneral intent (that she was aware of what she was doing),\nwhen her crimes require specific intent (that she had an\nillegal purpose). As her brief states, “[p]lainly she\n‘knowingly’ wrote checks from EAA to [Solutions] and\nmade record entries about them; the question was whether\nshe intended to defraud EAA and NASA, or to obstruct\njustice, by doing so.” Nicholas Br. 24. We cannot agree\nwith her characterization that the instruction resulted in the\n“effective omission” of the intent element from the jury\ninstructions.\n 121\n\f725, 733–34 (1993); United States v. Dobson, 419 F.3d\n231, 239–40 (3d Cir. 2005). If these requirements are met,\nwe may then exercise our discretion to address the error,\nbut only if we conclude that the error seriously affected the\nfairness, integrity, or public reputation of the judicial\nproceeding. United States v. Andrews, 681 F.3d 509, 517\n(3d Cir. 2012) (quoting Johnson v. United States, 520 U.S.\n461, 467 (1997)). A failure to instruct the jury on a\nnecessary element of an offense ordinarily constitutes\nplain error, unless the instructions as a whole otherwise\nmake clear to the jury all the necessary elements of the\noffense. United States v. Stimler, 864 F.3d 253, 270 (3d\nCir. 2017).\n Nicholas acknowledges, as she must, that the\ninstruction given was a verbatim recitation of Instruction\n5.03 of the Third Circuit’s Model Criminal Jury\nInstructions. She nonetheless contends that our Model\nInstruction is erroneous. Even if we were to accept\nNicholas’s contention that the instruction is incorrect, a\nproposition we consider as highly doubtful, see Petersen,\n622 F.3d at 208 (“We have a hard time concluding that the\nuse of our own model jury instruction can constitute error\n. . . .”), we conclude that, considering the instructions as a\nwhole, the District Court clearly and specifically\ninstructed the jury on the intent element as it applied to\neach of Nicholas’s charged crimes.\n\n The disputed intent instruction was given at the\nbeginning of the final charge, explaining the general\n\n 122\n\fmeaning of the intent applicable to “[c]ertain of the\noffenses charged.”23 JA5787. The District Court went on\nto instruct the jury in specific detail on the elements of\neach of the crimes of which Nicholas was accused,\n\n\n\n\n23\n The introductory definition did not end with the\nlanguage Nicholas cites. The District Court elaborated that\nacting in good faith is a complete defense to the charges:\n\n The offenses charged in the indictment\n require proof that the charged defendants\n acted with criminal intent. If you find that a\n defendant acted in good faith that would be a\n complete defense to such a charge, because\n good faith on the part of the defendant would\n be inconsistent with his or her acting\n knowingly, willfully, corruptly, or with intent\n to defraud or intent to impede, obstruct, or\n wrongfully influence.\n\nJA5788–89 (emphasis added). This instruction\nundermines Nicholas’s claim that the jury could have\nreasonably concluded that she “ ‘knowingly’ wrote\nchecks” but did not “intend[] to defraud . . . or to obstruct\njustice[] by doing so,” Nicholas Br. 24, as this instruction\nleaves little room for doubt that good faith is at odds with\n“criminal intent.”\n\n 123\n\fexplaining also the intent element of each. 24 See JA5791\n(describing the third element of the RICO conspiracy\ncharge as: “the particular defendant and at least one other\nalleged conspirator shared a unity of purpose and the intent\nto achieve the objective of conducting or participating in\nthe conduct of an enterprise’s affairs through a pattern of\nracketeering activity”); JA5823 (regarding wire fraud,\ninstructing that the government must prove “[t]hat the\ndefendant under consideration acted with the intent to\ndefraud”); JA5838–39 (regarding obstruction of justice,\ninstructing that the defendant must have acted “with the\nintent to impair the record, document, or object’s integrity\nor availability for use in an official proceeding,” and must\nhave acted corruptly “with the purpose of wrongfully\nimpeding the due administration of justice”); JA5860\n(explaining that falsification of records requires that “the\ndefendant under consideration acted with the intent to\nimpede, obstruct or influence the investigation or proper\nadministration of a matter”). These instructions are\nconsistent with both our Model Jury Instructions and our\ncase law concerning the elements of these crimes. See\nThird Circuit Model Criminal Jury Instruction 6.18.1962D\n(RICO), 6.18.1343 (wire fraud), 6.18.1512A2 (obstruction\nof justice); United States v. Sussman, 709 F.3d 155, 168\n(3d Cir. 2013) (obstruction of justice); United States v.\n\n24\n Nicholas did not object to the knowledge and intent\ninstructions when the District Court discussed each of the\nindividual charges, and does not identify a disagreement\nwith any specific instruction on any particular charge.\n 124\n\fMoyer, 674 F.3d 192, 208–09 (3d Cir. 2012) (falsification\nof records); United States v. Pelullo (Pelullo I), 964 F.2d\n193, 216 (3d Cir. 1992) (wire fraud).\n The District Court also provided a separate\ndefinition of the knowledge element of each charge,\nillustrating the difference between knowledge and intent.\nSee JA5793 (explaining that the evidence must show that\na RICO defendant “knowingly agreed to facilitate or\nfurther a course of conduct, which if completed would\ninclude a pattern of racketeering activity”); JA5823 (wire\nfraud means that the defendant “knowingly devised a\nscheme to defraud a victim . . . by materially false or\nfraudulent pretenses”); JA5860 (falsification of records\nhas as an element “[t]hat the defendant under\nconsideration knowingly concealed, covered up, falsified\nor made false entries in a document or record”). These\ninstructions made clear that knowledge and intent are\nseparate considerations, undermining Nicholas’s\ncontention that the jury was led to believe that “knowledge\nis sufficient to prove intent.” Nicholas Br. 24.\n The District Court provided each member of the\njury with more than 100 pages of instructions before\ndeliberations began. Viewing those instructions as a\nwhole, we are satisfied that the jury was apprised of the\ncorrect meaning of intent as an element of the crimes with\nwhich Nicholas was charged, as well as the distinction\nbetween knowledge and intent. We perceive no error,\n\n\n 125\n\fmuch less error that is plain, in the District Court’s\ninstructions to the jury. 25\n\n VIII. Sending the Indictment to the Jury\n At trial, Vederman, Nicholas, and Brand objected to\nthe District Court’s decision to give the jury a redacted\ncopy of the indictment to use during its deliberations. Only\nNicholas and Brand raise this issue on appeal. In\nNicholas’s view, sending the indictment to the jury\nunfairly prejudiced her because it contained unsupported\nallegations that she had obstructed federal agencies and\nreferred to a nonexistent certification requirement for\nSallie Mae funds. Brand argues that he was prejudiced by\nthe indictment’s references to “schemes” and “fake”\ncontracts, and because it mentioned Brand’s spouse and\nthat she was a former member of Fattah’s congressional\nstaff. Nicholas and Brand together assert that the\nindictment included legal theories on which the jury was\nnot instructed. They contend that the indictment’s\nnarrative of the Government’s case set out a roadmap that\nomitted any averments relating to the defense theory and\nallowed the Government to yet again present its case. To\nbuttress that argument, Nicholas and Brand cite the\ntestimony of Juror 12, who described the jury’s initial\n\n\n\n25\n Accordingly, we need not consider the merits of\nNicholas’s argument that Model Criminal Jury Instruction\n5.03 is erroneous.\n 126\n\fdeliberations and alleged that the jurors viewed the\nindictment as evidence.\n In United States v. Todaro, 448 F.2d 64, 66 (3d Cir.\n1971), we held that the decision to allow “jurors to have a\ncopy of the indictment with them during their\ndeliberations . . . is a matter within the discretion of the\nDistrict Judge, subject to a limiting instruction that the\nindictment does not constitute evidence, but is an\naccusation only.” Subsequently, in United States v.\nPungitore, 910 F.2d 1084, 1142 n.83 (3d Cir. 1990), we\nacknowledged that the District Court has the power to\nredact the indictment if doing so would be appropriate to\navoid prejudice to the defendant. See also United States v.\nRoy, 473 F.3d 1232, 1237 n.2 (D.C. Cir. 2007) (noting that\ncourt may redact an indictment before submitting it to the\njury).\n\n While both Nicholas and Brand objected in general\nterms to the District Court’s decision to provide the\nindictment to the jury, they have not directed us to any\nspecific request to redact the information they now claim\nis prejudicial. And the District Court provided a limiting\ninstruction on four occasions during its charge, repeatedly\nemphasizing that the indictment was not evidence.\nJA5765, 5767, 5782, 5880. The Court instructed the jury\non its duty to base its verdict “solely upon the evidence in\nthe case.” JA5764. Just before the jury retired to\ndeliberate, the Court reiterated that the purpose of the\n\n\n 127\n\findictment is to set forth the charges, and that it is “merely\nan accusation.” JA5909.\n “[J]uries are presumed to follow their instructions\n. . . .” Richardson v. Marsh, 481 U.S. 200, 211 (1987). In\nour view, Juror 12’s assertion that the indictment was\nbeing considered evidence does not, standing alone,\nestablish that his fellow jurors actually did so. We reject\nthe notion that the jury, after hearing weeks of testimony\nand having viewed substantial documentary evidence,\nwent on to ignore the Court’s limiting instruction\nconcerning the indictment. 26 Accordingly, we conclude\n\n\n26\n We acknowledge that our case law provides minimal\nguidance to district courts concerning the practice of\nsending an indictment to the jury for their use during\ndeliberations. We are also aware that some courts have\ndisapproved the practice of sending the indictment out\nwith the jury. See United States v. Esso, 684 F.3d 347, 352\nn.5 (2d Cir. 2012); Roy, 473 F.3d at 1237 n.2. We\nemphasize that this practice is committed to the sound\ndiscretion of the district judge. Todaro, 448 F.2d at 66. In\nour view, such an exercise of a judge’s discretion should\nbe informed by considering the nature of the case, the\nnumber of defendants, the length of the indictment, the\nextent of the factual recitation supporting the criminal\ncharges, and most importantly, whether the indictment\n(especially if lengthy and fact-laden) will be useful to the\njury, in light of the judge’s own carefully tailored jury\n 128\n\fthat the District Court did not abuse its discretion in\nsending the indictment out to the jury.\n\n IX. The District Court’s Evidentiary Rulings\n Vederman, Nicholas, and Brand each challenge\nevidentiary rulings by the District Court. We conclude that\nnone of these contentions warrants setting aside their\nconvictions.\n\n A. The District Court’s Application of Rule 404(b)\n Vederman argues that the District Court misapplied\nFederal Rule of Evidence 404(b) when it excluded\nevidence of Vederman’s prior gift-giving. 27 This Court\nreviews a district court’s application of Rule 404(b) for\nabuse of discretion. United States v. Daraio, 445 F.3d 253,\n\ninstruction, as supplemented by a verdict slip. See Esso,\n684 F.3d at 352 n.5.\n27\n Although Rule 404(b) determinations are usually in\nresponse to attempts to introduce “bad” acts evidence,\nVederman’s attempt to introduce “good” acts of gift-\ngiving is properly analyzed under the same rule. Ansell v.\nGreen Acres Contracting Co., 347 F.3d 515, 520 (3d Cir.\n2003) (“The evidence admitted in this case differs from\ngarden variety Rule 404(b) matter because it is evidence,\nnot of a prior bad act in a criminal case, but of a subsequent\ngood act in a civil case. Nonetheless, this evidence is\nencompassed by the plain text of Rule 404(b) which\naddresses ‘other . . . acts,’ not just prior bad acts.”).\n 129\n\f259 (3d Cir. 2006); Ansell v. Green Acres Contracting Co.,\n347 F.3d 515, 519 (3d Cir. 2003). A trial court commits\n“[a]n abuse of discretion . . . when [the] district court’s\ndecision rests upon a clearly erroneous finding of fact, an\nerrant conclusion of law or an improper application of law\nto fact.” Pardini v. Allegheny Intermediate Unit, 524 F.3d\n419, 422 (3d Cir. 2008) (quoting P.N. v. Clementon Bd. of\nEduc., 442 F.3d 848, 852 (3d Cir. 2006)).\n\n Federal Rule of Evidence 404(b) provides in part:\n (b) Crimes, Wrongs, or Other Acts.\n\n (1) Prohibited Uses. Evidence of a\n crime, wrong, or other act is not\n admissible to prove a person’s\n character in order to show that on a\n particular occasion the person\n acted in accordance with the\n character.\n\n (2) Permitted Uses; Notice in a\n Criminal Case. This evidence may\n be admissible for another purpose,\n such as proving motive,\n opportunity, intent, preparation,\n plan, knowledge, identity, absence\n of mistake, or lack of accident.\nFed. R. Evid. 404(b)(1)–(2).\n\n 130\n\f At trial, Vederman sought to present a witness from\nAmerican University who would have testified that\n“Vederman agreed, on more than fifty instances, to\nfinancially assist students [at American] who needed help\nwith tuition, book money, or travel funds to visit their\nfamilies.” Vederman Br. 42 (emphasis omitted).\nAccording to Vederman, the testimony was relevant to\nrefuting the Government’s argument that he agreed to\nguarantee the tuition expenses of Fattah’s au pair as a way\nof bribing the congressman. In excluding this evidence\nunder Rule 404(b), the District Court stated at sidebar:\n\n I sustain the government’s objection to\n calling a representative of American\n University to testify on behalf of Herbert\n Vederman.\n\n In my view the testimony runs afoul of\n Rule 404(b)(1) of the Federal Rules of\n Evidence. I find it to be propensity evidence.\n He or she would be testifying about Mr.\n Vederman’s financial generosity with respect\n to students of American University.\n The issue here is payment of partial\n tuition of a student at the Philadelphia\n University. I see no connection between the\n generosity at American University and the\n situation with Philadelphia University.\n\n\n 131\n\fJA4459–60. Vederman argues that because the proposed\nevidence related to Vederman’s intent, and not solely his\npropensity to perform good acts, we should conclude that\nthe District Court abused its discretion. We see no error in\nthe District Court’s ruling.\n\n Vederman challenges as arbitrary the District\nCourt’s “assertion that support for American University\nstudents is too remote from support for Philadelphia\nUniversity students” such that it constitutes inadmissible\nevidence. Vederman Reply Br. 23. This distinction was far\nfrom arbitrary. Vederman may well have financially\nsupported American University students because of\nconnections he had to that school or to the D.C.\ncommunity at large—connections Vederman did not have\nto Philadelphia University. And the excluded testimony\nappears to have described support for students Vederman\ndid not previously know. By supporting Fattah’s au pair,\nVederman was helping an employee of a man whom he\nknew quite well. JA889 (“[Fattah and Vederman] spent a\nlot of time together traveling back and forth to\nWashington, in the case of a death in the family attending\ncertain ceremonies that were important, and above all\nspending time with each other and their families\ntogether.”). Vederman’s decision to help Fattah’s au pair,\nwho wished to attend Philadelphia University, seems more\nlike a departure from, rather than a continuation of, his\npattern of support for American University students.\n\n\n\n 132\n\f As the party seeking admission of evidence under\nRule 404(b), Vederman bore “the burden of demonstrating\nits applicability” and “identifying a proper purpose.”\nUnited States v. Caldwell, 760 F.3d 267, 276 (3d Cir.\n2014). By failing to explain sufficiently why the factual\ndistinctions discussed above were not material, Vederman\nfailed to meet his burden. In particular, although\nVederman argues that he offered evidence of his prior gift-\ngiving to prove intent—“a proper non-propensity\npurpose”—he failed to show why the proposed testimony\nwas “relevant to that identified purpose.” Id. at 277. 28 As\nwe noted in Ansell v. Green Acres Contracting, an\nemployment discrimination case on which Vederman\nheavily relies, “[t]here is. . . no bright line rule for\ndetermining when evidence is too remote to be relevant.”\n347 F.3d at 525. As such, a district court’s determination\nunder Rule 404(b) “will not be disturbed on appeal unless\nit amounts to an abuse of discretion.” Id. The District\n\n\n\n28\n Under Rule 404(b), “prior act evidence is inadmissible\nunless the evidence is (1) offered for a proper non-\npropensity purpose that is at issue in the case; (2) relevant\nto that identified purpose; (3) sufficiently probative under\nRule 403 such that its probative value is not outweighed\nby any inherent danger of unfair prejudice; and\n(4) accompanied by a limiting instruction, if requested.”\nUnited States v. Caldwell, 760 F.3d 267, 277–78 (3d Cir.\n2014).\n 133\n\fCourt did not abuse its discretion in excluding evidence of\nVederman’s support for students at American University.\n\nB. Evidentiary Rulings Regarding Nicholas’s Defense\n Nicholas argues that the District Court rendered\nthree erroneous evidentiary rulings that prejudiced her\ndefense. We do not find any of her arguments convincing.\n\n 1. The EAA Board Minutes\n In support of its theory that Nicholas defrauded\nEAA, the Government introduced minutes from EAA’s\nBoard. Minutes from 2005 revealed that the Board limited\nNicholas’s signing authority to $100,000. Minutes from\nDecember 2007, February 2008, and May 2008 failed to\nreference either the EAA–Solutions contract or the checks,\ndrawn from EAA’s account for $500,000 and $100,000,\nthat were purportedly paid pursuant to the contract.\nNicholas contends that the Board minutes were\nerroneously admitted because they constituted improper\nhearsay which failed to satisfy either the exception for\nbusiness records under Federal Rule of Evidence 803(6)\nor the absence of records exception under Federal Rule of\nEvidence 803(7). “We review the District Court’s\nevidentiary ruling[s] for abuse of discretion, but also\n‘exercise plenary review . . . to the extent [the rulings] are\nbased on a legal interpretation of the Federal Rules of\nEvidence.’ ” Repak, 852 F.3d at 240 (citations omitted)\n(second alteration in original).\n\n 134\n\f Applying those standards here,29 we conclude there\nwas sufficient basis to admit exhibit EAA-48 under\nFederal Rule of Evidence 803(6) as a business record.\nAlthough allowing the prosecution to inquire over\nNicholas’s earlier objection based on Federal Rule of\nEvidence 803(7) to the absence of any mention of the\n$500,000 check in the 2008 Board Minutes was error, it\nwas not reversible error. Other evidence in the record\noverwhelmingly showed that Nicholas made the $500,000\nand $100,000 payments to Solutions with the requisite\nfraudulent intent. That evidence included the 2005 policy\nlimiting Nicholas’s authority to approve expenditures to\n$100,000, the accountant’s testimony about the\ndisbursement policy requiring the completion of a check\nrequest form for the issuance of a check, and Jones’\ntestimony that he never saw a request for the $500,000\ncheck. That evidence, coupled with Nicholas’s tendering\nof the upfront half-million dollar payment before the terms\nof the purported agreement had been finalized or executed,\nher failure to mention the $600,000 in payments to\nSolutions during her interview with FBI Agent\n\n29\n We note that the argument section of Nicholas’s brief on\nthis issue specifically cited to the page in the record where\nexhibit EAA-48 was admitted without objection by any\ndefense counsel. See Appellant’s Br. at 57 (citing JA4381-\n82). Nonetheless, there was an earlier objection to the\nadmission of exhibit EAA-48 that was preserved and that\nwas referenced in a string citation elsewhere in Nicholas’s\nbrief.\n 135\n\fDieffenbach, and her alteration of EAA’s general ledger\nto conceal the $100,000 payment, makes it “highly\nprobable” that the jury would have reached the same\nresult. See United States v. Friedman, 658 F.3d 342, 352\n(3d Cir. 2011).\n\n Nicholas also asserts that the Board minutes were\nunfairly prejudicial. We disagree. Any possible prejudice\nwas minimized by the fact that the Board minutes make no\nreference to either the EAA–Solutions contract or to any\nfinancial matters whatsoever. Indeed, given these lacunae\nin the Government’s proof, a reasonable factfinder might\nwell have concluded that the Board’s intention to limit\nNicholas’s signing authority had not been implemented\nand that Nicholas had not concealed the contract from the\nBoard.\n\n 2. Jones’ Memory Regarding Other Contracts\n Nicholas next asserts that the District Court erred\nduring her cross-examination of Board Chairman Jones by\nsustaining the prosecution’s objection to her inquiry into\nwhether he remembered other contracts in excess of\n$100,000 being brought to the Board. See JA1386–87. The\nbasis of the prosecution’s objection seemed to be that\nNicholas’s line of inquiry was beyond the scope of the\ndirect testimony. JA1387 (“I showed checks concerning\nwhat’s going on, not other programs.”); see Fed. R. Evid.\n611(b). The District Court sustained the objection,\ndeclaring that “it has absolutely nothing to do with this\ncase.” JA1387. Nicholas contends that if Jones did not\n 136\n\frecall whether other large contracts had been presented to\nthe Board, his inability to recall the EAA–Solutions\ncontract would have been “unremarkable rather than\nevidence of fraud or concealment.” Nicholas Br. 61.\n\n We acknowledge that whether Jones remembered\nother large contracts requiring Board approval had some\nrelevance under Rule 401. Yet any error by the District\nCourt in prohibiting Nicholas’s counsel from pursuing this\nline of inquiry is harmless. Jones admitted that he did not\nknow if the Board ever implemented the policy requiring\nits approval of contracts exceeding $100,000. He also\nconceded that the EAA Board focused less on the financial\nside of EAA than on its programs. JA1383–85. Nicholas\ncould not have been prejudiced by the District Court’s\nruling.\n\n 3. Exclusion of NOAA Evidence\n Nicholas defended against the criminal charges\narising out of the non-existent October 2012 conference\nby asserting that she acted in “good faith in spending the\nNOAA funds on EAA expenses,” Nicholas Br. 64, that the\ndifference in the dates in the paperwork was not material,\nand that NOAA had received the benefits of the\nsponsorship because its logo was displayed on the signage\nused at the February conference. Nicholas succeeded in\npresenting testimony and introducing photographs that\nshowed NOAA’s logo on the February 2012 annual\nconference bags, padfolios, and name tags. The Court\nexcluded a photograph of a NOAA intern at the February\n 137\n\f2012 conference, other photographs of the February\nconference signage, and some checks that pertained to the\nFebruary conference. Nicholas claims that her inability to\nintroduce those exhibits frustrated her ability to present\nher good faith defense. We are not persuaded.\n\n The photographs were excluded as cumulative, the\nsort of ruling to which we afford trial judges very broad\ndiscretion. See Fed. R. Evid. 403; United States v.\nDalfonso, 707 F.2d 757, 762 (3d Cir. 1983). It was not\nerror to exclude the student intern’s photograph. The\nconference brochure included photographs from previous\nconferences, and the witness from NOAA was unable to\ntestify to the year the student served as an intern. Finally,\nthe checks tendered for the travel expenses incurred for the\nFebruary conference were excluded as irrelevant to\nwhether Nicholas had a good faith belief that NOAA\nsponsored the October conference.\n\nC. The Cooperating Witness’s Mental Health Records\n During discovery, Brand learned that a cooperating\nwitness was diagnosed with bipolar II disorder and was\ntaking medication to treat that condition. Brand\nsubpoenaed mental health records kept by the witness’s\ncurrent and former psychiatrists in hopes of using those\nrecords to attack the witness’s memory, truthfulness, and\ncredibility. The witness and the Government both filed\nmotions to quash the subpoena, arguing that the witness’s\nmental health records were protected by the\npsychotherapist–patient privilege recognized by the\n 138\n\fSupreme Court in Jaffee v. Redmond, 518 U.S. 1 (1996).\nThe Government also filed a motion in limine seeking to\nrestrict the scope of cross-examination to prevent Brand\nfrom questioning the witness about his mental health.\n\n Alongside his motion to quash, the witness\nvoluntarily produced for the Court his mental health\nrecords. The Court concluded that the psychotherapist–\npatient privilege would ordinarily apply to the mental\nhealth records, but that the privilege was not absolute,\nespecially when invoked in response to a criminal\ndefendant’s efforts to obtain through discovery evidence\nthat is favorable to his case. Following the procedure set\nforth in Pennsylvania v. Ritchie, 480 U.S. 39 (1987), the\nDistrict Court conducted an in camera review of the\nmental health records to determine if they contained\nmaterial evidence—that is, evidence that would “give[]\nrise to a reasonable probability that it [would] affect the\noutcome of the case.” JA149. The District Court found\n“nothing in the mental health records of the [witness] . . .\nmaterial for this criminal action,” noting that “[t]he\nrecords reveal nothing that calls into question [the\nwitness’s] memory, perception, competence, or veracity.”\nJA150. Accordingly, the Court entered an order granting\nthe motions to quash the subpoena.\n The District Court also granted the Government’s\nmotion in limine and restricted the scope of cross-\nexamination, ruling that “no reference may be made to [the\nwitness’s] bipolar disorder or the medications he takes to\n\n 139\n\fmanage it.” JA142, 156. The Court reasoned that bipolar\ndisorder varied in its effects from person to person, and\nconcluded that Brand had not shown that the effects of the\ndisorder had any bearing on the witness’s credibility. The\nDistrict Court ruled that cross-examination would not\nserve any valid impeachment purpose.\n Brand claims that the District Court’s order ran\nafoul of the Due Process Clause of the Fifth Amendment\nand the Confrontation Clause of the Sixth Amendment.\nWe review a district court’s rulings to quash a subpoena\nand to limit the scope of cross-examination for abuse of\ndiscretion. United States v. Tykarsky, 446 F.3d 458, 475\n(3d Cir. 2006); NLRB v. Frazier, 966 F.2d 812, 815 (3d\nCir. 1992). Here, the District Court did not abuse that\ndiscretion.\n\n1. The District Court’s Denial of Access to the Mental\n Health Records\n In claiming that the District Court’s decision to\nreview the mental health records in camera before ruling\non their admissibility violated his rights under both the\nFifth and Sixth Amendments, Brand specifically argues\nthat his right to confront the witness was impeded because\nhe was denied access to records he could have used to\nimpeach the witness. This very argument was considered\nand rejected by a plurality of the Supreme Court in Ritchie,\nwhich noted that “the effect [of the argument] would be to\ntransform the Confrontation Clause into a constitutionally\ncompelled rule of pretrial discovery. . . . [T]he right to\n 140\n\fconfrontation is a trial right, designed to prevent improper\nrestrictions on the types of questions that defense counsel\nmay ask during cross-examination.” 480 U.S. at 52. We\nfollow the Ritchie plurality, and conclude that the\nConfrontation Clause did not require the District Court to\ngrant Brand access to the witness’s mental health records.\n Brand next challenges the District Court’s decision\nto quash the subpoena as a violation of the Fifth\nAmendment’s Due Process Clause. He concedes that\nRitchie’s Due Process holding allowed the District Court\nto review the mental health records in camera without\ndisclosing them to him. See id. at 59–60 (“A defendant’s\nright to discover exculpatory evidence does not include the\nunsupervised authority to search through [the\nGovernment’s] files. . . . We find that [the defendant’s]\ninterest . . . in ensuring a fair trial can be protected fully by\nrequiring that the [privileged] files be submitted only to\nthe trial court for in camera review.”). Brand instead\nargues that the District Court abused its discretion by\nfocusing on “irrelevant facts and spurious symptoms. . . .\nsuch as ‘hallucinations,’ ” and by “refus[ing] to consider\nevidence of cognitive impairment and memory issues.”\nBrand Br. 30. The record reveals, however, that the\nDistrict Court reviewed the mental health records and\ndetermined that they “reveal[ed] nothing that calls into\nquestion [the witness’s] memory, perception, competence,\nor veracity.” JA150. This hardly amounts to a refusal to\nconsider evidence of cognitive impairment or memory\nissues.\n 141\n\f Brand also challenges the legal standard applied by\nthe District Court, arguing that the court “focused solely\non whether disclosure would ‘change the outcome’ of\nBrand’s trial,” Brand Br. 29 (quoting JA148), rather than\nconsidering “whether the ultimate verdict is one ‘worthy\nof confidence.’ ” Id. (quoting United States v. Robinson,\n583 F.3d 1265, 1270 (10th Cir. 2009)). Brand\nmisleadingly quotes from the District Court’s opinion. The\nDistrict Court considered, in accordance with Ritchie,\n“whether there is a reasonable probability that disclosure\nwould change the outcome” of Brand’s trial, JA148\n(emphasis added), not whether disclosure would\nnecessarily change the outcome. As articulated in Ritchie,\na “ ‘reasonable probability’ is a probability sufficient to\nundermine confidence in the outcome.” 480 U.S. at 57\n(quoting United States v. Bagley, 473 U.S. 667, 682 (1985)\n(Blackmun, J.)). The District Court applied the correct\nstandard.\n\n2. The District Court’s Grant of the Motion in Limine\n In granting the Government’s motion in limine, the\nDistrict Court ruled that Brand could not “reference . . .\n[the witness’s] bipolar disorder or the medications he takes\nto manage it.” JA156. Yet that ruling placed no restriction\non Brand’s ability to cross-examine the witness with\nrespect to “his memory, competence, or truthfulness.” Id.\nBrand argues, nevertheless, that his Sixth Amendment\nright “to be confronted with the witnesses against him”\nwas violated. U.S. Const. amend. VI.\n\n 142\n\f The Confrontation Clause protects a defendant’s\nright to cross-examine a witness with respect to any\ntestimonial statements made by that witness. United States\nv. Berrios, 676 F.3d 118, 125–26 (3d Cir. 2012) (citing\nCrawford v. Washington, 541 U.S. 36, 51 (2004), and\nDavis v. Washington, 547 U.S. 813, 823–24 (2006)). But\nthe scope of cross-examination is not unlimited, and “[a]\ndistrict court retains ‘wide latitude insofar as the\nConfrontation Clause is concerned to impose reasonable\nlimits on such cross-examination based on concerns about\n. . . harassment, prejudice, confusion of the issues, the\nwitness’ safety, or interrogation that is repetitive or only\nmarginally relevant.’ ” John-Baptiste, 747 F.3d at 211\n(quoting United States v. Mussare, 405 F.3d 161, 169 (3d\nCir. 2005)). We review limitations on cross-examination\nfor abuse of discretion, and reverse “only when the\nrestriction ‘is so severe as to constitute a denial of the\ndefendant’s right to confront witnesses against him and . . .\nis prejudicial to [his] substantial rights.’ ” Id. (alternation\nin original) (quoting United States v. Conley, 92 F.3d 157,\n169 (3d Cir. 1996)).\n In United States v. Chandler, 326 F.3d 210, 219 (3d\nCir. 2003), we analyzed whether a district court’s decision\nto limit cross-examination with respect to a witness’s\nmotivation for testifying violated the Confrontation\nClause. See also Mussare, 405 F.3d at 169; John-Baptiste,\n747 F.3d at 211–12. Consistent with Delaware v. Van\nArsdall, 475 U.S. 673 (1986), we first concluded that “the\nexposure of a witness’ motivation in testifying is a proper\n 143\n\fand important function of the constitutionally protected\nright of cross-examination.” Chandler, 326 F.3d at 219–\n20 (quoting Van Arsdall, 475 U.S. at 678–79). We also\nnoted that the Confrontation Clause does not prevent a trial\njudge from imposing reasonable limits on cross-\nexamination. Id. In reviewing a district judge’s imposition\nof such limitations, we apply a two-part analysis. As we\nhave since described, “we inquire into: ‘(1) whether the\nlimitation significantly limited the defendant’s right to\ninquire into a witness’s motivation for testifying; and\n(2) whether the constraints imposed fell within the\nreasonable limits that a district court has the authority to\nimpose.’ ” John-Baptiste, 747 F.3d at 211–12 (quoting\nMussare, 405 F.3d at 169).\n The same analytical framework is appropriate when\ndetermining whether a restriction on the cross-\nexamination of a witness with respect to his memory and\nperception violates the Confrontation Clause. See Davis v.\nAlaska, 415 U.S. 308, 316 (1974); Greene v. McElroy, 360\nU.S. 474, 496 (1959); United States v. Segal, 534 F.2d\n578, 582 (3d Cir. 1976). Memory and perception, like\nmotivation for testifying, are central issues affecting the\ncredibility of any witness, and unreasonable limitations on\nthe right to cross-examine on those subjects cannot be\ncountenanced. We therefore ask, paraphrasing Chandler:\n(1) whether the District Court’s decision to put the\nwitness’s diagnosis and medications off limits\nsignificantly impaired Brand’s right to inquire into the\nwitness’s memory and perception; and (2) whether the\n 144\n\fruling fell within the reasonable limits that the District\nCourt has the authority to impose.\n We conclude that the District Court did not err. As\nan initial matter, the District Court permitted Brand to\ncross-examine the witness about his memory and\nperception, and limited cross-examination only with\nrespect to the witness’s bipolar disorder and the\nmedications he was taking to treat that condition. Brand\nwas free to question the witness about his memory and\nperception, and indeed did so. The restriction on asking\nthe witness about his bipolar disorder was not a significant\nlimitation of Brand’s right to inquire into the witness’s\nmemory or perception. Moreover, as the District Court\npointed out, Brand failed to show how inquiry into the\nwitness’s bipolar disorder would be useful for\nimpeachment purposes. See JA154.\n\n Given that failure, the District Court’s limits on\ncross-examination were reasonable. The Court concluded,\nafter reviewing the evidence submitted by Brand and the\nwitness’s mental health records, that any mention of the\nwitness’s bipolar disorder would “only be designed to\nconfuse the jury or to stigmatize him unfairly because of a\n‘mental problem’ without any countervailing probative\nvalue.” JA155. The District Court did not abuse its\ndiscretion in limiting Brand’s cross-examination on a topic\nthat would be far more prejudicial than probative. See\nTykarsky, 446 F.3d at 476–77 (“[T]he District Court acted\n\n\n 145\n\fwell within its discretion to restrict irrelevant and\nconfusing testimony.”).\n All of this is not to suggest that a witness’s mental\nhealth is always off limits. The appropriate course in any\ngiven case must be determined from the facts and\ncircumstances surrounding that case and the witness’s\nparticular condition. See United States v. George, 532 F.3d\n933, 937 (D.C. Cir. 2008) (“The days are long past when\nany mental illness was presumed to undermine a witness’s\ncompetence to testify. . . . [M]ental illness [is] potentially\nrelevant in a broad[] range of circumstances . . . . [But]\nsome indication is needed that a particular witness’s\nmedical history throws some doubt on the witness’s\ncompetence or credibility.”). Here, Brand failed to show,\nthrough mental health records or otherwise, any\nparticularized reason to doubt the credibility of the witness\nfor medical reasons.\n\n Brand states that the witness provided “the only\nevidence offered” on the intent element of his conspiracy\nconviction and that he should therefore be entitled to\nunrestricted cross-examination. Brand Br. 12 n.3. Yet no\nmatter the importance of a witness to any party, a district\ncourt may always place reasonable limits on cross-\nexamination to avoid “harassment, prejudice, confusion of\nthe issues, the witness’ safety, or interrogation that is\nrepetitive or only marginally relevant.” John-Baptiste, 747\nF.3d at 211 (citation omitted).\n\n\n 146\n\f We conclude that the District Court did not abuse\nits discretion in restricting the scope of Brand’s cross-\nexamination of the cooperating witness.\n\n X. The Government’s Cross-Appeal\n The jury convicted Fattah, Vederman, and Bowser\nof bank fraud, 18 U.S.C. § 134430 (Count 19) and making\nfalse statements to a financial institution, 18 U.S.C.\n§ 1014 31 (Count 20). In response to post-trial motions, the\nDistrict Court granted a judgment of acquittal on both\ncounts under Fed. R. Crim. P. 29, concluding that the\n\n30\n “Whoever knowingly executes, or attempts to execute,\na scheme or artifice . . . to defraud a financial institution\n. . . shall be fined not more than $1,000,000 or imprisoned\nnot more than 30 years, or both.” The definition of\n“financial institution” for purposes of § 1344 is set forth at\n18 U.S.C. § 20, and includes “a credit union with accounts\ninsured by the National Credit Union Share Insurance\nFund” and “a mortgage lending business (as defined in\nsection 27 of this Title).” 18 U.S.C. §§ 20(2), (10).\n31\n “Whoever knowingly makes any false statement or\nreport, or willfully overvalues any land, property or\nsecurity, for the purpose of influencing in any way the\naction of . . . a Federal credit union . . . any institution the\naccounts of which are insured by . . . the National Credit\nUnion Administration Board . . . or a mortgage lending\nbusiness . . . shall be fined not more than $1,000,000 or\nimprisoned not more than 30 years, or both.”\n 147\n\fevidence was insufficient to establish that the Credit\nUnion Mortgage Association (CUMA), the entity to whom\nFattah, Vederman, and Bowser made the false statements,\nis a “financial institution,” or, more specifically, a\n“mortgage lending business” as defined in 18 U.S.C. § 27.\nThe Government claims that, viewing the evidence in the\nlight most favorable to it, the District Court erred and that\nCUMA is, indeed, a “mortgage lending business.” We\nagree. Because the evidence is sufficient to support the\njury’s verdict, we will remand so Fattah and Vederman\nmay be resentenced on these charges.32\n\n A. CUMA is a Mortgage Lending Business\n In reviewing the District Court’s post-verdict\njudgment of acquittal under Rule 29 of the Federal Rules\nof Civil Procedure, we consider whether the evidence,\nwhen viewed in a light most favorable to the government,\nsupports the jury’s verdict. United States v. Dixon, 658\nF.2d 181, 188 (3d Cir. 1981). Our standard of review is the\nsame as that applied by the District Court, and we must\nuphold the jury’s verdict unless no reasonable juror could\naccept the evidence as sufficient to support the defendant’s\nguilt beyond a reasonable doubt. United States v.\nColeman, 811 F.2d 804, 807 (3d Cir. 1987).\n\n32\n Because the Government did not file an appeal as to\nBowser, the cross-appeal is limited to Fattah and\nVederman. The judgment of acquittal as to Bowser is\ntherefore unaffected by our ruling today.\n 148\n\f Initially, the grand jury’s indictment alleged that\nCUMA is a financial institution because it is federally\ninsured. JA302–03. At trial, however, the jury was\ninstructed that CUMA could qualify as a financial\ninstitution either because it is federally insured or because\nit is a “mortgage lending business.” See JA111, 401–02. A\n“mortgage lending business” is “an organization which\nfinances or refinances any debt secured by an interest in\nreal estate, including private mortgage companies and any\nsubsidiaries of such organizations, and whose activities\naffect interstate or foreign commerce.” 18 U.S.C. § 27.\n\n At trial, CUMA’s president and CEO, Eddie Scott\nToler, testified that CUMA is not federally insured.\nJA4235. The Government therefore attempted to prove\nthat CUMA is a “mortgage lending business” by\npresenting evidence that CUMA funds mortgages and then\nsells them in a secondary market.\n\n Toler also testified that CUMA is a “credit union\nservice organization”—a for-profit company owned by 48\ncredit unions, which serves small credit unions that do not\nhave the infrastructure or in-house expertise to handle\nmortgage loans themselves. JA4235. According to Toler,\n“[CUMA] exclusively provide[s] First Trust Residential\nMortgage loaning [sic] services, all the way from the\norigination of the mortgage loan through processing,\nunderwriting, closing and access to the secondary market\nwhere—and we’re selling the mortgage loan on the\nsecondary market.” JA4236–37. In jurisdictions in which\n\n 149\n\fCUMA is licensed, 33 CUMA holds the mortgage for a\nlimited period, generally from two to thirty days, and then\nsells the mortgage either to a partner credit union or on the\nsecondary market. JA4240.\n\n The District Court concluded that CUMA is not a\n“mortgage lending business” because “[t]he record is\ndevoid of any evidence that CUMA finances or refinances\nany debt.” JA113. Concluding that CUMA “simply is a\nloan processor for various credit unions which do the\nfinancing or refinancing,” id., the District Court ruled that\nCUMA’s “activity does not constitute the financing or\nrefinancing of any debt. CUMA is not the mortgagee. It is\nmerely selling the debt instrument to a third party.” JA114.\n We cannot agree with the District Court’s view of\nthe evidence. Toler testified that in “Maryland, D.C., and\nVirginia . . . all of the loans are closed in the name of\nCUMA.” JA4238–39. As Toler described it, CUMA\nborrows on a line of credit to fund the loan, and when the\nloan is sold, CUMA pays off its line of credit. JA4239–40.\nSo contrary to the District Court’s assessment, the\nevidence, viewed in a light most favorable to the\nGovernment, shows that CUMA is indeed the\nmortgagee—at least during the time from closing until the\nloan is sold to a partner credit union or on the secondary\nmarket. The fact that CUMA funds the closing and then\n\n33\n CUMA is licensed in Maryland, Washington, D.C., and\nVirginia. JA4238.\n 150\n\fholds the mortgage, even for a brief time, is sufficient to\nsupport a conclusion that CUMA is “an organization\nwhich finances or refinances any debt secured by an\ninterest in real estate.” 18 U.S.C. § 27.\n\n Fattah and Vederman attempt to refute the argument\nthat CUMA engages in financing mortgages by focusing\non Toler’s testimony that CUMA “doesn’t actually have\nany money to fund these mortgage loans.” JA4239; see\nFattah Reply Br. 38, Vederman Reply Br. 36. But Toler\ntestified that CUMA employs a credit line to borrow the\nfunds necessary to close on mortgages. See JA4239. That\nCUMA incurs debt to finance mortgages hardly\nundermines a conclusion that CUMA finances mortgages.\nIndeed, it is the very nature of modern banking that\nfinancial institutions do not hold cash reserves equal to the\nfull amount of their liabilities. See, e.g., Timothy C.\nHarker, Bailment Ailment: An Analysis of the Legal Status\nof Ordinary Demand Deposits in the Shadow of the\nFinancial Crisis of 2008, 19 Fordham J. Corp. & Fin. L.\n543, 561 (2014) (“[F]ractional reserve banking . . . is the\nde facto standard for all modern banks.”).\n\n Vederman also argues that, even if CUMA acts as a\nmortgage lending business in some transactions, it was not\nacting as a mortgage lending business in this transaction.\nVederman points to Toler’s testimony that, in a state in\nwhich CUMA is not licensed, the mortgage is closed in the\nname of a credit union. In such cases, the credit union, and\nnot CUMA, owns the mortgage for the short period before\n\n 151\n\fthe loan is sold on the secondary market. JA4241. CUMA\nis not licensed in the Commonwealth of Pennsylvania. See\nid. Thus, according to Vederman, CUMA was acting in its\ncapacity as a mortgage servicing company for Fattah’s\nvacation home purchase and did not—and could not—\nfinance Fattah’s mortgage. That would mean that CUMA\ncould not have been a victim of a crime against a financial\ninstitution in this instance: “When an entity is not\nfunctioning as a mortgage lender, the ‘pertinent federal\ninterest’ behind the statutes is not implicated.” Vederman\nReply Br. 38 (citation omitted).\n\n The Government responds that neither of the\nstatutes of conviction requires that the fraud or false\nstatement occur in connection with the same transaction\nthat places the entity within the definition of “financial\ninstitution.” Gov’t Fourth Step Br. 4. We agree with the\nGovernment.\n\n Both § 1344 and § 1014 protect entities that fall\nwithin the definition of “financial institution” and are\notherwise quite broad in their application. See Loughrin v.\nUnited States, 134 S. Ct. 2384, 2389 (2014) (interpreting\n§ 1344 as not requiring specific intent to defraud a bank);\nUnited States v. Boren, 278 F.3d 911, 914 (9th Cir. 2002)\n(“[Section 1014’s] reach is not limited to false statements\nmade with regard to loans, but extends to any application,\ncommitment or other specified transaction.”). Neither\nstatute is expressly limited in the manner that Vederman\nsuggests. Williams v. United States, 458 U.S. 279, 284\n\n 152\n\f(1982) (“To obtain a conviction under § 1014, the\nGovernment must establish two propositions: it must\ndemonstrate (1) that the defendant made a ‘false statement\nor report,’ . . . and (2) that he did so ‘for the purpose of\ninfluencing in any way the action of [a described financial\ninstitution] upon any application, advance, . . .\ncommitment, or loan.’ ”); United States v. Leahy, 445 F.3d\n634, 646 (3d Cir. 2006) (“The purpose of the bank fraud\nstatute is to protect the ‘financial integrity of [banking]\ninstitutions.’ ”) (citing S. Rep. No. 98-225, at 377 (1983),\nas reprinted in 1984 U.S.C.C.A.N. 3517), abrogated on\nother grounds by Loughrin, 134 S. Ct. at 2389.\n In support of his position, Vederman relies on\nUnited States v. Devoll, 39 F.3d 575 (5th Cir. 1994), in\nwhich the Fifth Circuit concluded that § 1014 (false\nstatements to a financial institution) is not intended to\ncapture fraud unrelated to an entity’s lending activities,\nand therefore held that it “applies only to actions involving\nlending transactions.” Id. at 580. The Fifth Circuit stated:\n [W]e are not persuaded that the statute\n imposes liability whenever a defendant’s\n false statement was intended to interfere with\n any activity of a financial institution; such a\n broad interpretation of section 1014\n presumably would encompass fraud or false\n representations having nothing to do with\n financial transactions, such as fraud in an\n employment contract or, for example, in a\n\n 153\n\f contract to provide goods or services for\n custodial care, premises repair, or renovation.\nId.\n\n Yet a majority of circuits, including our own, have\ndeclined to follow Devoll’s suggestion that § 1014 is\nrestricted to lending transactions. As the Ninth Circuit has\nheld, “we join at least six of our sister circuits—the First,\nThird, Fourth, Sixth, Seventh, and Tenth—in holding that\n18 U.S.C. § 1014 is not limited to lending transactions,\nand reject the minority rule to the contrary.” Boren, 278\nF.3d at 915. And even if we were to adopt Devoll’s narrow\nconstruction of § 1014 to lending transactions, that would\nnot resolve the more specific question of whether the\ndefrauded entity must be defined as a “mortgage lending\nbusiness” by virtue of the specific transaction in which the\nfalse statements arose.\n Recently, the Eighth Circuit addressed precisely\nthis issue. In United States v. Springer, 866 F.3d 949 (8th\nCir. 2017), that Court considered the defendant’s appeal\nfrom the district court’s denial of a Rule 29 motion on\ngrounds that GMAC, the entity defrauded, was not a\n“financial institution.” The Court upheld the district\ncourt’s determination that the evidence was sufficient to\nestablish that GMAC is in the mortgage lending business\nbecause there was testimony that “it had made hundreds or\nthousands of loans secured by mortgages in 2010 and 2011\nin states all across the country,” which established that its\nactivities affect interstate commerce. Id. at 953. It was not\n 154\n\fdeterminative that GMAC did not own the specific loan at\nissue in the case: “we discern no requirement in the\ndefinition of ‘mortgage lending business’ that the business\nown the particular loan in question; it need only finance or\nrefinance any debt secured by an interest in real estate, or,\nin other words, be in the interstate mortgage lending\nbusiness in general.” Id.\n\n In our view, the Eighth Circuit’s analysis is correct.\nWe therefore adopt that Court’s reasoning in Springer and\nconclude that it is of no moment that CUMA did not\nfinance the mortgage at issue in Fattah’s case. CUMA is a\n“mortgage lending business,” and that alone suffices to\nsupport the convictions under §§ 1014 and 1344.\n\n B. Sufficiency of the Evidence\n Finally, Vederman argues that, even if CUMA is a\nfinancial institution, the judgment of acquittal should\nstand because the Government did not put forth any\nevidence that he made a false representation to CUMA.34\nSpecifically, Vederman argues that the title to the Porsche\nwas actually changed to his name, making it a “true sale”\nas a matter of law, without regard to whether Fattah’s wife\n\n34\n Although Vederman presented this argument in his Rule\n29 motion, the District Court did not need to reach it in the\ncontext of Counts 19 and 20 because the Court granted the\nmotion on the ground that CUMA is not a financial\ninstitution. The District Court rejected the argument as to\nCounts 16, 17, and 18. See JA100–02.\n 155\n\fcontinued to retain possession. See United States v.\nCastro, 704 F.3d 125, 139 (3d Cir. 2013) (holding in\nanother context that “the government must be able to show\nthat [the defendant] made a statement to government\nagents that was untrue, and the government cannot satisfy\nthat burden by showing that the defendant intended to\ndeceive, if in fact he told the literal truth”); see also 75 Pa.\nCons. Stat. § 102 (defining “owner” as “[a] person, other\nthan a lienholder, having the property right in or title to a\nvehicle”).\n\n The Government responds that, regardless of\nwhether it is legally possible for one person to hold a title\nwhile a different person possesses the vehicle, the jury was\npermitted to consider all the circumstances in deciding\nwhether the Porsche sale was a sham. We agree.\n\n First, as the District Court observed, it was unclear\nas to whether the title had been properly executed under\nPennsylvania law. For instance, Fattah’s wife never\nappeared before a notary. 35 JA101. In addition, title 75,\nsection 1111(a) of the Pennsylvania Consolidated Statutes\nrequires that, “[i]n the event of the sale or transfer of the\nownership of a vehicle within this Commonwealth, the\nowner shall . . . deliver the certificate to the transferee at\n\n35\n Vederman argues that it is of no significance that the\nparties did not appear before a notary as the statute\nrequires, but he offers cases only from states other than\nPennsylvania to support this proposition.\n 156\n\fthe time of the delivery of the vehicle.” And, the transferee\nmust, within twenty days of the assignment of the vehicle,\napply for a new title. See 75 Pa. Cons. Stat. § 1111(b).\nNeither of these requirements was fulfilled. Finally,\nVederman never registered the Porsche in his name with\nthe Department of Motor Vehicles. See id.; JA4254.\n Second, and more importantly, even if the title had\nbeen properly transferred to Vederman, the title provisions\nof the Pennsylvania Motor Vehicle Code “were [not]\ndesigned to establish conclusively the ownership of an\nautomobile.” Weigelt v. Factors Credit Corp., 101 A.2d\n404, 404 (Pa. Super. Ct. 1953). Indeed, “[t]he purpose of\na certificate of title is not to conclusively establish\nownership in a motor vehicle, but rather to establish the\nperson entitled to possession.” Speck Cadillac-Olds, Inc.\nv. Goodman, 95 A.2d 191, 193 (Pa. 1953). Thus, a title\nprovides evidence of ownership; it is not dispositive of the\nissue. Wasilko v. Home Mut. Cas. Co., 232 A.2d 60, 61\n(Pa. Super. Ct. 1967).\n Vederman’s argument that the title in his name\nconstitutes conclusive evidence of ownership rests upon\nan erroneous conclusion that the jury was prohibited from\nconsidering all the circumstances of the transfer. As the\nDistrict Court observed, though, Pennsylvania’s\nCommonwealth Court has held that “[w]hether a\ntransferor has transferred ownership of a motor vehicle to\na transferee is a factual determination to be made by the\ncourt below.” Dep’t. of Transp. v. Walker, 584 A.2d 1080,\n\n 157\n\f1082 (Pa. Commw. Ct. 1990). Thus, the signed certificate\nof title was appropriately treated as one piece of evidence\nfor the jury to consider in assessing the validity of the\nvehicle transfer. Considered in the light most favorable to\nthe Government, the totality of the evidence is sufficient\nto support the jury’s conclusion that the Porsche sale was\na sham.\n\n XI. Prejudicial Spillover\n Finally, Fattah, Vederman, Nicholas, and Brand\neach contend that their convictions on various counts\nresulted from prejudicial spillover. We are not persuaded.\n We exercise plenary review over a district court’s\ndenial of a claim of prejudicial spillover, United States v.\nLee, 612 F.3d 170, 178–79 (3d Cir. 2010), and we apply a\ntwo-step test when reviewing such a claim. United States\nv. Wright, 665 F.3d 560, 575 (3d Cir. 2002). First, a court\nmust consider “whether the jury heard evidence that would\nhave been inadmissible at a trial limited to the remaining\nvalid count[s].” Id. (quoting United States v. Cross, 308\nF.3d 308, 317 (3d Cir. 2002)). The second step requires\nthat we “ask whether that evidence (the ‘spillover\nevidence’) was prejudicial.” Id. We consider four factors:\n“whether (1) the charges are intertwined with each other;\n(2) the evidence for the remaining counts is sufficiently\ndistinct to support the verdict on these counts; (3) the\nelimination of the invalid count [will] significantly\nchange[] the strategy of the trial; and (4) the prosecution\nused language of the sort to arouse a jury.” Id. (quoting\n 158\n\fUnited States v. Murphy, 323 F.3d 102, 118 (3d Cir.\n2003)); see also United States v. Pelullo (Pellulo II), 14\nF.3d 881, 898–99 (3d. Cir. 1994). These four factors are\nconsidered in a light “somewhat favorable to the\ndefendant.” Wright, 665 F.3d at 575 (quoting Murphy, 323\nF.3d at 122); see also Gov’t Br. 198 (same).\n\n A. Fattah’s Claim of Prejudicial Spillover\n Fattah argues that he suffered prejudicial spillover\non the remaining counts of conviction in light of (1)\nevidence pertinent to the alleged Vederman bribery\nschemes that is now arguably inadmissible under\nMcDonnell; and (2) “the government’s flawed RICO\nconspiracy theory.” Fattah Br. 50, 64. Fattah’s argument\nis undercut substantially because of our determination that\nMcDonnell requires a new trial for Counts 16, 17, 22, and\n23 and our decision to affirm the RICO conspiracy\nconviction. The only possible spillover left to consider is\nthe evidence pertaining to Fattah’s arranging a meeting\nbetween Vederman and the U.S. Trade Representative,\nRon Kirk, which in light of McDonnell is now arguably\ninadmissible.36\n\n The evidence of the Kirk meeting admitted during\nthis five-week trial was limited. Although this evidence\n\n36\n Nothing in this opinion is intended to foreclose the\npossibility that evidence of the Kirk meeting may be\nadmissible on retrial for some purpose other than as proof\nof an official act.\n 159\n\fwas part of the Government’s proof as to both the RICO\nand the bribery related charges, there is more than\nsufficient—and distinct —evidence to support Fattah’s\nconviction on all the other counts. In our view, eliminating\nany evidence of the Kirk meeting would not have altered\nthe strategy of the trial, nor should it significantly change\nthe strategy for any new trial that may be held. Because\nFattah has not pointed us to any argument by the\nprosecution relating to this meeting that could have\ninflamed the jury, we conclude that Fattah’s prejudicial\nspillover claim fails. Like the District Court, we presume\nthat the jury followed the Court’s instructions to consider\nand weigh separately the evidence on each count as to each\ndefendant and not to be swayed by evidence pertaining to\nother defendants. 37\n\n B. Vederman’s Assertion of Prejudicial Spillover\n Because the District Court acquitted Vederman of\nthe RICO charge, Vederman argues that he was “severely\nprejudiced by the presentation to the jury of a legally\nflawed racketeering conspiracy charge,” and as a\nconsequence his bribery and money laundering\n\n37\n We likewise reject Brand’s prejudicial spillover\narguments. See Brand Br. 6 (“Brand adopts the significant\nissue advanced by his co-appellant pursuant to Fed. R.\nApp. P. 28(i) that improper jury instructions and the\nresulting spillover of related improperly admitted\nevidence and argument unfairly prejudiced Brand.”).\n 160\n\fconvictions should be overturned. Vederman Br. 46. In\nresponse to the Government’s appeal of the District\nCourt’s Rule 29 acquittal on Counts 19–20 involving\nCUMA, Vederman asserts that these two counts also were\naffected by spillover evidence because the Government’s\ntheory tied the bribery charges to the actions taken to\ndefraud CUMA. In that we are vacating Vederman’s\nconvictions of Counts 16–18 and 22–23 based on\nMcDonnell and remanding for further proceedings, we\nneed address only Vederman’s argument of prejudicial\nspillover as it relates to the charges involving CUMA in\nCounts 19–20, charges that we will reinstate.\n The District Court’s acquittal of Vederman on the\nRICO count establishes that step one of the Wright\nspillover test has been met. “[T]he jury heard evidence that\nwould have been inadmissible at a trial limited” to the\nbribery and CUMA-related counts. Wright, 665 F.3d at\n575 (quoting Cross, 308 F.3d at 317).\n\n Wright’s second step requires “ask[ing] whether\nthat evidence (the ‘spillover evidence’) was prejudicial.”\nId. Vederman submits that the RICO, bribery, and CUMA-\nrelated charges were intertwined “in that the acts relating\nto the alleged bribery scheme were also charged as\n‘predicates’ under RICO.” Vederman Br. 49. We disagree.\n\n To be sure, the RICO, bribery, and CUMA Counts\nare related to one another. But in this instance, mere\nrelatedness is not enough to demonstrate the foundation\nnecessary for spillover. This is so because the bribery\n 161\n\fcharges were a predicate to the RICO charge. In other\nwords, the jury had to determine if Vederman was guilty\nof bribery, and the jury then used that “predicate” to\nconsider whether he was also guilty of the RICO\nconspiracy. Thus, the necessarily tiered structure of the\nquestions presented to the jury refute Vederman’s\nargument that the counts were intertwined.\n\n That the bribery charges were predicates for the\nRICO conspiracy further demonstrates that the “evidence\nfor the different counts was sufficiently distinct to support\nthe verdict on other separate counts.” Pelullo II, 14 F.3d at\n898. Regardless of the evidence pertaining solely to the\nRICO conviction, the evidence supporting both the bribery\ncharges and the charges involving CUMA in Counts 19–\n20 would have remained the same.\n\n The next factor we address is “whether the\nelimination of the count on which the defendant was\ninvalidly convicted would have significantly changed the\n[defendant’s] strategy of the trial.” Id. As Vederman\nargues, “the RICO charge interfered with Vederman’s\ncentral defense to the bribery charge—that his gestures\ntoward Fattah ‘were motivated purely by friendship.’ ”\nVederman Reply Br. 28 (citing Gov’t Br. 200). In other\nwords, the “RICO count made it dangerous to unduly\nemphasize [Vederman’s] close friendship” with Fattah. Id.\nFrom Vederman’s perspective, “a bribery-only trial would\nhave reduced this danger and allowed a freer presentation\nof the defense.” Id.\n\n 162\n\f It is quite likely that Vederman’s claim of friendship\nwould have been less risky as a litigation strategy if he had\nnot been facing a RICO charge. But Vederman\nnevertheless chose to take that risk and fully presented his\nfriendship argument to the jury. Moreover, while\nVederman’s reliance on friendship might have helped him\ndefend against the bribery charges, that friendship would\nnot have altered the evidence pertaining to Counts 19–20\ninvolving CUMA. Whether done for friendship or some\nother reason, submitting fraudulent information to a\nfinancial institution is unlawful.\n\n Finally, we “examine the charges, the language that\nthe government used, and the evidence introduced during\nthe trial to see whether they are ‘of the sort to arouse a\njury.’ ” Pelullo II, 14 F.3d at 899 (quoting United States v.\nIvic, 700 F.2d 51, 65 (2d Cir. 1983)). Vederman points out\nthat Fattah was presented as “a backslapping, corrupt party\nboss,” with “predictable spillover to his friend and\nassociate, Vederman.” Vederman Br. 50 (quoting United\nStates v. Murphy, 323 F.3d 102, 118 (3d Cir. 2003)). But\nthis description was of Fattah, not Vederman. Vederman\ncites other examples of prejudicial, pejorative language in\nthe Government’s closing arguments. At one point, the\nGovernment referred to “conspirators engaged in what can\nonly be described as a white collar crime spree from\nPhiladelphia all the way to Washington, D.C.” and\npromised “to untangle the webs of lies and deception that\nthese conspirators spun.” Vederman Br. 51 (quoting\nJA5295, 5297). Whatever rhetorical flair these words\n 163\n\fcontained, they did not obscure the evidence which\nindependently supported the convictions for bank fraud at\nCount 19 and for making false statements to CUMA at\nCount 20. Accordingly, because we presume that the jury\nfollowed the District Court’s instruction to consider and to\nweigh separately the evidence on each count and as to each\ndefendant, and because the evidence supporting the\nCUMA-related charges in Counts 19–20 is sufficiently\ndistinct from the RICO conspiracy, we conclude that\nVederman’s spillover argument is unavailing.38\n\n XII. Conclusion\n We will vacate the convictions of Chaka Fattah, Sr.\nand Herbert Vederman as to Counts 16, 17, 18, 22, and 23.\n\n38\n Nicholas adopted “pertinent portions” of the prejudicial\nspillover arguments advanced by Vederman and Fattah.\nNicholas Br. 65. Her spillover claim has no more merit\nthan theirs. Nicholas’s involvement in the RICO\nconspiracy was distinct from the bribery charges, which\ndid not unfairly influence the other counts. As to\nNicholas’s assertion that the NOAA charges did not\nbelong in the indictment and should have been tried\nseparately, we fail to see how this relates to a claim of\nprejudicial spillover. To the extent it challenges the\nDistrict Court’s denial of Nicholas’s motion for a\nseverance, Nicholas has failed to provide legal support for\nsuch a contention. See Fed. R. App. P. 28(a)(8)(A); United\nStates v. Irizarry, 341 F.3d 273, 305 (3d Cir. 2003).\n 164\n\fFattah and Vederman may be retried on these counts\nbefore a properly instructed jury. We will also reverse the\nDistrict Court’s judgment of acquittal on Counts 19 and\n20. The convictions of Chaka Fattah, Sr. and Herbert\nVederman will be reinstated, and the case will be\nremanded for sentencing on those counts. In all other\nrespects, the judgments of the District Court will be\naffirmed.\n\n\n\n\n 165\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Appellant in 17-1346 v. Chaka FATTAH, Sr., Appellant in 16-4397 Karen Nicholas, Appellant in 16-4410 Robert Brand, Appellant in 16-4411 Herbert Vederman, Appellant in 16-4427\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-16\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n Nos. 16-4397, 16-4410, 16-4411,\\n 16-4427, 17-1346\\n _____________\\n\\n UNITED STATES OF AMERICA\\n Appellant in 17-1346\\n\\n v.\\n\\n CHAKA FATTAH, SR.,\\n Appellant in 16-4397\\n\\n KAREN NICHOLAS,\\n Appellant in 16-4410\\n\\n ROBERT BRAND,\\n Appellant in 16-4411\\n\\n HERBERT VEDERMAN,\\n Appellant in 16-4427\\n _____________\\n\\nOn Appeal from the United States District Court\\n for the Eastern District of Pennsylvania\\n District Court Nos. 2-15-cr-00346-001,\\n\\f 2-15-cr-00346-002, 2-15-cr-00346-003,\\n 2-15-cr-00346-004\\n District Judge: The Honorable Harvey Bartle III\\n\\n Argued January 18, 2018\\n\\nBefore: SMITH, Chief Judge, GREENAWAY, JR., and\\n KRAUSE, Circuit Judges\\n\\n (Filed: January 16, 2019)\\n\\nAndrea G. Foulkes\\nEric L. Gibson\\nPaul L. Gray\\nRobert A. Zauzmer\\nOffice of United States Attorney\\n615 Chestnut Street\\nSuite 1250\\nPhiladelphia, PA 19106\\n\\nJonathan Ian Kravis [ARGUED]\\nUnited States Department of Justice\\nCriminal Division, Public Integrity Section\\n1400 New York Avenue, N.W.\\nWashington, DC 20005\\n Counsel for the United States\\n\\nMark M. Lee\\nBruce P. Merenstein [ARGUED]\\nSamuel W. Silver\\n 2\\n\\fSchnader Harrison Segal & Lewis\\n1600 Market Street\\nSuite 3600\\nPhiladelphia, PA 19103\\n Counsel for Appellant Fattah\\n\\nAnn C. Flannery [ARGUED]\\nSuite 2700\\n1835 Market Street\\nPhiladelphia, PA 19103\\n\\nLisa A. Mathewson\\nSuite 810\\n123 South Broad Street\\nPhiladelphia, PA 19109\\n Counsel for Appellant Nicholas\\n\\nAlan Silber\\nPashman Stein Walder Hayden\\n21 Main Street\\nSuite 200\\nHackensack, NJ 07601\\n Counsel for National Association of Criminal\\n Defense Lawyers, Amicus Appellant Nicholas\\n\\nMira E. Baylson\\nBarry Gross [ARGUED]\\nMeredith C. Slawe\\nDrinker Biddle & Reath\\nOne Logan Square\\n 3\\n\\fSuite 2000\\nPhiladelphia, PA 19103\\n Counsel for Appellant Brand\\n\\nHenry W. Asbill\\nBuckley Sandler\\n1250 24th Street, N.W.\\nSuite 700\\nWashington, DC 20037\\n\\nGlen D. Nager [ARGUED]\\nJacob M. Roth\\nJulia W. M. F. Sheketoff\\nJones Day\\n51 Louisiana Avenue, N.W.\\nWashington, DC 20001\\n Counsel for Appellant Vederman\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\n\\nSMITH, Chief Judge.\\n\\n\\n\\n\\n 4\\n\\f Table of Contents\\nI. Introduction ................................................................... 8\\nII. Background .................................................................. 9\\n A. The Fattah for Mayor Scheme ................................. 9\\n 1. The Lord Loan and Its Repayment ..................... 10\\n 2. The College Tuition Component of the FFM\\n Scheme ................................................................ 27\\n 3. The NOAA Grant and the Phantom Conference 28\\n B. The Blue Guardians Scheme.................................. 31\\n C. The Fattah–Vederman Bribery Scheme................. 33\\n D. The Indictment and Trial ....................................... 39\\nIII. Juror Misconduct and Dismissal of Juror 12 ........... 58\\n A. Investigation of Alleged Juror Misconduct ........... 58\\n B. Dismissal of Juror 12 ............................................. 64\\nIV. The District Court’s Instructions Under McDonnell 70\\n A. The McDonnell Framework................................... 71\\n B. The Kirk Meeting ................................................... 76\\n C. Fattah’s Efforts to Secure Vederman an\\n Ambassadorship.......................................................... 79\\n D. The Zionts Hiring .................................................. 82\\n E. Vederman’s Sufficiency Challenge to Counts 16–18\\n and 22–23.................................................................... 89\\n F. Blue Guardians ....................................................... 91\\n\\n 5\\n\\fV. Sufficiency of the Evidence for the RICO Conspiracy\\nConviction ...................................................................... 95\\nVI. Variance from the Indictment and Sufficiency of the\\nEvidence for Count 2.................................................... 110\\nVII. The District Court’s Instruction to the Jury on the\\nMeaning of Intent ......................................................... 120\\nVIII. Sending the Indictment to the Jury ...................... 126\\nIX. The District Court’s Evidentiary Rulings .............. 129\\n A. The District Court’s Application of Rule 404(b) 129\\n B. Evidentiary Rulings Regarding Nicholas’s\\n Defense ..................................................................... 134\\n 1. The EAA Board Minutes .................................. 134\\n 2. Jones’ Memory Regarding Other Contracts ..... 136\\n 3. Exclusion of NOAA Evidence.......................... 137\\n C. The Cooperating Witness’s Mental Health\\n Records ..................................................................... 138\\n 1. The District Court’s Denial of Access to the\\n Mental Health Records ..................................... 140\\n 2. The District Court’s Grant of the Motion in\\n Limine ............................................................... 142\\nX. The Government’s Cross-Appeal ............................ 147\\n A. CUMA is a Mortgage Lending Business............. 148\\n B. Sufficiency of the Evidence ................................. 155\\nXI. Prejudicial Spillover ............................................... 158\\n A. Fattah’s Claim of Prejudicial Spillover ............... 159\\n 6\\n\\f B. Vederman’s Assertion of Prejudicial Spillover ... 160\\nXII. Conclusion ............................................................ 164\\n\\n\\n\\n\\n 7\\n\\f I. Introduction\\n Chaka Fattah, Sr., a powerful and prominent fixture\\nin Philadelphia politics, financially overextended himself\\nin both his personal life and his professional career during\\nan ultimately unsuccessful run for mayor. Fattah received\\na substantial illicit loan to his mayoral campaign and used\\nhis political influence and personal connections to engage\\nfriends, employees, and others in an elaborate series of\\nschemes aimed at preserving his political status by hiding\\nthe source of the illicit loan and its repayment. In so doing,\\nFattah and his allies engaged in shady and, at times, illegal\\nbehavior, including the misuse of federal grant money and\\nfederal appropriations, the siphoning of money from\\nnonprofit organizations to pay campaign debts, and the\\nmisappropriation of campaign funds to pay personal\\nobligations.\\n Based upon their actions, Fattah and four of his\\nassociates—Herbert Vederman, Robert Brand, Bonnie\\nBowser, and Karen Nicholas—were charged with\\nnumerous criminal acts in a twenty-nine count indictment.\\nAfter a jury trial, each was convicted on multiple counts.\\nAll but Bowser appealed. As we explain below, the\\nDistrict Court’s judgment will be affirmed in part and\\nreversed in part.\\n\\n\\n\\n\\n 8\\n\\f II. Background1\\n During the 1980s and ’90s, Fattah served in both\\nhouses of the Pennsylvania General Assembly, first as a\\nmember of the House of Representatives and later as a\\nSenator. In 1995, Fattah was elected to the United States\\nHouse of Representatives for Pennsylvania’s Second\\nCongressional District. In 2006, Fattah launched an\\nunsuccessful run for Mayor of Philadelphia, setting in\\nmotion the events that would lead to his criminal\\nconviction and resignation from Congress ten years later.\\n\\n A. The Fattah for Mayor Scheme\\n Fattah declared his candidacy for mayor in\\nNovember of 2006. Thomas Lindenfeld, a political\\nconsultant on Fattah’s exploratory committee, believed\\nthat “[a]t the beginning of the campaign, [Fattah] was a\\nconsiderable . . . candidate and somebody who had a very\\nlikely chance of success.” JA1618. But Fattah’s campaign\\nsoon began to experience difficulties, particularly with\\nfundraising. Philadelphia had adopted its first-ever\\ncampaign contribution limits, which limited contributions\\nto $2,500 from individuals and $10,000 from political\\naction committees and certain types of business\\norganizations. Fattah’s fundraising difficulties led him to\\n\\n\\n\\n1\\n The facts are drawn from the trial record unless otherwise\\nnoted.\\n 9\\n\\fseek a substantial loan, far in excess of the new\\ncontribution limits.\\n\\n 1. The Lord Loan and Its Repayment\\n While serving in Congress, Fattah became\\nacquainted with Albert Lord, II. The two first met around\\n1998, when Lord was a member of the Board of Directors\\nof Sallie Mae.\\n As the May 15, 2007 primary date for the\\nPhiladelphia mayoral race approached, Fattah met Lord to\\nask for assistance, telling Lord that the Fattah for Mayor\\n(FFM) campaign was running low on funds. Fattah asked\\nLord to meet with Thomas Lindenfeld, a political\\nconsultant in Washington, D.C., and part-owner of LSG\\nStrategies, Inc. (Strategies), a company that was working\\nwith the FFM campaign and that specialized in direct voter\\ncontact initiatives. Lindenfeld had been part of the\\nexploratory group that initially considered Fattah’s\\nviability as a candidate for mayor. Lindenfeld had known\\nFattah since 1999, when Fattah endorsed Philadelphia\\nMayor John Street. Through Fattah, Lindenfeld had also\\ngotten to know several of Fattah’s associates, including\\nHerbert Vederman, Robert Brand, and Bonnie Bowser.\\nHerbert Vederman, a businessman and former state\\nofficial, was the finance director for the FFM campaign.\\nRobert Brand owned Solutions for Progress (Solutions), a\\n“Philadelphia-based public policy technology company,\\nwhose mission [was] to deliver technology that directly\\nassists low and middle income families [in obtaining]\\n 10\\n\\fpublic benefits.” JA6551. Bowser was Fattah’s Chief of\\nStaff and campaign treasurer, and served in his district\\noffice in Philadelphia.\\n Lord’s assistant contacted Lindenfeld to arrange a\\nmeeting, and Lindenfeld informed Fattah that he would be\\nmeeting with Lord. Lindenfeld, along with his partner,\\nMichael Matthews, met with Lord and discussed Fattah’s\\nneed for funds to mount an intensive media campaign.\\nAfter that meeting, Lindenfeld reported to Fattah that Lord\\nwanted to help, but that they had not discussed a specific\\ndollar amount. Approximately a week later, Fattah\\ninstructed Lindenfeld to meet with Lord a second time.\\nLord “wanted to know if he could give a substantial\\namount of money, a million dollars” to Fattah’s campaign.\\nJA1630. That prompted Lindenfeld to reply that the\\namount “would be beyond the campaign finance limits.”\\nId.\\n\\n Lord proposed a solution: he offered to instead give\\na million dollars to Strategies in the form of a loan. To that\\nend, Lindenfeld had a promissory note drafted which\\nspecified that Lord was lending Strategies $1 million, and\\nthat Strategies promised to repay the $1 million at 9.25%\\ninterest, with repayment to commence January 31, 2008.\\nLindenfeld later acknowledged that the promissory note\\nwould make it appear as though Lord’s $1 million was not\\na contribution directly to the Congressman, although he\\nknew that it was actually a loan to the FFM campaign.\\nIndeed, Lindenfeld confirmed with Fattah that neither\\n\\n 11\\n\\fLindenfeld nor Strategies would be responsible for\\nrepayment. With that understanding, Lindenfeld executed\\nboth the note and a security agreement purporting to\\nencumber Strategies’ accounts receivable and all its assets.\\n\\n On May 1, shortly before the primary election, Lord\\nwired $1 million to Lindenfeld. Lindenfeld held the money\\nin Strategies’ operating account until Fattah told him how\\nit was to be spent. Some of the money was eventually used\\nfor print materials mailed directly to voters. And, at\\nFattah’s direction, Lindenfeld wired a substantial sum to\\nSydney Lei and Associates (SLA), a company owned by\\nGregory Naylor which specialized in “get out the vote”\\nefforts.\\n Naylor had known Fattah for more than 30 years.2\\nDuring the campaign, Naylor worked as the field director\\nand was in charge of getting out the vote on election day.\\n\\n2\\n Naylor first worked with Fattah when he was in the state\\nlegislature. When Fattah was elected to Congress, Naylor\\nworked in his Philadelphia office. Naylor met Nicholas\\nwhen she joined Fattah’s staff at some point in the 1990s.\\nAfter concluding her employment with Fattah’s office,\\nNicholas worked with the Educational Advancement\\nAlliance (EAA), an education nonprofit entity founded by\\nFattah. This entity helped to recruit underrepresented\\nstudents for scholarship and college opportunities. Around\\n2009, Naylor left Fattah’s office to work exclusively with\\nSLA. Naylor also knew Brand.\\n 12\\n\\fOn the final day of the campaign, Naylor worked with\\nVederman, who allowed Naylor to use his credit card to\\nrent vans that would transport Fattah voters to the polls.\\n As the primary date neared, Fattah and Naylor knew\\nthe campaign was running out of money. The campaign\\nwas unable to finance “media buys,” and Naylor needed\\nmoney for field operations to cover Philadelphia’s more\\nthan one thousand polling places. In early May,\\nLindenfeld called Naylor to say that Lindenfeld “would be\\nsending some money [Naylor’s] way.” JA3057. Within\\ndays, SLA received a six-figure sum for Naylor to use in\\nthe campaign and on election day. Naylor used the money\\nto pay some outstanding bills, including salaries for FFM\\nemployees, and allocated $200,000 to field operations for\\nelection day.\\n\\n Fattah lost the mayoral primary on May 15, 2007.\\nAfterward, Lindenfeld spoke with Fattah, Naylor and\\nBowser about accounting for the FFM campaign money\\nfrom Lord that had been spent. They decided that the\\namounts should not appear in the FFM campaign finance\\nreports, and Fattah instructed Naylor to have his firm,\\nSLA, create an invoice. Naylor did so, creating an invoice\\ndated June 1, 2007 from SLA to FFM, seeking payment of\\n$193,580.19. Naylor later acknowledged that the FFM\\ncampaign did not actually owe money to SLA, and that the\\nfalse invoice was created to “hide the transaction that took\\nplace earlier” and “make it look like [SLA] was owed\\nmoney.” JA3075–76. Although FFM did not owe SLA\\n\\n 13\\n\\fanything for the election day expenses, the FFM campaign\\nfinance reports from 2009 through 2013 listed a $20,000\\nin-kind contribution from SLA for each year, thereby\\nlowering FFM’s alleged outstanding debt to SLA.\\n\\n Of the total $1 million Lord loan, $400,000 had not\\nbeen spent. Lindenfeld returned that sum to Lord on June\\n3, 2007. He included a cover letter which stated: “As it\\nturns out the business opportunities we had contemplated\\ndo not seem to be as fruitful as previously expected.”\\nJA1254. Lindenfeld later admitted that there were no such\\n“business opportunities” and that the letter was simply an\\neffort to conceal the loan.\\n In late 2007, faced with financial pressures, Lord\\nasked his son, Albert Lord, III, to collect the outstanding\\n$600,000 balance on the loan to Strategies. Lord III\\ncontacted Lindenfeld about repayment and expressed a\\nwillingness to forgive the interest owed if the principal\\nwas paid. Lindenfeld immediately called Fattah and\\ninformed him that repayment could not be put off any\\nlonger. Fattah told Lindenfeld more than once that “[h]e\\nwould take care of it,” JA1652, but Fattah did not act.\\nNeeding someone who might have Fattah’s ear,\\nLindenfeld reached out to Naylor and Bowser. Naylor\\ntalked to Fattah on several occasions and told him that\\nLindenfeld was under considerable pressure to repay the\\nloan. Fattah told Naylor more than once that he was\\n“working on it.” JA3082–83.\\n\\n\\n 14\\n\\f During his political career, Fattah had focused on\\neducation, especially for the underprivileged. Indeed,\\nFattah founded two nonprofit organizations: College\\nOpportunity Resources for Education (CORE), and the\\nEducational Advancement Alliance (EAA).\\n\\n EAA held the annual Fattah Conference on Higher\\nEducation (the “annual conference”) to acquaint high\\nschool students with higher education options. JA3079.\\nSallie Mae regularly sponsored the conference. According\\nto Raymond Jones, EAA’s chairman of the board from\\n2004 through 2007, EAA offered a variety of programs to\\nprovide “marginalized students with educational\\nopportunities so they could continue and go to college.”\\nJA1360. EAA was funded with federal grant money which\\ncould only be spent for the purposes described in the\\nparticular grant. Karen Nicholas served as EAA’s\\nexecutive director, handling the organization’s day-to-day\\nadministrative responsibilities. Nicholas had previously\\nbeen a staffer for Fattah when he was a member of\\nPennsylvania’s House of Representatives.\\n CORE was an organization that awarded\\nscholarships to graduating high school students in\\nPhiladelphia who had gained admission to a state\\nuniversity or the Community College of Philadelphia.\\nCORE received funding from a variety of sources,\\nincluding Sallie Mae. Because CORE also received\\nfederal funds, and because EAA had experience working\\nwith federal grants, EAA received and handled the federal\\n\\n 15\\n\\ffunds awarded to CORE. In short, EAA functioned as a\\nfiduciary for CORE. When money became a problem for\\nthe FFM campaign, Fattah’s involvement with EAA and\\nCORE soon became less about helping underprivileged\\nstudents, and more about providing an avenue for\\ndisguising efforts to repay the illicit campaign funds from\\nLord.\\n\\n On January 7, 2008, Robert Brand contacted Fattah\\nby telephone. Shortly thereafter, Lindenfeld received an\\nunexpected call from Brand proposing an arrangement for\\nBrand’s company, Solutions, to work with Strategies.\\nSolutions had developed a software tool called “The\\nBenefit Bank,” which was designed to “assist low and\\nmoderate income families to have enhanced access to\\nbenefits and taxes.” JA1993. During the telephone call,\\nBrand referred to The Benefit Bank and suggested a\\ncontract under which Strategies would be paid $600,000\\nupfront. JA1666. Shortly thereafter, on January 9, 2008,\\nBrand followed up on his call to Lindenfeld with an email\\nabout “develop[ing] a working relationship where you\\ncould help us to grow The Benefit Bank and our process\\nof civic engagement. While I know this is not your core\\nbusiness I would like to try to convince you to take us on\\nas a client.” JA6427. Lindenfeld responded that he was\\ninterested. To Lindenfeld, “this was the way that\\nCongressman Fattah was going to repay the debt to Al\\nLord.” JA1654. When Lindenfeld called Fattah and told\\nhim of the contact from Brand, Fattah simply replied that\\nLindenfeld “should just proceed.” JA1666–67.\\n 16\\n\\f A few days later, Brand emailed Nicholas at EAA a\\nproposal from Solutions concerning The Benefit Bank,\\nwhich sought EAA’s support in developing an education\\nedition of The Benefit Bank and a $900,000 upfront\\npayment.\\n\\n As the January 31 date for repayment of the balance\\nof the $1 million Lord loan approached, a flurry of activity\\ntook place. On January 24, both Raymond Jones, chair of\\nthe EAA Board, and Nicholas signed a check from EAA\\nmade out to Solutions in the amount of $500,000.\\nAlthough no contract existed between EAA and Solutions,\\nthe memo line of the check indicated that it was for a\\ncontract, and Nicholas entered it into EAA’s ledger.3\\n\\n That same day, Ivy Butts, an employee of\\nStrategies, emailed Lindenfeld the instructions Brand\\nwould need to wire the $600,000 balance on the Lord loan.\\n\\n3\\n Raymond Jones, who was EAA’s Chairman of the Board\\nfrom 2004 through 2007, recalled at trial that the Board\\nhad a limit on the amount that Nicholas could spend\\nwithout board approval. JA1358, 1369. Nicholas was\\nauthorized to sign contracts on behalf of EAA for no more\\nthan $100,000. JA1369–71. Jones did not recall the\\ncontract between EAA and Solutions, nor did the EAA\\nboard minutes for December 2007, February 2008, or May\\n2008 refer to the EAA–Solutions contract or to the\\nsubstantial upfront payment of half a million dollars upon\\nexecution of the agreement. JA6358–63; 6567.\\n 17\\n\\fWithin minutes, Lindenfeld forwarded that email to Brand\\nat Solutions. Brand then made two telephone calls to\\nFattah. By late afternoon, Brand emailed Nicholas,\\ninforming her that he had “met with all the people I need\\nto meet with and have a pretty clear schedule of what\\nworks best for us. I am also seeing what line of credit we\\nhave to stretch out the payments until you get your line of\\ncredit in place.” JA6558. Brand asked if they could talk\\nand “finalize this effort.” JA6558. On January 25 and 26,\\nthere were a number of calls between Fattah, Brand, and\\nNicholas.\\n\\n On Sunday January 27, at 5:46 pm, Brand\\ntelephoned Fattah. At 10:59 pm, Brand emailed Nicholas\\na revised contract between EAA and Solutions for the\\nengagement of services. Brand indicated he would send\\nsomeone to pick up the check at about 1:00 pm the\\nfollowing day. The revised contract called for the same\\n$900,000 payment from EAA to Solutions, yet specified\\nthat $500,000 was to be paid on signing, with $100,000\\ndue three weeks later, and another $100,000 to be paid six\\nweeks out. No due date for the $200,000 balance was\\nspecified. The terms of the contract called for EAA to\\nassist Solutions with further developing The Benefit Bank.\\nIn addition, under the contract, EAA would receive certain\\n\\n\\n\\n\\n 18\\n\\ffunds from the Commonwealth of Pennsylvania for a\\nprogram relating to FAFSA applications. 4\\n\\n The same evening, Brand sent Lindenfeld a contract\\nentitled “Cooperative Development Agreement to Provide\\nServices to Solutions for Progress, Inc. for Growth of The\\nBenefit Bank.” JA6569. The agreement proposed a\\nworking partnership in which Strategies would work with\\nSolutions to identify and secure a Benefit Bank affiliate in\\nthe District of Columbia and two other states, and to\\nfacilitate introductions to key officials in other states\\nwhere The Benefit Bank might expand. The terms of the\\nagreement provided that Solutions would pay $600,000 to\\nStrategies by January 31, 2008, which would “enable\\n[Strategies’] team to assess opportunities and develop\\ndetailed work plans for each area.” JA6572. Brand copied\\nSolutions’ Chief Financial Officer, Michael Golden.\\nLindenfeld responded to Brand’s email within a minute,\\nasking if Brand had received the wiring instructions.\\nBrand immediately confirmed that he had.\\n\\n Concerned that Solutions did not have $600,000 to\\npay Strategies, Golden talked to Brand, who informed him\\nthat Solutions would be receiving a check for $500,000\\nfrom EAA. Early the next morning, Nicholas responded to\\nBrand’s email from the night before. She advised Brand\\nthat he could pick up the check, “but as I stated I am not\\n\\n4\\n FAFSA is an acronym for Free Application for Federal\\nStudent Aid.\\n 19\\n\\fin a position to sign a contract committing funds that I am\\nnot sure that I will have.” Gov’t Supp. App. (GSA) 1. That\\nsame day, a $540,000 transfer was made from the\\nconference account, which EAA handled, into EAA’s\\nchecking account. The conference account was maintained\\nto handle expenses for Fattah’s annual higher education\\nconference. Prior to this transfer, EAA had only\\n$23,170.95 in its account. EAA then tendered a $500,000\\ncheck to Solutions, which promptly deposited the check\\nbefore the close of that day’s business. EAA never\\nreplenished the $540,000 withdrawal from the conference\\naccount.\\n Brand received the executed contract between\\nSolutions and Strategies on January 28. Even though the\\ncontract called for Strategies to perform services in\\nexchange for the $600,000 payment, Lindenfeld neither\\nexpected to do any work for the $600,000, nor did he in\\nfact do any work.\\n\\n In sum, by January 28, Solutions had received\\n$500,000 from EAA, but it still had to come up with\\n$100,000 to provide Strategies with the entire amount\\nneeded to repay the Lord loan. Golden obtained the needed\\nfunds the following day by drawing $150,000 on a line of\\ncredit held by Brand’s wife. Brand and Fattah spoke four\\nmore times on the telephone on January 29. Trial evidence\\nlater showed that, during the month of January 2008,\\nneither the FFM campaign bank account nor Fattah’s\\n\\n\\n 20\\n\\fpersonal account had a sufficient balance to fund a\\n$600,000 payment.\\n On the morning of January 30, frustrated by the\\ndelay, Lindenfeld sent Brand an email with a subject line\\n“You are killing me.” JA6430. Lindenfeld stated that he\\nhad “made a commitment based on yours to me. Please\\ndon’t drag this out. I have a lot on the line.” Id. Brand\\nresponded late in the afternoon, stating: “just met with\\nMichael. He does the transfer at 8 AM tomorrow. It should\\nbe in your account ($600K) early tomorrow morning.” Id.\\nLindenfeld replied: “The earlier the better.” Id. The\\nfollowing morning, Golden wired $600,000 from\\nSolutions’ Pennsylvania bank account into Strategies’\\nWashington D.C. bank account. JA2745, 2874. Strategies\\nin turn, wired the same amount from its Washington D.C.\\nbank account to Lord’s bank account in Virginia. JA2874,\\n6549. Around noon, Brand telephoned Lindenfeld.\\n\\n In the days following the exhaustive efforts to meet\\nthe January 31 loan repayment deadline, four more\\ntelephone calls took place between Brand and Fattah.5\\nNaylor learned at some point that the loan had been paid\\noff. When Naylor asked Fattah about details of the\\nrepayment, Fattah simply replied “[t]hat it went through\\nEAA to Solutions and it was done.” JA3088.\\n\\n5\\n By contrast, between October to December 2007, Brand\\nand Fattah spoke by telephone only “once or twice [a]\\nmonth.” JA2734.\\n 21\\n\\f Meanwhile, at some point in January, EAA received\\nnotice that the Department of Justice Office of the\\nInspector General (DOJ) intended to audit its books.6 DOJ\\nauditors told EAA to provide, at the “entrance\\nconference,” documentation containing budgetary and\\naccounting information. EAA failed to produce any\\naccounting information.\\n Although Lindenfeld was no longer making\\ndemands of Brand, Brand was still owed the remaining\\n$100,000 that Solutions had paid to satisfy the Lord loan.\\nOn March 23, 2008, Brand sent Nicholas an email\\noutlining his efforts to contact her over the previous two\\nweeks about documentation on the CORE work, how to\\nproceed with the paperwork for the Commonwealth of\\nPennsylvania, and “how we can get our proposed contract\\nsigned and the outstanding payments made.” JA2749.\\nNicholas responded that evening, writing:\\n\\n I can appreciate your urgency however I do\\n have EAA work that I continue to do,\\n including the [usual] facilitation of programs,\\n our financial audit, the start-up of two new\\n programs[,] and of course the DOJ audit. I am\\n still trying to obtain a line of credit without a\\n completed 2007 audit and things are getting a\\n\\n\\n\\n6\\n One of the terms and conditions of a federal grant is that\\nthe recipient “be readily prepared for an audit.” JA2314.\\n 22\\n\\f little uncomfortable now as I try to keep us\\n afloat.\\nJA6576. Nicholas told Brand that the DOJ auditors were\\nmaking demands and would soon be on site. She noted that\\n“[t]hey are still very uncomfortable with your contract\\namongst other things and depending on their findings\\nsome of the funding received may have to be returned.” Id.\\nNicholas said that she had submitted the paperwork to the\\nstate, and she told Brand that “in the future . . . as a result\\nof the DOJ audit I will not be in a position to do another\\ncontract such as this.” Id.\\n Shortly after Nicholas’s reply to Brand, Nicholas\\nforwarded the Brand–Nicholas email chain to Fattah. The\\nbody of the email stated, in its entirety: “I really don’t\\nappreciate the tone of Bob’s email. I can appreciate that he\\nhas some things going on however I am doing my best to\\nassist him. Some other things are a priority. He needs to\\nback off.” GSA2. Later that night, Bowser sent Fattah an\\nemail with a subject line that read “Karen N” and a\\ntelephone number. JA2752.\\n\\n As the audit continued, the auditors found other\\ndeficiencies. During April of 2008, DOJ issued a notice of\\nirregularity to EAA, which resulted in the audit being\\nreferred to DOJ’s Investigations Division for a more\\ncomprehensive review.\\n\\n On April 24, 2008, Brand emailed Nicholas asking\\nfor a time to update her on The Benefit Bank. In early May,\\n 23\\n\\fBrand sent another email to Nicholas attaching a revised\\nEAA–Solutions contract proposal, which decreased the\\ninitial upfront cost from $900,000 to $700,000.\\n Although Solutions and EAA had still not signed a\\ncontract, EAA paid Solutions another $100,000 in May.\\nThat money was obtained via a loan to EAA from CORE.\\nThomas Butler, who had worked for Fattah both when\\nFattah was in Congress and when he was in the General\\nAssembly, was CORE’s executive director. Butler had\\nbeen contacted in mid-May by Jackie Barnett, a member\\nof CORE’s Board who had also worked with\\nCongressman Fattah. Barnett informed Butler that\\nNicholas had requested a loan from CORE to EAA, and\\nthat Fattah, as Chairman of CORE’s Board, had approved\\nit. Butler and Barnett withdrew funds from two CORE\\nbank accounts and obtained a cashier’s check, dated May\\n19, in the amount of $225,000 and made payable to EAA.\\nThe withdrawals were from accounts used for Sallie Mae\\nfunds and other scholarship money.\\n After EAA received the $225,000 check, EAA\\ntendered a $100,000 check to Solutions. The check bore\\nthe notation “Commonwealth of Pennsylvania.” EAA\\nrepaid CORE the following month. Because EAA lacked\\nsufficient funds of its own to cover this payment, EAA\\ndrew on grant money that it had received from NASA.\\n\\n Brand and Lindenfeld continued to communicate\\nconcerning The Benefit Bank. In July of 2008, a meeting\\nwas held at Solutions with Brand, Lindenfeld, Golden, and\\n 24\\n\\fother Solutions employees to discuss “an enormous\\namount of work” that Brand wanted Strategies to do.\\nJA1670. Lindenfeld said in response “we’d be glad to do\\nthat, but . . . we would have to be paid.” Id. At that point,\\nsomeone in the meeting stated that Strategies “had already\\nbeen paid” $600,000. Id. Lindenfeld replied: “well, that\\nwas for Congressman Fattah, . . . that’s not for us. So if\\nyou want us to do work, we have to get paid for it\\nseparately.” Id. Brand became upset with Lindenfeld over\\nhis comment about being paid because his colleagues at\\nSolutions were not aware of the reason for the $600,000\\npayment.\\n Meanwhile, EAA was attempting to meet the\\ndemands of the DOJ auditors, who were focused on the\\nrelationship between EAA and CORE. DOJ served a\\nsubpoena upon Solutions to produce “[a]ny and all\\ndocuments including, but not limited to, contract\\ndocuments, invoices, correspondence, timesheets,\\ndeliverables and proof of payment related to any services\\nprovided to or payments received” from CORE or EAA.\\nJA2350.\\n\\n Special Agent Dieffenbach, from the DOJ,\\ninterviewed Nicholas on July 14, 2008. During that\\ninterview, Nicholas discussed the relationship between\\nEAA and CORE, how invoices were paid, and how\\nconsultants were handled. Nicholas also answered\\nquestions about EAA’s relationship with Solutions,\\nincluding the payment of invoices. She did not inform\\n\\n 25\\n\\fAgent Dieffenbach of the $500,000 payment in January or\\nthe subsequent $100,000 payment in May. Nor did the\\ninterview address the EAA–Solutions contract that\\npurportedly required those payments, because the contract\\nhad yet to be produced.\\n\\n Solutions failed to comply with the subpoena,\\nprompting an email from Agent Dieffenbach on August 26\\nasking for an update concerning Solutions’ reply to the\\nDOJ subpoena. Solutions then produced an undated\\nversion of the EAA–Solutions contract that required the\\n$600,000 upfront payment. Neither Brand nor Nicholas\\nprovided the auditors with the January and May checks\\nfrom EAA to Solutions.\\n Efforts to conceal the repayment of the Lord loan\\nand to promote the political and financial interests of\\nFattah continued. The FFM campaign reports indicated in-\\nkind contributions of debt forgiveness by SLA even\\nthough there had been no actual debt. In September of\\n2009, with EAA’s ledgers still under scrutiny, Nicholas\\naltered the description of the entry for the $100,000 check\\nto Solutions from “professional fees consulting” to\\n“CORE Philly.” JA2546. Other FFM campaign debt was\\nreduced further after Vederman negotiated with creditors.\\n\\n EAA never fully recovered from its payment of the\\n$600,000 balance on the Lord loan and the audits that took\\nplace in 2008. It began laying off employees in 2011, and\\nby June of 2012, only four employees remained. JA3659.\\nEAA ceased operations at some point in 2012. JA1530.\\n 26\\n\\f 2. The College Tuition Component of the FFM\\n Scheme\\n Although the FFM campaign was close to insolvent,\\nit nevertheless made tuition payments for Fattah’s son,\\nChaka Fattah Jr., also known as Chip. Chip attended\\nDrexel University, but had yet to complete his coursework\\nbecause he had failed to pay an outstanding tuition\\nbalance. As the FFM campaign got underway in 2007,\\nFattah wanted Chip to re-enroll in classes at Drexel and\\nget a degree. Fattah asked Naylor to help financially, and\\nhe did so by writing checks from SLA to Drexel toward\\nChip’s outstanding tuition. By October of 2007, Chip was\\npermitted to re-enroll in classes.\\n Although Naylor never directly addressed the issue\\nwith Fattah, he agreed to assist with Chip’s outstanding\\ntuition with the expectation that SLA would be repaid. The\\nfirst check to Drexel in the amount of $5,000 was sent in\\nAugust of 2007, with $400 payments in the months that\\nfollowed until August of 2008. At some point, Chip\\ninformed Naylor that the payee was no longer Drexel, but\\nSallie Mae. Naylor then began sending monthly checks\\nfrom SLA to Sallie Mae. Those payments, in the amount\\nof $525.52, began in March of 2009 and continued until\\nApril of 2011, after which Fattah told Naylor he no longer\\nneeded to make them. SLA’s payments to Drexel and\\nSallie Mae totaled $23,063.52.\\n\\n Naylor’s expectation of repayment was eventually\\nrealized. Beginning in January of 2008 and continuing\\n 27\\n\\funtil November 2010, Bowser sporadically sent SLA\\nreimbursement checks from the FFM campaign with a\\nnotation that payment was for “election day operation\\nexpenses.” JA3136. The FFM funds had been transferred\\nfrom the Fattah for Congress campaign. These\\nreimbursement checks totaled $25,400. In an effort to\\nconceal the source of the payments to Drexel and Sallie\\nMae, and to make it appear that the younger Fattah had\\nperformed services for SLA, Naylor created false tax\\nforms for Chip. Chip, however, had never performed\\nservices for SLA.\\n\\n 3. The NOAA Grant and the Phantom Conference\\n In mid-December 2011, when EAA was\\nexperiencing serious financial difficulties, Nicholas\\nsubmitted an email request to the educational partnership\\nprogram of the National Oceanic & Atmospheric\\nAdministration (NOAA) for a grant “designed to provide\\ntraining opportunities and funding to students at minority\\nserving institutions” interested in science, technology,\\nengineering, and math fields related to NOAA’s mission.\\nJA3354–55. The request sought $409,000 to fund EAA’s\\nannual conference scheduled for February 17–19, 2012.\\nJacqueline Rousseau, a supervisory program manager at\\nNOAA, participated in a conference call with Nicholas\\nshortly thereafter and advised Nicholas that the agency\\ncould not afford the $409,000 request but would consider\\na smaller grant. Rousseau advised Nicholas that EAA\\n\\n\\n 28\\n\\fwould need to submit an application if it wished to be\\nconsidered for a grant.\\n Before submitting a grant application, Nicholas\\nemailed Rousseau about sponsoring the conference. On\\nJanuary 11, 2012, Rousseau informed Nicholas that the\\n“NOAA Office of Education, Scholarship Programs has\\nagreed to participate and provide sponsorship funds of\\n$50K to support the referenced conference.” JA6453.\\nRousseau also informed Nicholas that Chantell Haskins,\\nwho also worked with the student scholarship program,\\nwould be the point of contact for NOAA.\\n In February 2012, EAA held its annual conference\\nat the Sheraton Hotel in downtown Philadelphia. The\\nconference had been held at the same location each year\\nsince 2008.\\n\\n Nicholas contacted Haskins at some point in early\\n2012, inquiring about the $50,000 grant. On May 8, 2012,\\nHaskins sent Nicholas an e-mail which included\\ninformation about submitting proposals to fund a\\nconference for students. EAA then submitted a grant\\napplication, which Haskins reviewed. She advised\\nNicholas on June 28, 2012 that the grant could not be used\\nto provide meals, and that the date of the conference would\\nhave to be pushed back, with the new date included in a\\nmodified application. When Nicholas asked if expenses\\nfrom a previous conference could be paid from the new\\ngrant, Haskins informed her that this was not allowed.\\n\\n 29\\n\\f In early July 2012, Nicholas sent a modified grant\\nproposal to Haskins. It eliminated the budget item for food\\nand changed the date of the 2012 conference to October\\n19–21, 2012 at the same Sheraton Hotel in Philadelphia\\nwhere EAA’s annual conference had taken place earlier in\\nthe year. NOAA approved a $50,000 grant for the October\\n2012 conference—a conference that would never be held.\\n\\n Unaware that no October 2012 conference had\\ntaken place, NOAA allowed Nicholas access to the\\n$50,000 grant in March of 2013. She then transferred the\\nentire amount from NOAA to EAA’s bank account a few\\ndays later. Naylor had performed services for EAA for\\nwhich he was still owed $116,590. JA3119. In discussions\\nwith Naylor, Nicholas had informed him that the\\nlikelihood of EAA’s being able to pay him was “[n]ot very\\ngood.” JA3120. Yet several days after EAA had received\\nthe $50,000 from NOAA, Nicholas sent Naylor a check\\nfor $20,000. JA3120, 4283.\\n\\n On April 3, 2013, Nicholas submitted a final report\\nto NOAA concerning EAA’s use of the grant. Notably,\\npage 4 of the report stated the conference had been held in\\nFebruary 2012, while page 17 stated that the conference\\nhad been held from October 19 to 21, 2012. NOAA issued\\na notice asking for clarification and for a list of students\\nwho had been supported at the conference. Nicholas failed\\nto file either a clarifying report regarding the date of the\\nconference or a timely report regarding the disbursement\\nof the grant. Finally, in November of 2013, Nicholas\\n\\n 30\\n\\fsubmitted the final Federal Financial Report in which she\\ncertified, falsely, that the $50,000 had been used for a\\nproject during the period from August 1, 2012 to\\nDecember 30, 2012.\\n\\n B. The Blue Guardians Scheme\\n In addition to functioning as the conduit for Lord’s\\n$1 million loan to Fattah’s campaign, Lindenfeld’s\\ncompany, Strategies, also performed services for the\\ncampaign. The work resulted in indebtedness from FFM\\nto Strategies of approximately $95,000. Fattah made\\nseveral small payments, but failed to pay the full amount\\ndue. Although Lindenfeld spoke to Fattah, Naylor and\\nBowser about the debt, no payments were forthcoming.\\nDuring a meeting in Fattah’s D.C. office, Fattah told\\nLindenfeld “that [repayment] really wasn’t going to be\\npossible because the campaign had been over for a long\\ntime” and the funds were not available. JA1693. Fattah\\nthen asked Lindenfeld if he could write off the debt on his\\nFFM campaign finance reports. Id. Lindenfeld told Fattah\\nthat as long as he was paid, it was not his business how\\nFattah disclosed it on the campaign finance reports.\\nJA1694.\\n In lieu of repayment, Fattah suggested that\\nStrategies could claim to be interested in setting up an\\nentity to address environmental issues and ocean pollution\\nalong the coastline and in the Caribbean. Fattah explained\\nthat creating such an entity would make it possible to\\nobtain an appropriation from the government. Hearing\\n 31\\n\\fthis, Lindenfeld knew he was not going to be paid by the\\nFFM campaign, and was amenable to receiving money\\nfrom an appropriation instead. At a later meeting,\\nLindenfeld told Fattah that the name of the entity would\\nbe “Blue Guardians.” Lindenfeld consulted with an\\nattorney about creating Blue Guardians as an entity to\\nreceive the federal grant. He emailed Fattah, asking\\nquestions about how to complete an application to the\\nHouse Appropriations Committee. Fattah provided\\nsuggestions, and an application was eventually completed.\\nIt indicated that Blue Guardians would be “in operation for\\na minimum of ten years,” and, in accordance with Fattah’s\\nguidance, requested $15 million in federal funds. JA1711–\\n13.\\n Lindenfeld submitted the application to Fattah’s\\noffice in April of 2009. Afterward, a Fattah staffer\\ncontacted Lindenfeld to suggest that he change his\\nWashington, D.C., address to Philadelphia because that\\nwas the location of Fattah’s district. Fattah later suggested\\nto Lindenfeld that Brand might allow the use of his\\nPhiladelphia office address, a plan to which Brand agreed.\\n\\n In February 2010, Lindenfeld submitted a second\\napplication to the Appropriations Committee. In March,\\nFattah submitted a project request using his congressional\\nletterhead and seeking $3,000,000 for the “Blue\\nGuardians, Coastal Environmental Education Outreach\\nProgram.” JA6432. Within a month, Blue Guardians had\\nboth articles of incorporation and a bank account. Around\\n\\n 32\\n\\fthat time, a news reporter contacted Lindenfeld to discuss\\nthe new Blue Guardians entity. The inquiry made\\nLindenfeld uncomfortable, and he ultimately decided to\\nabandon the Blue Guardians project. He continued to seek\\npayment from Fattah, to no avail.\\n\\n Nonetheless, having obtained Lindenfeld’s\\nacquiescence to writing off the campaign’s debt to\\nStrategies, Fattah started falsifying FFM’s campaign\\nreports. Beginning in 2009 and extending through 2013,\\nthe FFM campaign reports executed by Fattah and Bowser\\nstated that Strategies made in-kind contributions of\\n$20,000, until the debt appeared to have been paid in full.\\n\\n C. The Fattah–Vederman Bribery Scheme\\n Vederman and Fattah were personal friends.\\nVederman was a successful businessman who had also\\nserved in prominent roles in the administrations of Ed\\nRendell when he was Mayor of Philadelphia and Governor\\nof Pennsylvania. In November of 2008, Vederman was a\\nsenior consultant in the government and public affairs\\npractice group of a Philadelphia law firm. His assistance\\nto the FFM campaign included paying for rented vans used\\nin the get-out-the-vote effort.\\n\\n After Fattah’s electoral defeat, the campaign still\\nowed more than $84,000 to a different law firm for\\nservices performed for the campaign. Vederman\\napproached that firm in the summer of 2008 asking if it\\nwould forgive FFM’s debt. Negotiations resulted in a\\n 33\\n\\fcommitment from FFM to pay the firm $30,000 by the end\\nof 2008 in exchange for forgiveness of $20,000, all of\\nwhich would appear on the FFM campaign finance report.\\nVederman’s efforts also led to payment by Fattah of an\\nadditional $10,000 in 2009 to the law firm, in exchange\\nfor additional forgiveness of $20,000 of debt. It was not\\nlong after Vederman’s successful efforts to lower Fattah’s\\ncampaign debt, that Fattah wrote a letter to U.S. Senator\\nRobert P. Casey recommending Vederman for an\\nambassadorship.\\n\\n At some point in 2010, Vederman again intervened\\non behalf of the FFM campaign. FFM remained in debt to\\nan advertising and public relations firm owned by Robert\\nDilella. By late 2011, Vederman and Dilella had worked\\nout a settlement to resolve the outstanding debt. Pursuant\\nto that settlement, Dilella received partial payment from\\nthe FFM campaign: $25,000 in satisfaction of a $55,000\\ndebt. Dilella testified at trial that he would not have agreed\\nto retire a portion of the debt had he known the FFM\\ncampaign was paying college tuition for Fattah’s son.\\n Vederman helped Fattah financially in other ways.\\nBefore the 2006 FFM campaign, Fattah and his wife,\\nRenee Chenault-Fattah, sponsored a young woman named\\nSimone Muller to live with them as an au pair exchange\\nvisitor. Muller was from South Africa, and her J-1 visa\\nallowed her to serve as a nanny and to study in the United\\nStates. Muller later applied for and received a second visa,\\nan F-1 student visa that indicated she had been accepted as\\n\\n 34\\n\\fan international student at the Community College of\\nPhiladelphia. The application indicated that Muller would\\nagain be residing with the Fattahs. Notwithstanding this\\nliving arrangement, Fattah identified Vederman as the\\nperson who would be paying for Muller’s trip to the\\nUnited States.\\n By the beginning of 2010, Muller wished to transfer\\nto Philadelphia University. This required her to submit\\nverification that funds were available to pay for her study.\\nAlthough the Fattahs were Muller’s sponsors, Fattah\\nexplained to the University’s Dean of Enrollment Services\\nthat he was submitting a letter of secondary support from\\nVederman. JA3754, 3763–65, 6504. Without Vederman’s\\nJanuary 2010 letter of support, the University would not\\nhave admitted Muller. In addition to this pledge of support,\\nVederman paid $3,000 of Muller’s tuition. Shortly\\nthereafter, Fattah resumed his efforts to secure an\\nambassadorship for Vederman.\\n\\n In February of 2010, Fattah staffer Maisha Leek\\ncontacted Katherine Kochman, a scheduler for White\\nHouse Chief of Staff Rahm Emanuel. Leek requested a\\ntelephone conference with Emanuel, Rendell, and Fattah\\nto discuss Vederman’s “serving his country in an\\ninternational capacity.” JA2893. In a follow-up email on\\nMarch 26, Leek sent documents to Kristin Sheehy, a\\nsecretary to White House Deputy Chief of Staff James\\nMessina. The documents included Fattah’s 2008 letter to\\nSenator Casey and Vederman’s biography. After\\n\\n 35\\n\\fparticipating in a telephone conference about Vederman\\nwith Fattah and Rendell, Messina sent Vederman’s\\nbiography to the White House personnel office for\\nconsideration.\\n\\n As the April 2010 tax deadline approached, Fattah\\nstill owed the City of Philadelphia earned income tax in\\nthe amount of $2,381. Just days before the filing deadline,\\nVederman gave a check to Chip Fattah for $3,500. The\\nyounger Fattah quickly deposited $2,310 into his father’s\\nbank account. Fattah paid his tax bill on April 15. Without\\nChip’s deposit into his father’s bank account, the older\\nFattah would not have had sufficient funds to pay his tax\\nbill.\\n On October 30, 2010, Vederman gave Chip another\\ncheck, this one for $2,800. That same day, Fattah hand-\\ndelivered a letter to President Obama recommending\\nVederman for an ambassadorship. A few weeks later,\\nFattah’s staffer, Leek, sent the letter that Fattah had given\\nto President Obama to Messina’s office. That letter\\npointed out that both Rendell and Fattah had sent letters\\non behalf of Vederman, and that he was an\\n“unquestionably exceptional candidate for an\\nambassadorship.” JA6291–92.\\n\\n Fattah’s efforts to secure Vederman an\\nambassadorship were unsuccessful. Fattah then shifted\\ngears and sought to secure Vederman a position on a\\nfederal trade committee. Fattah approached Ron Kirk, who\\nserved as U.S. Trade Representative, and asked him to\\n 36\\n\\fspeak with a constituent. In May of 2011, Leek followed\\nup on that discussion by emailing Kirk and asking him to\\nmeet with Vederman. Kirk met with Vederman on June 5,\\n2011 and explained to him the role of the trade advisory\\ncommittees. Although the two men “had a very nice\\nconversation,” JA 3566, it soon became “pretty apparent\\nto [Kirk and his staff] that [serving on a trade advisory\\ncommittee was] not what Mr. Vederman was interested\\nin.” JA3567. As Kirk put it, “it was obvious that\\n[Vederman] was looking for something perhaps more\\nrobust in his mind or . . . higher profile than one of our\\nadvisory committees.” Id. Given Vederman’s lukewarm\\ninterest, no appointment to an advisory committee was\\nforthcoming.\\n In late December 2011, the Fattahs applied for a\\nmortgage so they could purchase a second home in the\\nPoconos. Shortly after applying for the mortgage, Fattah\\nemailed Vederman, offering to sell him his wife’s 1989\\nPorsche for $18,000. Vederman accepted the offer. The\\nnext day, Vederman wired $18,000 to Fattah’s Wright\\nPatman Federal Credit Union account.\\n\\n The Credit Union Mortgage Association (CUMA)\\nacted as the loan processing organization for the home\\nmortgage. Because CUMA is required to verify the source\\nof any large deposits, CUMA’s mortgage loan processor,\\nVictoria Souza, contacted Fattah on January 17, 2012, to\\nconfirm the source of the $18,000. Fattah informed Souza\\nthat the $18,000 represented the proceeds of the Porsche\\n\\n 37\\n\\fsale. Souza requested documentation, including a signed\\nbill of sale and title.\\n That same day, Bowser emailed Vederman a blank\\nbill of sale for the Porsche. After Vederman signed the bill\\nof sale, Fattah forwarded it to Souza. The bill of sale was\\ndated January 16, 2012, which was the day before Souza\\nhad requested the documentation. It bore the signatures of\\nRenee Chenault-Fattah and Herbert Vederman, with\\nBonnie Bowser as a witness.\\n\\n Fattah also provided Souza with a copy of the\\nPorsche’s title. It was dated the same day it was sent to\\nSouza, and bore signatures of Chenault-Fattah as the seller\\nand Vederman as buyer, along with a notary’s stamp.\\nNeither Vederman nor Chenault-Fattah actually appeared\\nbefore the notary.\\n\\n Vederman never took possession of the Porsche.\\nRenee Chenault-Fattah continued to have the Porsche\\nserviced and insured long after the purported sale had\\ntaken place. Moreover, the Porsche remained registered in\\nChenault-Fattah’s name, and was never registered to\\nHerbert Vederman. When FBI agents searched the\\nFattahs’ home in 2014, the Porsche was discovered in the\\nFattahs’ garage.\\n\\n On January 24, 2012, the Fattahs wired $25,000 to\\nthe attorney handling the escrow account for the purchase\\nof the vacation home. Without the $18,000 transfer from\\n\\n 38\\n\\fVederman, the Fattahs would not have had sufficient funds\\nin their bank accounts to close on the home.\\n Around the same time that the Fattahs were\\npurchasing the house in the Poconos, Fattah’s Philadelphia\\noffice hired Vederman’s longtime girlfriend, Alexandra\\nZionts. Zionts had long worked for a federal magistrate\\njudge in Florida. Near the end of 2011, the magistrate\\njudge retired, leaving Zionts ten months shy of obtaining\\nthe necessary service required to receive retirement\\nbenefits. If Zionts could find another job in the federal\\ngovernment, her benefits and pension would not be\\nadversely affected. Vederman assisted Zionts in her job\\nsearch, which included calling Fattah. Fattah hired her, a\\nmove that put his congressional office overbudget. Zionts\\nworked in Fattah’s office for only about two months,\\nleaving to work for a congressman from Florida.\\n\\n Tia Watson, who performed constituent services for\\nFattah and worked on the same floor as Zionts in Fattah’s\\ndistrict office, testified she had no idea what work Zionts\\nperformed. Although Zionts contacted Temple University\\nabout archiving Fattah’s papers from his career in both the\\nstate and federal government, an employee from Temple\\nUniversity observed that Zionts’ work contributed nothing\\nof value to the papers project.\\n\\n D. The Indictment and Trial\\n Fattah’s schemes eventually unraveled. On July 29,\\n2015, a federal grand jury in the Eastern District of\\n 39\\n\\fPennsylvania returned a twenty-nine count indictment\\nalleging that Fattah and his associates had engaged in a\\nvariety of criminal acts. Fattah, Vederman, Nicholas,\\nBrand, and Bowser were charged with unlawfully\\nconspiring to violate the Racketeer Influenced and Corrupt\\nOrganizations Act (RICO), 18 U.S.C. § 1962(d). In\\naddition to the RICO charge, the indictment alleged that\\nFattah and certain co-defendants had unlawfully conspired\\nto commit wire fraud, 18 U.S.C. §§ 1343, 1349; honest\\nservices fraud, 18 U.S.C. §§ 1343, 1346, 1349; mail fraud,\\n18 U.S.C. §§ 1341, 1349; money laundering, 18 U.S.C.\\n§ 1956; and to defraud the United States, 18 U.S.C. § 371.\\nSeveral defendants were also charged with making false\\nstatements to banks, 18 U.S.C. § 1014; falsifying records,\\n18 U.S.C. § 1519; laundering money, 18 U.S.C. § 1957;\\nand engaging in mail, wire, and bank fraud, 18 U.S.C.\\n§§ 1341, 1343, and 1344.\\n\\n The RICO charge alleged that the defendants and\\nother co-conspirators constituted an enterprise aimed at\\nsupporting and promoting Fattah’s political and financial\\ninterests. The efforts to conceal the $1 million Lord loan\\nand its repayment are at the heart of the RICO conspiracy\\nand the Fattah for Mayor scheme. The indictment further\\nalleged that the RICO enterprise involved: (1) the scheme\\nto satisfy an outstanding campaign debt by creating the\\nfake “Blue Guardians” nonprofit; and (2) the bribery\\nscheme to obtain payments and things of value from\\nVederman in exchange for Fattah’s efforts to secure\\nVederman an appointment as a United States Ambassador.\\n 40\\n\\f A jury trial, before the Honorable Harvey Bartle III\\nof the Eastern District of Pennsylvania, began on May 16,\\n2016, and lasted about a month. 7 Judge Bartle charged the\\njury on Wednesday, June 15, 2016, and deliberations\\nbegan late that afternoon. The following day, after\\ndeliberating for only four hours, the jury sent a note to the\\njudge. Written by the foreperson, the note read:\\n Juror Number 12 refuses to vote by the letter\\n of the law. He will not, after proof, still\\n change his vote. His answer will not change.\\n He has the 11 of us a total wreck knowing that\\n we are not getting anywhere in the hour of\\n deliberation yesterday and the three hours\\n today. We have zero verdicts at this time all\\n due to Juror Number 12. He will not listen or\\n reason with anybody. He is killing every\\n other juror’s experience. We showed him all\\n the proof. He doesn’t care. Juror Number 12\\n has an agenda or ax to grind w/govt.\\nJA5916.\\n\\n Shortly after receiving the foreperson’s note, the\\nCourt received a second communication—a note signed\\n\\n\\n\\n 7\\n The District Court dismissed one charge prior to\\ntrial: an individual money laundering count against\\nNicholas.\\n 41\\n\\fby nine jurors, including the foreperson. The second note\\nread:\\n We feel that [Juror 12] is argumentative,\\n incapable of making decision. He constantly\\n scream [sic] at all of us.\\nId.\\n Judge Bartle met with counsel in his chambers and\\nadvised them of his intention to voir dire both the\\nforeperson and Juror 12 in an effort to determine whether\\nthe juror was deliberating as required by his oath. The\\nJudge also indicated that he would “stay away from the\\nmerits of the case,” and that whether he would voir dire\\nmore jurors “remain[ed] to be seen.” JA5917.\\n Counsel for the defendants objected to the Court’s\\nproposed inquiry. As a group, they indicated that while the\\nnote could be read as suggesting “a flat refusal to\\ndeliberate,” they were of the opinion that it sounded “more\\nin the manner of a disagreement over the evidence.”\\nJA5918. Nicholas’s counsel specifically argued that\\nquestioning the jurors so quickly after the start of\\ndeliberations would send a message that differences of\\nopinion among a block of jurors could be resolved by\\ncomplaining to the Court. Defense counsel acknowledged\\nthat the case law gave Judge Bartle wide discretion on how\\nto proceed, but suggested that a “less intrusive” course of\\naction was preferred. JA5918–19. They collectively urged\\n\\n 42\\n\\fthe Court to do nothing more than remind the jurors of\\ntheir duty to deliberate.\\n The Government agreed with Judge Bartle’s\\nproposed voir dire. In the prosecution’s view, the Court\\nhad already given proper instructions to the jury on their\\nduty to deliberate. The Government further argued that if\\nJuror 12 had exhibited bias, as suggested in the notes, he\\nwould have lied during the voir dire process and his\\nrefusal to deliberate would be “further evidence of that and\\nhis unsuitability as a juror.” JA5921.\\n\\n With all counsel present, and over defense counsel’s\\nobjections, Judge Bartle ultimately questioned five jurors\\nin chambers. He questioned Juror 2 (the foreperson), Juror\\n12 (the subject of the complaints), Juror 3, Juror 6, and\\nJuror 1.\\n\\n Judge Bartle began each voir dire by informing the\\njuror that he would ask a series of questions, but would not\\ninquire into the merits of the case or how any juror was\\nvoting. Each juror was placed under oath, and Judge Bartle\\nasked, among other questions, whether screaming was\\noccurring; whether the jurors were discussing the\\nevidence; whether Juror 12 was placing his hands on other\\njurors; and whether Juror 12 was unwilling to follow his\\ninstructions.\\n The foreperson acknowledged that he had written\\nthe initial note during lunch earlier that day. He stated that\\nJuror 12 was not willing to follow the law, but instead\\n 43\\n\\f“want[ed] to add his own piece of the law . . . which has\\nnothing to do with it.” JA5927–28. The foreperson further\\ntestified that Juror 12 “was standing up screaming” and\\nthat “[i]t was everybody pretty much against [Juror 12].”\\nJA5929. He testified that Juror 12 “has his own agenda,”\\nand that Juror 12 put his hand on another juror. JA5930.\\nThe foreperson also stated that the jury had discussed only\\na single count since the day before, and that they were still\\ndiscussing it. When the District Court responded that the\\njurors should understand that they could take as much time\\nas they needed, the foreperson responded: “I understand\\nthat. . . . [W]e all understand it. But we feel that he’s just—\\nhe’s got another agenda.” JA5934.\\n Judge Bartle advised counsel that he considered this\\n“a very serious situation” and that he would proceed to\\nvoir dire Juror 12. JA5937. Fattah’s counsel renewed his\\nobjection to questioning Juror 12, which the Court\\noverruled. Brand’s counsel argued that because the Court\\nhad decided to voir dire Juror 12, it should also voir dire\\nan additional juror. The Court agreed to do so.\\n When the Court questioned Juror 12, he admitted to\\nhaving “yelled back” at others, but only when they raised\\ntheir voices to him. JA5939. Juror 12 contended that he, in\\nfact, was “the only one” deliberating. Id. When an initial\\nvote was taken the previous afternoon, his vote “was\\ndifferent than everybody else’s.” Id. Juror 12 explained to\\nthe other jurors why his vote was different, bringing up\\nspecific evidence. In response, the other jurors said “that\\n\\n 44\\n\\fdoesn’t mean anything” and “pointed to the indictment.”\\nJA5940. Juror 12 told the other jurors that the indictment\\nis not evidence. Id. In response, the others “threatened to\\nhave [him] thrown off.” Id.\\n\\n Juror 12 testified that a similar sequence of events\\nhad taken place that morning. After a brief period of\\ndeliberations, another vote was taken, and with the same\\nresult as the previous afternoon. A discussion ensued, and\\nthe other jurors again “point[ed] to the indictment.” Id.\\nJuror 12 told them to “read the charge,” “[t]he indictment\\nis not evidence.” Id. They read the charge, and Juror 12\\nagain attempted to explain his view, but the other jurors\\npaid little attention. Accordingly, Juror 12 told the others\\nthat if they did not want him there, he “[didn’t] want to be\\n[there]”—he would be “[o]kay with it” if they wanted him\\ntaken off the jury. JA5941.\\n Upon hearing this testimony, Judge Bartle again\\nasked about the tone of deliberations. Juror 12 repeated\\nthat he raised his voice only in response to others who did\\nso—he did “not want to yell at anybody.” JA5942. Judge\\nBartle then asked whether he had touched other jurors.\\nJuror 12 replied that he had not hurt anyone. When asked\\nif he had put his hand on anybody’s shoulder, Juror 12\\nanswered: “I couldn’t remember to be honest with you.”\\nJA5946.\\n\\n Following Juror 12’s voir dire, the Court summoned\\nJuror 3 to chambers. Juror 3 testified that, after discussion\\nof a particular count, there was one juror at odds with the\\n 45\\n\\fothers. According to Juror 3, “the rest of the jurors\\npounced on the gentleman with the . . . dissenting\\nopinion.” JA5948. Juror 3 testified that Juror 12 “got very\\ndefensive and just a little bit [] impatient” and that “the\\nother jurors were very impatient with him.” Id. Juror 3 did\\nnot recall witnessing Juror 12 putting his hand on any\\nother jurors.\\n\\n The Government requested that the Court voir dire\\nanother juror. Defense counsel objected, claiming that the\\nquestioning “threaten[ed] . . . the entire deliberative\\nprocess.” JA5949–50. Judge Bartle reminded counsel that\\nhe had the authority to question each juror, and called for\\nvoir dire of Juror 6.\\n Juror 6 testified that the jury had been discussing the\\ncase and reviewing the evidence, but that Juror 12 “wants\\nto be seen” and was “being obstinate.” JA5951–52.\\nAccording to Juror 6, Juror 12 “may not agree” with the\\nconclusion of other jurors but “doesn’t give valid reasons\\nas to why he may disagree with the charge.” JA5952. Juror\\n6 also revealed that Juror 12 was the first to raise his voice,\\nand that he may have touched her and another juror. When\\nasked to clarify what she meant by Juror 12 disagreeing\\nwith “the charge,” Juror 6 testified that Juror 12 was\\n“reading maybe too deeply into it and putting his own\\nemotions into it instead of just looking at what it says [and]\\nwhat the facts are.” JA5952, 5955. According to Juror 6,\\nJuror 12 “just continues to read past that into his own mind\\nof what he feels it should be.” JA5955. Juror 6 testified\\n\\n 46\\n\\fthat Juror 12’s “justification for some of his responses [did\\nnot] seem to relate to what the matter [was] before\\n[them].” JA5957.\\n Judge Bartle chose to hear from yet another juror.\\nJuror 1 was called and informed the Court and counsel that\\nthe jury “really [hadn’t] been able to even start the\\ndeliberation process” in light of the disruptive behavior of\\n“one particular individual.” JA5958–59. The particular\\nindividual, according to Juror 1, was “very opinionated”\\nand “[came] into the process with his view already\\nestablished, refusing to even listen to any of the evidence\\n. . . [being] very forceful . . . standing up, yelling, pointing\\nhis finger.” JA5959. When asked if this individual was\\nwilling to follow the Court’s instructions, Juror 1 testified\\nthat he “pours [sic] over the documents very well” but that\\nhe was adding other factors to answer the question on the\\nverdict form, such as “what did this person feel.” JA5961.\\nWhen Judge Bartle advised that intent was an appropriate\\nconsideration, Juror 1 agreed but said that Juror 12 was\\n“trying to investigate . . . going way beyond the scope” of\\nthe evidence before them. JA5961–62. Juror 12, he said,\\n“has an opinion and that opinion is established.” JA5962.\\nHe stated that Juror 12 was “not willing to listen to any\\nsort of reason or any sort of what everyone else is saying”\\nbut instead, was “trying to force everyone else to get to his\\npoint of view.” Id. “[I]f he feels like he’s not getting there,\\nhe gets louder and louder and points and puts his hand on\\nyour shoulder . . . .” Id.\\n\\n 47\\n\\f After questioning the five jurors (Jurors 1, 2, 3, 6,\\nand 12), Judge Bartle heard argument from counsel. The\\nattorney for the Government pointed out that the Court\\nwould have to make a credibility determination because\\nJuror 12 stated that he did not recall touching anyone. In\\nthe Government’s view, Juror 12 was disrupting the\\nprocess and should be removed. Defense counsel\\ndisagreed. They argued that Juror 12 was conscientious\\nand was engaging with the evidence. They pointed out that\\ndespite the testimony that Juror 12 was reading too deeply\\ninto the instructions or introducing new factors for the jury\\nto consider, Juror 6 had testified that the jurors “talked it\\nthrough” and resolved the concern. JA5965. Defense\\ncounsel argued that the jury was discussing intent, an issue\\nthat was at the heart of the case. Defense counsel perceived\\nno breakdown in deliberations and argued that dismissal\\nwould be premature. They suggested, instead, that the\\nCourt provide a supplemental instruction.\\n\\n Judge Bartle decided to adjourn for the afternoon.\\nBut before he left the courtroom, defense counsel brought\\ntwo matters to his attention. First, in light of testimony\\nduring the voir dire, they asked that the jury be\\nreinstructed that the verdict form and indictment were not\\nevidence. Second, they apprised the Judge of the standard\\nfor juror dismissal set forth in United States v. Kemp, 500\\nF.3d 257 (3d Cir. 2007). Defense counsel stated that under\\nKemp, a request to discharge a juror must be denied if there\\nis a possibility that the request stems from the juror’s view\\nof the evidence. Judge Bartle expressed hesitation on\\n 48\\n\\freinstructing the jury, but agreed that Kemp would control\\nhis determination as to whether dismissal was appropriate.\\n With the following morning came a new revelation.\\nWith counsel in chambers, the Judge informed them that\\n“additional significant evidence” had come to light since\\nthe previous day’s recess. JA5980. He placed his\\ncourtroom deputy under oath, and she proceeded to testify\\nto an exchange that had occurred the previous day as she\\nwas escorting Juror 12 back to the jury room after he had\\nbeen voir dired. According to the deputy, Juror 12 stopped\\nher in the hallway, placed his hand on her shoulder, and\\nlooked her “straight in the eye.” JA5981. He then said:\\n“I’m going to hang this jury.” Id. The deputy then related\\nthat before any further conversation could take place\\nbetween Juror 12 and the deputy, Judge Bartle summoned\\nJuror 12 back to his chambers. Later that day, however,\\nJuror 12 and the courtroom deputy had another exchange.\\nShe testified that after all five jurors had been questioned,\\nJuror 12 emerged from the jury room and told her “I really\\nneed to talk to you.” JA5982. She informed Judge Bartle\\nand counsel that Juror 12 “said more about how they’re\\ntreating him and what he’s saying to them.” Id. He flatly\\nstated that “it’s going to be 11 to 1 no matter what.” Id.\\n\\n There were no follow-up questions for the deputy.\\nInstead, defense counsel suggested that what Juror 12 may\\nhave meant was that he was willing to hang the jury\\nbecause of a lack of evidence. They requested that Juror\\n12 be asked about his comments to the deputy.\\n\\n 49\\n\\f After once again summoning Juror 12 to his\\nchambers, the Judge advised him that “[s]ome questions\\nhave arisen” about what he may have done after being voir\\ndired the previous day. JA5985. Juror 12 acknowledged\\nhaving conversations with the courtroom deputy. When\\nasked “what happened” and “[w]hat occurred,” Juror 12\\nresponded: “Basically, I said that there was a lot of name\\ncalling going on.” JA5985. He said comments had been\\nmade by other jurors about his service in the military. He\\nspecifically referred to other jurors’ suggesting that he had\\npossibly “hit [his] head . . . hard a few times” while\\nserving in a parachute regiment. JA5986. He testified he\\nhad conveyed these comments to the deputy and that he\\nfound them offensive. When asked if he said anything else\\nto the deputy, Juror 12 responded: “I may have. I really\\ncan’t recall.” JA5987. And when Judge Bartle followed up\\nby asking if he could recall anything else that he said to\\nthe deputy, Juror 12 simply replied: “No. To me, that was\\nthe most important thing.” Id. Juror 12 was then excused\\nfrom chambers.\\n Defense counsel next requested that the juror be\\nasked directly whether he told the courtroom deputy that\\nhe was going to “hang this jury.” JA5988. Juror 12 was\\nrecalled to chambers, and the following back and forth\\ntook place:\\n\\n The Court: You may be seated. And, of\\n course, [Juror 12], you know you’re under\\n oath here from yesterday?\\n\\n 50\\n\\f Juror 12: Yes, sir.\\n The Court: . . . Did you say to [the courtroom\\n deputy] that you’re going to hang this jury?\\n Juror 12: I said I would.\\n The Court: You did?\\n Juror 12: I did. I said—I told her—I said, we\\n don’t agree; I’m not just going to say guilty\\n because everybody wants me to, and if that\\n hangs this jury, so be it.\\n ....\\n Juror 12: I did say that, sir.\\n The Court: You didn’t remember that before?\\n Juror 12: I’m more concerned about people\\n spitting on my military record.\\n The Court: Did you say that you’d hang the\\n jury no matter what?\\n Juror 12: If they do—if we cannot come to—\\n The Court: No. The question is what you said\\n to her. Did you say to her you would hang the\\n jury no matter what?\\n Juror 12: I can’t really remember that. I did\\n say that if we didn’t—a person—no matter\\n what, I can’t recall that exactly.\\n The Court: All right. Thank you very much.\\n You can wait just out there in the anteroom.\\nJA5989–90.\\n\\n Defense counsel continued to oppose Juror 12’s\\ndismissal. They argued that the juror’s concern was about\\n\\n 51\\n\\fthe evidence, and that his comments to the courtroom\\ndeputy reflected a conviction that “he’s not going to agree\\njust because others want him to agree.” JA5991. They also\\nargued that nothing should be made of Juror 12’s failure\\nto mention the comments when initially questioned by the\\nCourt, and that a supplemental instruction was all that was\\nwarranted given the early stage of the deliberations.\\n\\n The Government strongly disagreed. The Assistant\\nUnited States Attorney argued that Juror 12 “should\\nabsolutely be removed” because “his demeanor ha[d]\\ndemonstrated a hostility . . . both to the other jurors and to\\nthe court.” JA5993. The Government also suggested that\\nJuror 12’s comments that he would hang the jury meant\\nthat he was not participating in the deliberations and was\\nignoring the evidence and the law.\\n\\n Ruling from the bench, Judge Bartle announced:\\n I find [the deputy clerk] to be credible. I find\\n [Juror 12], not to be credible. I find that [Juror\\n 12] did tell [the deputy clerk] that he was\\n going to hang this jury no matter what.\\n There have been only approximately\\n four hours of deliberation. There’s no way in\\n the world he could have reviewed and\\n considered all of the evidence in the case and\\n my instructions on the law.\\n I instructed the jury to deliberate,\\n meaning to discuss the evidence; obviously,\\n to hold onto your honestly held beliefs, but at\\n 52\\n\\f least you have to be willing to discuss the\\n evidence and participate in the discussion\\n with other jurors.\\n Juror number 12 has delayed,\\n disrupted, impeded, and obstructed the\\n deliberative process and had the intent to do\\n so. I base that having observed him, based on\\n his words and his demeanor before me.\\n He wants only to have his own voice\\n heard. He has preconceived notions about the\\n case. He has violated his oath as a juror.\\n And I do not believe that any further\\n instructions or admonitions would do any\\n good. I think he’s intent on, as he said,\\n hanging this jury no matter what the law is,\\n no matter what the evidence is.\\n Therefore, he will be excused, and I\\n will replace him with the next alternate . . . .\\n\\nJA5994–95.\\n In response, defense counsel moved for a mistrial,\\nwhich the judge promptly denied. He then informed the\\nreconstituted jury that deliberations would need to start\\nover, and reinstructed them on certain points of law,\\nincluding that the verdict slip does not constitute evidence.\\n\\n Judge Bartle elaborated upon his decision to remove\\nJuror 12 in two post-trial memorandum opinions. In the\\nfirst, ruling on a media request for the sealed transcripts,\\nhe explained:\\n 53\\n\\f Here, there is no doubt that Juror 12\\n intentionally refused to deliberate when he\\n declared so early in the process that he would\\n hang the jury no matter what. This finding\\n was predicated on the admission of Juror 12\\n as reported by the court’s deputy clerk. The\\n facts became clear to the court after hearing\\n the credible testimony of the deputy clerk and\\n the less credible testimony of Juror 12. The\\n demeanor of Juror 12 before the court\\n confirmed the court’s findings.\\n\\nGSA23–24. The second opinion addressed motions for\\nbail pending appeal from Nicholas and Brand. GSA25.\\nThere, Judge Bartle explained:\\n\\n The law is well-settled that the court has\\n discretion to act as it did under these\\n circumstances. See United States v. Kemp,\\n 500 F.3d 257, 304 (3d Cir. 2007). The court,\\n after taking testimony, specifically found that\\n the juror, following only a few hours of\\n deliberation, stated to the court’s courtroom\\n deputy clerk that he would hang this jury no\\n matter what. He could not possibly have\\n reviewed all of the law and evidence of this\\n five-week trial at the time he made his\\n remark. The court examined the deputy clerk\\n and the juror under oath in the presence of\\n counsel for all parties. The undersigned\\n\\n 54\\n\\f found the deputy clerk to be credible and the\\n juror not to be credible. Based on the juror’s\\n demeanor, it was clear he would not change\\n his attitude and that his intent had been and\\n would continue to be to refuse to deliberate\\n in good faith concerning the law and the\\n evidence.\\n\\nGSA32.\\n After deliberating for approximately 15 hours, the\\njury returned with its verdicts on June 21, 2016, finding\\nthe defendants guilty on most counts. Fattah, Vederman,\\nand Brand were convicted on all counts. The jury acquitted\\nBowser on sixteen counts, but found her guilty of the\\nbribery conspiracy and the associated charges of bank\\nfraud, making false statements to a financial institution,\\nfalsifying records, and money laundering (Counts 16, 19,\\n20, 21 and 22). The jury also acquitted Nicholas of wire\\nfraud (Count 24). See Nicholas Supp. App. (NSA) 36.\\n The following week, on June 27, the Supreme Court\\nissued its opinion in McDonnell v. United States, 136 S.\\nCt. 2355 (2016). McDonnell provided new limitations on\\nthe definition of “official acts” as used in the honest\\nservices fraud and bribery statutes under which Fattah and\\nVederman had been convicted. Id. at 2369–72. Fattah and\\nVederman both moved to set aside their convictions. The\\nDistrict Court “acknowledge[d] that under McDonnell our\\ninstructions to the jury on the meaning of official act\\nturned out to be incomplete and thus erroneous.” JA103.\\n 55\\n\\fBut the Court held that “the incomplete and thus erroneous\\njury instruction on the meaning of official acts did not\\ninfluence the verdict on the bribery counts” and upheld the\\nverdict on Counts 16–18 and 22–23. JA107, 121.\\n\\n Fattah, Vederman, and Bowser had more success\\nwith their other post-verdict motions. The District Court,\\nin a thoughtful opinion, granted relief under Federal Rule\\nof Criminal Procedure 29, acquitting Vederman of the\\nRICO conspiracy (Count 1) and Fattah, Vederman, and\\nBowser of bank fraud, making false statements to a\\nfinancial institution, and falsifying records (Counts 19, 20,\\nand 21). JA37–139.\\n This appeal followed. 8 The defendants raise a\\nvariety of challenges to their convictions. All defendants\\nbut Bowser challenge the District Court’s decision to\\ndismiss Juror 12. Fattah and Vederman argue that the\\nDistrict Court erred in upholding the jury’s verdict on the\\nbribery and honest services fraud counts in light of the\\nSupreme Court’s decision in McDonnell. Fattah, Brand\\nand Nicholas challenge the sufficiency of the evidence\\nunderlying the RICO conviction. Several of the defendants\\ncontend the District Court erred in its instruction on intent\\nand by sending the indictment out to the jury. There are\\n\\n\\n\\n8\\n Fattah, Brand, Vederman, and Nicholas each filed a\\ntimely notice of appeal, but Bowser did not challenge her\\nconvictions.\\n 56\\n\\falso several evidentiary challenges.9 The Government\\ncross-appeals from the District Court’s judgment\\nacquitting Fattah and Vederman on Counts 19 and 20,\\narguing that the District Court erred in interpreting the\\ndefinition of a “mortgage lending business” under 18\\nU.S.C. § 27. We address these arguments in turn.\\n\\n We hold that the District Court erred in upholding\\nthe jury verdict in light of McDonnell, and we will\\ntherefore reverse and remand for retrial on Counts 16, 17,\\n18, 22, and 23. We also hold that the District Court erred\\n\\n9\\n Pursuant to Rule 28(i), “Fattah joins in the arguments of\\nHerbert Vederman, Robert Brand, and Karen Nicholas to\\nthe extent their arguments on appeal apply to Mr. Fattah.”\\nFattah Br. 19 n.69. Federal Rule of Appellate Procedure\\n28(i) provides that a defendant, “[i]n a case involving\\nmore than one appellant . . . may adopt by reference a part\\nof another’s brief.” Here, Fattah’s decision to join fails to\\nspecify which of the many issues of his codefendants he\\nbelieves worthy of our consideration. Rather, it appears\\nthat he presumes we will scour the record and make that\\ndetermination for him. This type of blanket request fails to\\nsatisfy Rule 28(a)(5)’s directive requiring that the\\n“appellant’s brief must contain . . . a statement of the\\nissues presented for review.” Fed. R. App. P. 28(a)(5). We\\nconclude that expecting the appellate court to identify the\\nissues to be adopted simply results in the abandonment and\\nwaiver of the unspecified issues. See Kost v. Kozakiewicz,\\n1 F.3d 176, 182 (3d Cir. 1993).\\n 57\\n\\fin acquitting Fattah and Vederman on Counts 19 and 20.\\nBecause the jury’s verdict was supported by the evidence,\\nwe will reinstate the convictions as to those counts. In all\\nother respects, we will affirm the judgment of the District\\nCourt.\\n\\n III. Juror Misconduct and Dismissal of Juror 12 10\\n Defendant Fattah challenges the District Court’s\\ndecision to conduct an in camera inquiry into alleged juror\\nmisconduct and the ultimate dismissal of Juror 12. 11 We\\nreject both challenges. The record reveals credible\\nallegations of juror misconduct and a sufficient basis to\\nsupport the finding that Juror 12 violated his oath.\\n\\n A. Investigation of Alleged Juror Misconduct\\n We first consider whether the District Court erred in\\nits handling of the two notes from jurors. A trial court’s\\nresponse to allegations of juror misconduct is reviewed\\nunder an abuse of discretion standard. United States v.\\nBoone, 458 F.3d 321, 326 (3d Cir. 2006) (citing United\\nStates v. Resko, 3 F.3d 684, 690 (3d Cir. 1993)). We\\nconclude that the District Court did not abuse its discretion\\n\\n\\n10\\n The District Court had jurisdiction under 18 U.S.C.\\n§ 3231. We have jurisdiction under 28 U.S.C. § 1291 and\\n18 U.S.C. § 3742(a).\\n11\\n Vederman, Nicholas, and Brand adopt Fattah’s claim of\\nreversible error concerning the dismissal of Juror 12.\\n 58\\n\\fin addressing the issues raised in the jurors’ notes to the\\nCourt.\\n Trial courts are afforded discretion in responding to\\nallegations of juror misconduct. This is so because “the\\ntrial court is in a superior position to observe the ‘mood at\\ntrial and the predilections of the jury.’ ” Resko, 3 F.3d at\\n690 (quoting United States v. Chiantese, 582 F.2d 974,\\n980 (5th Cir. 1978)). But this discretion is not unlimited.\\nOnce the jury retires to deliberate, the confidentiality of its\\ndeliberations must be closely guarded. An accused is\\nconstitutionally entitled to be tried before a jury of his\\npeers. As ordinary citizens, jurors are “expected to speak,\\ndebate, argue, and make decisions the way ordinary people\\ndo in their daily lives.” Pena-Rodriguez v. Colorado, 137\\nS. Ct. 855, 874 (2017) (Alito, J., dissenting). To protect\\nagainst intrusion into a defendant’s right to be judged only\\nby fellow citizens, “the door to the jury room [is] locked.”\\nId. at 875.\\n In Boone, this Court considered the threshold for\\nintervention by a trial judge who is presented with\\nallegations of juror misconduct during the course of\\ndeliberations. 458 F.3d at 327. We recognized that “[i]t is\\nbeyond question that the secrecy of deliberations is critical\\nto the success of the jury system.” Id. at 329. But that\\nsecrecy abuts a competing interest—the jury’s proper\\nexecution of its duties. That is, “a juror who refuses to\\ndeliberate or who commits jury nullification violates the\\nsworn jury oath and prevents the jury from fulfilling its\\n\\n 59\\n\\fconstitutional role.” Id. Recognizing these competing\\ninterests, we declined in Boone to adopt a sweeping\\nlimitation on a trial court’s ability to investigate\\nallegations of misconduct during jury deliberations. See id.\\nConsistent with the standard applied at other stages of\\ncriminal proceedings, Boone teaches that “where\\nsubstantial evidence of jury misconduct—including\\ncredible allegations of jury nullification or of a refusal to\\ndeliberate—arises during deliberations, a district court\\nmay, within its sound discretion, investigate the\\nallegations through juror questioning or other appropriate\\nmeans.” Id.\\n Fattah argues that the District Court had no basis to\\nquestion any of the jurors. Fattah Br. 20. We disagree. In\\nBoone, notes from the jury presented substantial credible\\nevidence of misconduct. 458 F.3d at 330. Here, the initial\\nnote from the foreperson alleged that Juror 12 “refuse[d]\\nto vote by the letter of the law,” would “not listen or reason\\nwith anybody,” and that he had “an agenda or ax to grind”\\nwith the Government. JA5916. The note contained\\nallegations of both a refusal to deliberate and a suggestion\\nof nullification. A refusal to deliberate is a violation of a\\njuror’s oath. Boone, 458 F.3d at 329 (citing United States\\nv. Baker, 262 F.3d 124, 130 (2d Cir. 2001) (“It is well-\\nsettled that jurors have a duty to deliberate.”)). Moreover,\\nnullification—a juror’s refusal to follow the law—is a\\nviolation of the juror’s sworn oath to render a verdict\\naccording to the law and evidence. See United States v.\\nThomas, 116 F.3d 606, 614–18 (2d Cir. 1997) (discussing\\n 60\\n\\fboth “benevolent” and “shameful” examples of juror\\nnullification, but “categorically reject[ing] the idea that, in\\na society committed to the rule of law, jury nullification is\\ndesirable or that courts may permit it to occur when it is\\nwithin their authority to prevent”). The second jury note,\\nsigned by nine jurors, supported the claim of misconduct\\nby asserting that Juror 12 was “incapable of making\\ndecision[s]” and was “constantly scream[ing]” at the other\\njurors. JA5916–17. We conclude that the District Court\\ndid not abuse its discretion in deciding to initially question\\nJuror 2, and subsequently, Jurors 12, 3, 6 and 1.\\n\\n Fattah also challenges the scope of the District\\nCourt’s questioning. He argues that the rights to an\\nimpartial jury and to a unanimous verdict “would be\\nrendered toothless if trial courts had free rein to question\\njurors during deliberations.” Fattah Br. 36. Indeed, we\\nacknowledged the legitimacy of such a concern in Boone.\\nDespite adopting a modest “credible allegations” standard\\nfor investigating misconduct, we “ke[pt] in mind the\\nimportance of maintaining deliberative secrecy.” Boone,\\n458 F.3d at 329. Fattah asserts that the trial court’s\\nquestions to the five jurors were “intrusive and pointed”\\nand “nothing like the questioning . . . approved in Boone.”\\nFattah Br. 38. But Fattah does not elaborate on how, in his\\nview, the questions posed by Judge Bartle specifically\\nintruded into deliberative secrecy.\\n\\n To be sure, Judge Bartle’s questioning of each juror\\nwas more extemporaneous than the juror questioning in\\n\\n 61\\n\\fBoone. There, the district court asked a single juror four\\n“concise and carefully-worded” questions. 458 F.3d at\\n330. Judge Bartle’s voir dire of each of the five jurors took\\non a more conversational tone. We take no issue with that\\napproach. The substance of the judge’s questions was\\nlimited and mirrored that of questions we deemed\\nappropriate in Kemp. There, the court conducted three\\nrounds of questioning. In the first round, each juror was\\nasked:\\n (1) “Are you personally experiencing any\\n problems with how the deliberations are\\n proceeding without telling us anything about\\n the votes as to guilt or innocence? If yes,\\n describe the problem.” (2) “Are all the jurors\\n discussing the evidence or lack of evidence?”\\n (3) “Are all the jurors following the court’s\\n instructions on the law?”\\n\\nKemp, 500 F.3d at 273. In the second and third rounds,\\neach juror was asked:\\n (1) “Is there any juror or jurors who are\\n refusing to deliberate?” (2) “Is there any juror\\n who is refusing to discuss the evidence or\\n lack of evidence?” (3) “Is there any juror who\\n is refusing to follow the Court’s\\n instructions?”\\nId. at 274. Here, Judge Bartle began his voir dire of each\\njuror by stating that he did not wish for the juror to discuss\\n 62\\n\\fthe merits of the case or to reveal the content of the\\ndeliberations that had taken place. He asked the jurors\\nwhether screaming was occurring, whether the jurors were\\ndiscussing the evidence, whether Juror 12 was placing his\\nhands on other jurors, and whether Juror 12 was unwilling\\nto follow his instructions.\\n Fattah points to no specific question posed or topic\\ndiscussed that was inappropriate, and we see little to no\\nsubstantive difference between the questions here and\\nthose asked by the trial judge in Kemp. As in Kemp, “the\\nDistrict Court took care to limit its questions to appropriate\\nmatters that did not touch on the merits of the jury’s\\ndeliberation, and expressly informed each juror on\\nmultiple occasions that he or she should not reveal the\\nsubstance of the deliberations.” Id. at 302 (citing United\\nStates v. Edwards, 303 F.3d 606, 634 n.16 (5th Cir. 2002)).\\n Fattah also argues that once the remarks of Juror 2\\nand Juror 12 revealed no further evidence of misconduct,\\nthe court had no basis to question other jurors. Fattah\\nReply 19. Yet, our cases make clear that a trial court may,\\nin its discretion, examine each juror. Kemp, 500 F.3d at\\n302 (“We have recognized that there are times in which\\nindividual questioning is the optimal way in which to root\\nout misconduct.”). Indeed, “the District Court must utilize\\nprocedures that will ‘provide a reasonable assurance for\\nthe discovery of prejudice.’ ” Id. (quoting Martin v.\\n\\n\\n\\n 63\\n\\fWarden, Huntingdon State Corr. Inst., 653 F.2d 799, 807\\n(3d Cir. 1981)). 12\\n\\n Judge Bartle, a very able and experienced district\\njudge, was in the best position to determine what type of\\ninquiry was warranted under the circumstances. We\\nconclude that his questioning of the five jurors was not an\\nabuse of discretion. See id. at 302.\\n\\n B. Dismissal of Juror 12\\n Fattah, joined by Vederman, Brand, and Nicholas,\\nstrongly contends that the District Court committed\\nreversible error by dismissing Juror 12. “We review the\\ndismissal of a juror for cause for abuse of discretion.”\\n\\n12\\n Our cases do not suggest that a trial judge confronted\\nwith allegations that a jury’s deliberations are being\\nobstructed by one of its members should always resort to\\ninterviewing jurors. Reinstructing the jury on its duty to\\ndeliberate will often be the better course at the first sign of\\ntrouble. Mere disagreement among jurors—even spirited\\ndisagreement—is no ground for intervention.\\nFurthermore, intrusive or leading questions about the\\ndeliberative process may work against the twin goals of\\nprotecting that process and ensuring that jurors remain\\nfaithful to their oaths. We share the Eleventh Circuit’s\\npreference of “err[ing] on the side of too little inquiry as\\nopposed to too much.” United States v. Oscar, 877 F.3d\\n1270, 1287 (11th Cir. 2017) (quoting United States v.\\nAugustin, 661 F.3d 1105, 1133 (11th Cir. 2011)).\\n 64\\n\\fKemp, 500 F.3d at 303. That deferential standard compels\\nus to affirm.\\n Rule 23(b) of the Federal Rules of Criminal\\nProcedure permits a trial court to excuse a deliberating\\njuror for good cause. See id. (citing Fed. R. Crim. P.\\n23(b)). Good cause exists where a juror refuses to apply\\nthe law, refuses to follow the court’s instructions, refuses\\nto deliberate with his or her fellow jurors, or demonstrates\\nbias. See Kemp, 500 F.3d at 305–06; United States v.\\nOscar, 877 F.3d 1270, 1287 (11th Cir. 2017); Thomas, 116\\nF.3d at 617. Good cause does not exist when there is\\nreasonable but sustained disagreement about how a juror\\nviews the evidence. The courts of appeals are emphatic\\nthat trial courts “may not dismiss a juror during\\ndeliberations if the request for discharge stems from\\ndoubts the juror harbors about the sufficiency of the\\ngovernment’s evidence.” Kemp, 500 F.3d at 303 (quoting\\nUnited States v. Brown, 823 F.2d 591, 596 (D.C. Cir.\\n1987)); see also Oscar, 877 F.3d at 1287 (same); United\\nStates v. Symington, 195 F.3d 1080, 1087 (9th Cir. 1999);\\nThomas, 116 F.3d at 622.\\n\\n To reinforce a defendant’s right to a unanimous\\njury, we have adopted a high standard for juror dismissal.\\nKemp, 500 F.3d at 304 & n.26. “[D]istrict courts may\\ndischarge a juror for bias, failure to deliberate, failure to\\nfollow the district court’s instructions, or jury nullification\\nwhen there is no reasonable possibility that the allegations\\nof misconduct stem from the juror’s view of the evidence.”\\n\\n 65\\n\\fId. at 304 (emphasis added). This “no reasonable\\npossibility” standard is “by no means lax.” Id. Rather, “[i]t\\ncorresponds with the burden for establishing guilt in a\\ncriminal trial.” Id.\\n\\n We first applied this standard in Kemp, but have not\\nhad occasion to do so since. There, the evidence\\nsupporting the district court’s removal decision was\\n“overwhelming.” 500 F.3d at 304. Ten jurors separately\\nand consistently reported that a juror was improperly\\nbiased, and did so only after three rounds of questioning\\nand careful and correct instructions from the district court\\nas to the distinction between appropriate skepticism and\\nimpermissible bias. Id. at 304–05; see id. at 275–76\\n(district court’s instruction). The testimony also showed\\nthat the juror in question refused to deliberate or to discuss\\nthe evidence with her fellow jurors. Id. at 305.\\n Whether the evidence of misconduct in this case is\\nas strong as that in Kemp is beside the point. After only\\nfour hours of deliberations, Juror 12 stated unequivocally\\nto the courtroom deputy that he was “going to hang” the\\njury, and that it would be “11 to 1 no matter what.”\\nJA5981–82 (emphasis added). These statements, coupled\\nwith the District Court’s finding that Juror 12 lacked\\ncredibility, provided a sufficient basis for Juror 12’s\\ndismissal.\\n\\n As grounds for excusing Juror 12, the District Court\\nfound that he refused to deliberate in good faith, “delayed,\\ndisrupted, impeded, and obstructed the deliberative\\n 66\\n\\fprocess and had the intent to do so,” JA5995, and that he\\nwas “intent on . . . hanging this jury no matter what the law\\nis, no matter what the evidence is.” Id. The District Court\\ndetermined from this that Juror 12 had violated his oath as\\na juror and that no further instructions or admonitions\\ncould rehabilitate the juror. Id. The District Court based\\nthese findings on personal observation, including Juror\\n12’s words and demeanor, and making the specific finding\\nthat Juror 12 was not credible. That finding is amply\\nsupported by the record.\\n\\n In United States v. Abbell, 271 F.3d 1286, 1303 (9th\\nCir. 2001), the Ninth Circuit recognized that “the\\ndemeanor of the pertinent juror is important to juror\\nmisconduct determinations” because the “juror’s\\nmotivations and intentions are at issue.” That court\\nemphasized, as we do, that a district judge is best situated\\nto assess the demeanor of a juror. Id. Here, Juror 12 stated\\nhe could not recall putting his hand on another juror’s\\nshoulder, while his fellow jurors’ testimony was consistent\\non this point. Juror 12 also failed, at first, to recall his\\ntroubling statements to the courtroom deputy despite\\nhaving made those statements only the previous afternoon.\\nWhen questioned a second time and asked directly about\\nthe statements, he admitted to saying that he would hang\\nthe jury but claimed he could not “really remember”\\nsaying “no matter what” the day before. JA5989–90. Juror\\n12’s spotty recollection of the previous day’s events\\nfurther supports the District Court’s finding that he was\\nnot credible.\\n 67\\n\\f Fattah argues that the credibility determination was\\nnot, by itself, a sufficient reason to dismiss the juror\\nbecause the record demonstrates more than a reasonable\\npossibility that the complaints about his conduct stemmed\\nfrom Juror 12’s own view of the Government’s case.\\nFattah Reply Br. 11; Fattah Br. 25, 28. Fattah claims that\\nthe District Court abused its discretion by dismissing Juror\\n12 “on the basis of, in effect, six words the juror\\npurportedly said to the court’s deputy after he was verbally\\nattacked by other jurors.” Fattah Br. 24. According to\\nFattah, the questioning of the other jurors “confirmed that\\nthere were no legitimate grounds for removing juror 12.”\\nId. at 26. We conclude otherwise.\\n “A district court’s finding on the question whether\\na juror has impermissibly refused to participate in the\\ndeliberation process is a finding of fact to which\\nappropriate deference is due.” Baker, 262 F.3d at 130.\\nWhile district courts must apply a high standard for juror\\ndismissal, their underlying findings are afforded\\nconsiderable deference on appeal. Kemp, 500 F.3d at 304\\n(citing Abbell, 271 F.3d at 1302–03). We will reverse only\\nif the decision to dismiss a juror was “without factual\\nsupport, or for a legally irrelevant reason.” Abbell, 271\\nF.3d at 1302 (citation omitted).\\n Here, the District Court had a legitimate reason for\\nremoving Juror 12. Refusal to deliberate constitutes good\\ncause for dismissal. Although the judge did not expressly\\narticulate the Kemp standard when he announced that he\\n\\n 68\\n\\fwould dismiss Juror 12, he did acknowledge the “no\\nreasonable possibility” standard in his discussion with\\ncounsel. The unmistakable import of the District Court’s\\nstatement from the bench is that there was no reasonable\\npossibility that Juror 12’s intransigence was based on his\\nview of the evidence. See Oscar, 877 F.3d at 1288 n.16.\\n Fattah contends that there is no record support for\\nthe finding that Juror 12 said “he was going to hang this\\njury no matter what.” Fattah Br. 29. To be sure, the\\ncourtroom deputy’s testimony is not that Juror 12 used the\\nwords “hang this jury” and “no matter what” in the same\\nsentence. She testified that Juror 12 first stated “I am going\\nto hang this jury,” then later stated “it is going to be 11 to\\n1 no matter what.” JA5981–82. This is a distinction\\nwithout a difference. Likewise, Fattah challenges the\\nDistrict Court’s finding that Juror 12 was determined to\\nhang the jury “no matter what the law is” and “no matter\\nwhat the evidence is.” Fattah Br. 29. Although there is no\\nevidence that Juror 12 uttered the phrases “no matter what\\nthe law is” or “no matter what the evidence is,” the District\\nCourt was describing the import of Juror 12’s statements.\\nThis was not error.\\n Fattah expresses the concern that “[i]f jurors are\\nasked the right questions or interrogated long enough, it\\nwould not be difficult for a trial court to elicit testimony\\nfrom [a] majority [of] jurors that can be held up as\\nevidence of a dissenting juror’s bias or refusal to\\ndeliberate.” Fattah Br. 22. He also worries that a group of\\n\\n 69\\n\\fjurors might have an incentive to rid themselves of a juror\\nwho holds a different view. Id. These are valid concerns—\\nbut no basis existed for such concerns in this case. Juror\\n12’s own words provided most of the support for his\\neventual dismissal. Furthermore, his statements were\\nmade early in the deliberations, in a complex case, before\\nany juror could reasonably be expected to have reached\\nfinal verdicts on the twenty-nine counts before the jury.\\n\\n The able District Judge did not err in finding that\\nJuror 12 refused to deliberate and therefore violated his\\noath.\\n\\n IV. The District Court’s Instructions Under\\n McDonnell\\n On appeal, Fattah and Vederman renew their\\nchallenge to the jury instructions given on Counts 3, 16,\\n17, 18, 22, and 23, concerning the meaning of the term\\n“official act” as used in the bribery statute (pursuant to\\nwhich both were convicted) and the honest services fraud\\nstatute (pursuant to which Fattah alone was convicted).\\n\\n In light of the Supreme Court’s opinion in\\nMcDonnell v. United States, 136 S. Ct. 2355 (2016),\\nreleased the week after the jury verdict, the District Court\\nconceded that its instructions were incomplete and\\nerroneous, at least as to Counts 16–18. Nevertheless, the\\nDistrict Court held that the erroneous jury instructions had\\nnot influenced the verdict on the bribery counts, and\\ndeclined to set aside Fattah and Vederman’s convictions.\\n 70\\n\\fAs to Counts 16–18 and 22–23, we disagree, and will\\nreverse the District Court’s judgment. The District Court’s\\njudgment with respect to Count 3, which did not involve\\nVederman, will be affirmed. JA78–79.\\n\\n A. The McDonnell Framework\\n In McDonnell, the Supreme Court interpreted the\\nterm “official act” as defined in 18 U.S.C. § 201(a)(3). 136\\nS. Ct. at 2368. The statute defines an “official act” as “any\\ndecision or action on any question, matter, cause, suit,\\nproceeding or controversy, which may at any time be\\npending, or which may by law be brought before any\\npublic official, in such official’s official capacity, or in\\nsuch official’s place of trust or profit.” 18 U.S.C.\\n§ 201(a)(3). The McDonnell Court distilled this definition\\ninto two requirements:\\n First, the Government must identify a\\n “question, matter, cause, suit, proceeding or\\n controversy” that “may at any time be\\n pending” or “may by law be brought” before\\n a public official. Second, the Government\\n must prove that the public official made a\\n decision or took an action “on” that question,\\n matter, cause, suit, proceeding, or\\n controversy, or agreed to do so.\\n\\n136 S. Ct. at 2368. Applying this two-step test to Governor\\nRobert McDonnell’s convictions, the Supreme Court\\nconcluded that “the jury was not correctly instructed on\\n 71\\n\\fthe meaning of ‘official act,’ ” and as a result, “may have\\nconvicted Governor McDonnell for conduct that is not\\nunlawful.” Id. at 2375. Given that uncertainty, the Court\\n“[could not] conclude that the errors in the jury\\ninstructions were ‘harmless beyond a reasonable doubt.’ ”\\nId. (quoting Neder v. United States, 527 U.S. 1, 16 (1999)).\\nThe Supreme Court, therefore, vacated Governor\\nMcDonnell’s convictions. Id.\\n\\n McDonnell lays out a clear path for the Government\\nto follow in proving that an accused has performed an\\n“official act.” First, the Government must “identify a\\n‘question, matter, cause, suit, proceeding or controversy’\\nthat ‘may at any time be pending’ or ‘may by law be\\nbrought’ before a public official.” 136 S. Ct. at 2368\\n(quoting 18 U.S.C. § 201(a)(3)). This first step is divided\\ninto two sub-components. In Step 1(A), the Government\\nmust “identify a ‘question, matter, cause, suit, proceeding\\nor controversy.’ ” Id. Step 1(B) then clarifies that the\\nidentified “question, matter, cause, suit, proceeding or\\ncontroversy” be one that “ ‘may at any time be pending’ or\\n‘may by law be brought’ before a public official.” Id.\\n\\n Under Step 1(A), a “question, matter, cause, suit,\\nproceeding or controversy” must be “a formal exercise of\\ngovernmental power that is similar in nature to a lawsuit\\nbefore a court, a determination before an agency, or a\\nhearing before a committee.” Id. at 2372. Importantly, “a\\ntypical meeting, telephone call, or event arranged by a\\n\\n\\n 72\\n\\fpublic official” does not qualify as such a formal exercise\\nof governmental power. Id. at 2368.\\n Step 1(B) then requires us to ask whether the\\nqualifying “question, matter, cause, suit, proceeding or\\ncontroversy” was one that “ ‘may at any time be pending’\\nor ‘may by law be brought’ before a public official.” Id.\\nAs the McDonnell Court clarified, “ ‘[p]ending’ and ‘may\\nby law be brought’ suggest something that is relatively\\ncircumscribed—the kind of thing that can be put on an\\nagenda, tracked for progress, and then checked off as\\ncomplete.” Id. at 2369; accord United States v. Repak, 852\\nF.3d 230, 252 (3d Cir. 2017) (quoting McDonnell, 136 S.\\nCt. at 2369). By contrast, matters described at a high level\\nof generality—for example, “[e]conomic development,”\\n“justice,” and “national security”—are not sufficiently\\n“focused and concrete.” McDonnell, 136 S. Ct. at 2369.\\n\\n In McDonnell, the Court concluded that at least\\nthree questions or matters identified by the Fourth Circuit\\nwere sufficiently focused:\\n (1) whether researchers at any of Virginia’s\\n state universities would initiate a study of [a\\n drug]; (2) whether the state-created Tobacco\\n Indemnification and Community\\n Revitalization Commission would allocate\\n grant money for the study of [a chemical\\n compound]; and (3) whether the health\\n insurance plan for state employees in\\n\\n 73\\n\\f Virginia would include [a specific drug] as a\\n covered drug.\\nId. at 2370 (internal quotations omitted) (quoting United\\nStates v. McDonnell, 792 F.3d 478, 515–16 (4th Cir.\\n2015)). We provided guidance in the form of a fourth\\nexample in Repak, when we held that a redevelopment\\nauthority’s awarding of contracts was “a concrete\\ndetermination made by the [redevelopment authority’s]\\nBoard of Directors.” 852 F.3d at 253.\\n\\n Step 2 requires the Government to prove that the\\npublic official made a “decision” or took “an action” on\\nthe identified “question, matter, cause, suit, proceeding or\\ncontroversy.” McDonnell, 136 S. Ct. at 2368. The\\nMcDonnell Court explained:\\n Setting up a meeting, hosting an event, or\\n calling an official (or agreeing to do so)\\n merely to talk about a research study or to\\n gather additional information . . . does not\\n qualify as a decision or action on the pending\\n question of whether to initiate the study.\\n Simply expressing support for the research\\n study at a meeting, event, or call—or sending\\n a subordinate to such a meeting, event, or\\n call—similarly does not qualify as a decision\\n or action on the study, as long as the public\\n official does not intend to exert pressure on\\n another official or provide advice, knowing\\n\\n 74\\n\\f or intending such advice to form the basis for\\n an “official act.”\\nId. at 2371. The Court further clarified:\\n\\n If an official sets up a meeting, hosts an\\n event, or makes a phone call on a question or\\n matter that is or could be pending before\\n another official, that could serve as evidence\\n of an agreement to take an official act. A jury\\n could conclude, for example, that the official\\n was attempting to pressure or advise another\\n official on a pending matter. And if the\\n official agreed to exert that pressure or give\\n that advice in exchange for a thing of value,\\n that would be illegal.\\nId.\\n Here, Fattah was charged with engaging in three\\ncategories of official acts, which we analyze in accordance\\nwith the McDonnell framework. In Counts 16–18 and 22–\\n23, Fattah is alleged to have set up a meeting between\\nVederman and the U.S. Trade Representative, attempted\\nto secure Vederman an ambassadorship, and hired\\nVederman’s girlfriend, all in return for a course of conduct\\nwherein Vederman provided things of value to Fattah.\\n\\n In this case, as in McDonnell, the jury instructions\\nwere erroneous. We conclude that the first category of the\\ncharged acts—setting up a meeting between Vederman\\n 75\\n\\fand the U.S. Trade Representative—is not unlawful, and\\nthat the second category—attempting to secure Vederman\\nan ambassadorship—requires reconsideration by a\\nproperly instructed jury. The third charged act—hiring\\nVederman’s girlfriend—is clearly an official act. But\\nbecause we cannot isolate the jury’s consideration of the\\nhiring from the first two categories of charged acts, we\\nmust reverse and remand the judgment of the District\\nCourt.\\n\\n B. The Kirk Meeting\\n We turn first to Fattah’s scheduling of a meeting\\nbetween Vederman and the U.S. Trade Representative,\\nRon Kirk. Under McDonnell, “setting up a meeting . . .\\ndoes not, standing alone, qualify as an ‘official act.’ ” 136\\nS. Ct. at 2368. Fattah’s setting up the meeting between\\nVederman and Kirk was therefore not an official act, a\\nconcession implicit in the Government’s opening brief.\\nSee Gov’t Br. 32 (failing to mention the Kirk meeting as\\none of the “two categories” of allegedly “official acts”).\\nBut the jury was not properly instructed on this point.\\nWithout the benefit of the principles laid down in\\nMcDonnell, the jury was free to conclude that arranging\\nthe Kirk meeting was an official act—and it may have\\ndone so. The District Court’s erroneous jury instructions,\\ntherefore, cannot survive harmless error review.\\n\\n In a footnote in its brief to this Court, the\\nGovernment argues that evidence about the Kirk meeting\\nwas offered only “because it established the strength of\\n 76\\n\\fVederman’s desire to be an ambassador” and not because\\nthe Government was attempting to establish the meeting\\nas an independent official act. Id. at79–80 n.6. But the\\nrecord undercuts the Government’s post hoc justification.\\n\\n The indictment, provided to the jury in redacted\\nform for use in its deliberations, lists Fattah’s setting up\\nthe Kirk meeting as an official act under the heading\\n“FATTAH’s Official Acts for VEDERMAN.” JA494.\\nUnder this heading are three distinct subheadings:\\n(1) “The Pursuit of an Ambassadorship,” (2) “The Pursuit\\nof Another Executive Branch Position,” and (3) “Hiring\\nthe Lobbyist’s Girlfriend to the Congressional Staff.”\\nJA494–95. The second subheading, “The Pursuit of\\nAnother Executive Branch Position,” describes the\\narrangement of the Kirk meeting. Quite clearly, then, this\\nthree-part structure demonstrates that setting up the Kirk\\nmeeting was one of three distinct categories of official acts\\nalleged by the Government.\\n\\n Although there is some support for the\\nGovernment’s argument that evidence of the Kirk meeting\\nwas presented at trial only to establish the extent of\\nVederman’s interest in becoming an ambassador, JA827,\\n852–53 (mentioning the Kirk meeting in close proximity\\nto references to Fattah’s attempts to secure Vederman an\\nambassadorship), it is undermined by language in the\\nredacted indictment itself, and by the way in which the\\nGovernment presented its case at trial as a “pattern” of\\nconnected acts.\\n\\n 77\\n\\f The redacted indictment, for example, refers to the\\nKirk meeting as “The Pursuit of Another Executive\\nBranch Position.” JA495 (emphasis added). The use of the\\nword “Another” strongly suggests that evidence about the\\nKirk meeting was not merely evidence of Fattah’s attempt\\nto secure Vederman an ambassadorship, but was also\\nevidence of a separate and distinct attempt to secure\\nVederman a position on a federal trade-related\\ncommission. The redacted indictment also notes that “[i]n\\nor around May 2011, with little progress made on securing\\nan ambassadorship for VEDERMAN, FATTAH turned\\ntowards obtaining for VEDERMAN an appointment in the\\nExecutive Branch to a federal trade commission.” Id.\\n(emphasis added). The words “turned towards,” taken\\nliterally, clearly convey that arranging the Kirk meeting\\nwas presented as distinct from Fattah’s efforts to secure\\nVederman an ambassadorship.\\n\\n The District Court denied Fattah and Vederman a\\nnew trial on Counts 17 and 18, referring to evidence of the\\nKirk meeting as “de minimis” and noting that “Kirk’s\\ntestimony during this lengthy trial lasted a mere sixteen\\nminutes.” JA97 n.14. In the District Court’s view,\\nevidence of the Kirk meeting “played no role in the\\noutcome” of the case. Id. Considering the record in light\\nof McDonnell, we are not so sure.\\n\\n Although it is possible that evidence of the Kirk\\nmeeting played a minor role at trial when compared to the\\nother acts on which the Government presented evidence,\\n\\n 78\\n\\fthe redacted indictment suggests that the Kirk meeting was\\na significant part of the Government’s case. The\\nindictment dedicates five paragraphs to describing the\\nKirk meeting, but just three paragraphs to describing the\\nhiring of Vederman’s girlfriend—a hiring that, as we\\nexplain below, is clearly an official act. JA495–96. While\\nneither the number of minutes used at trial nor the number\\nof paragraphs contained in an indictment is a dispositive\\nunit of measurement for determining the significance of\\nevidence, we conclude that the District Court’s erroneous\\njury instructions pertaining to the Kirk meeting were not\\nharmless.\\n We conclude, in accordance with McDonnell, that\\nFattah’s arranging a meeting between Vederman and the\\nU.S. Trade Representative was not itself an official act.\\nBecause the jury may have convicted Fattah for conduct\\nthat is not unlawful, we cannot conclude that the error in\\nthe jury instruction was harmless beyond a reasonable\\ndoubt, and we must vacate and remand the convictions of\\nFattah and Vederman as to Counts 16, 17, 18, 22 and 23.\\n\\n C. Fattah’s Efforts to Secure Vederman an\\n Ambassadorship\\n The nature of Fattah’s efforts to secure Vederman\\nan ambassadorship is less clear, and presents a closer\\nquestion than the Kirk meeting. We ultimately conclude\\nthat the question warrants remand so that it may be\\nanswered by a properly instructed jury. On remand, the\\njury must decide whether Fattah’s conduct constituted a\\n 79\\n\\f“decision” or “action” under Step 2 of the McDonnell\\nanalysis.\\n At the outset, it is clear to us that, under Steps 1(A)\\nand 1(B), a formal appointment of Vederman as an\\nambassador would qualify as a “matter” that “may at any\\ntime be pending” before a public official. The formal\\nappointment of a particular person (Vederman), to a\\nspecific position (an ambassadorship), constitutes a matter\\nthat is sufficiently focused and concrete. The formal\\nappointment of an ambassador is a matter that is “pending”\\nbefore the President—the constitutional actor charged\\nwith nominating ambassadors—as well Senators, who are\\ncharged with confirming the President’s ambassadorial\\nnominations. U.S. Const. art. II § 2 (“[H]e shall nominate,\\nand by and with the Advice and Consent of the Senate,\\nshall appoint Ambassadors . . . .”). It is beyond cavil that\\nthe formal appointment of an ambassador satisfies both\\nsub-components of McDonnell’s Step 1.\\n Turning to Step 2, we consider whether Fattah’s\\nefforts to secure Vederman an ambassadorship qualify as\\nmaking a “decision” or taking “an action” on the identified\\n“matter” of appointment. McDonnell, 136 S. Ct. at 2368.\\nAlthough those efforts—three emails, two letters, and one\\nphone call—do not themselves qualify as a “question,\\nmatter, cause, suit, proceeding, or controversy” under\\nMcDonnell’s Step 1, they may nonetheless qualify as the\\nmaking of a “decision” or taking “an action” on the\\nidentified matter of appointment. Id.\\n\\n 80\\n\\f McDonnell’s Step 2 requires us to determine\\nwhether Fattah’s efforts qualify as permissible attempts to\\n“express[] support,” or impermissible attempts “to\\npressure or advise another official on a pending matter.”\\nId. at 2371. At trial, the jury was not instructed that they\\nhad to place Fattah’s efforts on one side or the other of this\\ndivide. The jury might even have thought they were\\npermitted to find Fattah’s efforts—three emails, two\\nletters, and one phone call—to themselves be official acts,\\nrather than a “decision” or “action” on the properly\\nidentified matter of appointment. Such a determination\\nwould have been contrary to the dictates of McDonnell.\\n Faced with such uncertainty, we cannot assume the\\njury verdict was proper. Although the jury might not have\\nconcluded that Fattah’s efforts were themselves official\\nacts, and although the jury might not have concluded that\\nthose efforts crossed the line into impermissible attempts\\n“to pressure or advise,” we are unable to conclude that the\\njury necessarily did so. Nor can we, on the cold record\\nbefore us, determine whether Fattah’s efforts to secure\\nVederman an ambassadorship crossed the line.\\nDetermining, for example, just how forceful a strongly\\nworded letter of recommendation must be before it\\nbecomes impermissible “pressure or advice” is a fact-\\nintensive inquiry that falls within the domain of a properly\\ninstructed jury. Should the Government elect to retry these\\ncounts after remand, the finder of fact will need to decide\\nwhether Fattah’s efforts constituted permissible attempts\\nto “express[] support,” or impermissible attempts “to\\n 81\\n\\fpressure or advise another official on a pending matter.”\\nId.\\n\\n D. The Zionts Hiring\\n The third group of acts charged in the Fattah–\\nVederman scheme involves Fattah’s decision to hire\\nVederman’s girlfriend, Alexandra Zionts, as a\\ncongressional staffer. We conclude that the hiring was an\\nofficial act. A brief analysis of McDonnell’s two steps\\nsuffices to show why this is so.\\n Here, under McDonnell’s Step 1(A), the relevant\\n“matter” is the decision to hire Zionts. Step 1(B) of the\\nanalysis is satisfied because the hiring decision was\\n“pending” before Fattah himself. And that hiring was\\n“focused and concrete,” “within the specific duties of an\\nofficial’s position—the function conferred by the\\nauthority of his office.” Id. at 2369. Finally, McDonnell’s\\nStep 2 requires that the “Government . . . prove that the\\npublic official made a decision or took an action ‘on’ [the\\nidentified] question, matter, cause, suit, proceeding, or\\ncontroversy, or agreed to do so.” Id. at 2368. Fattah’s\\ndecision to hire Zionts clearly satisfies that requirement.\\nWe therefore conclude that the hiring of Zionts was an\\nofficial act under McDonnell.\\n\\n Vederman concedes that the Zionts hiring was an\\nofficial act. Oral Argument Transcript at 5–6. Fattah, for\\nhis part, maintains that “hiring someone for a routine, part-\\ntime, short-term position falls well outside [the] definition\\n 82\\n\\f[of ‘official act’] and is nothing like a lawsuit, agency\\ndetermination, or committee hearing, even if each shares\\nthe happenstance that federal funds will be used.” Fattah\\nReply Br. 25.\\n\\n Fattah’s argument lacks traction. Official acts need\\nnot be momentous decisions—or even notable ones.\\nJudges, for example, make “routine” evidentiary rulings\\nevery day, and yet it is beyond question that those rulings\\nare official acts. In the realm of official acts, it is of no\\nmoment that Zionts provided only “part-time, short term”\\nlabor. When a public official hires an employee to work in\\nhis government office, he has engaged in an official act.\\n * * *\\n If we could conclude that the Zionts hiring was the\\nonly category of actions that the jury relied on when it\\nfound that Fattah performed an official act under Counts\\n16–18 and 22–23, remand would not be necessary. But, as\\nwe have explained, we cannot rule out that the jury\\nerroneously convicted Fattah and Vederman based on\\nother actions that were not official acts under\\nMcDonnell.13\\n\\n\\n13\\n More specifically, the incomplete, and therefore\\nerroneous, instructions could have led the jury to commit\\nat least one of three mistakes. First, the jury could have\\nimproperly convicted Vederman and Fattah based on the\\nKirk meeting alone, or misunderstood the Kirk meeting to\\n 83\\n\\f The Government argues that because the Zionts\\nhiring was an official act, the effect of the erroneous jury\\ninstructions could be no more than harmless. The jury’s\\nverdict, the Government contends, permits us to deduce\\nthat the jury necessarily concluded the Zionts hiring was\\nan official act, and that this conclusion alone supported\\nFattah’s and Vederman’s convictions as to Counts 16–18\\nand 22–23—regardless of whether the jury erroneously\\nfound any unofficial acts to be official acts. We disagree.\\n Fattah and Vederman objected to the definition of\\n“official act” at trial. We thus apply the harmless error\\nstandard of review. McDonnell, 136 S. Ct. at 2375. The\\nGovernment argues that because the jury convicted Fattah\\nand Vederman of illegally laundering the proceeds of a\\n“scheme to commit bribery” under Count 23, the jury\\nfound that the scheme must have encompassed only the\\nZionts hiring. JA531.That would mean that the jury did not\\nconclude that the “scheme to commit bribery” included\\n\\nbe a necessary component of an impermissible “pattern”\\nof official acts. Second, the jury might have concluded that\\nFattah’s efforts to secure Vederman an ambassadorship\\nwere themselves official acts. Third, the jury might have\\nconcluded that Fattah’s efforts to secure Vederman an\\nambassadorship were merely attempts to “express[]\\nsupport,” rather than to “exert pressure . . . or provide\\nadvice,” but nonetheless erroneously concluded that those\\nexpressions of support were official acts. McDonnell, 136\\nS. Ct. at 2371.\\n 84\\n\\fany acts that McDonnell now makes clear were unofficial.\\nYet the redacted indictment, jury instructions, and the fact\\nthat the Government presented its case under a “pattern”\\ntheory at trial compel us to reject the Government’s\\nargument.\\n\\n The very first sentence under Count 23 of the\\nredacted indictment incorporates all three categories of\\n“Overt Acts” contained within paragraphs “58 through 95\\nof Count One.” 14 All three of these categories fall under a\\ngeneral heading within the redacted indictment titled “The\\nBribery and Fraud Scheme [redacted].” JA494. The jury\\nhad before it instructions for Count 23 which referred to\\n“the alleged bribery scheme involving an $18,000\\npayment,” JA448 (emphasis added), and the redacted\\nindictment which referred to “a scheme to commit\\nbribery,” JA531 (emphasis added). The parallel language\\ncould well lead a rational jury to conclude that the relevant\\n“scheme” included all three categories of acts listed under\\nthe general heading: “The Bribery and Fraud Scheme\\n[redacted].” JA494 (emphasis added).\\n\\n\\n\\n14\\n JA531. Paragraphs 58 through 95 of Count 1 refer to the\\nthree categories of allegedly official acts discussed above:\\n(1) “The Pursuit of an Ambassadorship,” (2) “The Pursuit\\nof Another Executive Branch Position,” and (3) the\\n“Hiring of the Lobbyist’s Girlfriend to the Congressional\\nStaff.” JA494–95.\\n 85\\n\\f Like the redacted indictment and jury instructions,\\nthe Government’s trial arguments referred to patterns and\\na course of conduct, and stressed that the jury need not\\nconnect specific payments to particular official acts. In its\\nclosing argument to the jury, the Government stated that\\nthe alleged “scheme took place over a period of several\\nyears. Over and over again you’re going to see the same\\npattern.” JA5383 (emphasis added). Then, in its rebuttal\\nargument, the Government went out of its way to\\nexplicitly distinguish its “pattern” theory from an\\nalternative theory that would have directly connected\\nindividual payments to individual acts. As the prosecutor\\nargued to the jury:\\n Ms. Recker appears to argue that each thing\\n of value must coincide with some specific\\n official act, but that is not the law and that is\\n not what Judge Bartle is going to instruct you.\\n Instead what he will tell you is that the\\n government is not required to prove that\\n Vederman intended to influence Fattah to\\n perform a set number of official acts in return\\n for things of value so long as the evidence\\n shows a course of conduct of giving things of\\n value, things of value to Fattah in exchange\\n for a pattern of official acts favorable to\\n Vederman. In other words a stream of\\n benefits. These for those, not this for that.\\n\\n\\n\\n 86\\n\\fJA5715–16 (emphases added). In closing to the jury, the\\nGovernment made several other references to this\\n“pattern” theory, 15 and the District Court referred to this\\n“pattern” theory in its instructions to the jury. As Judge\\nBartle instructed:\\n\\n [I]t is not necessary for the government to\\n prove that a defendant intended to induce a\\n public official to perform a number of official\\n acts in return for things of value.\\n So as long as the evidence shows a\\n course of conduct of giving things of value to\\n a public official in exchange for a pattern of\\n official acts favorable to the giver.\\n\\nJA5833–34 (emphasis added). On appeal, the Government\\nchanges course, asking us to assume that the jury ignored\\nthese repeated references to a “pattern of official acts” and\\n\\n15\\n See, e.g., JA5389 (“And the exchange of an official act\\nfor a thing of value is called a bribe. There’s the pattern.\\nFattah needs money, Vederman gets an official act.”); JA\\n5393 (“That’s why you see the pattern over and over again.\\nFattah needs money, Vederman gets an official act.”);\\nJA5400 (“The same pattern we saw over and over again.\\nFattah needs money, Vederman gets an official act.”);\\nJA5409 (“[Y]ou know that these were bribes because of\\nthe pattern you saw over and over and over again. Fattah\\nneeds money, Vederman gets an official act, that makes\\nthese things a bribe.”).\\n 87\\n\\finstead considered the Zionts hiring and Vederman’s\\n$18,000 payment to Fattah as an isolated quid pro quo.\\nThis is an invitation to speculate, and we decline to do so.16\\nThe jury began its deliberations accompanied by a copy of\\nthe redacted indictment which alleged a pattern of official\\nacts, consisting of any combination of three categories of\\nacts: pursuing an ambassadorship, arranging the Kirk\\nmeeting, and hiring Zionts. In light of the erroneous\\ninstructions, and because only one category clearly\\n\\n16\\n Providing some support to the Government’s ultimately\\nunconvincing argument that the jury considered the Zionts\\nhiring and $18,000 payment in isolation, we note that the\\nredacted indictment does mention those two events side-\\nby-side in paragraph 78 of the indictment’s Part V. JA497\\n(“On January 13, 2012, VEDERMAN wired $18,000 to\\nFATTAH, and six days later, on January 19, 2012,\\nBOWSER emailed VEDERMAN’s girlfriend, A.Z.,\\nwelcoming her as a new employee to FATTAH’s\\nCongressional Staff.”). But although paragraph 78\\nmentions the $18,000 wire transfer and the Zionts hiring\\nin the same breath, paragraph 78 does not instruct the jury\\nto connect these two events apart from the rest of the\\nevidence presented at trial. In light of the other instructions\\nand arguments indicating that the jury should not consider\\nthe Zionts hiring in isolation, but instead should consider\\nthe hiring as one part of a three-part scheme, paragraph 78\\nis not sufficient to avoid a reversal and remand on the\\nconvictions of Fattah and Vederman as to Counts 16–18\\nand 22–23.\\n 88\\n\\fqualifies as an “official act,” the jury’s deliberations were\\nfraught with the potential for McDonnell error. We will\\nvacate the convictions of Fattah and Vederman as to\\nCounts 16, 17, 18, 22, and 23, and remand to the District\\nCourt.\\n\\nE. Vederman’s Sufficiency Challenge to Counts 16–18\\n and 22–23\\n Vederman argues that there is insufficient evidence\\nto support a conviction, even if a jury were properly\\ninstructed under McDonnell. Specifically, Vederman\\nargues that there is insufficient evidence to convict him\\nand Fattah, after remand, on Counts 16–18 and 22–23\\nbecause “[a]t least seven of the eight alleged ‘official acts’\\nwere, as a matter of law, not official at all.” Vederman Br.\\n35. As to the single act that Vederman implicitly concedes\\nto be an official act—the Zionts hiring—Vederman argues\\nthat “[t]he only thing that even arguably associates” the\\nZionts hiring with Vederman was its timing in relation to\\nVederman’s sham purchase of the Fattahs’ Porsche. Id.\\nAccording to Vederman, “the undisputed chronology\\nprecludes any inference that Vederman conferred this\\nbenefit on his friend as an illegal bribe.” Id. (emphasis\\nomitted). Vederman is wrong. Sufficient evidence was\\nproduced at trial to have allowed a properly-instructed jury\\nto convict Fattah and Vederman of Counts 16–18 and 22–\\n23.\\n To begin with, even if the Zionts hiring had been the\\nsole official act to survive this Court’s interpretation of\\n 89\\n\\fMcDonnell, there would still be sufficient evidence to\\nconvict Fattah and Vederman. Zionts did not receive\\nwritten notice of her official hiring until six days after the\\nsham Porsche purchase. Moreover, the jury would not be\\nrestricted to considering the chronology of the sham\\npurchase alone. It would be free to consider Vederman’s\\nentire course of conduct. Under the general heading\\n“VEDERMAN’S Payments and Things of Value to\\nFATTAH,” the redacted indictment not only refers to the\\n$18,000 wire transaction from Vederman to Fattah as part\\nof the sham Porsche purchase, but also to Vederman’s\\n$3,000 payment for the college tuition of Simone Muller,\\nFattah’s live-in au pair, as well as thousands of dollars in\\npayments made by Vederman for Chip Fattah’s college\\ntuition. JA496–97.\\n And the Zionts hiring is not the only act to survive\\nour application of McDonnell. As we explained, a jury\\ncould find that Fattah’s efforts to secure Vederman an\\nambassadorship—three emails, two letters, and a phone\\ncall—were an impermissible attempt to “pressure or\\nadvise” President Obama, Senator Casey, or both men.17\\n\\n17\\n Although Fattah’s efforts to secure Vederman an\\nambassadorship present a jury question that is not for us to\\nanswer on appeal, we note that not one of these efforts\\nalone could qualify as an official act itself. See McDonnell,\\n136 S. Ct. at 2372 (“Setting up a meeting, talking to\\nanother official, or organizing an event (or agreeing to do\\nso)—without more—does not fit that definition of ‘official\\n 90\\n\\fThis means that a properly instructed jury on remand,\\npresented with evidence of Fattah’s efforts to secure an\\nambassadorship for Vederman and evidence of the Zionts\\nhiring, could find more than a single official act.\\n\\n F. Blue Guardians\\n In addition to the charges arising from his dealings\\nwith Vederman, Fattah was charged in Count 3 with\\n\\n\\nact.’ ”). The relevant question for a jury to consider on\\nremand, then, is whether these actions constituted “a\\n‘decision or action’ on a different question or matter”—to\\nwit, the formal appointment of an ambassador. Id. at 2369\\n(emphasis omitted).\\n Even though the emails, letters, and phone call are\\nnot, individually, official acts, it will be for a jury to decide\\nif Fattah’s efforts to secure an ambassadorship for\\nVederman crossed the line from permissible “support” to\\nimpermissible “pressure or advice.” While we express\\ndoubt that some of Fattah’s efforts concerning the\\nambassadorship are, when considered in isolation, enough\\nto cross that line, a properly instructed jury considering all\\nof the facts in context might nonetheless conclude that\\nother efforts—such as a hand-delivered letter to the\\nPresident of the United States—indeed crossed that line.\\nFurther, a jury might find that in the aggregate, three\\nemails, two letters, and a phone call crossed the line and\\ntherefore constituted a “decision or action” on the\\nidentified matter of appointment.\\n 91\\n\\fparticipating in a scheme with Lindenfeld to funnel money\\nto a fraudulent nonprofit organization. In connection with\\nthis scheme, Fattah was convicted of conspiring to commit\\nhonest services fraud.\\n\\n Fattah owed Lindenfeld nearly $100,000 for work\\nperformed on Fattah’s 2007 mayoral campaign. In lieu of\\nrepayment, Fattah suggested that Lindenfeld create an\\nentity, later named Blue Guardians, to which Fattah would\\ndirect $15,000,000 in public funds by using his position as\\na member of the House Committee on Appropriations.\\nNothing in McDonnell requires us to upset Fattah’s\\nconviction on Count 3.\\n Step 1(A) of our McDonnell analysis requires the\\nGovernment to “identify a ‘question, matter, cause, suit,\\nproceeding or controversy.’ ” 136 S. Ct. at 2368. Here, the\\n“matter” is the appropriation of millions of dollars in\\npublic funds. See Repak, 852 F.3d at 253–54 (holding the\\nawarding of redevelopment funds to be an official act). In\\nparticular, it was Fattah’s promise to perform this official\\nact that was unlawful. As McDonnell makes clear:\\n\\n [A] public official is not required to actually\\n make a decision or take an action on a\\n “question, matter, cause, suit, proceeding or\\n controversy”; it is enough that the official\\n agree to do so. The agreement need not be\\n explicit, and the public official need not\\n specify the means that he will use to perform\\n his end of the bargain.\\n 92\\n\\f136 S. Ct. at 2370–71 (internal citations omitted). That\\nFattah took steps to actually carry out his promise (e.g., by\\ndrafting and sending a formal appropriations request on\\nofficial congressional letterhead) is evidence of his illegal\\npromise. See id. at 2371.\\n\\n Step 1(B) requires the Government to establish that\\nthe “ ‘question, matter, cause, suit, proceeding or\\ncontroversy’ . . . ‘may at any time be pending’ or ‘may by\\nlaw be brought’ before a public official.” McDonnell, 136\\nS. Ct. at 2368. Appropriating public funds was not only a\\nmatter that was pending before Fattah as a member of the\\nAppropriations Committee, it was also a matter that was\\npending before the Chairman and Ranking Member of an\\nAppropriations Subcommittee to whom Fattah ultimately\\nsent a formal written request. See id. at 2369 (“[T]he\\nmatter may be pending either before the public official\\nwho is performing the official act, or before another public\\nofficial.”). Appropriating millions of dollars in response to\\nthe Blue Guardians request is “focused and concrete,” and\\n“the kind of thing that can be put on an agenda, tracked for\\nprogress, and then checked off as complete.” Id.\\n\\n Given Fattah’s membership on the Appropriations\\nCommittee, this was “something within the specific duties\\nof an official’s position—the function conferred by the\\nauthority of his office.” Id. Even if we were to assume,\\nagainst all reason, that an appropriation is not “something\\nwithin the specific duties” of either Fattah or the Chairman\\nor Ranking Member of an Appropriations Subcommittee,\\n\\n 93\\n\\fFattah’s formal request for an appropriation was\\nsomething that Fattah had the authority to do. Like the\\nExecutive Director in Repak, who lacked authority himself\\nto award redevelopment funds but could request such\\nfunds from the Board, Fattah used his position as a\\nCongressman to formally request appropriations for the\\nBlue Guardians. 852 F.3d at 254 (“Repak had the power\\nto, and indeed did, make recommendations to the\\n[redevelopment authority.\\n Step 2 of McDonnell requires the Government to\\n“prove that the public official made a decision or took an\\naction ‘on’ that question, matter, cause, suit, proceeding,\\nor controversy, or agreed to do so.” 136 S. Ct. at 2368\\n(emphasis added). Here, Fattah agreed to request an\\nappropriation for a bogus purpose. Unlike Fattah’s letters,\\nemails, and phone call seeking an ambassadorship for\\nVederman, there is no potential for the jury to have made\\na mistake when it found Fattah’s Blue Guardians promise\\nunlawful.\\n Fattah argues that the Government presented “[n]o\\nevidence . . . that would have allowed [the jury] to\\nconclude that [he] made a decision or took an action, or\\ncould have done so, on the question whether Blue\\nGuardians would receive a $15 million federal grant.”\\nFattah Br. 46. This argument misses the point. It was\\nFattah’s agreement to engage in the official act of formally\\nrequesting the appropriation that was illegal. See\\nMcDonnell, 136 S. Ct. at 2371.\\n\\n 94\\n\\f Lindenfeld’s trial testimony provided sufficient\\nevidence of Fattah’s illegal agreement. JA1694–96, 1954.\\nFattah’s letter provided additional evidence from which\\nthe jury could have concluded that Fattah illegally agreed\\nto perform an official act. 18 In short, the agreement itself\\nwas illegal, and the Government provided sufficient\\nevidence for the jury to conclude that the illegal agreement\\ntook place.\\n\\n The Government’s evidence in support of the Blue\\nGuardians scheme meets the requirements of McDonnell,\\nand the Count 3 verdict will stand.\\n\\n V. Sufficiency of the Evidence for the RICO\\n Conspiracy Conviction\\n The jury found Fattah, Vederman, Brand, and\\nNicholas guilty of the RICO conspiracy charged in Count\\n1 of the indictment, but acquitted Bowser. Vederman filed\\na post-verdict motion, and the District Court overturned\\nhis RICO conspiracy conviction.\\n\\n\\n\\n18\\n Despite Fattah’s protestation to the contrary, there is\\nevidence that Fattah took steps to carry out his official act.\\nJA6432–33 (Letter from Congressman Fattah to House\\nAppropriations Subcommittee members “request[ing]\\nfunding and support for the following projects and\\nprograms of critical importance,” including $3,000,000\\nfor “Blue Guardians”).\\n 95\\n\\f On appeal, Fattah, Brand, and Nicholas challenge\\nthe sufficiency of the evidence supporting their RICO\\nconspiracy convictions. We “review[] the sufficiency of\\nthe evidence in the light most favorable to the government\\nand must credit all available inferences in favor of the\\ngovernment.” United States v. Riddick, 156 F.3d 505, 509\\n(3d Cir. 1998). If a rational juror could have found the\\nelements of the crime beyond a reasonable doubt, we must\\nsustain the verdict. United States v. Cartwright, 359 F.3d\\n281, 286 (3d Cir. 2004), abrogated on other grounds by\\nUnited States v. Caraballo-Rodriguez, 726 F.3d 418 (3d\\nCir. 2013) (en banc).\\n The indictment charged a RICO conspiracy in\\nviolation of 18 U.S.C. § 1962(d), which makes it\\n“unlawful for any person to conspire to violate” § 1962(c).\\nSection 1962(c) provides:\\n It shall be unlawful for any person . . .\\n associated with any enterprise engaged in, or\\n the activities of which affect, interstate . . .\\n commerce, to conduct or participate, directly\\n or indirectly, in the conduct of such\\n enterprise’s affairs through a pattern of\\n racketeering activity . . . .\\n\\n18 U.S.C. § 1962(c).\\n\\n In Salinas v. United States, 522 U.S. 52 (1997), the\\ndefendant was convicted of a § 1962(d) RICO conspiracy,\\nbut a jury acquitted him of the substantive RICO offense\\n 96\\n\\funder § 1962(c). Id. at 55. The Supreme Court rejected\\nSalinas’s contention that his conviction had to be set aside\\nbecause he had neither committed nor agreed to commit\\nthe two predicate acts required for the § 1962(c) offense.\\nId. at 66. The Court declared that liability for a RICO\\nconspiracy under § 1962(d), “unlike the general\\nconspiracy provision applicable to federal crimes,” does\\nnot require proof of an overt act. Id. at 63. A conspiracy\\nmay be found, the Court explained, “even if a conspirator\\ndoes not agree to commit or facilitate each and every part\\nof the substantive offense. The partners in the criminal\\nplan must agree to pursue the same criminal objective and\\nmay divide up the work, yet each is responsible for the acts\\nof each other.” Id. at 63–64 (citations omitted). This means\\nthat, if a plan “calls for some conspirators to perpetrate the\\ncrime and others to provide support, the supporters are as\\nguilty as the perpetrators.” Id. at 64. Thus, opting into and\\nparticipating in a conspiracy may result in criminal\\nliability for the acts of one’s co-conspirators. Smith v.\\nBerg, 247 F.3d 532, 537 (3d Cir. 2001).\\n Accordingly, liability for a RICO conspiracy may\\nbe found where the conspirator intended to “further an\\nendeavor which, if completed, would satisfy all of the\\nelements of a substantive criminal offense, but it suffices\\nthat he adopt the goal of furthering or facilitating the\\ncriminal endeavor.” Salinas, 522 U.S. at 65. Because the\\nsubstantive criminal offense here was conducting a\\n§ 1962(c) enterprise, the government had to prove:\\n\\n 97\\n\\f (1) that two or more persons agreed to\\n conduct or to participate, directly or\\n indirectly, in the conduct of an enterprise’s\\n affairs through a pattern of racketeering\\n activity; (2) that the defendant was a party to\\n or member of that agreement; and (3) that the\\n defendant joined the agreement or conspiracy\\n knowing of its objective to conduct or\\n participate, directly or indirectly, in the\\n conduct of an enterprise’s affairs through a\\n pattern of racketeering activity.\\n\\nUnited States v. John-Baptiste, 747 F.3d 186, 207 (3d Cir.\\n2014).\\n In United States v. Turkette, 452 U.S. 576 (1981),\\nthe Supreme Court instructed that an enterprise is a “group\\nof persons associated together for a common purpose of\\nengaging in a course of conduct.” Id. at 583. The\\ngovernment can prove an enterprise “by evidence of an\\nongoing organization, formal or informal, and by evidence\\nthat the various associates function as a continuing unit.”\\nId. In Boyle v. United States, 556 U.S. 938 (2009), the\\nSupreme Court established that an “association-in-fact\\nenterprise must have at least three structural features: a\\npurpose, relationships among those associated with the\\nenterprise, and longevity sufficient to permit these\\nassociates to pursue the enterprise’s purpose.” Id. at 946.\\nThe structure necessary for a § 1962(c) enterprise is not\\ncomplex. Boyle explained that an enterprise\\n\\n 98\\n\\f need not have a hierarchical structure or a\\n “chain of command”; decisions may be made\\n on an ad hoc basis and by any number of\\n methods—by majority vote, consensus, a\\n show of strength, etc. Members of the group\\n need not have fixed roles; different members\\n may perform different roles at different\\n times. The group need not have a name,\\n regular meetings, dues, [or] established rules\\n and regulations . . . .While the group must\\n function as a continuing unit and remain in\\n existence long enough to pursue a course of\\n conduct, nothing in RICO exempts an\\n enterprise whose associates engage in spurts\\n of activity punctuated by periods of\\n quiescence.\\n\\nId. at 948.\\n\\n Another element of a substantive § 1962(c) RICO\\nenterprise is that the enterprise must conduct its affairs\\nthrough a pattern of racketeering activity. Section 1961\\ndefines racketeering activity to include various criminal\\noffenses, including wire fraud, 18 U.S.C. § 1344, and\\nobstruction of justice, 18 U.S.C. § 1511. See 18 U.S.C.\\n§ 1961(1). A pattern of such activity “requires at least two\\nacts of racketeering activity.” Id. § 1961(5). The\\nracketeering predicates may establish a pattern if they\\n“related and . . . amounted to, or threatened the likelihood\\n\\n\\n 99\\n\\fof, continued criminal activity.” H.J. Inc. v. Nw. Bell Tel.\\nCo., 492 U.S. 229, 237 (1989).\\n Here, the District Court denied the post-trial\\nsufficiency arguments raised by Fattah, Brand, and\\nNicholas. It reasoned:\\n For a RICO conspiracy to exist, the\\n conspirators must agree to participate in an\\n enterprise with a unity of purpose as well as\\n relationships among those involved. The\\n evidence demonstrates that an agreement\\n among Fattah, Brand, Nicholas, Lindenfeld,\\n and Naylor existed for the overall purpose of\\n maintaining and enhancing Fattah as a\\n political figure and of preventing his standing\\n from being weakened by the failure to be able\\n to pay or write down his campaign debts.\\n These five persons agreed to work together as\\n a continuing unit, albeit with different roles.\\n The Government established that\\n Fattah, Brand, and Nicholas conspired along\\n with Naylor and Lindenfeld to conceal and\\n repay the 2007 illegal $1,000,000 loan to the\\n Fattah for Mayor campaign.\\n\\nJA128–29. The District Court further determined that\\n [w]hile each member may not have been\\n involved in every aspect of the enterprise, its\\n activities were sufficiently structured and\\n 100\\n\\f coordinated to achieve the purpose of\\n maintaining and enhancing Fattah’s political\\n standing and of preventing him from being\\n weakened politically because of his\\n campaign debts.\\n A RICO conspiracy also requires an\\n agreement to participate in an enterprise with\\n longevity sufficient to pursue its purpose.\\n This was established. In May 2007 the illegal\\n loan was obtained and continued through its\\n repayment in January 2008 and into at least\\n 2014 when the last campaign report reducing\\n a fake campaign debt to Naylor’s consulting\\n firm was filed by Fattah.\\nJA131.\\n\\n The defendants argue that the evidence is\\ninsufficient to show either an enterprise for purposes of\\n§ 1962(c) or an agreement as required for a § 1962(d)\\nconspiracy. We disagree, and conclude that the District\\nCourt’s analysis is on the mark.\\n\\n We begin by considering whether there was an\\nagreement. The evidence showed that Fattah knew each\\nmember involved in the scheme to conceal the unlawful\\ncampaign loan. When Lindenfeld learned of the $1 million\\nloan, he informed Fattah that it exceeded campaign\\nfinance limits. In short, the transaction was unlawful, and\\nthe two knew it. The transaction nonetheless went\\nforward, disguised as a loan, with Lindenfeld executing\\n 101\\n\\fthe promissory note as Strategies’ officer and obligating\\nStrategies to repay Lord $1 million. The concealment\\nefforts continued as Lindenfeld funneled a substantial\\nportion of the loan proceeds to Naylor for get-out-the-vote\\nefforts. After the losing campaign, Lindenfeld spoke with\\nFattah and Naylor about accounting for the funds that had\\nbeen spent. They decided not to include the amounts in the\\nFFM campaign reports. Fattah instructed Naylor to\\nprepare a fictitious invoice, and Naylor complied. The\\nFFM campaign reports filed from 2008 to 2014 disclosed\\nnothing about the unlawful $1 million loan. Instead, they\\nfalsely showed that Naylor’s consulting firm made yearly\\nin-kind contributions of $20,000 in debt forgiveness, when\\nin reality there was no debt to forgive.\\n As Lindenfeld fretted over repaying the $600,000\\nbalance of the Lord loan, Naylor assured him that Fattah\\nhad promised to take care of the repayment. And the\\nevidence supports an inference that Fattah recruited both\\nNicholas and Brand in doing so. As EAA’s director,\\nNicholas could fund the repayment. Brand, through his\\ncompany, Solutions, acted as the middleman: he received\\nthe payment from EAA pursuant to a fictitious contract,\\nand then forwarded the balance due to Strategies pursuant\\nto yet another fictitious contract. Nicholas and Brand\\ncontinued in the spring and summer of 2008 to hide the\\nfictitious agreement and the $600,000 payment to\\nLindenfeld to satisfy the Lord loan.\\n\\n\\n\\n 102\\n\\f In short, this evidence shows that Fattah,\\nLindenfeld, Naylor, Brand, and Nicholas all agreed to\\nparticipate in Fattah’s plan to conceal the unlawful\\ncampaign loan to maintain his political stature. Nicholas\\nand Brand claim that they had no knowledge of the false\\ncampaign reporting aspect of the plan. But as Salinas\\ninstructs, conspirators need not “agree to commit or\\nfacilitate each and every part of the” conspiracy. 522 U.S.\\nat 63. Rather, they “must agree to pursue the same criminal\\nobjective and may divide up the work, yet each [be]\\nresponsible for the acts of each other.” Id. at 63–64. Thus,\\na conspirator may agree to “facilitate only some of the acts\\nleading to the substantive offense” yet still be criminally\\nliable. Id. at 65.\\n The evidence showed that a substantial amount of\\nmoney was needed to repay Lord, and that the source of\\nthe repayment was EAA, a non-profit organization whose\\nfunds could be spent only for purposes consistent with the\\nterms of the grants it received. It also showed that Nicholas\\nwas presented with a sham contract to legitimize the\\nEAA–Solutions transaction. We conclude that the\\nevidence is sufficient to support an inference that Nicholas\\nknew at the start that the plan was unlawful. Yet she still\\nagreed to provide the requisite funds and to play a role in\\nconcealing the illegal campaign loan so that Fattah could\\nmaintain his political stature.\\n\\n As to Brand, even if he did not know that false\\ncampaign reports were being filed, the evidence is\\n\\n 103\\n\\fsufficient to show he played a key role in the enterprise.\\nFrom the outset, Brand worked to disguise the repayment\\nof the Lord loan as the consideration in a sham contract\\nbetween EAA and Solutions. He then arranged for the\\ntransfer of funds to Strategies in satisfaction of a\\ncontractual term in another purported business agreement\\nbetween Solutions and Strategies. The evidence reveals\\nthat Brand was the point man in the effort to meet the\\nJanuary 31, 2008 deadline to repay the Lord loan, and it\\namply shows that Brand also agreed to participate in the\\nplan to hide the illegal campaign loan and its repayment to\\nbenefit Fattah politically.\\n Fattah, Brand, and Nicholas attack their RICO\\nconspiracy convictions on another front. They argue that\\nthose verdicts should be set aside because the evidence\\nfails to show that the various schemes alleged in the\\nindictment as part of the RICO conspiracy are connected.\\nThe RICO count, they assert, charges a hub-and-spoke\\nconspiracy that is unconnected by a rim. In their view,\\nFattah is the hub, and the spokes consist of a series of\\nindependent schemes: the Vederman bribery scheme, the\\npayment of the outstanding tuition debt of Fattah’s son\\nChip, the Blue Guardians plan, and the repayment of the\\nillegal Lord loan to maintain Fattah’s political stature.\\nThey argue that, without a unifying rim, their actions\\ncannot constitute an enterprise. Again, we disagree.\\n\\n In In re Insurance Brokerage Antitrust Litigation,\\n618 F.3d 300 (3d Cir. 2010), we concluded, in analyzing\\n\\n 104\\n\\fone of plaintiffs’ RICO claims, that the alleged hub-and-\\nspoke enterprise—comprised of broker hubs and insurer\\nspokes—could not withstand a motion to dismiss because\\nit did not have a unifying rim. Id. at 374. We explained\\nthat the allegations did “not plausibly imply concerted\\naction—as opposed to merely parallel conduct—by the\\ninsurers, and therefore cannot provide a ‘rim’ enclosing\\nthe ‘spokes’ of these alleged ‘hub-and-spoke’\\nenterprises.” Id. Thus, the allegations did not “adequately\\nplead an association-in-fact enterprise” because the hub-\\nand-spoke conspiracy failed to “function as a unit.” Id.\\n\\n That is not the case here. The evidence showed that\\nFattah, Brand, and Nicholas agreed to conceal the illegal\\nLord loan. Each acted for the common purpose of\\nfurthering Fattah’s political interests. In short, they\\nengaged in concerted activity and functioned as a unit. The\\njury convicted Fattah, Brand, and Nicholas of the RICO\\nconspiracy based on the racketeering activity of wire fraud\\nand obstruction of justice to conceal the unlawful\\ntransaction. Because the evidence shows that Fattah,\\nLindenfeld, Naylor, Brand, and Nicholas agreed to protect\\nFattah’s political status by acting to maintain the secrecy\\nof the unlawful Lord loan, the alleged lack of a unifying\\n“rim” is not fatal to this RICO enterprise. What matters in\\nanalyzing the structure of this enterprise is that it\\nfunctioned as a unit. Boyle, 556 U.S. at 945; In re Ins.\\nBrokerage Antitrust Litig., 618 F.3d at 374. That “basic\\nrequirement” was met. Id.\\n\\n 105\\n\\f We turn next to the contention that the evidence\\nfails to establish other components of an enterprise. We\\nconclude that much of the evidence supporting the\\nexistence of an agreement also shows that there was an\\nassociation-in-fact enterprise.\\n\\n Boyle made clear that an association-in-fact\\nenterprise must have “a purpose, relationships among\\nthose associated with the enterprise, and longevity\\nsufficient to permit these associates to pursue the\\nenterprise’s purpose.” 556 U.S. at 946. The purpose, as we\\nhave repeatedly observed, was to maintain and preserve\\nFattah’s political stature by concealing the illegal loan and\\nits repayment. Though informal, there were relationships\\namong those associated with the enterprise. Fattah was at\\nthe center of this association and he directed its activity.\\nHe knew each of the association’s members, and the\\nmembers knew each other (except, perhaps, for Nicholas,\\nwho may not have known Lindenfeld).19\\n\\n\\n19\\n Nicholas’s lack of familiarity with Lindenfeld does not\\nundermine her membership in this association-in-fact\\nenterprise. We have previously explained that “[i]t is well-\\nestablished that one conspirator need not know the\\nidentities of all his co-conspirators, nor be aware of all the\\ndetails of the conspiracy in order to be found to have\\nagreed to participate in it.” United States v. Riccobene, 709\\nF.2d 214, 225 (3d Cir. 1983), abrogated on other grounds\\nby Griffin v. United States, 502 U.S. 46 (1991).\\n 106\\n\\f The Government also adduced sufficient proof of\\nthe longevity component required for an enterprise. The\\nscheme began in mid-2007, when Lord made the\\ncampaign loan, directing the proceeds of the loan to\\nStrategies. From the outset, Fattah, Lindenfeld, and Naylor\\nall knew they needed to conceal this illegal transaction.\\nThey began by fabricating an explanation for the source of\\nthe funds they spent on election day. SLA created a fake\\ninvoice for the campaign, showing a fictitious debt that\\nNaylor could later forgive by fictitious in-kind\\ncontributions existing only on Fattah’s campaign finance\\nreports.\\n The effort to disguise the Lord loan was not limited\\nto filing false campaign reports. Nicholas and Brand, who\\njoined the conspiracy a few months later than the other\\nmembers, understood that they too had to make the\\nfraudulent $600,000 payment by EAA to Solutions appear\\nlegitimate. Nicholas and Brand tried to disguise the sham\\ncontract as an ordinary transaction (even though it called\\nfor a six-figure upfront payment simply to support\\nSolutions’ various projects), and they succeeded in\\nkeeping it out of the DOJ auditors’ view until August\\n2008. The ruse continued as Solutions funneled the\\n$600,000 payment to Strategies under the guise of another\\nsham contract (which also required an upfront six-figure\\npayment). The scheme then continued as Fattah submitted\\nfalse FFM campaign reports from 2008 through 2014.\\n\\n\\n\\n 107\\n\\f Finally, we consider whether the enterprise\\nconducted its affairs through a pattern of racketeering\\nactivity, as required for a § 1962(c) enterprise. Wire fraud\\nand obstruction of justice may constitute “racketeering\\nactivity” under § 1961(1). As the Supreme Court\\ninstructed in H.J. Inc., the “multiple predicates within a\\nsingle scheme” must be related and “amount[] to, or\\nthreaten[] the likelihood of, continued criminal activity.”\\n492 U.S. at 237. Here, the amount of the illegal loan to be\\nconcealed was substantial. The enterprise needed to write\\noff the fictitious debt to Naylor’s consulting firm, and it\\nwas urgent that both the EAA–Solutions contract and the\\nSolutions–Strategies contract be legitimized. We conclude\\nthe evidence was sufficient to establish that this enterprise\\nconducted its affairs through a pattern of racketeering\\nactivity and that the predicate acts of wire fraud and\\nobstruction of justice were related. The racketeering\\nactivity furthered the goals of maintaining the secrecy of\\nthis $1 million illicit campaign loan and of preserving\\nFattah’s political stature.\\n Nicholas contends that the evidence fails to\\nestablish a pattern of racketeering activity because the\\nactions to which she agreed did not “extend[] over a\\nsubstantial period of time” as H.J. Inc. requires. 492 U.S.\\nat 242. That case indeed instructs that the continuity\\nrequirement of a pattern is a “temporal concept,” and that\\n“[p]redicate acts extending over a few weeks or months”\\ndo not satisfy the continuity concept. Id. But the Supreme\\nCourt explained that continuity may also be established by\\n 108\\n\\fshowing that there is a “threat of continued racketeering\\nactivity.” Id. Here, the course of fraudulent conduct\\nundertaken to secure and to conceal the $1 million Lord\\nloan consisted of the creation of sham debts, fictitious\\ncontracts, and false accounting entries over the course of\\nabout a year. But because Fattah needed to appear able to\\nretire his campaign debt, the enterprise needed to continue\\nfiling false campaign reports for several years, allowing\\nthe annual $20,000 in-kind debt forgiveness contributions\\nto appear to satisfy Naylor’s fake $193,000 invoice. That\\nevidence was sufficient to establish the requisite threat of\\ncontinued criminal activity. See H.J. Inc., 492 U.S. at 242–\\n43.\\n We conclude that the Government met its burden in\\nproving that Fattah, Brand, and Nicholas 20 engaged in a\\nRICO conspiracy in violation of § 1962(d).\\n\\n\\n20\\n Nicholas also asserts, in passing, that that her conviction\\nunder § 1962(d) should be set aside because that statutory\\nprovision is unconstitutionally vague as applied to her.\\nAccording to Nicholas, a person of ordinary intelligence\\nwould not know that her actions constituted an agreement\\nto participate in a RICO enterprise. See United States v.\\nPungitore, 910 F.2d 1084, 1104–05 (3d Cir. 1990). To the\\ncontrary, a person of ordinary intelligence, who had been\\nemployed by a prominent politician and then became the\\nCEO of a nonprofit organization which that politician had\\nfounded (and, to some extent, continued to direct), would\\n 109\\n\\f VI. Variance from the Indictment and Sufficiency of\\n the Evidence for Count 2\\n Brand and Nicholas challenge their convictions for\\nconspiracy to commit wire fraud by arguing that the\\nGovernment’s evidence at trial impermissibly varied from\\nthe indictment. Nicholas also challenges the sufficiency of\\nthe evidence to support her conviction for conspiracy to\\ncommit wire fraud. We address these contentions\\ntogether. 21\\n\\n Count 2 of the indictment alleged a single\\nconspiracy. JA277–79. Brand and Nicholas assert that the\\nGovernment’s evidence at trial did not support the\\nexistence of a single conspiracy but instead showed two\\nindependent conspiracies, only one of which involved the\\ntwo of them. According to Brand and Nicholas, the only\\nconspiracy with which they were involved ended more\\nthan five years before the Government charged them. That\\nwould mean that all their conduct falls outside the five-\\nyear limitations period for wire fraud conspiracy under 18\\nU.S.C. § 3282.\\n\\n\\nrealize that agreeing to participate with others in hiding an\\nunlawful campaign loan of $1 million could constitute an\\nunlawful RICO conspiracy.\\n21\\n In her briefing, Nicholas discusses variance in far less\\ndetail than Brand, so we refer primarily to Brand’s\\narguments. See Nicholas Br. 54–56. Her variance\\narguments fail for the same reasons that Brand’s fail.\\n 110\\n\\f “A conviction must be vacated when (1) there is a\\nvariance between the indictment and the proof presented\\nat trial and (2) the variance prejudices a substantial right\\nof the defendant.” Kemp, 500 F.3d at 287 (quoting United\\nStates v. Kelly, 892 F.2d 255, 258 (3d Cir. 1989)). We see\\nno variance, and will affirm the District Court.\\n A variance exists “if the indictment charges a single\\nconspiracy while the evidence presented at trial proves\\nonly the existence of multiple conspiracies.” Id. “We must\\ndetermine ‘whether there was sufficient evidence from\\nwhich the jury could have concluded that the government\\nproved the single conspiracy alleged in the indictment.’ ”\\nId. (quoting Kelly, 892 F.2d at 258). Viewing the record in\\nthe light most favorable to the Government, we consider\\nthree factors: (1) “whether there was a common goal\\namong the conspirators”; (2) “whether the agreement\\ncontemplated bringing to pass a continuous result that will\\nnot continue without the continuous cooperation of the\\nconspirators”; and (3) “the extent to which the participants\\noverlap in the various dealings.” Id. (quoting Kelly, 892\\nF.2d at 259).\\n\\n Brand argues that the Government failed to\\nestablish a common goal among the conspirators. To\\ndetermine whether the conspirators shared a common\\ngoal, “we look to the underlying purpose of the alleged\\ncriminal activity” in a fairly broad sense. United States v.\\nRigas, 605 F.3d 194, 214 (3d Cir. 2010) (en banc). In\\nRigas, we described the common goal of the defendants as\\n\\n 111\\n\\f“enriching [themselves] through the plunder of [their\\ncorporate employer],” id., and we have similarly\\narticulated the common goal in fairly general terms\\nelsewhere. See United States v. Greenidge, 495 F.3d 85,\\n93 (3d Cir. 2007) (“There was certainly evidence of a\\ncommon goal among these co-conspirators: to make\\nmoney by depositing stolen and altered corporate checks\\ninto business accounts.”); Kelly, 892 F.2d at 259 (“[T]he\\ncommon goal of all the participants was simply to make\\nmoney selling ‘speed.’ ”). Importantly, a common goal\\nmay exist even when “conspirators individually or in\\ngroups perform different tasks in pursuing the common\\ngoal,” and a single conspiracy may “attract[] different\\nmembers at different times” or “involve[] different sub-\\ngroups committing acts in furtherance of the overall plan.”\\nUnited States v. Boyd, 595 F.2d 120, 123 (3d Cir. 1978).\\n\\n Here, the indictment described the purpose of the\\nunified conspiracy in Count 2 at length:\\n\\n It was a purpose of the conspiracy to obtain\\n an illegal campaign loan and to fraudulently\\n repay that loan with hundreds of thousands of\\n dollars of misappropriated charitable funds\\n from Sallie Mae and federal grant funds from\\n NASA which were intended for educational\\n purposes.\\n\\n . . . . It was further a purpose of the\\n conspiracy to present FATTAH to the public\\n as a perennially viable candidate for public\\n 112\\n\\f office who honored his obligations to his\\n creditors and was able to retire his publicly\\n reported campaign debts.\\n . . . . It was further a purpose of the\\n conspiracy to promote FATTAH’s political\\n and financial goals through deception by\\n concealing and protecting the conspirators’\\n activities from detection and prosecution by\\n law enforcement officials and the federal\\n judiciary, as well as from exposure by the\\n news media, through means that included\\n obstruction of justice and the falsification of\\n documents, including Campaign Finance\\n Reports, false invoices, contracts, and other\\n documents and records.\\n\\nJA277–78, ¶¶ 3–5.\\n Brand characterizes the evidence at trial as\\nestablishing two distinct conspiracies. The first he labels\\nthe “diversion of funds scheme,” covering the\\nmisappropriation of funds by Nicholas, Brand,\\nLindenfeld, and Fattah to repay the Lord loan. Brand Br.\\n34. Brand calls the second conspiracy the “CFR scheme,”\\nin which Fattah and Naylor filed the false campaign\\nfinance reports showing Naylor gradually forgiving a non-\\nexistent debt. Id.\\n Brand argues that the only goal of the CFR scheme\\nwas to cover up how the funds from the illegal campaign\\n 113\\n\\floan were spent, a goal he distinguishes from that of the\\ndiversion of funds scheme, which he characterizes as a\\nplan to cover up the repayment of the loan with stolen\\nfunds. He also argues that the evidence does not establish\\nhe was involved in, or even aware of, the false campaign\\nfinance reports filed by Fattah. In Brand’s view, that\\nnecessarily means the evidence showed two separate\\nconspiracies.\\n\\n In considering these arguments, we begin by noting\\nthat one conspiracy can involve multiple subsidiary\\nschemes. Rigas, 605 F.3d at 214. It is true that the false\\ncampaign finance reports, in the narrowest sense, had the\\nspecific purpose of covering up how the illegal loan funds\\nwere used during the election. But the false campaign\\nfinance reports were also filed in furtherance of a broader\\ngoal shared by the conspirators involved in repayment of\\nthe Lord loan. They sought to promote Fattah’s political\\nand financial goals by preserving his image as a viable\\ncandidate and making him appear able to repay or\\notherwise service his campaign debts without resorting to\\nillegal means in doing so. The two subsidiary schemes\\nworked in concert in furtherance of this overarching goal,\\nand both were directed at covering up how the loan was\\ntruly repaid. The “diversion of funds scheme” hid the\\nillegal (but real) loan repayment through the use of fake\\ncontracts; the “CFR scheme” showed the seemingly legal\\n(but fake) loan forgiveness installments through the\\ncreation of fake invoices and campaign finance reports.\\nThe existence of two concealment schemes acting in\\n 114\\n\\fconcert does not undermine the unity of the conspiracy of\\nwhich they were both a part. We have no difficulty\\nconcluding that the false campaign finance reports and the\\nconcealed use of stolen funds to repay the Lord loan\\noperated together in furtherance of a common goal.\\n\\n As for Brand’s argument that he was unaware of the\\nfalse campaign finance reports and therefore could not be\\na part of any conspiracy involving them, it is well-settled\\nthat “each member of the charged conspiracy is liable for\\nthe substantive crimes his coconspirators commit in\\nfurtherance of the conspiracy even if he neither\\nparticipates in his co-conspirators’ crimes nor has any\\nknowledge of them.” United States v. Bailey, 840 F.3d 99,\\n112 (3d Cir. 2016) (citing Pinkerton v. United States, 328\\nU.S. 640 (1946)). The exceptions to that rule allow a\\ndefendant to escape liability for a co-conspirator’s crime\\nif: (1) “the substantive offense committed by one of the\\nconspirators was not in fact done in furtherance of the\\nconspiracy,” (2) “the substantive offense committed by\\none of the conspirators ‘did not fall within the scope of the\\nunlawful project,’ ” or (3) “the substantive offense\\ncommitted by one of the conspirators ‘could not be\\nreasonably foreseen as a necessary or natural consequence\\nof the unlawful agreement.’ ” Id. (quoting Pinkerton, 328\\nU.S. at 647–48). There was, as we have concluded, a unity\\nof purpose between the co-conspirators to further Fattah’s\\npolitical and financial goals by secretly obtaining and\\nrepaying an illegal campaign loan with stolen funds. The\\nfiling of false campaign reports does not fit within any of\\n 115\\n\\fthe recognized exceptions to co-conspirator liability, as it\\nwas in furtherance of the conspiracy’s shared goal, within\\nthe scope of the agreement to conceal the loan, and\\nforeseeable to Brand and Nicholas.\\n\\n Neither Brand nor Nicholas briefed the other two\\nfactors we consider when determining whether the\\nevidence impermissibly varied from the evidence,\\n“whether the agreement contemplated bringing to pass a\\ncontinuous result that will not continue without the\\ncontinuous cooperation of the conspirators,” and “the\\nextent to which the participants overlap in the various\\ndealings.” Kemp, 500 F.3d at 287 (quoting Kelly, 892 F.2d\\nat 258). The unified goal of promoting Fattah’s political\\ncareer and maintaining secrecy surrounding the illegal\\nloan and the misappropriated funds used to repay it\\nrequired the continuous cooperation of the conspirators.\\nIndeed, the efforts of several of them overlapped in every\\naspect of the scheme. And Lindenfeld and Fattah were, at\\na minimum, involved in some way in nearly every aspect\\nof the origination of the loan, the false campaign finance\\nreports, and the use of misappropriated funds to repay the\\nloan. For his part, Naylor was involved in the use of the\\nfunds, the false campaign finance reports, and to a lesser\\nextent, the repayment of the loan.\\n Brand (as part of his variance argument) and\\nNicholas (as part of her sufficiency argument) argue that\\nthe Government did not prove they agreed to conceal their\\nactions, and thus the false campaign reports would not be\\n\\n 116\\n\\fsufficient to extend the duration of the conspiracy so that\\nit fell within the statute of limitations. Acts of\\nconcealment, such as the false campaign reports, are not\\nautomatically “in furtherance” of a conspiracy. We must\\ndetermine whether there was “an express original\\nagreement among the conspirators to continue to act in\\nconcert in order to cover up, for their own self-protection,\\ntraces of the crime after its commission,” as opposed to “a\\nconspiracy to conceal . . . being implied from elements\\nwhich will be present in virtually every conspiracy case,\\nthat is, secrecy plus overt acts of concealment.”\\nGrunewald v. United States, 353 U.S. 391, 404 (1957). If\\nthe indictment “specifically alleges a continuing\\nconspiracy” to conceal the crime after the completion of\\nthe wire fraud, and such a conspiracy can be proven, the\\nstatute of limitations does not begin to run until the last\\novert act of concealment. United States v. Moses, 148 F.3d\\n277, 282 (3d Cir. 1998).\\n\\n Here, the evidence shows that the conspirators\\nexpressly agreed to conceal the loan and its repayment. As\\nan initial matter, Brand’s only role in the conspiracy was\\nto cover up the use of stolen funds by (1) serving as an\\nintermediary between Nicholas and Lindenfeld; and\\n(2) agreeing to create false documentation (the contracts)\\nwith both EAA and Strategies for the sole purpose of\\ndisguising the payments and covering up the wire fraud\\nconspiracy. Nicholas could simply have paid Lindenfeld\\nherself (or paid Lord) if she and Brand had not agreed to\\nconceal the crime from the start. Additionally, and as\\n 117\\n\\fBrand acknowledges, the false campaign finance reports\\nbegan before the loan was repaid, proving that\\nconcealment of the crime was contemplated and begun as\\na direct purpose of the conspiracy before Brand and\\nNicholas became involved in the repayment. Nicholas too\\nagreed to conceal the repayment, as she implicitly\\nacknowledged in her emails with Brand and Fattah. GSA2.\\nFinally, when Lindenfeld briefly strayed from the\\nconspiracy’s commitment to secrecy by mentioning the\\nrepayment in front of others who did not know of the\\nscheme, Brand became “angry,” “took [Lindenfeld] out in\\nthe hallway,” and chastised him, saying that “[Lindenfeld]\\ncouldn’t say that sort of []thing” in front of other people.\\nJA1670–71. We conclude that the evidence is consistent\\nwith the allegations in the indictment, which charge a\\nsingle conspiracy consisting of an original agreement to\\nconceal the illegal loan and its subsequent illegal\\nrepayment to further Fattah’s political career.\\n\\n Nicholas makes several arguments in passing. She\\nsuggests that the District Court upheld the conviction after\\ntrial “on a theory not submitted to the jury.” Nicholas Br.\\n51. This argument is, essentially, that the indictment and\\nthe District Court’s post-trial ruling described the\\nconspiracy one way, but that the jury charge described the\\nconspiracy differently. Nicholas argues that the jury was\\npresented with the theory that the sole purpose of the false\\ncampaign reports under Count 2 was to “conceal[] the\\nalleged scheme to defraud,” JA5849, rather than to support\\n\\n 118\\n\\fFattah’s political career, as the District Court described the\\npurpose after trial, see JA74.\\n Nicholas ignores that part of the jury charge which\\ninstructed that Count 2 required a finding “[t]hat two or\\nmore persons agreed to commit wire fraud as charged in\\nthe indictment.” JA5845 (emphasis added). The jury had\\naccess to the indictment, and as Nicholas points out,\\nNicholas Br. 45–46, the indictment outlines the offense in\\nthe same way the District Court later described it in its\\npost-trial ruling. The District Court consistently described\\nthe count, and we see no reversible error.\\n Nicholas also argues that the conspiracy charged in\\nCount 2 has an objective—“to ‘present Fattah’ as\\n‘perennially viable’ ”—and that such an objective is not\\nillegal. Nicholas Br. 53. But, of course, the jury was not\\ninstructed that it was illegal to be a Fattah supporter, or\\neven to work on his campaign. The jury was charged\\nspecifically on the crime of wire fraud.\\n\\n We conclude that there was no impermissible\\nvariance between the indictment and the Government’s\\nevidence at trial, and that there was sufficient evidence to\\nsupport the convictions. We will affirm the convictions of\\nBrand and Nicholas for conspiracy to commit wire fraud\\nunder Count 2.\\n\\n\\n\\n\\n 119\\n\\f VII. The District Court’s Instruction to the Jury on\\n the Meaning of Intent\\n Nicholas contends that the District Court\\nimproperly instructed the jury by using the disjunctive\\nrather than the conjunctive at one point in its definition of\\nintent. When providing its final charge to the jury, the\\nDistrict Court explained:\\n Certain of the offenses charged in the\\n indictment require that the government prove\\n that the charged defendant acted intentionally\\n or with intent. This means that the\\n government must prove either that (1), it was\\n the defendant’s conscious desire or purpose\\n to act in a certain way or to cause a certain\\n result; or (2), the defendant knew that he or\\n she was acting in that way or it would be\\n practically certain to cause that result.\\n\\nJA5787 (emphasis added). According to Nicholas, an\\naccurate definition of intent required that the final “or” be\\nan “and.” Nicholas argues that this was an error so\\ngrievous as to “effectively eliminate[] the intent element\\nfrom each offense of conviction.” 22 Nicholas Br. 26.\\n\\n\\n22\\n The Comment to Third Circuit Model Criminal Jury\\nInstruction 5.03 makes clear that the definition of intent\\nencapsulates both “specific intent” (acting “purposely” or\\nwith “conscious object”) and “general intent” (acting\\n 120\\n\\f Our review of whether a jury instruction stated the\\nproper legal standard is plenary. United States v. Petersen,\\n622 F.3d 196, 207 n.7 (3d Cir. 2010). At trial, Nicholas\\nfailed to object to this portion of the jury charge.\\nAccordingly, our review must be for plain error. See\\nUnited States v. Flores-Mejia, 759 F.3d 253, 258 (3d Cir.\\n2014) (en banc).\\n\\n To prevail on plain error review, Nicholas must\\nestablish that there was an error, that it was plain (i.e., clear\\nunder current law), and that it affected her substantial\\nrights (i.e., whether there is a reasonable likelihood that\\nthe jury applied the challenged instruction in an\\nimpermissible manner). United States v. Olano, 507 U.S.\\n\\n“knowingly” or “with awareness”). Although Nicholas\\ndescribes the alleged error as “essentially eliminating” the\\nelement of intent, we think Nicholas’s argument is better\\nunderstood as a claim that the instruction given could have\\npermitted a jury to conclude that she acted with only\\ngeneral intent (that she was aware of what she was doing),\\nwhen her crimes require specific intent (that she had an\\nillegal purpose). As her brief states, “[p]lainly she\\n‘knowingly’ wrote checks from EAA to [Solutions] and\\nmade record entries about them; the question was whether\\nshe intended to defraud EAA and NASA, or to obstruct\\njustice, by doing so.” Nicholas Br. 24. We cannot agree\\nwith her characterization that the instruction resulted in the\\n“effective omission” of the intent element from the jury\\ninstructions.\\n 121\\n\\f725, 733–34 (1993); United States v. Dobson, 419 F.3d\\n231, 239–40 (3d Cir. 2005). If these requirements are met,\\nwe may then exercise our discretion to address the error,\\nbut only if we conclude that the error seriously affected the\\nfairness, integrity, or public reputation of the judicial\\nproceeding. United States v. Andrews, 681 F.3d 509, 517\\n(3d Cir. 2012) (quoting Johnson v. United States, 520 U.S.\\n461, 467 (1997)). A failure to instruct the jury on a\\nnecessary element of an offense ordinarily constitutes\\nplain error, unless the instructions as a whole otherwise\\nmake clear to the jury all the necessary elements of the\\noffense. United States v. Stimler, 864 F.3d 253, 270 (3d\\nCir. 2017).\\n Nicholas acknowledges, as she must, that the\\ninstruction given was a verbatim recitation of Instruction\\n5.03 of the Third Circuit’s Model Criminal Jury\\nInstructions. She nonetheless contends that our Model\\nInstruction is erroneous. Even if we were to accept\\nNicholas’s contention that the instruction is incorrect, a\\nproposition we consider as highly doubtful, see Petersen,\\n622 F.3d at 208 (“We have a hard time concluding that the\\nuse of our own model jury instruction can constitute error\\n. . . .”), we conclude that, considering the instructions as a\\nwhole, the District Court clearly and specifically\\ninstructed the jury on the intent element as it applied to\\neach of Nicholas’s charged crimes.\\n\\n The disputed intent instruction was given at the\\nbeginning of the final charge, explaining the general\\n\\n 122\\n\\fmeaning of the intent applicable to “[c]ertain of the\\noffenses charged.”23 JA5787. The District Court went on\\nto instruct the jury in specific detail on the elements of\\neach of the crimes of which Nicholas was accused,\\n\\n\\n\\n\\n23\\n The introductory definition did not end with the\\nlanguage Nicholas cites. The District Court elaborated that\\nacting in good faith is a complete defense to the charges:\\n\\n The offenses charged in the indictment\\n require proof that the charged defendants\\n acted with criminal intent. If you find that a\\n defendant acted in good faith that would be a\\n complete defense to such a charge, because\\n good faith on the part of the defendant would\\n be inconsistent with his or her acting\\n knowingly, willfully, corruptly, or with intent\\n to defraud or intent to impede, obstruct, or\\n wrongfully influence.\\n\\nJA5788–89 (emphasis added). This instruction\\nundermines Nicholas’s claim that the jury could have\\nreasonably concluded that she “ ‘knowingly’ wrote\\nchecks” but did not “intend[] to defraud . . . or to obstruct\\njustice[] by doing so,” Nicholas Br. 24, as this instruction\\nleaves little room for doubt that good faith is at odds with\\n“criminal intent.”\\n\\n 123\\n\\fexplaining also the intent element of each. 24 See JA5791\\n(describing the third element of the RICO conspiracy\\ncharge as: “the particular defendant and at least one other\\nalleged conspirator shared a unity of purpose and the intent\\nto achieve the objective of conducting or participating in\\nthe conduct of an enterprise’s affairs through a pattern of\\nracketeering activity”); JA5823 (regarding wire fraud,\\ninstructing that the government must prove “[t]hat the\\ndefendant under consideration acted with the intent to\\ndefraud”); JA5838–39 (regarding obstruction of justice,\\ninstructing that the defendant must have acted “with the\\nintent to impair the record, document, or object’s integrity\\nor availability for use in an official proceeding,” and must\\nhave acted corruptly “with the purpose of wrongfully\\nimpeding the due administration of justice”); JA5860\\n(explaining that falsification of records requires that “the\\ndefendant under consideration acted with the intent to\\nimpede, obstruct or influence the investigation or proper\\nadministration of a matter”). These instructions are\\nconsistent with both our Model Jury Instructions and our\\ncase law concerning the elements of these crimes. See\\nThird Circuit Model Criminal Jury Instruction 6.18.1962D\\n(RICO), 6.18.1343 (wire fraud), 6.18.1512A2 (obstruction\\nof justice); United States v. Sussman, 709 F.3d 155, 168\\n(3d Cir. 2013) (obstruction of justice); United States v.\\n\\n24\\n Nicholas did not object to the knowledge and intent\\ninstructions when the District Court discussed each of the\\nindividual charges, and does not identify a disagreement\\nwith any specific instruction on any particular charge.\\n 124\\n\\fMoyer, 674 F.3d 192, 208–09 (3d Cir. 2012) (falsification\\nof records); United States v. Pelullo (Pelullo I), 964 F.2d\\n193, 216 (3d Cir. 1992) (wire fraud).\\n The District Court also provided a separate\\ndefinition of the knowledge element of each charge,\\nillustrating the difference between knowledge and intent.\\nSee JA5793 (explaining that the evidence must show that\\na RICO defendant “knowingly agreed to facilitate or\\nfurther a course of conduct, which if completed would\\ninclude a pattern of racketeering activity”); JA5823 (wire\\nfraud means that the defendant “knowingly devised a\\nscheme to defraud a victim . . . by materially false or\\nfraudulent pretenses”); JA5860 (falsification of records\\nhas as an element “[t]hat the defendant under\\nconsideration knowingly concealed, covered up, falsified\\nor made false entries in a document or record”). These\\ninstructions made clear that knowledge and intent are\\nseparate considerations, undermining Nicholas’s\\ncontention that the jury was led to believe that “knowledge\\nis sufficient to prove intent.” Nicholas Br. 24.\\n The District Court provided each member of the\\njury with more than 100 pages of instructions before\\ndeliberations began. Viewing those instructions as a\\nwhole, we are satisfied that the jury was apprised of the\\ncorrect meaning of intent as an element of the crimes with\\nwhich Nicholas was charged, as well as the distinction\\nbetween knowledge and intent. We perceive no error,\\n\\n\\n 125\\n\\fmuch less error that is plain, in the District Court’s\\ninstructions to the jury. 25\\n\\n VIII. Sending the Indictment to the Jury\\n At trial, Vederman, Nicholas, and Brand objected to\\nthe District Court’s decision to give the jury a redacted\\ncopy of the indictment to use during its deliberations. Only\\nNicholas and Brand raise this issue on appeal. In\\nNicholas’s view, sending the indictment to the jury\\nunfairly prejudiced her because it contained unsupported\\nallegations that she had obstructed federal agencies and\\nreferred to a nonexistent certification requirement for\\nSallie Mae funds. Brand argues that he was prejudiced by\\nthe indictment’s references to “schemes” and “fake”\\ncontracts, and because it mentioned Brand’s spouse and\\nthat she was a former member of Fattah’s congressional\\nstaff. Nicholas and Brand together assert that the\\nindictment included legal theories on which the jury was\\nnot instructed. They contend that the indictment’s\\nnarrative of the Government’s case set out a roadmap that\\nomitted any averments relating to the defense theory and\\nallowed the Government to yet again present its case. To\\nbuttress that argument, Nicholas and Brand cite the\\ntestimony of Juror 12, who described the jury’s initial\\n\\n\\n\\n25\\n Accordingly, we need not consider the merits of\\nNicholas’s argument that Model Criminal Jury Instruction\\n5.03 is erroneous.\\n 126\\n\\fdeliberations and alleged that the jurors viewed the\\nindictment as evidence.\\n In United States v. Todaro, 448 F.2d 64, 66 (3d Cir.\\n1971), we held that the decision to allow “jurors to have a\\ncopy of the indictment with them during their\\ndeliberations . . . is a matter within the discretion of the\\nDistrict Judge, subject to a limiting instruction that the\\nindictment does not constitute evidence, but is an\\naccusation only.” Subsequently, in United States v.\\nPungitore, 910 F.2d 1084, 1142 n.83 (3d Cir. 1990), we\\nacknowledged that the District Court has the power to\\nredact the indictment if doing so would be appropriate to\\navoid prejudice to the defendant. See also United States v.\\nRoy, 473 F.3d 1232, 1237 n.2 (D.C. Cir. 2007) (noting that\\ncourt may redact an indictment before submitting it to the\\njury).\\n\\n While both Nicholas and Brand objected in general\\nterms to the District Court’s decision to provide the\\nindictment to the jury, they have not directed us to any\\nspecific request to redact the information they now claim\\nis prejudicial. And the District Court provided a limiting\\ninstruction on four occasions during its charge, repeatedly\\nemphasizing that the indictment was not evidence.\\nJA5765, 5767, 5782, 5880. The Court instructed the jury\\non its duty to base its verdict “solely upon the evidence in\\nthe case.” JA5764. Just before the jury retired to\\ndeliberate, the Court reiterated that the purpose of the\\n\\n\\n 127\\n\\findictment is to set forth the charges, and that it is “merely\\nan accusation.” JA5909.\\n “[J]uries are presumed to follow their instructions\\n. . . .” Richardson v. Marsh, 481 U.S. 200, 211 (1987). In\\nour view, Juror 12’s assertion that the indictment was\\nbeing considered evidence does not, standing alone,\\nestablish that his fellow jurors actually did so. We reject\\nthe notion that the jury, after hearing weeks of testimony\\nand having viewed substantial documentary evidence,\\nwent on to ignore the Court’s limiting instruction\\nconcerning the indictment. 26 Accordingly, we conclude\\n\\n\\n26\\n We acknowledge that our case law provides minimal\\nguidance to district courts concerning the practice of\\nsending an indictment to the jury for their use during\\ndeliberations. We are also aware that some courts have\\ndisapproved the practice of sending the indictment out\\nwith the jury. See United States v. Esso, 684 F.3d 347, 352\\nn.5 (2d Cir. 2012); Roy, 473 F.3d at 1237 n.2. We\\nemphasize that this practice is committed to the sound\\ndiscretion of the district judge. Todaro, 448 F.2d at 66. In\\nour view, such an exercise of a judge’s discretion should\\nbe informed by considering the nature of the case, the\\nnumber of defendants, the length of the indictment, the\\nextent of the factual recitation supporting the criminal\\ncharges, and most importantly, whether the indictment\\n(especially if lengthy and fact-laden) will be useful to the\\njury, in light of the judge’s own carefully tailored jury\\n 128\\n\\fthat the District Court did not abuse its discretion in\\nsending the indictment out to the jury.\\n\\n IX. The District Court’s Evidentiary Rulings\\n Vederman, Nicholas, and Brand each challenge\\nevidentiary rulings by the District Court. We conclude that\\nnone of these contentions warrants setting aside their\\nconvictions.\\n\\n A. The District Court’s Application of Rule 404(b)\\n Vederman argues that the District Court misapplied\\nFederal Rule of Evidence 404(b) when it excluded\\nevidence of Vederman’s prior gift-giving. 27 This Court\\nreviews a district court’s application of Rule 404(b) for\\nabuse of discretion. United States v. Daraio, 445 F.3d 253,\\n\\ninstruction, as supplemented by a verdict slip. See Esso,\\n684 F.3d at 352 n.5.\\n27\\n Although Rule 404(b) determinations are usually in\\nresponse to attempts to introduce “bad” acts evidence,\\nVederman’s attempt to introduce “good” acts of gift-\\ngiving is properly analyzed under the same rule. Ansell v.\\nGreen Acres Contracting Co., 347 F.3d 515, 520 (3d Cir.\\n2003) (“The evidence admitted in this case differs from\\ngarden variety Rule 404(b) matter because it is evidence,\\nnot of a prior bad act in a criminal case, but of a subsequent\\ngood act in a civil case. Nonetheless, this evidence is\\nencompassed by the plain text of Rule 404(b) which\\naddresses ‘other . . . acts,’ not just prior bad acts.”).\\n 129\\n\\f259 (3d Cir. 2006); Ansell v. Green Acres Contracting Co.,\\n347 F.3d 515, 519 (3d Cir. 2003). A trial court commits\\n“[a]n abuse of discretion . . . when [the] district court’s\\ndecision rests upon a clearly erroneous finding of fact, an\\nerrant conclusion of law or an improper application of law\\nto fact.” Pardini v. Allegheny Intermediate Unit, 524 F.3d\\n419, 422 (3d Cir. 2008) (quoting P.N. v. Clementon Bd. of\\nEduc., 442 F.3d 848, 852 (3d Cir. 2006)).\\n\\n Federal Rule of Evidence 404(b) provides in part:\\n (b) Crimes, Wrongs, or Other Acts.\\n\\n (1) Prohibited Uses. Evidence of a\\n crime, wrong, or other act is not\\n admissible to prove a person’s\\n character in order to show that on a\\n particular occasion the person\\n acted in accordance with the\\n character.\\n\\n (2) Permitted Uses; Notice in a\\n Criminal Case. This evidence may\\n be admissible for another purpose,\\n such as proving motive,\\n opportunity, intent, preparation,\\n plan, knowledge, identity, absence\\n of mistake, or lack of accident.\\nFed. R. Evid. 404(b)(1)–(2).\\n\\n 130\\n\\f At trial, Vederman sought to present a witness from\\nAmerican University who would have testified that\\n“Vederman agreed, on more than fifty instances, to\\nfinancially assist students [at American] who needed help\\nwith tuition, book money, or travel funds to visit their\\nfamilies.” Vederman Br. 42 (emphasis omitted).\\nAccording to Vederman, the testimony was relevant to\\nrefuting the Government’s argument that he agreed to\\nguarantee the tuition expenses of Fattah’s au pair as a way\\nof bribing the congressman. In excluding this evidence\\nunder Rule 404(b), the District Court stated at sidebar:\\n\\n I sustain the government’s objection to\\n calling a representative of American\\n University to testify on behalf of Herbert\\n Vederman.\\n\\n In my view the testimony runs afoul of\\n Rule 404(b)(1) of the Federal Rules of\\n Evidence. I find it to be propensity evidence.\\n He or she would be testifying about Mr.\\n Vederman’s financial generosity with respect\\n to students of American University.\\n The issue here is payment of partial\\n tuition of a student at the Philadelphia\\n University. I see no connection between the\\n generosity at American University and the\\n situation with Philadelphia University.\\n\\n\\n 131\\n\\fJA4459–60. Vederman argues that because the proposed\\nevidence related to Vederman’s intent, and not solely his\\npropensity to perform good acts, we should conclude that\\nthe District Court abused its discretion. We see no error in\\nthe District Court’s ruling.\\n\\n Vederman challenges as arbitrary the District\\nCourt’s “assertion that support for American University\\nstudents is too remote from support for Philadelphia\\nUniversity students” such that it constitutes inadmissible\\nevidence. Vederman Reply Br. 23. This distinction was far\\nfrom arbitrary. Vederman may well have financially\\nsupported American University students because of\\nconnections he had to that school or to the D.C.\\ncommunity at large—connections Vederman did not have\\nto Philadelphia University. And the excluded testimony\\nappears to have described support for students Vederman\\ndid not previously know. By supporting Fattah’s au pair,\\nVederman was helping an employee of a man whom he\\nknew quite well. JA889 (“[Fattah and Vederman] spent a\\nlot of time together traveling back and forth to\\nWashington, in the case of a death in the family attending\\ncertain ceremonies that were important, and above all\\nspending time with each other and their families\\ntogether.”). Vederman’s decision to help Fattah’s au pair,\\nwho wished to attend Philadelphia University, seems more\\nlike a departure from, rather than a continuation of, his\\npattern of support for American University students.\\n\\n\\n\\n 132\\n\\f As the party seeking admission of evidence under\\nRule 404(b), Vederman bore “the burden of demonstrating\\nits applicability” and “identifying a proper purpose.”\\nUnited States v. Caldwell, 760 F.3d 267, 276 (3d Cir.\\n2014). By failing to explain sufficiently why the factual\\ndistinctions discussed above were not material, Vederman\\nfailed to meet his burden. In particular, although\\nVederman argues that he offered evidence of his prior gift-\\ngiving to prove intent—“a proper non-propensity\\npurpose”—he failed to show why the proposed testimony\\nwas “relevant to that identified purpose.” Id. at 277. 28 As\\nwe noted in Ansell v. Green Acres Contracting, an\\nemployment discrimination case on which Vederman\\nheavily relies, “[t]here is. . . no bright line rule for\\ndetermining when evidence is too remote to be relevant.”\\n347 F.3d at 525. As such, a district court’s determination\\nunder Rule 404(b) “will not be disturbed on appeal unless\\nit amounts to an abuse of discretion.” Id. The District\\n\\n\\n\\n28\\n Under Rule 404(b), “prior act evidence is inadmissible\\nunless the evidence is (1) offered for a proper non-\\npropensity purpose that is at issue in the case; (2) relevant\\nto that identified purpose; (3) sufficiently probative under\\nRule 403 such that its probative value is not outweighed\\nby any inherent danger of unfair prejudice; and\\n(4) accompanied by a limiting instruction, if requested.”\\nUnited States v. Caldwell, 760 F.3d 267, 277–78 (3d Cir.\\n2014).\\n 133\\n\\fCourt did not abuse its discretion in excluding evidence of\\nVederman’s support for students at American University.\\n\\nB. Evidentiary Rulings Regarding Nicholas’s Defense\\n Nicholas argues that the District Court rendered\\nthree erroneous evidentiary rulings that prejudiced her\\ndefense. We do not find any of her arguments convincing.\\n\\n 1. The EAA Board Minutes\\n In support of its theory that Nicholas defrauded\\nEAA, the Government introduced minutes from EAA’s\\nBoard. Minutes from 2005 revealed that the Board limited\\nNicholas’s signing authority to $100,000. Minutes from\\nDecember 2007, February 2008, and May 2008 failed to\\nreference either the EAA–Solutions contract or the checks,\\ndrawn from EAA’s account for $500,000 and $100,000,\\nthat were purportedly paid pursuant to the contract.\\nNicholas contends that the Board minutes were\\nerroneously admitted because they constituted improper\\nhearsay which failed to satisfy either the exception for\\nbusiness records under Federal Rule of Evidence 803(6)\\nor the absence of records exception under Federal Rule of\\nEvidence 803(7). “We review the District Court’s\\nevidentiary ruling[s] for abuse of discretion, but also\\n‘exercise plenary review . . . to the extent [the rulings] are\\nbased on a legal interpretation of the Federal Rules of\\nEvidence.’ ” Repak, 852 F.3d at 240 (citations omitted)\\n(second alteration in original).\\n\\n 134\\n\\f Applying those standards here,29 we conclude there\\nwas sufficient basis to admit exhibit EAA-48 under\\nFederal Rule of Evidence 803(6) as a business record.\\nAlthough allowing the prosecution to inquire over\\nNicholas’s earlier objection based on Federal Rule of\\nEvidence 803(7) to the absence of any mention of the\\n$500,000 check in the 2008 Board Minutes was error, it\\nwas not reversible error. Other evidence in the record\\noverwhelmingly showed that Nicholas made the $500,000\\nand $100,000 payments to Solutions with the requisite\\nfraudulent intent. That evidence included the 2005 policy\\nlimiting Nicholas’s authority to approve expenditures to\\n$100,000, the accountant’s testimony about the\\ndisbursement policy requiring the completion of a check\\nrequest form for the issuance of a check, and Jones’\\ntestimony that he never saw a request for the $500,000\\ncheck. That evidence, coupled with Nicholas’s tendering\\nof the upfront half-million dollar payment before the terms\\nof the purported agreement had been finalized or executed,\\nher failure to mention the $600,000 in payments to\\nSolutions during her interview with FBI Agent\\n\\n29\\n We note that the argument section of Nicholas’s brief on\\nthis issue specifically cited to the page in the record where\\nexhibit EAA-48 was admitted without objection by any\\ndefense counsel. See Appellant’s Br. at 57 (citing JA4381-\\n82). Nonetheless, there was an earlier objection to the\\nadmission of exhibit EAA-48 that was preserved and that\\nwas referenced in a string citation elsewhere in Nicholas’s\\nbrief.\\n 135\\n\\fDieffenbach, and her alteration of EAA’s general ledger\\nto conceal the $100,000 payment, makes it “highly\\nprobable” that the jury would have reached the same\\nresult. See United States v. Friedman, 658 F.3d 342, 352\\n(3d Cir. 2011).\\n\\n Nicholas also asserts that the Board minutes were\\nunfairly prejudicial. We disagree. Any possible prejudice\\nwas minimized by the fact that the Board minutes make no\\nreference to either the EAA–Solutions contract or to any\\nfinancial matters whatsoever. Indeed, given these lacunae\\nin the Government’s proof, a reasonable factfinder might\\nwell have concluded that the Board’s intention to limit\\nNicholas’s signing authority had not been implemented\\nand that Nicholas had not concealed the contract from the\\nBoard.\\n\\n 2. Jones’ Memory Regarding Other Contracts\\n Nicholas next asserts that the District Court erred\\nduring her cross-examination of Board Chairman Jones by\\nsustaining the prosecution’s objection to her inquiry into\\nwhether he remembered other contracts in excess of\\n$100,000 being brought to the Board. See JA1386–87. The\\nbasis of the prosecution’s objection seemed to be that\\nNicholas’s line of inquiry was beyond the scope of the\\ndirect testimony. JA1387 (“I showed checks concerning\\nwhat’s going on, not other programs.”); see Fed. R. Evid.\\n611(b). The District Court sustained the objection,\\ndeclaring that “it has absolutely nothing to do with this\\ncase.” JA1387. Nicholas contends that if Jones did not\\n 136\\n\\frecall whether other large contracts had been presented to\\nthe Board, his inability to recall the EAA–Solutions\\ncontract would have been “unremarkable rather than\\nevidence of fraud or concealment.” Nicholas Br. 61.\\n\\n We acknowledge that whether Jones remembered\\nother large contracts requiring Board approval had some\\nrelevance under Rule 401. Yet any error by the District\\nCourt in prohibiting Nicholas’s counsel from pursuing this\\nline of inquiry is harmless. Jones admitted that he did not\\nknow if the Board ever implemented the policy requiring\\nits approval of contracts exceeding $100,000. He also\\nconceded that the EAA Board focused less on the financial\\nside of EAA than on its programs. JA1383–85. Nicholas\\ncould not have been prejudiced by the District Court’s\\nruling.\\n\\n 3. Exclusion of NOAA Evidence\\n Nicholas defended against the criminal charges\\narising out of the non-existent October 2012 conference\\nby asserting that she acted in “good faith in spending the\\nNOAA funds on EAA expenses,” Nicholas Br. 64, that the\\ndifference in the dates in the paperwork was not material,\\nand that NOAA had received the benefits of the\\nsponsorship because its logo was displayed on the signage\\nused at the February conference. Nicholas succeeded in\\npresenting testimony and introducing photographs that\\nshowed NOAA’s logo on the February 2012 annual\\nconference bags, padfolios, and name tags. The Court\\nexcluded a photograph of a NOAA intern at the February\\n 137\\n\\f2012 conference, other photographs of the February\\nconference signage, and some checks that pertained to the\\nFebruary conference. Nicholas claims that her inability to\\nintroduce those exhibits frustrated her ability to present\\nher good faith defense. We are not persuaded.\\n\\n The photographs were excluded as cumulative, the\\nsort of ruling to which we afford trial judges very broad\\ndiscretion. See Fed. R. Evid. 403; United States v.\\nDalfonso, 707 F.2d 757, 762 (3d Cir. 1983). It was not\\nerror to exclude the student intern’s photograph. The\\nconference brochure included photographs from previous\\nconferences, and the witness from NOAA was unable to\\ntestify to the year the student served as an intern. Finally,\\nthe checks tendered for the travel expenses incurred for the\\nFebruary conference were excluded as irrelevant to\\nwhether Nicholas had a good faith belief that NOAA\\nsponsored the October conference.\\n\\nC. The Cooperating Witness’s Mental Health Records\\n During discovery, Brand learned that a cooperating\\nwitness was diagnosed with bipolar II disorder and was\\ntaking medication to treat that condition. Brand\\nsubpoenaed mental health records kept by the witness’s\\ncurrent and former psychiatrists in hopes of using those\\nrecords to attack the witness’s memory, truthfulness, and\\ncredibility. The witness and the Government both filed\\nmotions to quash the subpoena, arguing that the witness’s\\nmental health records were protected by the\\npsychotherapist–patient privilege recognized by the\\n 138\\n\\fSupreme Court in Jaffee v. Redmond, 518 U.S. 1 (1996).\\nThe Government also filed a motion in limine seeking to\\nrestrict the scope of cross-examination to prevent Brand\\nfrom questioning the witness about his mental health.\\n\\n Alongside his motion to quash, the witness\\nvoluntarily produced for the Court his mental health\\nrecords. The Court concluded that the psychotherapist–\\npatient privilege would ordinarily apply to the mental\\nhealth records, but that the privilege was not absolute,\\nespecially when invoked in response to a criminal\\ndefendant’s efforts to obtain through discovery evidence\\nthat is favorable to his case. Following the procedure set\\nforth in Pennsylvania v. Ritchie, 480 U.S. 39 (1987), the\\nDistrict Court conducted an in camera review of the\\nmental health records to determine if they contained\\nmaterial evidence—that is, evidence that would “give[]\\nrise to a reasonable probability that it [would] affect the\\noutcome of the case.” JA149. The District Court found\\n“nothing in the mental health records of the [witness] . . .\\nmaterial for this criminal action,” noting that “[t]he\\nrecords reveal nothing that calls into question [the\\nwitness’s] memory, perception, competence, or veracity.”\\nJA150. Accordingly, the Court entered an order granting\\nthe motions to quash the subpoena.\\n The District Court also granted the Government’s\\nmotion in limine and restricted the scope of cross-\\nexamination, ruling that “no reference may be made to [the\\nwitness’s] bipolar disorder or the medications he takes to\\n\\n 139\\n\\fmanage it.” JA142, 156. The Court reasoned that bipolar\\ndisorder varied in its effects from person to person, and\\nconcluded that Brand had not shown that the effects of the\\ndisorder had any bearing on the witness’s credibility. The\\nDistrict Court ruled that cross-examination would not\\nserve any valid impeachment purpose.\\n Brand claims that the District Court’s order ran\\nafoul of the Due Process Clause of the Fifth Amendment\\nand the Confrontation Clause of the Sixth Amendment.\\nWe review a district court’s rulings to quash a subpoena\\nand to limit the scope of cross-examination for abuse of\\ndiscretion. United States v. Tykarsky, 446 F.3d 458, 475\\n(3d Cir. 2006); NLRB v. Frazier, 966 F.2d 812, 815 (3d\\nCir. 1992). Here, the District Court did not abuse that\\ndiscretion.\\n\\n1. The District Court’s Denial of Access to the Mental\\n Health Records\\n In claiming that the District Court’s decision to\\nreview the mental health records in camera before ruling\\non their admissibility violated his rights under both the\\nFifth and Sixth Amendments, Brand specifically argues\\nthat his right to confront the witness was impeded because\\nhe was denied access to records he could have used to\\nimpeach the witness. This very argument was considered\\nand rejected by a plurality of the Supreme Court in Ritchie,\\nwhich noted that “the effect [of the argument] would be to\\ntransform the Confrontation Clause into a constitutionally\\ncompelled rule of pretrial discovery. . . . [T]he right to\\n 140\\n\\fconfrontation is a trial right, designed to prevent improper\\nrestrictions on the types of questions that defense counsel\\nmay ask during cross-examination.” 480 U.S. at 52. We\\nfollow the Ritchie plurality, and conclude that the\\nConfrontation Clause did not require the District Court to\\ngrant Brand access to the witness’s mental health records.\\n Brand next challenges the District Court’s decision\\nto quash the subpoena as a violation of the Fifth\\nAmendment’s Due Process Clause. He concedes that\\nRitchie’s Due Process holding allowed the District Court\\nto review the mental health records in camera without\\ndisclosing them to him. See id. at 59–60 (“A defendant’s\\nright to discover exculpatory evidence does not include the\\nunsupervised authority to search through [the\\nGovernment’s] files. . . . We find that [the defendant’s]\\ninterest . . . in ensuring a fair trial can be protected fully by\\nrequiring that the [privileged] files be submitted only to\\nthe trial court for in camera review.”). Brand instead\\nargues that the District Court abused its discretion by\\nfocusing on “irrelevant facts and spurious symptoms. . . .\\nsuch as ‘hallucinations,’ ” and by “refus[ing] to consider\\nevidence of cognitive impairment and memory issues.”\\nBrand Br. 30. The record reveals, however, that the\\nDistrict Court reviewed the mental health records and\\ndetermined that they “reveal[ed] nothing that calls into\\nquestion [the witness’s] memory, perception, competence,\\nor veracity.” JA150. This hardly amounts to a refusal to\\nconsider evidence of cognitive impairment or memory\\nissues.\\n 141\\n\\f Brand also challenges the legal standard applied by\\nthe District Court, arguing that the court “focused solely\\non whether disclosure would ‘change the outcome’ of\\nBrand’s trial,” Brand Br. 29 (quoting JA148), rather than\\nconsidering “whether the ultimate verdict is one ‘worthy\\nof confidence.’ ” Id. (quoting United States v. Robinson,\\n583 F.3d 1265, 1270 (10th Cir. 2009)). Brand\\nmisleadingly quotes from the District Court’s opinion. The\\nDistrict Court considered, in accordance with Ritchie,\\n“whether there is a reasonable probability that disclosure\\nwould change the outcome” of Brand’s trial, JA148\\n(emphasis added), not whether disclosure would\\nnecessarily change the outcome. As articulated in Ritchie,\\na “ ‘reasonable probability’ is a probability sufficient to\\nundermine confidence in the outcome.” 480 U.S. at 57\\n(quoting United States v. Bagley, 473 U.S. 667, 682 (1985)\\n(Blackmun, J.)). The District Court applied the correct\\nstandard.\\n\\n2. The District Court’s Grant of the Motion in Limine\\n In granting the Government’s motion in limine, the\\nDistrict Court ruled that Brand could not “reference . . .\\n[the witness’s] bipolar disorder or the medications he takes\\nto manage it.” JA156. Yet that ruling placed no restriction\\non Brand’s ability to cross-examine the witness with\\nrespect to “his memory, competence, or truthfulness.” Id.\\nBrand argues, nevertheless, that his Sixth Amendment\\nright “to be confronted with the witnesses against him”\\nwas violated. U.S. Const. amend. VI.\\n\\n 142\\n\\f The Confrontation Clause protects a defendant’s\\nright to cross-examine a witness with respect to any\\ntestimonial statements made by that witness. United States\\nv. Berrios, 676 F.3d 118, 125–26 (3d Cir. 2012) (citing\\nCrawford v. Washington, 541 U.S. 36, 51 (2004), and\\nDavis v. Washington, 547 U.S. 813, 823–24 (2006)). But\\nthe scope of cross-examination is not unlimited, and “[a]\\ndistrict court retains ‘wide latitude insofar as the\\nConfrontation Clause is concerned to impose reasonable\\nlimits on such cross-examination based on concerns about\\n. . . harassment, prejudice, confusion of the issues, the\\nwitness’ safety, or interrogation that is repetitive or only\\nmarginally relevant.’ ” John-Baptiste, 747 F.3d at 211\\n(quoting United States v. Mussare, 405 F.3d 161, 169 (3d\\nCir. 2005)). We review limitations on cross-examination\\nfor abuse of discretion, and reverse “only when the\\nrestriction ‘is so severe as to constitute a denial of the\\ndefendant’s right to confront witnesses against him and . . .\\nis prejudicial to [his] substantial rights.’ ” Id. (alternation\\nin original) (quoting United States v. Conley, 92 F.3d 157,\\n169 (3d Cir. 1996)).\\n In United States v. Chandler, 326 F.3d 210, 219 (3d\\nCir. 2003), we analyzed whether a district court’s decision\\nto limit cross-examination with respect to a witness’s\\nmotivation for testifying violated the Confrontation\\nClause. See also Mussare, 405 F.3d at 169; John-Baptiste,\\n747 F.3d at 211–12. Consistent with Delaware v. Van\\nArsdall, 475 U.S. 673 (1986), we first concluded that “the\\nexposure of a witness’ motivation in testifying is a proper\\n 143\\n\\fand important function of the constitutionally protected\\nright of cross-examination.” Chandler, 326 F.3d at 219–\\n20 (quoting Van Arsdall, 475 U.S. at 678–79). We also\\nnoted that the Confrontation Clause does not prevent a trial\\njudge from imposing reasonable limits on cross-\\nexamination. Id. In reviewing a district judge’s imposition\\nof such limitations, we apply a two-part analysis. As we\\nhave since described, “we inquire into: ‘(1) whether the\\nlimitation significantly limited the defendant’s right to\\ninquire into a witness’s motivation for testifying; and\\n(2) whether the constraints imposed fell within the\\nreasonable limits that a district court has the authority to\\nimpose.’ ” John-Baptiste, 747 F.3d at 211–12 (quoting\\nMussare, 405 F.3d at 169).\\n The same analytical framework is appropriate when\\ndetermining whether a restriction on the cross-\\nexamination of a witness with respect to his memory and\\nperception violates the Confrontation Clause. See Davis v.\\nAlaska, 415 U.S. 308, 316 (1974); Greene v. McElroy, 360\\nU.S. 474, 496 (1959); United States v. Segal, 534 F.2d\\n578, 582 (3d Cir. 1976). Memory and perception, like\\nmotivation for testifying, are central issues affecting the\\ncredibility of any witness, and unreasonable limitations on\\nthe right to cross-examine on those subjects cannot be\\ncountenanced. We therefore ask, paraphrasing Chandler:\\n(1) whether the District Court’s decision to put the\\nwitness’s diagnosis and medications off limits\\nsignificantly impaired Brand’s right to inquire into the\\nwitness’s memory and perception; and (2) whether the\\n 144\\n\\fruling fell within the reasonable limits that the District\\nCourt has the authority to impose.\\n We conclude that the District Court did not err. As\\nan initial matter, the District Court permitted Brand to\\ncross-examine the witness about his memory and\\nperception, and limited cross-examination only with\\nrespect to the witness’s bipolar disorder and the\\nmedications he was taking to treat that condition. Brand\\nwas free to question the witness about his memory and\\nperception, and indeed did so. The restriction on asking\\nthe witness about his bipolar disorder was not a significant\\nlimitation of Brand’s right to inquire into the witness’s\\nmemory or perception. Moreover, as the District Court\\npointed out, Brand failed to show how inquiry into the\\nwitness’s bipolar disorder would be useful for\\nimpeachment purposes. See JA154.\\n\\n Given that failure, the District Court’s limits on\\ncross-examination were reasonable. The Court concluded,\\nafter reviewing the evidence submitted by Brand and the\\nwitness’s mental health records, that any mention of the\\nwitness’s bipolar disorder would “only be designed to\\nconfuse the jury or to stigmatize him unfairly because of a\\n‘mental problem’ without any countervailing probative\\nvalue.” JA155. The District Court did not abuse its\\ndiscretion in limiting Brand’s cross-examination on a topic\\nthat would be far more prejudicial than probative. See\\nTykarsky, 446 F.3d at 476–77 (“[T]he District Court acted\\n\\n\\n 145\\n\\fwell within its discretion to restrict irrelevant and\\nconfusing testimony.”).\\n All of this is not to suggest that a witness’s mental\\nhealth is always off limits. The appropriate course in any\\ngiven case must be determined from the facts and\\ncircumstances surrounding that case and the witness’s\\nparticular condition. See United States v. George, 532 F.3d\\n933, 937 (D.C. Cir. 2008) (“The days are long past when\\nany mental illness was presumed to undermine a witness’s\\ncompetence to testify. . . . [M]ental illness [is] potentially\\nrelevant in a broad[] range of circumstances . . . . [But]\\nsome indication is needed that a particular witness’s\\nmedical history throws some doubt on the witness’s\\ncompetence or credibility.”). Here, Brand failed to show,\\nthrough mental health records or otherwise, any\\nparticularized reason to doubt the credibility of the witness\\nfor medical reasons.\\n\\n Brand states that the witness provided “the only\\nevidence offered” on the intent element of his conspiracy\\nconviction and that he should therefore be entitled to\\nunrestricted cross-examination. Brand Br. 12 n.3. Yet no\\nmatter the importance of a witness to any party, a district\\ncourt may always place reasonable limits on cross-\\nexamination to avoid “harassment, prejudice, confusion of\\nthe issues, the witness’ safety, or interrogation that is\\nrepetitive or only marginally relevant.” John-Baptiste, 747\\nF.3d at 211 (citation omitted).\\n\\n\\n 146\\n\\f We conclude that the District Court did not abuse\\nits discretion in restricting the scope of Brand’s cross-\\nexamination of the cooperating witness.\\n\\n X. The Government’s Cross-Appeal\\n The jury convicted Fattah, Vederman, and Bowser\\nof bank fraud, 18 U.S.C. § 134430 (Count 19) and making\\nfalse statements to a financial institution, 18 U.S.C.\\n§ 1014 31 (Count 20). In response to post-trial motions, the\\nDistrict Court granted a judgment of acquittal on both\\ncounts under Fed. R. Crim. P. 29, concluding that the\\n\\n30\\n “Whoever knowingly executes, or attempts to execute,\\na scheme or artifice . . . to defraud a financial institution\\n. . . shall be fined not more than $1,000,000 or imprisoned\\nnot more than 30 years, or both.” The definition of\\n“financial institution” for purposes of § 1344 is set forth at\\n18 U.S.C. § 20, and includes “a credit union with accounts\\ninsured by the National Credit Union Share Insurance\\nFund” and “a mortgage lending business (as defined in\\nsection 27 of this Title).” 18 U.S.C. §§ 20(2), (10).\\n31\\n “Whoever knowingly makes any false statement or\\nreport, or willfully overvalues any land, property or\\nsecurity, for the purpose of influencing in any way the\\naction of . . . a Federal credit union . . . any institution the\\naccounts of which are insured by . . . the National Credit\\nUnion Administration Board . . . or a mortgage lending\\nbusiness . . . shall be fined not more than $1,000,000 or\\nimprisoned not more than 30 years, or both.”\\n 147\\n\\fevidence was insufficient to establish that the Credit\\nUnion Mortgage Association (CUMA), the entity to whom\\nFattah, Vederman, and Bowser made the false statements,\\nis a “financial institution,” or, more specifically, a\\n“mortgage lending business” as defined in 18 U.S.C. § 27.\\nThe Government claims that, viewing the evidence in the\\nlight most favorable to it, the District Court erred and that\\nCUMA is, indeed, a “mortgage lending business.” We\\nagree. Because the evidence is sufficient to support the\\njury’s verdict, we will remand so Fattah and Vederman\\nmay be resentenced on these charges.32\\n\\n A. CUMA is a Mortgage Lending Business\\n In reviewing the District Court’s post-verdict\\njudgment of acquittal under Rule 29 of the Federal Rules\\nof Civil Procedure, we consider whether the evidence,\\nwhen viewed in a light most favorable to the government,\\nsupports the jury’s verdict. United States v. Dixon, 658\\nF.2d 181, 188 (3d Cir. 1981). Our standard of review is the\\nsame as that applied by the District Court, and we must\\nuphold the jury’s verdict unless no reasonable juror could\\naccept the evidence as sufficient to support the defendant’s\\nguilt beyond a reasonable doubt. United States v.\\nColeman, 811 F.2d 804, 807 (3d Cir. 1987).\\n\\n32\\n Because the Government did not file an appeal as to\\nBowser, the cross-appeal is limited to Fattah and\\nVederman. The judgment of acquittal as to Bowser is\\ntherefore unaffected by our ruling today.\\n 148\\n\\f Initially, the grand jury’s indictment alleged that\\nCUMA is a financial institution because it is federally\\ninsured. JA302–03. At trial, however, the jury was\\ninstructed that CUMA could qualify as a financial\\ninstitution either because it is federally insured or because\\nit is a “mortgage lending business.” See JA111, 401–02. A\\n“mortgage lending business” is “an organization which\\nfinances or refinances any debt secured by an interest in\\nreal estate, including private mortgage companies and any\\nsubsidiaries of such organizations, and whose activities\\naffect interstate or foreign commerce.” 18 U.S.C. § 27.\\n\\n At trial, CUMA’s president and CEO, Eddie Scott\\nToler, testified that CUMA is not federally insured.\\nJA4235. The Government therefore attempted to prove\\nthat CUMA is a “mortgage lending business” by\\npresenting evidence that CUMA funds mortgages and then\\nsells them in a secondary market.\\n\\n Toler also testified that CUMA is a “credit union\\nservice organization”—a for-profit company owned by 48\\ncredit unions, which serves small credit unions that do not\\nhave the infrastructure or in-house expertise to handle\\nmortgage loans themselves. JA4235. According to Toler,\\n“[CUMA] exclusively provide[s] First Trust Residential\\nMortgage loaning [sic] services, all the way from the\\norigination of the mortgage loan through processing,\\nunderwriting, closing and access to the secondary market\\nwhere—and we’re selling the mortgage loan on the\\nsecondary market.” JA4236–37. In jurisdictions in which\\n\\n 149\\n\\fCUMA is licensed, 33 CUMA holds the mortgage for a\\nlimited period, generally from two to thirty days, and then\\nsells the mortgage either to a partner credit union or on the\\nsecondary market. JA4240.\\n\\n The District Court concluded that CUMA is not a\\n“mortgage lending business” because “[t]he record is\\ndevoid of any evidence that CUMA finances or refinances\\nany debt.” JA113. Concluding that CUMA “simply is a\\nloan processor for various credit unions which do the\\nfinancing or refinancing,” id., the District Court ruled that\\nCUMA’s “activity does not constitute the financing or\\nrefinancing of any debt. CUMA is not the mortgagee. It is\\nmerely selling the debt instrument to a third party.” JA114.\\n We cannot agree with the District Court’s view of\\nthe evidence. Toler testified that in “Maryland, D.C., and\\nVirginia . . . all of the loans are closed in the name of\\nCUMA.” JA4238–39. As Toler described it, CUMA\\nborrows on a line of credit to fund the loan, and when the\\nloan is sold, CUMA pays off its line of credit. JA4239–40.\\nSo contrary to the District Court’s assessment, the\\nevidence, viewed in a light most favorable to the\\nGovernment, shows that CUMA is indeed the\\nmortgagee—at least during the time from closing until the\\nloan is sold to a partner credit union or on the secondary\\nmarket. The fact that CUMA funds the closing and then\\n\\n33\\n CUMA is licensed in Maryland, Washington, D.C., and\\nVirginia. JA4238.\\n 150\\n\\fholds the mortgage, even for a brief time, is sufficient to\\nsupport a conclusion that CUMA is “an organization\\nwhich finances or refinances any debt secured by an\\ninterest in real estate.” 18 U.S.C. § 27.\\n\\n Fattah and Vederman attempt to refute the argument\\nthat CUMA engages in financing mortgages by focusing\\non Toler’s testimony that CUMA “doesn’t actually have\\nany money to fund these mortgage loans.” JA4239; see\\nFattah Reply Br. 38, Vederman Reply Br. 36. But Toler\\ntestified that CUMA employs a credit line to borrow the\\nfunds necessary to close on mortgages. See JA4239. That\\nCUMA incurs debt to finance mortgages hardly\\nundermines a conclusion that CUMA finances mortgages.\\nIndeed, it is the very nature of modern banking that\\nfinancial institutions do not hold cash reserves equal to the\\nfull amount of their liabilities. See, e.g., Timothy C.\\nHarker, Bailment Ailment: An Analysis of the Legal Status\\nof Ordinary Demand Deposits in the Shadow of the\\nFinancial Crisis of 2008, 19 Fordham J. Corp. & Fin. L.\\n543, 561 (2014) (“[F]ractional reserve banking . . . is the\\nde facto standard for all modern banks.”).\\n\\n Vederman also argues that, even if CUMA acts as a\\nmortgage lending business in some transactions, it was not\\nacting as a mortgage lending business in this transaction.\\nVederman points to Toler’s testimony that, in a state in\\nwhich CUMA is not licensed, the mortgage is closed in the\\nname of a credit union. In such cases, the credit union, and\\nnot CUMA, owns the mortgage for the short period before\\n\\n 151\\n\\fthe loan is sold on the secondary market. JA4241. CUMA\\nis not licensed in the Commonwealth of Pennsylvania. See\\nid. Thus, according to Vederman, CUMA was acting in its\\ncapacity as a mortgage servicing company for Fattah’s\\nvacation home purchase and did not—and could not—\\nfinance Fattah’s mortgage. That would mean that CUMA\\ncould not have been a victim of a crime against a financial\\ninstitution in this instance: “When an entity is not\\nfunctioning as a mortgage lender, the ‘pertinent federal\\ninterest’ behind the statutes is not implicated.” Vederman\\nReply Br. 38 (citation omitted).\\n\\n The Government responds that neither of the\\nstatutes of conviction requires that the fraud or false\\nstatement occur in connection with the same transaction\\nthat places the entity within the definition of “financial\\ninstitution.” Gov’t Fourth Step Br. 4. We agree with the\\nGovernment.\\n\\n Both § 1344 and § 1014 protect entities that fall\\nwithin the definition of “financial institution” and are\\notherwise quite broad in their application. See Loughrin v.\\nUnited States, 134 S. Ct. 2384, 2389 (2014) (interpreting\\n§ 1344 as not requiring specific intent to defraud a bank);\\nUnited States v. Boren, 278 F.3d 911, 914 (9th Cir. 2002)\\n(“[Section 1014’s] reach is not limited to false statements\\nmade with regard to loans, but extends to any application,\\ncommitment or other specified transaction.”). Neither\\nstatute is expressly limited in the manner that Vederman\\nsuggests. Williams v. United States, 458 U.S. 279, 284\\n\\n 152\\n\\f(1982) (“To obtain a conviction under § 1014, the\\nGovernment must establish two propositions: it must\\ndemonstrate (1) that the defendant made a ‘false statement\\nor report,’ . . . and (2) that he did so ‘for the purpose of\\ninfluencing in any way the action of [a described financial\\ninstitution] upon any application, advance, . . .\\ncommitment, or loan.’ ”); United States v. Leahy, 445 F.3d\\n634, 646 (3d Cir. 2006) (“The purpose of the bank fraud\\nstatute is to protect the ‘financial integrity of [banking]\\ninstitutions.’ ”) (citing S. Rep. No. 98-225, at 377 (1983),\\nas reprinted in 1984 U.S.C.C.A.N. 3517), abrogated on\\nother grounds by Loughrin, 134 S. Ct. at 2389.\\n In support of his position, Vederman relies on\\nUnited States v. Devoll, 39 F.3d 575 (5th Cir. 1994), in\\nwhich the Fifth Circuit concluded that § 1014 (false\\nstatements to a financial institution) is not intended to\\ncapture fraud unrelated to an entity’s lending activities,\\nand therefore held that it “applies only to actions involving\\nlending transactions.” Id. at 580. The Fifth Circuit stated:\\n [W]e are not persuaded that the statute\\n imposes liability whenever a defendant’s\\n false statement was intended to interfere with\\n any activity of a financial institution; such a\\n broad interpretation of section 1014\\n presumably would encompass fraud or false\\n representations having nothing to do with\\n financial transactions, such as fraud in an\\n employment contract or, for example, in a\\n\\n 153\\n\\f contract to provide goods or services for\\n custodial care, premises repair, or renovation.\\nId.\\n\\n Yet a majority of circuits, including our own, have\\ndeclined to follow Devoll’s suggestion that § 1014 is\\nrestricted to lending transactions. As the Ninth Circuit has\\nheld, “we join at least six of our sister circuits—the First,\\nThird, Fourth, Sixth, Seventh, and Tenth—in holding that\\n18 U.S.C. § 1014 is not limited to lending transactions,\\nand reject the minority rule to the contrary.” Boren, 278\\nF.3d at 915. And even if we were to adopt Devoll’s narrow\\nconstruction of § 1014 to lending transactions, that would\\nnot resolve the more specific question of whether the\\ndefrauded entity must be defined as a “mortgage lending\\nbusiness” by virtue of the specific transaction in which the\\nfalse statements arose.\\n Recently, the Eighth Circuit addressed precisely\\nthis issue. In United States v. Springer, 866 F.3d 949 (8th\\nCir. 2017), that Court considered the defendant’s appeal\\nfrom the district court’s denial of a Rule 29 motion on\\ngrounds that GMAC, the entity defrauded, was not a\\n“financial institution.” The Court upheld the district\\ncourt’s determination that the evidence was sufficient to\\nestablish that GMAC is in the mortgage lending business\\nbecause there was testimony that “it had made hundreds or\\nthousands of loans secured by mortgages in 2010 and 2011\\nin states all across the country,” which established that its\\nactivities affect interstate commerce. Id. at 953. It was not\\n 154\\n\\fdeterminative that GMAC did not own the specific loan at\\nissue in the case: “we discern no requirement in the\\ndefinition of ‘mortgage lending business’ that the business\\nown the particular loan in question; it need only finance or\\nrefinance any debt secured by an interest in real estate, or,\\nin other words, be in the interstate mortgage lending\\nbusiness in general.” Id.\\n\\n In our view, the Eighth Circuit’s analysis is correct.\\nWe therefore adopt that Court’s reasoning in Springer and\\nconclude that it is of no moment that CUMA did not\\nfinance the mortgage at issue in Fattah’s case. CUMA is a\\n“mortgage lending business,” and that alone suffices to\\nsupport the convictions under §§ 1014 and 1344.\\n\\n B. Sufficiency of the Evidence\\n Finally, Vederman argues that, even if CUMA is a\\nfinancial institution, the judgment of acquittal should\\nstand because the Government did not put forth any\\nevidence that he made a false representation to CUMA.34\\nSpecifically, Vederman argues that the title to the Porsche\\nwas actually changed to his name, making it a “true sale”\\nas a matter of law, without regard to whether Fattah’s wife\\n\\n34\\n Although Vederman presented this argument in his Rule\\n29 motion, the District Court did not need to reach it in the\\ncontext of Counts 19 and 20 because the Court granted the\\nmotion on the ground that CUMA is not a financial\\ninstitution. The District Court rejected the argument as to\\nCounts 16, 17, and 18. See JA100–02.\\n 155\\n\\fcontinued to retain possession. See United States v.\\nCastro, 704 F.3d 125, 139 (3d Cir. 2013) (holding in\\nanother context that “the government must be able to show\\nthat [the defendant] made a statement to government\\nagents that was untrue, and the government cannot satisfy\\nthat burden by showing that the defendant intended to\\ndeceive, if in fact he told the literal truth”); see also 75 Pa.\\nCons. Stat. § 102 (defining “owner” as “[a] person, other\\nthan a lienholder, having the property right in or title to a\\nvehicle”).\\n\\n The Government responds that, regardless of\\nwhether it is legally possible for one person to hold a title\\nwhile a different person possesses the vehicle, the jury was\\npermitted to consider all the circumstances in deciding\\nwhether the Porsche sale was a sham. We agree.\\n\\n First, as the District Court observed, it was unclear\\nas to whether the title had been properly executed under\\nPennsylvania law. For instance, Fattah’s wife never\\nappeared before a notary. 35 JA101. In addition, title 75,\\nsection 1111(a) of the Pennsylvania Consolidated Statutes\\nrequires that, “[i]n the event of the sale or transfer of the\\nownership of a vehicle within this Commonwealth, the\\nowner shall . . . deliver the certificate to the transferee at\\n\\n35\\n Vederman argues that it is of no significance that the\\nparties did not appear before a notary as the statute\\nrequires, but he offers cases only from states other than\\nPennsylvania to support this proposition.\\n 156\\n\\fthe time of the delivery of the vehicle.” And, the transferee\\nmust, within twenty days of the assignment of the vehicle,\\napply for a new title. See 75 Pa. Cons. Stat. § 1111(b).\\nNeither of these requirements was fulfilled. Finally,\\nVederman never registered the Porsche in his name with\\nthe Department of Motor Vehicles. See id.; JA4254.\\n Second, and more importantly, even if the title had\\nbeen properly transferred to Vederman, the title provisions\\nof the Pennsylvania Motor Vehicle Code “were [not]\\ndesigned to establish conclusively the ownership of an\\nautomobile.” Weigelt v. Factors Credit Corp., 101 A.2d\\n404, 404 (Pa. Super. Ct. 1953). Indeed, “[t]he purpose of\\na certificate of title is not to conclusively establish\\nownership in a motor vehicle, but rather to establish the\\nperson entitled to possession.” Speck Cadillac-Olds, Inc.\\nv. Goodman, 95 A.2d 191, 193 (Pa. 1953). Thus, a title\\nprovides evidence of ownership; it is not dispositive of the\\nissue. Wasilko v. Home Mut. Cas. Co., 232 A.2d 60, 61\\n(Pa. Super. Ct. 1967).\\n Vederman’s argument that the title in his name\\nconstitutes conclusive evidence of ownership rests upon\\nan erroneous conclusion that the jury was prohibited from\\nconsidering all the circumstances of the transfer. As the\\nDistrict Court observed, though, Pennsylvania’s\\nCommonwealth Court has held that “[w]hether a\\ntransferor has transferred ownership of a motor vehicle to\\na transferee is a factual determination to be made by the\\ncourt below.” Dep’t. of Transp. v. Walker, 584 A.2d 1080,\\n\\n 157\\n\\f1082 (Pa. Commw. Ct. 1990). Thus, the signed certificate\\nof title was appropriately treated as one piece of evidence\\nfor the jury to consider in assessing the validity of the\\nvehicle transfer. Considered in the light most favorable to\\nthe Government, the totality of the evidence is sufficient\\nto support the jury’s conclusion that the Porsche sale was\\na sham.\\n\\n XI. Prejudicial Spillover\\n Finally, Fattah, Vederman, Nicholas, and Brand\\neach contend that their convictions on various counts\\nresulted from prejudicial spillover. We are not persuaded.\\n We exercise plenary review over a district court’s\\ndenial of a claim of prejudicial spillover, United States v.\\nLee, 612 F.3d 170, 178–79 (3d Cir. 2010), and we apply a\\ntwo-step test when reviewing such a claim. United States\\nv. Wright, 665 F.3d 560, 575 (3d Cir. 2002). First, a court\\nmust consider “whether the jury heard evidence that would\\nhave been inadmissible at a trial limited to the remaining\\nvalid count[s].” Id. (quoting United States v. Cross, 308\\nF.3d 308, 317 (3d Cir. 2002)). The second step requires\\nthat we “ask whether that evidence (the ‘spillover\\nevidence’) was prejudicial.” Id. We consider four factors:\\n“whether (1) the charges are intertwined with each other;\\n(2) the evidence for the remaining counts is sufficiently\\ndistinct to support the verdict on these counts; (3) the\\nelimination of the invalid count [will] significantly\\nchange[] the strategy of the trial; and (4) the prosecution\\nused language of the sort to arouse a jury.” Id. (quoting\\n 158\\n\\fUnited States v. Murphy, 323 F.3d 102, 118 (3d Cir.\\n2003)); see also United States v. Pelullo (Pellulo II), 14\\nF.3d 881, 898–99 (3d. Cir. 1994). These four factors are\\nconsidered in a light “somewhat favorable to the\\ndefendant.” Wright, 665 F.3d at 575 (quoting Murphy, 323\\nF.3d at 122); see also Gov’t Br. 198 (same).\\n\\n A. Fattah’s Claim of Prejudicial Spillover\\n Fattah argues that he suffered prejudicial spillover\\non the remaining counts of conviction in light of (1)\\nevidence pertinent to the alleged Vederman bribery\\nschemes that is now arguably inadmissible under\\nMcDonnell; and (2) “the government’s flawed RICO\\nconspiracy theory.” Fattah Br. 50, 64. Fattah’s argument\\nis undercut substantially because of our determination that\\nMcDonnell requires a new trial for Counts 16, 17, 22, and\\n23 and our decision to affirm the RICO conspiracy\\nconviction. The only possible spillover left to consider is\\nthe evidence pertaining to Fattah’s arranging a meeting\\nbetween Vederman and the U.S. Trade Representative,\\nRon Kirk, which in light of McDonnell is now arguably\\ninadmissible.36\\n\\n The evidence of the Kirk meeting admitted during\\nthis five-week trial was limited. Although this evidence\\n\\n36\\n Nothing in this opinion is intended to foreclose the\\npossibility that evidence of the Kirk meeting may be\\nadmissible on retrial for some purpose other than as proof\\nof an official act.\\n 159\\n\\fwas part of the Government’s proof as to both the RICO\\nand the bribery related charges, there is more than\\nsufficient—and distinct —evidence to support Fattah’s\\nconviction on all the other counts. In our view, eliminating\\nany evidence of the Kirk meeting would not have altered\\nthe strategy of the trial, nor should it significantly change\\nthe strategy for any new trial that may be held. Because\\nFattah has not pointed us to any argument by the\\nprosecution relating to this meeting that could have\\ninflamed the jury, we conclude that Fattah’s prejudicial\\nspillover claim fails. Like the District Court, we presume\\nthat the jury followed the Court’s instructions to consider\\nand weigh separately the evidence on each count as to each\\ndefendant and not to be swayed by evidence pertaining to\\nother defendants. 37\\n\\n B. Vederman’s Assertion of Prejudicial Spillover\\n Because the District Court acquitted Vederman of\\nthe RICO charge, Vederman argues that he was “severely\\nprejudiced by the presentation to the jury of a legally\\nflawed racketeering conspiracy charge,” and as a\\nconsequence his bribery and money laundering\\n\\n37\\n We likewise reject Brand’s prejudicial spillover\\narguments. See Brand Br. 6 (“Brand adopts the significant\\nissue advanced by his co-appellant pursuant to Fed. R.\\nApp. P. 28(i) that improper jury instructions and the\\nresulting spillover of related improperly admitted\\nevidence and argument unfairly prejudiced Brand.”).\\n 160\\n\\fconvictions should be overturned. Vederman Br. 46. In\\nresponse to the Government’s appeal of the District\\nCourt’s Rule 29 acquittal on Counts 19–20 involving\\nCUMA, Vederman asserts that these two counts also were\\naffected by spillover evidence because the Government’s\\ntheory tied the bribery charges to the actions taken to\\ndefraud CUMA. In that we are vacating Vederman’s\\nconvictions of Counts 16–18 and 22–23 based on\\nMcDonnell and remanding for further proceedings, we\\nneed address only Vederman’s argument of prejudicial\\nspillover as it relates to the charges involving CUMA in\\nCounts 19–20, charges that we will reinstate.\\n The District Court’s acquittal of Vederman on the\\nRICO count establishes that step one of the Wright\\nspillover test has been met. “[T]he jury heard evidence that\\nwould have been inadmissible at a trial limited” to the\\nbribery and CUMA-related counts. Wright, 665 F.3d at\\n575 (quoting Cross, 308 F.3d at 317).\\n\\n Wright’s second step requires “ask[ing] whether\\nthat evidence (the ‘spillover evidence’) was prejudicial.”\\nId. Vederman submits that the RICO, bribery, and CUMA-\\nrelated charges were intertwined “in that the acts relating\\nto the alleged bribery scheme were also charged as\\n‘predicates’ under RICO.” Vederman Br. 49. We disagree.\\n\\n To be sure, the RICO, bribery, and CUMA Counts\\nare related to one another. But in this instance, mere\\nrelatedness is not enough to demonstrate the foundation\\nnecessary for spillover. This is so because the bribery\\n 161\\n\\fcharges were a predicate to the RICO charge. In other\\nwords, the jury had to determine if Vederman was guilty\\nof bribery, and the jury then used that “predicate” to\\nconsider whether he was also guilty of the RICO\\nconspiracy. Thus, the necessarily tiered structure of the\\nquestions presented to the jury refute Vederman’s\\nargument that the counts were intertwined.\\n\\n That the bribery charges were predicates for the\\nRICO conspiracy further demonstrates that the “evidence\\nfor the different counts was sufficiently distinct to support\\nthe verdict on other separate counts.” Pelullo II, 14 F.3d at\\n898. Regardless of the evidence pertaining solely to the\\nRICO conviction, the evidence supporting both the bribery\\ncharges and the charges involving CUMA in Counts 19–\\n20 would have remained the same.\\n\\n The next factor we address is “whether the\\nelimination of the count on which the defendant was\\ninvalidly convicted would have significantly changed the\\n[defendant’s] strategy of the trial.” Id. As Vederman\\nargues, “the RICO charge interfered with Vederman’s\\ncentral defense to the bribery charge—that his gestures\\ntoward Fattah ‘were motivated purely by friendship.’ ”\\nVederman Reply Br. 28 (citing Gov’t Br. 200). In other\\nwords, the “RICO count made it dangerous to unduly\\nemphasize [Vederman’s] close friendship” with Fattah. Id.\\nFrom Vederman’s perspective, “a bribery-only trial would\\nhave reduced this danger and allowed a freer presentation\\nof the defense.” Id.\\n\\n 162\\n\\f It is quite likely that Vederman’s claim of friendship\\nwould have been less risky as a litigation strategy if he had\\nnot been facing a RICO charge. But Vederman\\nnevertheless chose to take that risk and fully presented his\\nfriendship argument to the jury. Moreover, while\\nVederman’s reliance on friendship might have helped him\\ndefend against the bribery charges, that friendship would\\nnot have altered the evidence pertaining to Counts 19–20\\ninvolving CUMA. Whether done for friendship or some\\nother reason, submitting fraudulent information to a\\nfinancial institution is unlawful.\\n\\n Finally, we “examine the charges, the language that\\nthe government used, and the evidence introduced during\\nthe trial to see whether they are ‘of the sort to arouse a\\njury.’ ” Pelullo II, 14 F.3d at 899 (quoting United States v.\\nIvic, 700 F.2d 51, 65 (2d Cir. 1983)). Vederman points out\\nthat Fattah was presented as “a backslapping, corrupt party\\nboss,” with “predictable spillover to his friend and\\nassociate, Vederman.” Vederman Br. 50 (quoting United\\nStates v. Murphy, 323 F.3d 102, 118 (3d Cir. 2003)). But\\nthis description was of Fattah, not Vederman. Vederman\\ncites other examples of prejudicial, pejorative language in\\nthe Government’s closing arguments. At one point, the\\nGovernment referred to “conspirators engaged in what can\\nonly be described as a white collar crime spree from\\nPhiladelphia all the way to Washington, D.C.” and\\npromised “to untangle the webs of lies and deception that\\nthese conspirators spun.” Vederman Br. 51 (quoting\\nJA5295, 5297). Whatever rhetorical flair these words\\n 163\\n\\fcontained, they did not obscure the evidence which\\nindependently supported the convictions for bank fraud at\\nCount 19 and for making false statements to CUMA at\\nCount 20. Accordingly, because we presume that the jury\\nfollowed the District Court’s instruction to consider and to\\nweigh separately the evidence on each count and as to each\\ndefendant, and because the evidence supporting the\\nCUMA-related charges in Counts 19–20 is sufficiently\\ndistinct from the RICO conspiracy, we conclude that\\nVederman’s spillover argument is unavailing.38\\n\\n XII. Conclusion\\n We will vacate the convictions of Chaka Fattah, Sr.\\nand Herbert Vederman as to Counts 16, 17, 18, 22, and 23.\\n\\n38\\n Nicholas adopted “pertinent portions” of the prejudicial\\nspillover arguments advanced by Vederman and Fattah.\\nNicholas Br. 65. Her spillover claim has no more merit\\nthan theirs. Nicholas’s involvement in the RICO\\nconspiracy was distinct from the bribery charges, which\\ndid not unfairly influence the other counts. As to\\nNicholas’s assertion that the NOAA charges did not\\nbelong in the indictment and should have been tried\\nseparately, we fail to see how this relates to a claim of\\nprejudicial spillover. To the extent it challenges the\\nDistrict Court’s denial of Nicholas’s motion for a\\nseverance, Nicholas has failed to provide legal support for\\nsuch a contention. See Fed. R. App. P. 28(a)(8)(A); United\\nStates v. Irizarry, 341 F.3d 273, 305 (3d Cir. 2003).\\n 164\\n\\fFattah and Vederman may be retried on these counts\\nbefore a properly instructed jury. We will also reverse the\\nDistrict Court’s judgment of acquittal on Counts 19 and\\n20. The convictions of Chaka Fattah, Sr. and Herbert\\nVederman will be reinstated, and the case will be\\nremanded for sentencing on those counts. In all other\\nrespects, the judgments of the District Court will be\\naffirmed.\\n\\n\\n\\n\\n 165\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":63,"cells":{"id":{"kind":"number","value":8443856,"string":"8,443,856"},"name":{"kind":"string","value":"United States v. Karen NICHOLAS"},"name_abbreviation":{"kind":"string","value":"United States v. Nicholas"},"decision_date":{"kind":"string","value":"2019-01-16"},"docket_number":{"kind":"string","value":"No. 16-4410"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Smith\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/8415283/\", \"author_raw\": \"\"}]}"},"judge1":{"kind":"string","value":"SMITH"},"judge2":{"kind":"string","value":"SMITH"},"judge3":{"kind":"string","value":""},"exactly_three_caps":{"kind":"number","value":0,"string":"0"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/8443856/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":0,"string":"0"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: United States v. Karen NICHOLAS\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-16\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: United States v. Karen NICHOLAS\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-16\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":64,"cells":{"id":{"kind":"number","value":4582573,"string":"4,582,573"},"name":{"kind":"string","value":"UNITED STATES of America, Appellant v. Raymont WRIGHT"},"name_abbreviation":{"kind":"string","value":"United States v. Raymont Wright"},"decision_date":{"kind":"string","value":"2019-01-17"},"docket_number":{"kind":"string","value":"17-1972"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Shwartz, Nygaard\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9887874/\", \"author_raw\": \"\"}, {\"author\": \"\", \"type\": \"040dissent\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9887875/\", \"author_raw\": \"\"}, {\"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-1972\\n _____________\\n\\n UNITED STATES OF AMERICA,\\n\\n Appellant\\n\\n v.\\n\\n RAYMONT WRIGHT\\n\\n ______________\\n\\n ON APPEAL FROM THE\\n UNITED STATES DISTRICT COURT\\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\\n (D.C. No. 2-14-cr-00292-001)\\n District Judge: Hon. Cathy Bissoon\\n ______________\\n\\n Argued May 24, 2018\\n ______________\\n\\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\\n Judges.\\n\\n (Opinion Filed: January 17, 2019)\\n\\n ______________\\n\\n OPINION OF THE COURT\\n ________________\\n\\nDonovan J. Cocas, Esq. [ARGUED]\\nJane M. Datttilo, Esq.\\nLaura S. Irwin, Esq.\\nOffice of the United States Attorney\\n700 Grant Street\\nSuite 4000\\nPittsburgh, PA 15219\\n\\n Attorney for Appellant\\n\\nRenee Pietropaolo, Esq. [ARGUED]\\nLisa B. Freeland, Esq.\\nAkin Adepoju, Esq.\\nOffice of the Federal Public Defender\\n1001 Liberty Avenue\\n1500 Liberty Center\\nPittsburgh, PA 15222\\n\\n Attorneys for Appellee Raymont Wright\\n\\nLawrence S. Lustberg, Esq. [ARGUED]\\nGibbons, P.C.\\nOne Gateway Center\\nNewark, NJ 07102\\n\\n Attorney for Amicus Appellee National Association of\\n Criminal Defense Lawyers\\n\\n\\n\\n\\n 2\\n\\nSHWARTZ, Circuit Judge.\\n\\n The District Court barred a retrial of and dismissed the\\nindictment against Defendant Raymont Wright with prejudice\\nafter two juries failed to reach a verdict. The Court did so\\nrelying on its inherent authority, but without finding that any\\nmisconduct had occurred or that Wright would suffer any\\nprejudice beyond the general anxiety and inconvenience of\\nfacing a retrial. Under such circumstances, the Court lacked\\nthe inherent authority to bar the retrial and dismiss the\\nindictment. Therefore, we will reverse the order dismissing the\\nindictment and remand for further proceedings.\\n\\n I\\n\\n In December 2014, Wright was charged with being a\\nfelon in possession of a firearm, in violation of 18 U.S.C.\\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\\nMay 2016. The jury was unable to reach a verdict. A second\\ntrial was held in March 2017, and that jury was also unable to\\nreach a verdict.\\n\\n During both trials, the jury heard evidence from police\\nofficers about Wright’s actions on July 24, 2014. 1 That\\nevening, five Pittsburgh Police detectives were patrolling in\\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\\nwere in the lead car, and Detectives Fallert and Goob were in\\nthe second car. Around 8:30 p.m. (when it was still daylight),\\nFallert and Goob saw a man, later identified as Wright, driving\\n\\n 1\\n The following facts are drawn largely from the\\nevidence presented at the first trial.\\n\\n\\n\\n\\n 3\\n\\na car in the opposite direction well above the 25-mile-per-hour\\nspeed limit. The detectives turned around to follow Wright,\\nand Wright sped up and turned onto a loop-shaped road. The\\ndetectives pursued Wright, who fled at a high speed and ran at\\nleast four stop signs. The lead car lost sight of Wright shortly\\nthereafter and discontinued pursuit.\\n\\n Officers in the lead car then noticed skid marks\\nsuggesting that a car had intended but failed to make a left turn\\nat the end of a street. Officers thereafter came upon Wright’s\\ncar in a parking lot below. The car had gone through a fence,\\nover a hillside, and into the lot. The car hit two unoccupied\\nparked cars, its tires blew out, and its windows were down.\\n\\n Detectives Baker and Henson exited the vehicle at the\\ntop of the hill and remained where Wright’s car broke through\\nthe fence, and Detective Kennedy drove his car down to the\\nparking lot’s entrance. Baker and Henson testified that they\\nsaw Wright search around the rear passenger seat of the car,\\nback out of the vehicle with a black semi-automatic handgun\\nin his right hand, and try to “rack the slide,” which can insert\\nor remove a round from the chamber. App. 118-19. They had\\ntheir weapons drawn and told Wright to drop the gun. At first,\\nWright merely stepped back, but he eventually tossed the gun\\nto the side, backed away, and lied on the ground. Pittsburgh\\npolice officer Elliott and his partner, who heard of the crash on\\nthe radio, were the first to reach Wright, and saw him lying on\\nthe ground with a handgun next to him. Henson stated that\\nwhen he made it down to the parking lot, he heard Wright say\\nto him, “Hey, big guy. You won this time or you won this\\nround, something of that nature. He [Wright] said: You feel\\nme? You won this time,” which Henson understood to mean\\nthat he had just avoided a shootout or that he caught Wright\\n\\n\\n\\n\\n 4\\n\\nafter the pursuit. App. 125. Henson subsequently took custody\\nof the gun and noticed the slide lever was bent, and when he\\nstraightened it, saw the gun was loaded with eight rounds, and\\none in the chamber. 2\\n\\n At the close of the Government’s case, Wright moved\\nfor a directed verdict, arguing that no reasonable juror could\\nfind beyond a reasonable doubt that Wright possessed the\\nfirearm. The District Court denied the motion because “the\\nevidence does thus far demonstrate that a reasonable juror\\ncould most certainly find the Defendant guilty of the charge in\\nthis case.” App. 171. Wright did not present a case.\\n\\n The jury deliberated for approximately five hours and\\nthen reported to the Court that it was deadlocked. After polling\\nthe jurors to confirm they were deadlocked and further\\ndeliberations would not bring them closer to a unanimous\\nverdict, the District Court declared a mistrial.\\n\\n At Wright’s March 2017 retrial, the Government\\npresented substantially the same evidence. The Government\\nalso called Detective Kennedy and Lieutenant Palermo, who\\nwere at the scene after Wright was arrested, as well as experts\\nwho testified regarding the collection of DNA and fingerprint\\nevidence from firearms to respond to Wright’s argument at the\\nfirst trial that investigators chose not to test the gun for forensic\\nevidence in an effort to cover up that they had planted the gun\\nat the scene.\\n\\n\\n 2\\n The parties stipulated Wright had been convicted of a\\nqualifying felony, and an ATF Special Agent testified about\\nthe gun’s interstate nexus.\\n\\n\\n\\n\\n 5\\n\\n At the close of the Government’s case, Wright again\\nmoved for a judgment of acquittal, which the Court denied\\nbecause “there is sufficient evidence in the record to establish\\nbeyond a reasonable doubt that Mr. Wright possessed the\\nfirearm in the case,” App. 650. Wright did not put on a case.\\n\\n The second jury deliberated for approximately three\\nhours and then reported that it was hopelessly deadlocked. The\\nCourt polled the jury to confirm the deadlock and then\\ndismissed the jury. 3\\n\\n After the Government notified the Court that it intended\\nto retry the case, the Court required the parties to brief\\n“whether the Court, through an exercise of its inherent\\nauthority, should prohibit or permit a second re-trial in this\\ncase.” App. 26. After considering the parties’ arguments, the\\nDistrict Court dismissed the indictment with prejudice, holding\\nthat it “ha[d] the inherent authority, under some circumstances,\\nto dismiss an indictment following multiple mistrials.” United\\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\\nunderlying the Double Jeopardy Clause also applied to a\\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\\n(2) other courts had dismissed indictments in similar\\n\\n 3\\n Wright asserted that in the first trial, jurors voted 8-4\\nfor acquittal, and in the second trial, the jury was evenly split.\\nThe Government asserted that in the first trial, jurors voted 7-\\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\\nnot explain how he obtained these numbers, the Government\\nsaid it obtained them by speaking with the jurors.\\n\\n\\n\\n\\n 6\\n\\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\\nexpressly allows the Government to retry a case after a mistrial,\\nnothing in the rule “limits a court’s inherent supervisory\\nauthority to dismiss an indictment in the interests of\\nfundamental fairness,” id. at *4; and (4) if the Court were to\\nadopt the Government’s position that there are no limit to the\\nnumber of times the Government can retry a defendant, it\\nwould be tantamount to a “type of jury shopping” that a court\\nshould not permit, id. at *4. The District Court also considered\\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\\nconcluded that most factors supported dismissal. 4\\n\\n 4\\n The Abbati factors are\\n\\n (1) the number of prior mistrials and the\\n outcome of the juries’ deliberations, so far as is\\n known; (2) the character of prior trials in terms\\n of length, complexity, and similarity of evidence\\n presented; (3) the likelihood of any substantial\\n difference in a subsequent trial, if allowed;\\n (4) the trial court’s own evaluation of the relative\\n strength of each party’s case; and (5) the\\n professional conduct and diligence of respective\\n counsel, particularly of the prosecuting attorney.\\n The court must also give due weight to the\\n prosecutor’s decision to reprosecute, assessing\\n the reasons for that decision, such as the gravity\\n\\n\\n\\n\\n 7\\n\\n The Government appeals.\\n\\n II 5\\n\\n We review the District Court’s order dismissing the\\nindictment based on the Court’s inherent power for abuse of\\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\\n\\n of the criminal charges and the public’s concern\\n in the effective and definitive conclusion of\\n criminal prosecutions. Conversely, the court\\n should accord careful consideration to the status\\n of the individual defendant and the impact of a\\n retrial upon the defendant in terms of untoward\\n hardship and unfairness.\\n\\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\\nat 521-22). For the reasons set forth herein, we would not\\nadopt Abbati, but even if we were to consider the Abbati\\nfactors, we would conclude that they do not support dismissal\\nin this case.\\n 5\\n The District Court had jurisdiction pursuant to 18\\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\\n§ 3731.\\n 6\\n The phrases “inherent power,” “inherent authority,”\\n“supervisory power,” and “supervisory authority” are all used\\nto describe the basis for a court action seeking to maintain the\\nintegrity of the proceedings that is not directly tethered to a\\nspecific rule, statute, or constitutional provision. See, e.g.,\\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\\n43 (1991) (inherent power); Bank of Nova Scotia v. United\\n\\n\\n\\n\\n 8\\n\\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\\nindictment for abuse of discretion); cf. Chambers v. NASCO,\\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\\nsanctions under its inherent power for abuse of discretion);\\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\\n2005) (“A trial court’s remedy for a discovery violation under\\nits supervisory powers is reviewed for abuse of discretion.”).\\nA district court abuses its discretion when it makes an errant\\nconclusion of law, an improper application of law to fact, or a\\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\\n\\n A\\n\\n Federal Rule of Criminal Procedure 31 allows the\\nGovernment to retry a case if the court declares a mistrial after\\na jury announces it is unable to reach a verdict. Specifically,\\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\\non one or more counts, the court may declare a mistrial on\\nthose counts. The government may retry any defendant on any\\ncount on which the jury could not agree.” Fed. R. Crim. P.\\n31(b)(3). The word “may” means that the Government has the\\n\\n\\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(supervisory power); United States v. Payner, 447 U.S. 727,\\n733-36 (1980) (supervisory power); United States v. Nobles,\\n422 U.S. 225, 231 (1975) (inherent power).\\n Even if we accepted the distinctions our dissenting\\ncolleague has drawn between inherent judicial powers,\\nlegislatively granted judicial powers, and supervisory powers,\\neach category must operate within the constitutional\\nframework, including the separation of powers.\\n\\n\\n\\n\\n 9\\n\\ndiscretion to retry a case, and nothing in the rule or its\\ncommentary provides or even suggests a limit on the number\\nof retrials it may conduct. See United States v. Wqas Khan,\\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\\n\\n 7\\n While Rule 31 does not limit the Government’s\\nauthority to retry a case, a handful of district courts have\\ndismissed indictments following a second hung jury, but those\\ndecisions are not persuasive. In Ingram, the district court\\ndismissed the indictment sua sponte (without any initial\\nobjection by the Government) after two mistrials—in which\\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\\njailed during the pendency of the trials, and “[t]he Government\\nha[d] no new proof; it simply want[ed] another chance.” 412\\nF. Supp. at 385. The court concluded that to permit a retrial\\nwould be “to ignore the reasonable doubt standard,” and so\\n“[t]he Court’s intervention [was] required in the interest of\\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\\n(McGowan, J., dissenting)). The Ingram court, however, relied\\nin part on the dissent in De Diego. Cases since Ingram have\\napplied the De Diego majority’s view concerning a court’s\\nlimited authority to dismiss an indictment. See, e.g., United\\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\\nDe Diego and reversing the district court’s dismissal of the\\nindictment where the district court found it would be\\n“unconscionable” to retry to the defendant); United States v.\\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\\nDiego and its dissent and holding a district court does not have\\nauthority to sua sponte dismiss an indictment based on the\\n\\n\\n\\n\\n 10\\n\\ndefendant’s poor health); United States v. Mussehl, 453 F.\\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\\nto dismiss the indictment based on alleged errors at trial, and\\nciting De Diego for the proposition that “[t]he duty [to\\nadminister justice] encompasses the concept of review of the\\nquestion whether the United States Attorney, in making his\\ndecision to prosecute, complied with the law, but does not\\nallow the Court to question a United States Attorney’s\\njudgment decision to prosecute, when lawfully made”).\\n The District Court also relied on Rossoff, where the\\ncourt denied the Government’s motion to dismiss the\\nindictment under Federal Rule of Criminal Procedure 48(a),\\nbut still dismissed the indictment with prejudice. 806 F. Supp.\\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\\nbeen two trials, and the Government sought to dismiss the\\nindictment and refile the charges in a different judicial district.\\nId. The court determined it had authority to dismiss an\\nindictment with prejudice if a retrial was “against the concept\\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\\nSupp. 384), and did so because, among other reasons, the\\ndefendant was in poor health, was under significant strain, and\\na majority of jurors at both trials found him not guilty, id. at\\n203. Rossoff, however, is distinguishable from Wright’s case\\nbecause in Rossoff, the Government sought to dismiss the\\nindictment so that it could refile charges in a different judicial\\ndistrict, which caused the court to question the Government’s\\ngood faith. In Wright’s case, the District Court made no\\nfinding that the Government’s desire to retry Wright was for\\nan improper purpose.\\n In addition, and significantly, neither Ingram nor\\nRossoff addressed the doctrine of separation of powers.\\nRather, each essentially relied on a general concept of fairness\\n\\n\\n\\n\\n 11\\n\\nthe text that empowers a court to prohibit the Government from\\nretrying a case. 8\\n B\\n\\n Apparently aware that Rule 31 did not provide it with a\\nbasis to preclude a retrial in these circumstances, the District\\nCourt concluded that it had the inherent authority to forbid the\\nretrial and dismiss the indictment. The District Court erred.\\n\\n The exercise of inherent authority must satisfy two\\nrequirements: (1) it “must be a reasonable response to the\\n\\n\\nto the defendant in deciding to dismiss an indictment. See\\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\\nIn this Circuit, however, “[t]he judiciary may not impose its\\npersonal and private notions of ‘fairness’ on law enforcement\\nofficials, but does have a limited authority to affect\\nprosecutorial actions when those actions are taken in violation\\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\\n596 (3d Cir. 1992) (citations omitted).\\n 8\\n Rule 31 differs from other Federal Rules of Criminal\\nProcedure because it makes no mention of the court’s\\nauthority. For instance, Rule 48(b) states that a court has\\nauthority to dismiss an indictment “if unnecessary delay occurs\\nin: (1) presenting a charge to the grand jury; (2) filing an\\ninformation against a defendant; or (3) bringing a defendant to\\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\\ngrounds on which a district court could also dismiss an\\nindictment, but each would be triggered by a motion, such as a\\nmotion to dismiss for failure to comply with Rule 16’s\\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\\n16(d)(2)(D), or a motion asserting a defect in the indictment,\\nFed. R. Crim. P. 12(b)(3)(B).\\n\\n\\n\\n\\n 12\\n\\nproblems and needs confronting the court’s fair administration\\nof justice,” and (2) it “cannot be contrary to any express grant\\nof or limitation on the district court’s power contained in a rule\\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\\n(citations and internal quotation marks omitted). We will\\nexamine each of these requirements in turn.\\n\\n 1\\n\\n As to the first Dietz requirement, “[g]uided by\\nconsiderations of justice, and in the exercise of supervisory\\npowers, federal courts may, within limits, formulate procedural\\nrules not specifically required by the Constitution or the\\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(internal quotation marks and citation omitted). Such rules\\nmust be imposed (1) “to implement a remedy for violation of\\nrecognized rights,” (2) “to preserve judicial integrity by\\nensuring that a conviction rests on appropriate considerations\\nvalidly before the jury,” and (3) “as a remedy designed to deter\\nillegal conduct.” Id. (citations omitted). Thus, a court may\\nexercise its inherent authority only when it is necessary to\\naddress improper conduct and ensure respect for the\\nproceedings.\\n\\n Under these principles, a court may dismiss an\\nindictment based upon its inherent authority only if the\\nGovernment engaged in misconduct, the defendant was\\nprejudiced, and no less severe remedy was available to address\\nthe prejudice. See Bank of Nova Scotia v. United States, 487\\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\\n(stating that “[a] court may dismiss an indictment under its\\nsupervisory powers only when the defendant suffers\\nsubstantial prejudice and where no lesser remedial action is\\n\\n\\n\\n\\n 13\\n\\navailable” (citations and internal quotation marks omitted));\\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\\n(observing that “a district court may not, in the management of\\nits docket, exercise its discretion to dismiss an indictment with\\nprejudice, either under Rule 48(b) or under its supervisory\\npower, unless the violation caused prejudice to the defendant\\nor posed a substantial threat thereof” (emphasis omitted));\\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\\n(holding that an indictment may not be dismissed for\\nprosecutorial misconduct absent a showing that the misconduct\\nprejudiced the defendants, and stating that “virtually every\\nother circuit to consider the issue post-Hasting and Nova Scotia\\nhas also held that an indictment may not be dismissed based on\\nprosecutorial misconduct, absent a showing of prejudice to the\\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\\n(7th Cir. 1993) (“A federal judge is not authorized to punish\\nthe misconduct of a prosecutor by letting the defendant walk,\\nunless the misconduct not only violated the defendant’s rights\\nbut also prejudiced his defense . . . .”); United States v. Tucker,\\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\\nexercise its supervisory authority to reverse a conviction or\\ndismiss an indictment absent prejudice to the defendant.”);\\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\\nHasting, and Bank of Nova Scotia form a trilogy admonishing\\nfederal courts to refrain from using the supervisory power to\\nconform executive conduct to judicially preferred norms by\\ndismissing charges, absent cognizable prejudice to a particular\\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\\nCir. 1992) (“Before it may invoke this [supervisory] power [to\\ndismiss an indictment], a court must first find that the\\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\\n1480 (9th Cir. 1994).\\n\\n\\n\\n\\n 14\\n\\n In this case, there has been no misconduct. Indeed, the\\nDistrict Court noted that the Government performed diligently\\nand professionally in both trials, Wright, 2017 WL 1179006,\\nat *4, and found that the evidence was sufficient to prove\\nbeyond a reasonable doubt that Wright possessed the gun. The\\nDistrict Court nonetheless applied its own predictions about\\nwhat another jury may do when presented with the same\\nevidence, emphasized the need for finality, and opined that the\\neffect of prosecution on the defendant precluded a proper\\nprosecution from proceeding. See id. at *5-6. Invoking its own\\nnotions about the unfairness of requiring a defendant to face a\\nretrial where the Government did not obtain a majority of the\\njurors’ votes is an improper exercise of a court’s supervisory\\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\nMoreover, there is no prejudice to a defendant simply because\\nhe faces the anxiety and the normal stress of undergoing a trial.\\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975) (“[A]nxiety is present to some degree in virtually every\\ncase. Something more than the normal anxiety that\\naccompanies a trial is necessary to show a degree of\\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\\nonly real harm alleged is the general unfairness to these\\ndefendants in having to go forward yet again with a lengthy\\ntrial, in their being ‘ground down’ by the several months’ drain\\non their mental, emotional, and financial resources. A lack of\\nsuch fairness, however, does not alone violate due process.”).\\nRather, prejudice sufficient for the District Court to intervene\\nin a proper prosecution based upon its inherent authority occurs\\nonly where the Government engages in actions that place a\\ndefendant at a disadvantage in addressing the charges. That\\nsort of prejudice is absent in this case.\\n\\n\\n\\n\\n 15\\n\\n Unless there is some constitutional basis, such as a due\\nprocess violation, it makes sense to limit a court’s authority to\\nbar retrial to instances of prosecutorial misconduct and\\nprejudice. First, it ensures that a judge’s personal preferences\\nabout a case do not influence whether the case proceeds. See\\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\\n(“The judiciary may not impose its personal and private\\nnotions of ‘fairness’ on law enforcement officials, but does\\nhave a limited authority to affect prosecutorial actions when\\nthose actions are taken in violation of the Constitution.”).\\nSecond, as more fully discussed below, it guarantees that a\\ncourt limits the Executive’s decision to prosecute only where\\nthere is a constitutionally sound reason to do so. 9 This brings\\nus to the second Dietz requirement.\\n\\n\\n 9\\n For these reasons, we find unpersuasive our dissenting\\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\\nobservation that a court has the inherent power to resolve a\\ncase, as authority for allowing a court dismiss an indictment\\nafter successive hung juries. As a general matter, there is no\\ndoubt that a court has the authority to dismiss a case, but it may\\nnot simply end a case because it decides that it should not be\\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\\ntheir progeny make clear, the court must point to evidentiary\\ndeficiency, prejudicial misconduct, or a constitutional basis,\\nsuch as double jeopardy or due process, to justify precluding a\\nprosecution. If a court believed that the evidence was deficient,\\nthe prosecutor engaged in prejudicial misconduct, or a retrial\\nwould violate the constitution, then it has a basis to preclude a\\nretrial. Requiring such reasons for barring a retrial ensures that\\n\\n\\n\\n\\n 16\\n\\n 2\\n\\n The second Dietz requirement reminds a court that the\\nexercise of its powers must be in accordance with the\\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\\nwith the Constitution, a court must be mindful of its role in our\\ntripartite form of government and the doctrine of separation of\\npowers. Separation-of-powers principles limit a court’s\\ninherent authority. “Regardless of whether the supervisory\\npower stems from the federal courts’ inherent power to check\\nintrusions by other branches of government or whether it is a\\nform of specialized federal common law, the separation-of-\\npowers principle imposes significant limits on it,” and\\n“[p]roper regard for judicial integrity does not justify a\\n‘chancellor’s foot veto’ over activities of coequal branches of\\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\\nCir. 1985) (internal quotation marks omitted) (quoting United\\nStates v. Russell, 411 U.S. 423, 435 (1973)).\\n\\n In the criminal context, the Executive Branch has\\n“broad discretion as to whom to prosecute,” and this discretion\\n“rests largely on the recognition that the decision to prosecute\\nis particularly ill-suited to judicial review.” Wayte v. United\\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\\nquotation marks omitted). A court is not equipped to evaluate\\n\\n [s]uch factors as . . . the prosecution’s general\\n deterrence value, the Government’s enforcement\\n priorities, and the case’s relationship to the\\n\\n\\nthe ruling is not based on a court’s own personal sense of\\nwhether a case is worthy of prosecution.\\n\\n\\n\\n\\n 17\\n\\n Government’s overall enforcement plan . . . .\\n Judicial supervision in this area, moreover,\\n entails systemic costs of particular concern.\\n Examining the basis of a prosecution delays the\\n criminal proceeding, threatens to chill law\\n enforcement by subjecting the prosecutor’s\\n motives and decisionmaking to outside inquiry,\\n and may undermine prosecutorial effectiveness\\n by revealing the Government’s enforcement\\n policy. All of these are substantial concerns that\\n make the courts properly hesitant to examine the\\n decision whether to prosecute.\\n\\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\\n(echoing similar sentiments with respect to Rule 48(a)\\ndismissals). Thus, absent constitutional concerns, the decision\\nto try or retry a case is at the discretion of the prosecutor.\\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\\nas superprosecutors, second-guessing the legitimate exercise of\\ncore elements of prosecutorial discretion, but rather as neutral\\narbiters of the law” (citation and internal quotation marks\\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\\n1994) (“[T]he choice to forego permanently a prosecution is\\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\\n676 (“In maintaining order in our own house, we should not\\nneedlessly trample on the interest of the prosecutor and of the\\npublic in securing proper, lasting convictions.”); Isgro, 974\\nF.2d at 1097 (stating that the doctrine of separation of powers\\n“mandates judicial respect for the independence of the\\nprosecutor,” and “[d]ismissal of an indictment with prejudice\\n\\n\\n\\n\\n 18\\n\\nis the most severe sanction possible”). 10 Accordingly,\\nseparation-of-powers principles preclude a court from\\nterminating a prosecution absent misconduct and prejudice to\\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\\n974 F.2d at 1094.\\n\\n In short, a court’s power to preclude a prosecution is\\nlimited by the separation of powers and, specifically, the\\nExecutive’s law-enforcement and prosecutorial prerogative.\\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\\nhere to dismiss an indictment in the absence of misconduct and\\nprejudice and based only on the fact that two juries could not\\nreach a verdict intrudes on the Executive’s domain and thereby\\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\\nat 138; Isgro, 974 F.2d 1091.\\n\\n 10\\n Several state courts have also refused to recognize\\nany inherent authority to dismiss an indictment to prevent a\\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\\n(Fla. Dist. Ct. App. 1980). Other states, however, have\\nrecognized a court’s authority to dismiss an indictment sua\\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\\n712; Witt, 572 S.W.2d at 917. These latter cases are\\nunpersuasive because they give too little weight to the\\nseparation of powers, a crucial constitutional principle in the\\nfederal system.\\n\\n\\n\\n\\n 19\\n\\n Finally, there is no statute or procedural rule that\\npermits a court to bar a retrial in the absence of misconduct and\\nprejudice. First, a court may not dismiss an indictment as a\\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\\n505. Second, a court’s inherent power does not “include the\\npower to develop rules that circumvent or conflict with the\\nFederal Rules of Criminal Procedure.” Carlisle v. United\\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\\nexercise of inherent authority circumvents the absence of\\npower of the district court to dismiss an indictment in Rule\\n31(b). As stated above, courts have inherent authority to\\ndismiss indictments, including, for instance, for prosecutorial\\nmisconduct if the defendant was prejudiced, Bank of Nova\\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\\nnor our Court has extended a court’s inherent authority to allow\\n\\n 11\\n In Chambers, for example, the Supreme Court\\nrecognized a court’s authority to impose silence, respect, and\\ndecorum based on its authority to manage its own affairs. 501\\nU.S. at 43. This authority has been exercised by controlling\\nadmission to the bar and disciplining its members; punishing\\nfor contempt, which penalizes disruption to proceedings and\\ndisobedience to court orders; disallowing fraud on the courts;\\nensuring the proceedings move forward; and curtailing\\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\\ncivil case for failure to prosecute to prevent delays and court\\ncongestion as part of a court’s inherent power to manage its\\nown affairs). Chambers and Link address how a court may\\nmanage its own proceedings, but they do not address how the\\ncourt must also account for issues of separation of powers in\\nthe context of a criminal case.\\n\\n\\n\\n\\n 20\\n\\nthe sua sponte dismissal of an indictment solely to preclude\\nmultiple mistrials following hung juries, see Chambers, 501\\nU.S. at 47; HSBC, 863 F.3d at 136. 12\\n\\n 12\\n Most cases concerning a court’s inherent authority\\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\\n(noting a court’s inherent powers to rescind a jury discharge\\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\\n(recognizing a court’s authority to vacate a judgment upon\\nproof that a fraud was perpetrated on the court, and, in\\nparticular, to assess as a sanction the entire amount of the\\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\\n(authority to dismiss a civil case sua sponte for failure to\\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\\n(1947) (dismissing an action based on the doctrine of forum\\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\\n(citing cases involving the scope of a district court’s inherent\\npower); Eash, 757 F.2d at 561-64 (same).\\n There are other circumstances in which district courts\\nlack the inherent authority to act, and most of those situations\\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\\n433 (holding that a court does not have authority to grant a\\npost-verdict motion for judgment of acquittal, filed one day\\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\\n45-50, 55 (holding that a district court does not have inherent\\nauthority to dismiss an indictment because the Government\\nfailed to disclose to the grand jury substantial exculpatory\\nevidence; “[b]ecause the grand jury is an institution separate\\nfrom the courts, over whose functioning the courts do not\\npreside, we think it clear that, as a general matter at least, no\\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\\nat 129, 135-37 (holding that the district court violated\\nseparation-of-powers principles by sua sponte invoking its\\n\\n\\n\\n\\n 21\\n\\n Thus, the District Court abused its discretion in barring\\na retrial and dismissing the indictment. 13\\n\\n III\\n\\n For the foregoing reasons, we will reverse and remand\\nfor further proceedings.\\n\\n\\n\\n\\nsupervisory power to oversee the government’s entry into and\\nimplementation of a deferred prosecution agreement).\\n 13\", \"author\": \"SHWARTZ, Circuit Judge.\"}, {\"type\": \"dissent\", \"author\": \"Our\", \"text\": \"Our dissenting colleague says that our approach\\ndeprives the court from taking action “when warranted to\\nprotect the institutional integrity of the judiciary.” Dissent at\\n3. We disagree. This approach recognizes a court’s role in our\\ntripartite system of government and ensures that a court\\nintercedes when proceeding would violate the Constitution.\\nFurthermore, our approach does not preclude a court from\\nending a case where the evidence is insufficient or the conduct\\nof the prosecution is improper.\\n\\n\\n\\n\\n 22\\n\\nNo. 17-1972, United States of America v. Raymont Wright\"}, {\"author\": \"NYGAARD, Circuit Judge, dissenting\", \"type\": \"dissent\", \"text\": \"NYGAARD, Circuit Judge, dissenting\\n\\n This appeal presents us with two issues: First, does a\\ndistrict court possess the inherent power to dismiss an\\nindictment after serial hung juries, and second, did the\\nDistrict Court here abuse its discretion by dismissing this\\nindictment after two of them. I answer yes to the first and no\\nto the second. Because I view this to be a matter of\\nsubstantial importance, I must respectfully dissent. 1\\n\\n As the majority notes, twice now, the Government has\\ntried Raymont Wright for a violation of federal law: being a\\nfelon in possession of a firearm. 2 Twice now, the\\nGovernment has done so on the basis of essentially the same\\nevidence at trials presided over by the same District Court.\\nAnd twice now, two different juries could not reach a verdict.\\nThus, when the Government announced its intention to put\\nWright on trial for the third time, the District Court was\\nskeptical. It asked for briefing on whether it possessed the\\ninherent power to prohibit the Government from taking a\\n\\n1\\n Whether the District Court had the inherent power to\\ndismiss the indictment is a legal question. We employ a\\nplenary standard of review to that issue. See United States v.\\nSchiff, 602 F.3d 152, 161 (3d Cir. 2010) (citing United States\\nv. Scott, 223 F.3d 208, 210 (3d Cir. 2000)). Whether the\\nDistrict Court appropriately exercised this power is reviewed\\nfor an abuse of discretion. Link v. Wabash R.R. Co., 370 U.S.\\n626, 633 (1962).\\n2\\n See 18 U.S.C. § 922(g).\\n\\nthird turn, and if it did, whether the court should use that\\npower. 3 After hearing from both sides, the District Court\\nconcluded that its inherent power applied to this\\ncircumstance. It then exercised its discretion to dismiss the\\nindictment.\\n\\n Neither the Government nor the majority disputes that\\ndistrict courts have the inherent authority to dismiss\\nindictments under at least some circumstances. Citing to\\nUnited States v. Hasting, 4 however, the majority cabins that\\nauthority to those instances in which there is evidence of\\nprosecutorial misconduct. In my view, in so doing, the\\nmajority conflates and confuses the various powers of the\\ncourt. And it also hobbles the court’s discretion to probe the\\nimpact on the fair administration of justice of those\\nprosecutorial decisions that sit outside the definition of bad\\nconduct but still pose—or threaten to pose—real institutional\\nharm.\\n\\n The executive office inheres prosecutors with the\\npower to bring a case to trial. The judicial office, on the other\\nhand, inheres the court with the power to end a case. 5 Both\\n\\n3\\n The District Court ordered the parties to “file cross briefs\\nstating their position regarding whether the Court, through an\\nexercise of its inherent authority, should prohibit or permit a\\nsecond re-trial in this case.” United States v. Wright, No. 14-\\ncr-292, 2017 WL 1179006, at *1 (W.D. Pa. 2017).\\n4\\n 461 U.S. 499, 505 (1983).\\n5\\n See Young v. U.S. ex rel. Vuitton et Fils S.A., 481 U.S. 787,\\n816 (1987)(Scalia, J. concurring)(“The judicial power is the\\npower to decide, in accordance with law, who should prevail\\nin a case or controversy. See Art. III, § 2. . . . [S]ince the\\n\\n\\n\\n\\n 2\\n\\noffices share a responsibility to safeguard the overall integrity\\nof the judicial process. But when a prosecutor decides to\\nproceed with another trial in the aftermath of multiple\\nmistrials, who but the court is empowered to question the\\nimpact of the prosecutor’s discretion on the fair\\nadministration of justice, particularly when the court has\\nconcerns that the proceedings—and the institution—will be\\ntainted by the abuse of jury shopping? It could be argued that\\ntwo mistrials may not in some instances be enough to inflict\\nserious institutional damage. But, the majority’s combined\\nreliance on Dietz v. Bouldin 6 and Fed. R. Crim. P. 31(b)(3) to\\nallow the prosecutor to bring an unlimited number of retrials,\\nso long as she or he does not stray into the realm of “illegal\\nconduct,” provides the prosecutor with an unchecked power.\\nThis poses a threat to the integrity of the judiciary and\\ncontradicts the inherent responsibility and authority vested in\\nthe judiciary by the framers of the Constitution. Thus, it is\\nthe majority’s decision—and not the District Court’s exercise\\nof its inherent authority—that violates the separation of\\npower principles on which the majority relies. We must\\naffirm that our trial court judges have the discretion,\\noriginating in the court’s inherent power, to take proper\\naction when warranted to protect the institutional integrity of\\nthe judiciary.\\n\\n Here, the District Court mindfully struck the balance\\nthat is necessary anytime the power of the court and the\\n\\n\\nprosecution of law violators is part of the implementation of\\nthe laws, it is—at least to the extent that it is publicly\\nexercised—executive power, vested by the Constitution in the\\nPresident.”) (footnote omitted)).\\n6\\n 136 S. Ct. 1885, 1892 (2016).\\n\\n\\n\\n\\n 3\\n\\npower of the prosecutor intersect. Drawing from factors set\\nout in State v. Abbati, 7 the District Court identified and\\ninvestigated a circumstance that it identified as harmful to the\\ninstitution and to the defendant: jury shopping. It also took\\nnote of the impact of serial retrials on the defendant. It then\\nproperly dismissed the indictment. Its use of the court’s\\ninherent discretion did not violate the separation of powers\\ndoctrine. To the contrary, it gave definition and substance to\\nit.\\n\\n I.\\n\\n Some review is appropriate to illuminate how and\\npossibly why I believe the majority confuses the court’s\\nvarious powers.\\n\\n A.\\n\\n Federal courts operate within a constitutional system\\nthat enumerates the powers of each branch of government, as\\nset forth in the founding document. Article I restrains\\ncongressional power to those “legislative Powers granted\\nherein.” 8 By comparison, Article II vests the President with\\n“the executive Power” without further description, limitation,\\nor restriction. 9 Analogous to Article II, Article III conveys\\nwithout restriction or limitation the “judicial Power” to\\nfederal courts. 10 Accordingly, the Supreme Court has—since\\nat least 1812—recognized that “[c]ertain implied powers must\\n\\n7\\n 493 A.2d 513, 521-22 (N.J. 1985).\\n8\\n U.S. Const. art. I, § 1.\\n9\\n U.S. Const. art. II, § 1.\\n10\\n U.S. Const. art. III, § 1.\\n\\n\\n\\n\\n 4\\n\\nnecessarily result to our Courts of justice from the nature of\\ntheir institution.” 11 “The moment the courts of the United\\nStates were called into existence and invested with\\njurisdiction over any subject, they became possessed of”\\ninherent authority. 12\\n\\n Moreover, two bedrock purposes of the Constitution—\\nchecking the actions of the states and ensuring that Congress\\nand the Executive do not overstep their boundaries—require a\\nfederal judiciary that exercises its own independent judicial\\npower. That is, it would be impossible for federal courts to\\ndischarge these vital duties if they lacked some inherent\\npower beyond the reach of the Executive or the legislature. I\\nthink of it this way: the elaborate measures set out in the\\nConstitution to protect the independence of the judiciary (life\\ntenure, removal from office only through impeachment, no\\ndecrease in salary during a judge’s tenure, for example)\\nwould be meaningless if there were not some inherent,\\nunimpeachable power vested solely in the federal courts.\\n\\n In Eash v. Riggins Trucking Inc., 13 we defined inherent\\npower as vesting in federal courts upon their creation and as\\nnot deriving from any statute. In this sense, the “judicial\\npower” given to the federal courts by Article III of the\\nConstitution is the “power to decide, in accordance with law,\\nwho should prevail in a case or controversy.” 14 No matter the\\ndescription, this power is intrinsic to the judicial office and\\n\\n11\\n United States v. Hudson, 11 U.S. (7 Cranch) 32, 34 (1812).\\n12\\n Ex parte Robinson, 86 U.S. 505, 510 (1873) (speaking of\\nthe inherent contempt power).\\n13\\n 757 F.2d 557, 561 (3d Cir. 1985) (en banc).\\n14\\n Young, 481 U.S. at 816 (Scalia, J., concurring).\\n\\n\\n\\n\\n 5\\n\\ncannot be inhibited by any rule or act of Congress. As we\\nhave recognized, the boundaries of this power are often\\n“nebulous” and “shadowy,” 15 and “it is not always possible to\\ncategorize inherent power.” 16 Yet, we have an outline.\\n\\n In Eash, we identified three main classes or categories\\nof inherent power: 1) inherent powers based in Article III,\\nthat is, the power of a lower federal court to decide a case\\nover which it has jurisdiction; 2) those powers “necessary to\\nthe exercise of all others,” 17 and 3) powers that include those\\nreasonably useful to achieve justice, which are “necessary\\nonly in the practical sense of being useful.” 18 Focusing on the\\nfirst category, the inherent power to decide a case is “so\\nfundamental to the essence of a court as a constitutional\\ntribunal that to divest the court of absolute command within\\nthis sphere is really to render practically meaningless the\\nterms ‘court’ and ‘judicial power.’” 19 In other words, powers\\n\\n15\\n Eash, 757 F.2d at 561 (citation omitted).\\n16\\n Id. at 562.\\n17\\n Id. (quoting Roadway Express, Inc., v. Piper, 447 U.S. 752,\\n764 (1980)).\\n18\\n Id. at 563; see also Am. Civil Liberties Union v. Holder,\\n673 F.3d 245, 255-56 (4th Cir. 2011) (applying Eash factors);\\nIn re Stone, 986 F.2d 898, 901-02 (5th Cir. 1993) (per\\ncuriam) (adopting Eash factors). In Chambers v. NASCO\\nInc., the Supreme Court was urged to adopt our approach to\\ninherent powers. But the Court held that it “ha[d] never so\\nclassified the inherent powers and . . . ha[d] no need to do so\\nnow.” 501 U.S. 32, 47 n.12 (1991).\\n19\\n Eash, 757 F.2d at 562. The third aspect of a court’s\\ninherent power is its authority to employ persons or\\ninstruments not connected with the court, such as experts and\\n\\n\\n\\n\\n 6\\n\\nin this category make a court a court; they are encoded into\\nthe judiciary’s DNA. Courts have referred to this power as a\\ncourt’s “irreducible inherent authority” 20 and “the core\\nArticle III power.” 21 It is nothing less than our ability to\\ndecide a case over which we have jurisdiction, without\\ninterference by Congress or the Executive. 22\\n\\n Drawing from this, when I refer to a district court’s\\ninherent power, I mean a ‘“[c]ertain implied power[] [that]\\nmust necessarily result to our Courts of justice from the\\nnature of their institution,’ [a] power[] ‘which cannot be\\ndispensed with in a Court, because they are necessary to the\\nexercise of all others.’” 23 It is “grounded in the separation of\\npowers concept,” since to deny it and yet maintain an\\nindependent judiciary “is a self-contradiction.” 24\\n\\n However, that is not to say that the court operates\\nsolely outside the realm of legislatively granted judicial\\n\\n\\nauditors, to assist in its decision-making function. This facet\\nof inherent power is not in play here.\\n20\\n Id.\\n21\\n Am. Civil Liberties Union v. Holder, 673 F.3d at 256.\\n22\\n United States v. Klein, 80 U.S. (13 Wall.) 128, 147 (1871),\\nEash, 757 F.2d at 562 (noting that courts may exercise this\\ntype of inherent power despite legislation to the contrary); see\\nalso Michaelson v. United States ex rel. Chicago, St. P., M. &\\nO. Ry. Co., 266 U.S. 42, 64 (1924) (acknowledging that the\\nConstitution vests courts with some powers unalterable by\\nlegislation).\\n23\\n Chambers, 501 U.S. at 43 (quoting Hudson, 11 U.S. (7\\nCranch) at 34.).\\n24\\n Eash, 757 F.2d at 562.\\n\\n\\n\\n\\n 7\\n\\npowers. 25 In fact, the categorization scheme in Eash was\\nintended largely as a means of explaining the relationship\\nbetween inherent judicial powers and legislatively granted\\njudicial powers. 26 It is here that I believe the majority’s\\nanalysis strays.\\n\\n B.\\n\\n The majority, the briefs, and the discussion at oral\\nargument reveal what has become a commonplace but\\nimprecise conflation of the terms “inherent power” and\\n“supervisory power.” 27 The Government, while referencing\\nthe District Court’s “inherent power,” also referred to the\\ncourt’s “supervisory power,” and its “inherent supervisory\\njudicial authority.” 28 The Appellee covers the entire panoply,\\nciting the District Court’s “supervisory authority,” its\\n\\n\\n25\\n See Hudson, 11 U.S. (7 Cranch) at 33.\\n26\\n See In re Tutu Wells Contamination Litig., 120 F.3d 368,\\n384 n.14 (3d Cir. 1997), overruled on other grounds by\\nCunningham v. Hamilton County, Ohio, 527 U.S. 198 (1999).\\n27\\n In Eash, we noted that “[t]he conceptual and definitional\\nproblems regarding inherent power . . . have bedeviled\\ncommentators for years,” 757 F.2d at 561, and that “those\\ncases that have employed inherent power appear to use that\\ngeneric term to describe several distinguishable court\\npowers,” id. at 562. We also noted that “this lack of\\nspecificity [has been compounded by courts] rel[ying] . . . on\\nprecedents involving one form of power to support the court’s\\nuse of another.” Id.\\n28\\n E.g., Appellant’s Br. at 13, 16; Appellant’s Reply Br. at 2,\\n14.\\n\\n\\n\\n\\n 8\\n\\n“supervisory power,” and its “inherent power.” 29 At times,\\nwe too have been guilty of adding to the confusion. 30 The\\nerroneous interchangeability of these terms clouds an\\nimportant distinction that is crucial to this appeal: the\\ndifference between inherent judicial powers and legislatively\\ngranted judicial powers. 31 As noted supra, inherent “judicial\\npower” is given to the federal courts by Article III of the\\nConstitution. 32 Through this grant, federal courts receive the\\n“power to decide, in accordance with law, who should prevail\\nin a case or controversy.” 33 The merging of the terms\\n“inherent” and “supervisory” likely has its genesis in the fact\\nthat some inherent powers are supervisory in function, such\\nas a federal court’s inherent power “to supervise the\\nadministration of criminal justice.” 34\\n\\n29\\n E.g., Appellee’s Br. at 22, 26.\\n30\\n See, e.g., United States v. Accetturo, 783 F.2d 382, 396 (3d\\nCir. 1986) (Sloviter, J., dissenting) (speaking of our “inherent\\nsupervisory power”); see also United States v. Watkins, 339\\nF.3d 167, 180 (3d Cir. 2003) (Nygaard, J., concurring)\\n(referring to both a court’s supervisory power and inherent\\npower to dismiss a case under Fed. R. Crim. P. 48(b)).\\n31\\n In re Tutu Wells Litig., 120 F.3d at 384 n. 14.\\n32\\n See U.S. Const. art. III, § 1.\\n33\\n Young, 481 U.S. at 816 (Scalia, J., concurring).\\n34\\n United States v. Payner, 447 U.S. 727, 735 n.7 (1980)\\n(quotation marks omitted); see also Sara Sun Beale,\\nReconsidering Supervisory Power in Criminal Cases;\\nConstitutional and Statutory Limits of the Federal Courts, 84\\nColum. L. Rev. 1433, 1433-34, 1465, 1470 (1984)\\n(identification of Article III “judicial power,” not\\ncongressional acts, as the source of the Supreme Court’s\\nsupervisory authority).\\n\\n\\n\\n\\n 9\\n\\n However, unlike inherent powers, a court’s\\nsupervisory authority may come from, and can be limited by,\\nacts of Congress or a court’s own rules. 35 Supervisory power\\noften speaks to the power “to mandate ‘procedures deemed\\ndesirable from the viewpoint of sound judicial practice.’” 36 A\\ncourt’s use of supervisory power can usually be classified in\\none of three ways. First, supervisory power can refer to an\\nappellate court’s supervision of a district court, through the\\nimposition of procedures in addition to those already imposed\\nby federal statute or constitutional provision. 37 We have, for\\nexample, relied on our supervisory power over district courts\\nto review the application of local rules of practice and\\nprocedure. 38 We have also used our supervisory power to\\n\\n\\n\\n\\n35\\n See, e.g., McNabb v. United States, 318 U.S. 332, 340-41\\n(1943); Hasting, 461 U.S. at 505.\\n36\\n United States v. Moreno, 809 F.3d 766, 780 (3d Cir. 2016)\\n(quoting Thomas v. Arn, 474 U.S. 140, 146-47 (1985)).\\n37\\n See, e.g., Castro v. United States, 540 U.S. 375, 384 (2003)\\n(instructing district courts to notify pro se litigants about\\nconsequences of re-characterizing motions as ones seeking\\nrelief under 28 U.S.C. § 2255); Thiel v. S. Pac. Co., 328 U.S.\\n217, 225 (1946) (announcing a new rule for the composition\\nof federal juries); Dunbar v. Triangle Lumber & Supply Co.,\\n816 F.2d 126, 129 (3d Cir. 1987) (prescribing procedures for\\nmotions to dismiss based on the conduct of a litigant’s\\ncounsel); United States v. Bazzano, 570 F.2d 1120, 1137-38\\n(3d Cir. 1977) (requiring district courts to state reasons for a\\ncriminal sentence).\\n38\\n See United States v. Wecht, 484 F.3d 194, 204-05 (3d Cir.\\n2007).\\n\\n\\n\\n\\n 10\\n\\nprohibit certain jury instructions in the district courts 39 and to\\nreview attorney-client fee arrangements. 40 Second, Courts—\\nboth trial and appellate—also refer to their “supervisory\\npower” when meaning their power to supervise pending\\nlitigation. 41 They can, for example, seal and unseal records, 42\\nreassign a case to a different judge on remand, 43 or disqualify\\nan attorney on ethical grounds. 44 Lastly, the power of a\\nfederal court to supervise law enforcement officials can also\\nbe what a court intends when it speaks of its “supervisory\\n\\n\\n\\n\\n39\\n See United States v. E. Med. Billing Inc., 230 F.3d 600,\\n607-12 (3d Cir. 2000).\\n40\\n See Ryan v. Butera, Beausang, Cohen & Brennan, 193 F.3d\\n210, 214 (3d Cir. 1999).\\n41\\n See, e.g., Carlisle v. United States, 517 U.S. 416, 425-26\\n(1996) (acknowledging “supervisory power” of district courts\\nover litigation before them).\\n42\\n See, e.g., Hagestad v. Tragesser, 49 F.3d 1430, 1434 (9th\\nCir. 1995).\\n43\\n See Gov’t of the Virgin Islands v. Walker, 261 F.3d 370,\\n376 (3d Cir. 2001) (noting that, “[a]lthough it is the standard\\npractice in the district courts and in this circuit that a case on\\nremand is assigned to the judge who originally heard it, we\\ncan, in the exercise of our supervisory power, reassign this\\ncase to a different judge upon remand.”) (quotation marks\\nomitted).\\n44\\n In re Grand Jury Investigation, 447 F. Supp. 2d 453, 456-\\n57 (E.D. Pa. 2006) (collecting cases); see also United States\\nv. Moreno, 809 F.3d at 780 (summarizing supervisory\\nauthority).\\n\\n\\n\\n\\n 11\\n\\npower.” 45 These powers broadly ensure that pending cases\\nare managed uniformly and efficiently.\\n\\n I concede that the boundary between supervisory\\nauthority that is inherent to the court and that which is granted\\nby the legislature can, at times, be difficult to identify.\\nHowever, these difficulties are irrelevant to this case because\\nI conclude that the District Court here acted pursuant to its\\ninherent power and not to any authority conferred by any\\nstatute or rule. The District Court’s action was not\\nundertaken in supervision of pending litigation—two trials\\nwere already concluded and a potential third trial had not yet\\nbegun. Nor was it exercised according to a rule of procedure\\nor practice newly announced by an appellate tribunal.\\nMoreover, its action was not a response to any prosecutorial\\nmisconduct or request from Wright to dismiss the indictment.\\nThere is simply no basis to conclude that the inherent power\\nthat the District Court exercised in this case derived from any\\nlegislative grant.\\n\\n To the contrary, the specific power under review here\\nis the power to dismiss an indictment after two mistrials\\nbecause of deadlocked juries in each instance. This power\\nfalls within Eash’s first category of power because it is an\\ninherent power to resolve a case. A court, by its nature, must\\nbe able to dismiss with prejudice actions brought before it,\\njust as it must have the power to decide cases and enter\\n\\n45\\n See, e.g., United States v. Thompson, 772 F.3d 752, 763 (3d\\nCir. 2014). For a comprehensive discussion of the origins\\nand uses of supervisory power, see Amy Coney Barrett, The\\nSupervisory Power of the Supreme Court, 106 Colum. L. Rev.\\n324, 330 (2006).\\n\\n\\n\\n\\n 12\\n\\njudgments. 46 Such exercises of power are fundamental to the\\nessence of a court. Were they not, the judicial system simply\\ncould not function. 47\\n\\n The inherent power to dismiss is “of ancient origin,\\nhaving its roots in judgments of nonsuit and non prosequitur\\nentered at common law,” and so is a power that is part of the\\nvery nature of the judicial institution. 48 It is incidental and\\nnecessary to the fair and efficient operation of the courts. 49\\nIndeed, “the power to dismiss exists in many situations. For\\nexample, a district court has the inherent power to dismiss sua\\nsponte for lack of jurisdiction, or under the doctrine of forum\\nnon conveniens.” 50 Because the power to resolve a case by\\ndismissing an indictment (in a criminal action) or a complaint\\n(in a civil action) is fundamental to the essence of a court of\\njustice, it cannot be interfered with. Indeed, as two\\ncommentators have explained, “McNabb, other Supreme\\n\\n46\\n We have also noted that our power to remand is a subset of\\nthe inherent power to dismiss a case. See Bradgate Assocs.,\\nInc. v. Fellows, Read & Assocs., Inc., 999 F.2d. 745, 750 n.4\\n(3d Cir. 1993).\\n47\\n See, e.g., Fitzgerald v. First E. Seventh St. Tenants Corp.,\\n221 F.3d 362, 363-364 (2d Cir. 2000) (holding a district court\\nhas the inherent power to dismiss a case, sua sponte, if it\\ndetermines that the action is frivolous or the court lacks\\njurisdiction over the matter).\\n48\\n Link, 370 U.S. at 630.\\n49\\n See, e.g., Bowers v. Nat’l Collegiate Athletic Ass’n, 564 F.\\nSupp. 2d 322, 333 (D.N.J. 2008) (citing Derzack v. County of\\nAllegheny, 173 F.R.D. 400, 411 (W.D. Pa. 1996), aff’d\\nwithout op., 118 F.3d 1575 (3d Cir. 1997)).\\n50\\n In re Prevot, 59 F.3d 556, 565-66 (6th Cir. 1995).\\n\\n\\n\\n\\n 13\\n\\nCourt cases, and an analysis of several lower court opinions\\naddressing this precise issue should sufficiently dispel any\\nnotion that the federal courts lack the power to bar repeated\\nattempts to obtain a conviction” following serial mistrials.51\\nThus, the District Court’s action here was well within the\\nboundaries of its inherent power.\\n\\n Therefore, the majority’s conclusion that “inherent\\nauthority,” “supervisory power,” and “supervisory authority”\\nall refer to the same thing (while understandable given the\\nrampant muddled references that persist) ultimately misses\\nthe point. The power at issue here is the inherent power of\\nthe court to decide a case: a power that is limited by the\\nboundaries of reason and discretion and is subject to appellate\\nreview for abuse. It is not subject to the power of Congress\\nor the Executive.\\n\\n II.\\n\\n There is no dispute that district courts have the\\ninherent power to dismiss indictments in at least some\\ncircumstance. The majority nevertheless concludes that the\\nDistrict Court lacked the power to do so in this case. The\\nmajority reaches that conclusion for three principal reasons,\\nbut none withstands scrutiny.\\n\\n A.\\n\\n51\\n Michael A. Berch & Rebecca White Berch, The Power of\\nthe Judiciary to Dismiss Criminal Charges After Several\\nHung Juries: A Proposed Rule to Control Judicial Discretion,\\n30 Loy. L.A. L. Rev. 535, 543 & nn. 42-43 (1997) (collecting\\ncases).\\n\\n\\n\\n\\n 14\\n\\n First, the majority agrees with the Government’s\\nargument that the District Court’s dismissal violated the\\nSeparation of Powers Doctrine. I agree that the District\\nCourt’s dismissal implicates the separation of powers. But its\\nactions were in furtherance—not in violation—of the\\ndoctrine. The separation of powers doctrine refers to the\\nbalance among the branches of Government which prevents\\none branch from disrupting the constitutional functions of\\nanother. 52\\n\\n Here, the majority concludes that, in dismissing the\\nindictment after two hung juries, the District Court\\nencroached on the independence of the Executive because it\\nprohibited the prosecution from exercising its constitutional\\nduty to enforce the laws of the United States. Certainly, the\\nUnited States Attorney, as a member of the Executive Branch,\\nhas such a responsibility. 53 And, just as certainly, the\\ndecision to prosecute “is soundly within the discretion of the\\nprosecutor, not the courts.” 54 The Government’s authority\\nnot to prosecute a case is clear as well. 55 But we see no sign\\nthat the District Court did anything to prevent the\\nGovernment from fulfilling its duty. To the contrary, the\\nGovernment was twice given a full and fair opportunity to\\n\\n52\\n See, e.g., Clinton v. Jones, 520 U.S. 681, 699-700 (1997);\\nMorrison v. Olson, 487 U.S. 654, 696 (1988); Nixon v. Adm’r\\nof Gen. Servs., 433 U.S. 425, 442-43 (1977); Baraka v.\\nMcGreevey, 481 F.3d 187, 201 (3d Cir. 2007).\\n53\\n See, e.g., In re Grand Jury, 286 F.3d 153, 163 (3d Cir.\\n2002).\\n54\\n United States v. Talley, 164 F.3d 989, 997 (6th Cir. 1999).\\n55\\n See, e.g., United States v. Quinn, 728 F.3d 243, 255-56 (3d\\nCir. 2013).\\n\\n\\n\\n\\n 15\\n\\npresent its case and makes no claim that the District Court\\never prevented it from doing so. Having had those\\nopportunities, the Government had no absolute right as a\\nmatter of separation of powers or otherwise to try again. As\\ntwo commentators have explained, a district court’s use of its\\ninherent power to dismiss an indictment after serial mistrials\\ndoes not raise “significant separation of powers concerns”\\nbecause the nature of that inherent power means that federal\\ncourts “need not automatically defer to a prosecutor’s\\ndecision to retry a defendant” in this situation. 56\\n\\n The majority nevertheless concludes that prosecutors\\nhave the unimpeded right to try persons for violating federal\\nlaw based on an indictment as many times as they wish and\\nthat the separation of powers doctrine prohibits a federal court\\nfrom interfering. This position is untenable because it is not a\\ntrue reflection of the separation of powers. It is axiomatic\\nthat no one branch of government is completely divorced\\nfrom the other two. In reality, “our constitutional system\\nimposes on the Branches a degree of overlapping\\nresponsibility, a duty of interdependence as well as\\nindependence.” 57 This overlap becomes problematic, of\\ncourse, when it results in an encroachment (when an action of\\none branch might undermine the independence of another\\nbranch) or an aggrandizement (where one branch seeks\\n“powers more appropriately diffused among separate\\nBranches”). 58\\n\\n\\n56\\n Berch & Berch, supra note 51, at 544.\\n57\\n Mistretta v. United States, 488 U.S. 361, 381 (1989).\\n58\\n Id. at 381; see also In re Tribune Media Co., 799 F.3d 272,\\n285 (3d Cir. 2015) (Ambro, J., concurring).\\n\\n\\n\\n\\n 16\\n\\n But recognizing a district court’s right to prohibit a\\nretrial following serial mistrials does not implicate these\\nconcerns. To the contrary, and putting the shoe on the other\\nfoot, the Government’s position that nothing limits its\\nopportunity to try and retry a defendant as many times as it\\nchooses violates the judicial branch’s constitutional mandate\\nto exercise its judicial power. Just as the filing of an\\nindictment is an exercise of executive power, the dismissal of\\none is an exercise of judicial power. The unlimited serial\\nprosecutions that the Government advocates for, and that the\\nmajority permits, would limit a court’s authority to dismiss an\\nindictment to only those instances in which the prosecutor\\nsteps outside the bounds of professional conduct. But our\\nindependence as an institution of government must include an\\nability to adjudicate, and thus dismiss with prejudice,\\nindividual cases when a district court, in its discretion, has\\nconcerns about the impact of serial retrials on the institution\\nand the defendant. We view the prosecution of a defendant\\nafter deadlocked juries as a tipping point in balancing the\\nseparation of powers. As the repeated prosecutions increase,\\nso too does the judiciary’s power to limit them. As we stated\\nin Eash, and as we said supra, a court’s exercise of its\\ninherent power to dismiss an indictment after retrials does not\\nviolate the separation of powers but is grounded in it. 59\\n\\n B.\\n\\n Second, and relatedly, the majority concludes that the\\nDistrict Court’s dismissal was in violation of Fed. R. Crim. P.\\n31(b)(3), which the majority claims confers on prosecutors\\nthe unlimited discretion to retry defendants following serial\\n\\n59\\n See Eash, 757 F.2d at 562.\\n\\n\\n\\n\\n 17\\n\\nmistrials. Rule 31 does nothing of the kind. Rule 31 provides\\nin relevant part that “if a jury cannot agree on a verdict on one\\nor more counts, the court may declare a mistrial on those\\ncounts. The government may retry any defendant on any\\ncounts on which the jury could not agree.” 60 The Supreme\\nCourt adopted this rule in its original form in 1944 as a\\n“restatement of existing law.” 61 The Supreme Court itself\\nappears never to have cited Rule 31(b)(3), and neither the few\\nCourts of Appeals to have done so 62 nor its Advisory\\nCommittee Notes have discussed its history or purpose in any\\ndetail. Arguably, the rule’s reference to the prosecutor’s\\ngeneral ability to retry a defendant following a mistrial may\\nbe nothing more than a recognition of the longstanding\\nprinciple that retrials following mistrials are not prohibited by\\nthe Double Jeopardy Clause, 63 which is not at issue here.\\n\\n In any event, this rule does not by its terms prohibit\\ndistrict courts from dismissing indictments following serial\\nmistrials. District courts have the inherent power to do so as\\nexplained above. A district court’s exercise of that power\\ncould be contrary to Rule 31(b)(3) only if the rule contained\\nan “express grant of or limitation on” that power. 64 It does\\nnot. The rule does not mandate a retrial after a mistrial. Nor\\n\\n60\\n Fed. R. Crim. P. 31(b)(3).\\n61\\n Id. advisory committee’s note to 1944 adoption.\\n62\\n See United States v. Melendez, 775 F.3d 50, 57 (1st Cir.\\n2014); United States v. Warren, 593 F.3d 540, 546 (7th Cir.\\n2010); United States v. Fort, 472 F.3d 1106, 1111 n.3 (9th\\nCir. 2007); United States v. Gotti, 451 F.3d 133, 137 (2d Cir.\\n2006).\\n63\\n See United States v. Perez, 22 U.S. 579, 580 (1824).\\n64\\n Dietz, 136 S. Ct. at 1892.\\n\\n\\n\\n\\n 18\\n\\ndoes it contain any other limitation on the district court’s\\npower to prohibit one. In fact, the rule does not even mention\\nthat issue. 65 Thus, as the Supreme Court has noted in\\naddressing other rules of court, “[i]t would require a much\\nclearer expression of purpose than [this rule] provides for us\\nto assume that it was intended to abrogate” the district courts’\\ninherent power. 66 Put simply, when there have been multiple\\nmistrials and the prosecutor seeks to try the case again, Rule\\n31(b)(3) does not purport to reduce the role of the district\\ncourts to that of a rubber stamp.\\n\\n C.\\n\\n Finally, the majority claims that a district court can\\nexercise its inherent power to dismiss an indictment only if\\nthere is evidence of willful bad faith or prosecutorial\\nmisconduct on the part of the government and resultant\\nprejudice to the defendant. It cites to numerous decisions that\\nit says supports this position. 67 But none of these cases deals\\n\\n65\\n The majority claims that Rule 31(b)(3)’s silence on this\\nissue supports the proposition that district courts lack the\\nauthority to dismiss an indictment following serial mistrials.\\nBut because district courts have the inherent power to do so\\nas explained above, the question is not whether Rule 31(b)(3)\\npermits district courts to dismiss an indictment in that\\ncircumstance. The question instead is whether Rule 31(b)(3)\\nprohibits them from doing so. It does not.\\n66\\n Link, 370 U.S. at 631-32.\\n67\\n See Bank of Nova Scotia v. United States, 487 U.S. 250,\\n254-56, 263 (1988); United States v. Chapman, 524 F.3d\\n1073, 1087 (9th Cir. 2008); United States v. Goodson, 204\\nF.3d 508, 514 (4th Cir. 2000); United States v. Derrick, 163\\n\\n\\n\\n\\n 19\\n\\nwith the particular circumstance we face here: the decision to\\nretry a defendant after serial mistrials. 68 In fact, many are\\ndismissals due to prosecutorial misconduct. The majority’s\\nreliance on such decisions is misplaced because it ignores the\\nfact that the dismissal in this case was not punitive in nature;\\nit was not a sanction for misconduct. 69 As two commentators\\nhave explained, “[a]lthough the inherent power principle has\\nusually involved cases of misconduct by the parties or a\\nvindication of statutory principles, the doctrine is not so\\nlimited.” 70 To the contrary, courts may use their inherent\\nauthority to dismiss indictments whenever necessary to\\nvindicate “principles of fairness to the defendant and the\\ninterests of the public in the effective administration of\\njustice.” 71\\n\\n That is just what the District Court did here. The\\nGovernment asked the District Court to dismiss without\\nprejudice “[e]ven if this court were inclined to dismiss the\\ncase.” 72 Yet the Government proffered no additional\\n\\n\\nF.3d 799, 808 (4th Cir. 1998); United States v. Tucker, 8 F.3d\\n673, 674 (9th Cir. 1993) (en banc); United States v. Van\\nEngel, 15 F.3d 623, 631-32 (7th Cir. 1993); United States v.\\nSantana, 6 F.3d 1, 11 (1st Cir. 1993); United States v. Isgro,\\n974 F.2d 1091, 1094 (9th Cir. 1992).\\n68\\n Derrick does deal with a dismissal of the indictment after\\nan initial grant of a retrial, but the circumstance differs from\\nthis case because the mistrials were not due to deadlocked\\nverdicts. See 163 F.3d at 803\\n69\\n Cf., e.g., Isgro, 974 F.2d at 1097.\\n70\\n Berch & Berch, supra note 51, at 548.\\n71\\n Id.\\n72\\n Wright, 2017 WL 1179006, at *7.\\n\\n\\n\\n\\n 20\\n\\nevidence it would present if Wright was re-indicted. It asked\\nto try the same case again before a third jury, merely hoping\\nfor a different result. The District Court’s dismissal of the\\nindictment with prejudice was based on the merits, or lack\\nthereof, of the Government’s request, no more and no less.\\n\\n Moreover, the dismissal was not, as the majority\\ncontends, a general declaration of unfairness simply because\\nthe government failed to obtain a conviction. 73 Nor was it\\nmerely an attempt to shield the defendant from the anxiety of\\na retrial. 74 Reference to Miller and Shepherd misconstrues\\nnot only the circumstance of this case, but also the gravity of\\nthe District Court’s concern. As I discuss next, the District\\nCourt weighed many factors, mindful of the importance of\\neach, before making its decision. From all of this—even\\ntaking into account the separation of powers and Rule\\n31(b)(3)—it is evident to me that the District Court correctly\\nconcluded it had the inherent authority to act upon the\\nprosecutor’s decision to retry this case in the wake of two\\nmistrials. 75\\n\\n73\\n See United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\n74\\n See United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975); see also Arizona v. Washington, 434 U.S. 497, 503-04\\n(1978).\\n75\\n Although we conclude that the District Court appropriately\\nexercised its inherent power as a court of law to dismiss an\\nindictment, thus placing its actions within Eash’s first\\ncategory, the District Court appeared at one point to tether its\\ndismissal to its “inherent authority to effectuate . . . the\\nspeedy and orderly administration of justice and to ensure\\nfundamental fairness.” Wright, 2017 WL 1179006, at *2.\\nThese actions are typically associated with the second\\n\\n\\n\\n\\n 21\\n\\n III.\\n\\n Before moving to the actual merits of the District\\nCourt’s decision, a word of caution is in order. Just because a\\ncourt has inherent power to dismiss an indictment after a\\nretrial does not mean it should always be exercised. 76 My\\ndissenting opinion today should not be interpreted as an\\nendorsement of unchecked and ungrounded judicial power.\\nNor should it be interpreted as permitting district courts in\\nthis Circuit to dismiss indictments without a significant basis\\nfor doing so. Moreover, nothing in this opinion should be\\nread as limiting reprosecution to two trials. Cases no doubt\\nexist where a third or fourth trial on the same indictment may\\nbe appropriate where the evidence so indicates. It is simply\\nmy conclusion that, in some cases, and in the proper exercise\\nof its discretion, a district court has the inherent power to\\nprohibit continued re-prosecution by dismissing an\\nindictment.\\n\\n IV.\\n\\n This is such a case. The District Court here rightly\\nproceeded with the Government’s request for another trial\\nwith deliberate caution. Recognizing the lack of guidance\\n\\n\\nclassification of Eash’s powers. See Eash, 757 F.2d at 562-\\n563. Nonetheless, it invoked the inherent power of the court\\nand dismissed the case and it is on this basis that I conclude\\nthe District Court did not reach the boundaries of its power.\\n76\\n See Lopez v. United States 373 U.S. 427, 440 (1963); see\\nalso Chambers, 501 U.S. at 44 (“Because of their very\\npotency and discretion, inherent powers must be exercised\\nwith restraint and discretion.”).\\n\\n\\n\\n\\n 22\\n\\nfrom this Court, the District Court turned to a decision of the\\nSupreme Court of New Jersey. In State v. Abbati, 77 that court\\nlisted several factors a trial court should consider before\\ndismissing an indictment after several hung juries. These\\nfactors are valid inquiries and include\\n\\n • the number of previous mistrials and the\\n outcome of the juries’ deliberations, as far as\\n can be determined;\\n • the character or nature of the previous trials,\\n considering their length, complexity of issues,\\n and similarities in evidence;\\n • the probability that any subsequent trial will be\\n much different from the previous ones;\\n • the relative strength of the party’s case, as\\n determined by the trial court;\\n • the conduct of counsel during the previous\\n trials. 78\\n\\nIn considering these factors, a district court must also accord\\nappropriate weight to the Government’s decision to continue\\nprosecution, giving deliberate consideration to the reasons for\\nthat choice. 79\\n\\n Other considerations might include the seriousness of\\nthe crimes charged, the public’s interest in the effective\\nresolution of criminal charges, and the criminal defendant’s\\ncircumstances, including the impact that continued\\nprosecution might have on him or her and the potential for\\n\\n77\\n 493 A.2d 513.\\n78\\n Id. at 521-22.\\n79\\n See id.\\n\\n\\n\\n\\n 23\\n\\nunfairness or unnecessary hardship. 80 The factors just\\noutlined are not an exhaustive list and district courts could\\nconsider other things that are reasonably useful in answering\\nwhether further prosecutions after deadlocked juries should\\nbe permitted. Moreover, all of these elements of inquiry\\nenable the court to assess the impact that a serial retrial has on\\nthe integrity of the judiciary as an institution.\\n\\n These avenues of inquiry make sense to me. Take\\ndifferences in evidence, for example. If the evidence would\\nbe different at a retrial, then there seems little chance that\\ncontinued prosecution should be curtailed. If, on the other\\nhand, there would be no substantial difference in evidence,\\nconcern about re-prosecution is appropriate. So too the\\nnumber of deadlocked juries is an important consideration.\\nContinued prosecution after two, three, or even four\\ndeadlocked juries could unbalance the scale. By inquiring\\ninto the seriousness of the charges, a district court could\\ncompare the crime being prosecuted to other cases when a\\ncourt dismissed an indictment after deadlocked juries. In\\nother words, a district court must make sufficient findings and\\nestablish a sufficient record supporting its decision, thus\\nenabling a court of appeals to accurately assess whether the\\ndistrict court abused its discretion or not. That is what the\\nDistrict Court did here.\\n\\n I see no abuse of discretion in the District Court’s\\nexercise of its inherent powers. The District Court’s ruling\\nwas not arbitrary and instead was based on a thorough,\\ncareful, and balanced consideration of the above factors. The\\nDistrict Court first acknowledged the weight of its actions\\n\\n80\\n See id.\\n\\n\\n\\n\\n 24\\n\\nwithin our constitutional scheme. It then found that the\\nevidence suggested that the deadlock was not the result of a\\nlone holdout. As to the character of the preceding trials, the\\nDistrict Court noted the Government’s position that this was a\\n“simple” case. It also stated that both previous trials were\\n“virtual duplicates” and that counsel on both sides was the\\nsame for both prosecutions. The District Court further\\nobserved the lack of any allegation of jury nullification or\\nbias. Instead, it found that “there is every indication that the\\ntwo juries engaged in deliberations in good faith, and, despite\\ntheir best efforts, were unable to reach a verdict.”\\n\\n The District Court also considered the strength of the\\nparties’ respective cases and determined that its opinion on\\nthis factor was irrelevant, given that two separate juries had\\nconcluded that the Government failed to meet its burden of\\nproof. It commended the professionalism and hence the\\neffectiveness of counsel on all sides, which it weighted as\\nfavoring disallowing any further prosecution. The District\\nCourt specifically considered the seriousness of the crime\\ncharged, and it noted that other courts had dismissed\\nindictments when the charges were far graver. 81 Lastly, the\\nDistrict Court thoroughly balanced the Government’s\\nauthority to prosecute against the effect of continued\\nprosecution on Wright. Recognizing that Wright has been on\\nbond since July of 2014, and on home detention for nearly\\ntwo years, the District Court concluded that this inquiry\\ntipped in his favor.\\n\\n81\\n Wright, 2017 WL 1179006, at *6 (citing United States v.\\nIngram, 412 F. Supp. 384, 385 (D.D.C. 1976); State v.\\nMoriwake, 647 P.2d 705, 708 (Haw. 1982); Abbati, 493 A.2d\\nat 517; and State v. Witt, 572 S.W.2d 913, 914 (Tenn. 1978)).\\n\\n\\n\\n\\n 25\\n\\n V.\\n\\n In conclusion, I see no abuse of discretion in the\\nDistrict Court’s careful and thorough balancing of relevant\\nfactors, a balancing which led it to invoke its inherent power\\nand to dismiss the Government’s indictment of Wright. For\\nall of these reasons, I respectfully dissent from my esteemed\\ncolleagues in the majority. I would affirm.\\n\\n\\n\\n\\n 26\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4359826/\", \"author_raw\": \"NYGAARD, Circuit Judge, dissenting\"}]}"},"judge1":{"kind":"string","value":"SHWARTZ"},"judge2":{"kind":"string","value":"NYGAARD"},"judge3":{"kind":"string","value":"SHWARTZ"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":5,"string":"5"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":3,"string":"3"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":2,"string":"2"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4582573/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":1,"string":"1"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Appellant v. Raymont WRIGHT\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-17\nOpinion type: majority\nHas dissenting opinion: Yes\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-1972\n _____________\n\n UNITED STATES OF AMERICA,\n\n Appellant\n\n v.\n\n RAYMONT WRIGHT\n\n ______________\n\n ON APPEAL FROM THE\n UNITED STATES DISTRICT COURT\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\n (D.C. No. 2-14-cr-00292-001)\n District Judge: Hon. Cathy Bissoon\n ______________\n\n Argued May 24, 2018\n ______________\n\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\n Judges.\n\n (Opinion Filed: January 17, 2019)\n\n ______________\n\n OPINION OF THE COURT\n ________________\n\nDonovan J. Cocas, Esq. [ARGUED]\nJane M. Datttilo, Esq.\nLaura S. Irwin, Esq.\nOffice of the United States Attorney\n700 Grant Street\nSuite 4000\nPittsburgh, PA 15219\n\n Attorney for Appellant\n\nRenee Pietropaolo, Esq. [ARGUED]\nLisa B. Freeland, Esq.\nAkin Adepoju, Esq.\nOffice of the Federal Public Defender\n1001 Liberty Avenue\n1500 Liberty Center\nPittsburgh, PA 15222\n\n Attorneys for Appellee Raymont Wright\n\nLawrence S. Lustberg, Esq. [ARGUED]\nGibbons, P.C.\nOne Gateway Center\nNewark, NJ 07102\n\n Attorney for Amicus Appellee National Association of\n Criminal Defense Lawyers\n\n\n\n\n 2\n\nSHWARTZ, Circuit Judge.\n\n The District Court barred a retrial of and dismissed the\nindictment against Defendant Raymont Wright with prejudice\nafter two juries failed to reach a verdict. The Court did so\nrelying on its inherent authority, but without finding that any\nmisconduct had occurred or that Wright would suffer any\nprejudice beyond the general anxiety and inconvenience of\nfacing a retrial. Under such circumstances, the Court lacked\nthe inherent authority to bar the retrial and dismiss the\nindictment. Therefore, we will reverse the order dismissing the\nindictment and remand for further proceedings.\n\n I\n\n In December 2014, Wright was charged with being a\nfelon in possession of a firearm, in violation of 18 U.S.C.\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\nMay 2016. The jury was unable to reach a verdict. A second\ntrial was held in March 2017, and that jury was also unable to\nreach a verdict.\n\n During both trials, the jury heard evidence from police\nofficers about Wright’s actions on July 24, 2014. 1 That\nevening, five Pittsburgh Police detectives were patrolling in\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\nwere in the lead car, and Detectives Fallert and Goob were in\nthe second car. Around 8:30 p.m. (when it was still daylight),\nFallert and Goob saw a man, later identified as Wright, driving\n\n 1\n The following facts are drawn largely from the\nevidence presented at the first trial.\n\n\n\n\n 3\n\na car in the opposite direction well above the 25-mile-per-hour\nspeed limit. The detectives turned around to follow Wright,\nand Wright sped up and turned onto a loop-shaped road. The\ndetectives pursued Wright, who fled at a high speed and ran at\nleast four stop signs. The lead car lost sight of Wright shortly\nthereafter and discontinued pursuit.\n\n Officers in the lead car then noticed skid marks\nsuggesting that a car had intended but failed to make a left turn\nat the end of a street. Officers thereafter came upon Wright’s\ncar in a parking lot below. The car had gone through a fence,\nover a hillside, and into the lot. The car hit two unoccupied\nparked cars, its tires blew out, and its windows were down.\n\n Detectives Baker and Henson exited the vehicle at the\ntop of the hill and remained where Wright’s car broke through\nthe fence, and Detective Kennedy drove his car down to the\nparking lot’s entrance. Baker and Henson testified that they\nsaw Wright search around the rear passenger seat of the car,\nback out of the vehicle with a black semi-automatic handgun\nin his right hand, and try to “rack the slide,” which can insert\nor remove a round from the chamber. App. 118-19. They had\ntheir weapons drawn and told Wright to drop the gun. At first,\nWright merely stepped back, but he eventually tossed the gun\nto the side, backed away, and lied on the ground. Pittsburgh\npolice officer Elliott and his partner, who heard of the crash on\nthe radio, were the first to reach Wright, and saw him lying on\nthe ground with a handgun next to him. Henson stated that\nwhen he made it down to the parking lot, he heard Wright say\nto him, “Hey, big guy. You won this time or you won this\nround, something of that nature. He [Wright] said: You feel\nme? You won this time,” which Henson understood to mean\nthat he had just avoided a shootout or that he caught Wright\n\n\n\n\n 4\n\nafter the pursuit. App. 125. Henson subsequently took custody\nof the gun and noticed the slide lever was bent, and when he\nstraightened it, saw the gun was loaded with eight rounds, and\none in the chamber. 2\n\n At the close of the Government’s case, Wright moved\nfor a directed verdict, arguing that no reasonable juror could\nfind beyond a reasonable doubt that Wright possessed the\nfirearm. The District Court denied the motion because “the\nevidence does thus far demonstrate that a reasonable juror\ncould most certainly find the Defendant guilty of the charge in\nthis case.” App. 171. Wright did not present a case.\n\n The jury deliberated for approximately five hours and\nthen reported to the Court that it was deadlocked. After polling\nthe jurors to confirm they were deadlocked and further\ndeliberations would not bring them closer to a unanimous\nverdict, the District Court declared a mistrial.\n\n At Wright’s March 2017 retrial, the Government\npresented substantially the same evidence. The Government\nalso called Detective Kennedy and Lieutenant Palermo, who\nwere at the scene after Wright was arrested, as well as experts\nwho testified regarding the collection of DNA and fingerprint\nevidence from firearms to respond to Wright’s argument at the\nfirst trial that investigators chose not to test the gun for forensic\nevidence in an effort to cover up that they had planted the gun\nat the scene.\n\n\n 2\n The parties stipulated Wright had been convicted of a\nqualifying felony, and an ATF Special Agent testified about\nthe gun’s interstate nexus.\n\n\n\n\n 5\n\n At the close of the Government’s case, Wright again\nmoved for a judgment of acquittal, which the Court denied\nbecause “there is sufficient evidence in the record to establish\nbeyond a reasonable doubt that Mr. Wright possessed the\nfirearm in the case,” App. 650. Wright did not put on a case.\n\n The second jury deliberated for approximately three\nhours and then reported that it was hopelessly deadlocked. The\nCourt polled the jury to confirm the deadlock and then\ndismissed the jury. 3\n\n After the Government notified the Court that it intended\nto retry the case, the Court required the parties to brief\n“whether the Court, through an exercise of its inherent\nauthority, should prohibit or permit a second re-trial in this\ncase.” App. 26. After considering the parties’ arguments, the\nDistrict Court dismissed the indictment with prejudice, holding\nthat it “ha[d] the inherent authority, under some circumstances,\nto dismiss an indictment following multiple mistrials.” United\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\nunderlying the Double Jeopardy Clause also applied to a\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\n(2) other courts had dismissed indictments in similar\n\n 3\n Wright asserted that in the first trial, jurors voted 8-4\nfor acquittal, and in the second trial, the jury was evenly split.\nThe Government asserted that in the first trial, jurors voted 7-\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\nnot explain how he obtained these numbers, the Government\nsaid it obtained them by speaking with the jurors.\n\n\n\n\n 6\n\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\nexpressly allows the Government to retry a case after a mistrial,\nnothing in the rule “limits a court’s inherent supervisory\nauthority to dismiss an indictment in the interests of\nfundamental fairness,” id. at *4; and (4) if the Court were to\nadopt the Government’s position that there are no limit to the\nnumber of times the Government can retry a defendant, it\nwould be tantamount to a “type of jury shopping” that a court\nshould not permit, id. at *4. The District Court also considered\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\nconcluded that most factors supported dismissal. 4\n\n 4\n The Abbati factors are\n\n (1) the number of prior mistrials and the\n outcome of the juries’ deliberations, so far as is\n known; (2) the character of prior trials in terms\n of length, complexity, and similarity of evidence\n presented; (3) the likelihood of any substantial\n difference in a subsequent trial, if allowed;\n (4) the trial court’s own evaluation of the relative\n strength of each party’s case; and (5) the\n professional conduct and diligence of respective\n counsel, particularly of the prosecuting attorney.\n The court must also give due weight to the\n prosecutor’s decision to reprosecute, assessing\n the reasons for that decision, such as the gravity\n\n\n\n\n 7\n\n The Government appeals.\n\n II 5\n\n We review the District Court’s order dismissing the\nindictment based on the Court’s inherent power for abuse of\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\n\n of the criminal charges and the public’s concern\n in the effective and definitive conclusion of\n criminal prosecutions. Conversely, the court\n should accord careful consideration to the status\n of the individual defendant and the impact of a\n retrial upon the defendant in terms of untoward\n hardship and unfairness.\n\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\nat 521-22). For the reasons set forth herein, we would not\nadopt Abbati, but even if we were to consider the Abbati\nfactors, we would conclude that they do not support dismissal\nin this case.\n 5\n The District Court had jurisdiction pursuant to 18\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\n§ 3731.\n 6\n The phrases “inherent power,” “inherent authority,”\n“supervisory power,” and “supervisory authority” are all used\nto describe the basis for a court action seeking to maintain the\nintegrity of the proceedings that is not directly tethered to a\nspecific rule, statute, or constitutional provision. See, e.g.,\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\n43 (1991) (inherent power); Bank of Nova Scotia v. United\n\n\n\n\n 8\n\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\nindictment for abuse of discretion); cf. Chambers v. NASCO,\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\nsanctions under its inherent power for abuse of discretion);\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\n2005) (“A trial court’s remedy for a discovery violation under\nits supervisory powers is reviewed for abuse of discretion.”).\nA district court abuses its discretion when it makes an errant\nconclusion of law, an improper application of law to fact, or a\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\n\n A\n\n Federal Rule of Criminal Procedure 31 allows the\nGovernment to retry a case if the court declares a mistrial after\na jury announces it is unable to reach a verdict. Specifically,\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\non one or more counts, the court may declare a mistrial on\nthose counts. The government may retry any defendant on any\ncount on which the jury could not agree.” Fed. R. Crim. P.\n31(b)(3). The word “may” means that the Government has the\n\n\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\n(supervisory power); United States v. Payner, 447 U.S. 727,\n733-36 (1980) (supervisory power); United States v. Nobles,\n422 U.S. 225, 231 (1975) (inherent power).\n Even if we accepted the distinctions our dissenting\ncolleague has drawn between inherent judicial powers,\nlegislatively granted judicial powers, and supervisory powers,\neach category must operate within the constitutional\nframework, including the separation of powers.\n\n\n\n\n 9\n\ndiscretion to retry a case, and nothing in the rule or its\ncommentary provides or even suggests a limit on the number\nof retrials it may conduct. See United States v. Wqas Khan,\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\n\n 7\n While Rule 31 does not limit the Government’s\nauthority to retry a case, a handful of district courts have\ndismissed indictments following a second hung jury, but those\ndecisions are not persuasive. In Ingram, the district court\ndismissed the indictment sua sponte (without any initial\nobjection by the Government) after two mistrials—in which\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\njailed during the pendency of the trials, and “[t]he Government\nha[d] no new proof; it simply want[ed] another chance.” 412\nF. Supp. at 385. The court concluded that to permit a retrial\nwould be “to ignore the reasonable doubt standard,” and so\n“[t]he Court’s intervention [was] required in the interest of\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\n(McGowan, J., dissenting)). The Ingram court, however, relied\nin part on the dissent in De Diego. Cases since Ingram have\napplied the De Diego majority’s view concerning a court’s\nlimited authority to dismiss an indictment. See, e.g., United\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\nDe Diego and reversing the district court’s dismissal of the\nindictment where the district court found it would be\n“unconscionable” to retry to the defendant); United States v.\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\nDiego and its dissent and holding a district court does not have\nauthority to sua sponte dismiss an indictment based on the\n\n\n\n\n 10\n\ndefendant’s poor health); United States v. Mussehl, 453 F.\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\nto dismiss the indictment based on alleged errors at trial, and\nciting De Diego for the proposition that “[t]he duty [to\nadminister justice] encompasses the concept of review of the\nquestion whether the United States Attorney, in making his\ndecision to prosecute, complied with the law, but does not\nallow the Court to question a United States Attorney’s\njudgment decision to prosecute, when lawfully made”).\n The District Court also relied on Rossoff, where the\ncourt denied the Government’s motion to dismiss the\nindictment under Federal Rule of Criminal Procedure 48(a),\nbut still dismissed the indictment with prejudice. 806 F. Supp.\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\nbeen two trials, and the Government sought to dismiss the\nindictment and refile the charges in a different judicial district.\nId. The court determined it had authority to dismiss an\nindictment with prejudice if a retrial was “against the concept\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\nSupp. 384), and did so because, among other reasons, the\ndefendant was in poor health, was under significant strain, and\na majority of jurors at both trials found him not guilty, id. at\n203. Rossoff, however, is distinguishable from Wright’s case\nbecause in Rossoff, the Government sought to dismiss the\nindictment so that it could refile charges in a different judicial\ndistrict, which caused the court to question the Government’s\ngood faith. In Wright’s case, the District Court made no\nfinding that the Government’s desire to retry Wright was for\nan improper purpose.\n In addition, and significantly, neither Ingram nor\nRossoff addressed the doctrine of separation of powers.\nRather, each essentially relied on a general concept of fairness\n\n\n\n\n 11\n\nthe text that empowers a court to prohibit the Government from\nretrying a case. 8\n B\n\n Apparently aware that Rule 31 did not provide it with a\nbasis to preclude a retrial in these circumstances, the District\nCourt concluded that it had the inherent authority to forbid the\nretrial and dismiss the indictment. The District Court erred.\n\n The exercise of inherent authority must satisfy two\nrequirements: (1) it “must be a reasonable response to the\n\n\nto the defendant in deciding to dismiss an indictment. See\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\nIn this Circuit, however, “[t]he judiciary may not impose its\npersonal and private notions of ‘fairness’ on law enforcement\nofficials, but does have a limited authority to affect\nprosecutorial actions when those actions are taken in violation\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\n596 (3d Cir. 1992) (citations omitted).\n 8\n Rule 31 differs from other Federal Rules of Criminal\nProcedure because it makes no mention of the court’s\nauthority. For instance, Rule 48(b) states that a court has\nauthority to dismiss an indictment “if unnecessary delay occurs\nin: (1) presenting a charge to the grand jury; (2) filing an\ninformation against a defendant; or (3) bringing a defendant to\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\ngrounds on which a district court could also dismiss an\nindictment, but each would be triggered by a motion, such as a\nmotion to dismiss for failure to comply with Rule 16’s\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\n16(d)(2)(D), or a motion asserting a defect in the indictment,\nFed. R. Crim. P. 12(b)(3)(B).\n\n\n\n\n 12\n\nproblems and needs confronting the court’s fair administration\nof justice,” and (2) it “cannot be contrary to any express grant\nof or limitation on the district court’s power contained in a rule\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\n(citations and internal quotation marks omitted). We will\nexamine each of these requirements in turn.\n\n 1\n\n As to the first Dietz requirement, “[g]uided by\nconsiderations of justice, and in the exercise of supervisory\npowers, federal courts may, within limits, formulate procedural\nrules not specifically required by the Constitution or the\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\n(internal quotation marks and citation omitted). Such rules\nmust be imposed (1) “to implement a remedy for violation of\nrecognized rights,” (2) “to preserve judicial integrity by\nensuring that a conviction rests on appropriate considerations\nvalidly before the jury,” and (3) “as a remedy designed to deter\nillegal conduct.” Id. (citations omitted). Thus, a court may\nexercise its inherent authority only when it is necessary to\naddress improper conduct and ensure respect for the\nproceedings.\n\n Under these principles, a court may dismiss an\nindictment based upon its inherent authority only if the\nGovernment engaged in misconduct, the defendant was\nprejudiced, and no less severe remedy was available to address\nthe prejudice. See Bank of Nova Scotia v. United States, 487\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\n(stating that “[a] court may dismiss an indictment under its\nsupervisory powers only when the defendant suffers\nsubstantial prejudice and where no lesser remedial action is\n\n\n\n\n 13\n\navailable” (citations and internal quotation marks omitted));\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\n(observing that “a district court may not, in the management of\nits docket, exercise its discretion to dismiss an indictment with\nprejudice, either under Rule 48(b) or under its supervisory\npower, unless the violation caused prejudice to the defendant\nor posed a substantial threat thereof” (emphasis omitted));\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\n(holding that an indictment may not be dismissed for\nprosecutorial misconduct absent a showing that the misconduct\nprejudiced the defendants, and stating that “virtually every\nother circuit to consider the issue post-Hasting and Nova Scotia\nhas also held that an indictment may not be dismissed based on\nprosecutorial misconduct, absent a showing of prejudice to the\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\n(7th Cir. 1993) (“A federal judge is not authorized to punish\nthe misconduct of a prosecutor by letting the defendant walk,\nunless the misconduct not only violated the defendant’s rights\nbut also prejudiced his defense . . . .”); United States v. Tucker,\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\nexercise its supervisory authority to reverse a conviction or\ndismiss an indictment absent prejudice to the defendant.”);\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\nHasting, and Bank of Nova Scotia form a trilogy admonishing\nfederal courts to refrain from using the supervisory power to\nconform executive conduct to judicially preferred norms by\ndismissing charges, absent cognizable prejudice to a particular\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\nCir. 1992) (“Before it may invoke this [supervisory] power [to\ndismiss an indictment], a court must first find that the\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\n1480 (9th Cir. 1994).\n\n\n\n\n 14\n\n In this case, there has been no misconduct. Indeed, the\nDistrict Court noted that the Government performed diligently\nand professionally in both trials, Wright, 2017 WL 1179006,\nat *4, and found that the evidence was sufficient to prove\nbeyond a reasonable doubt that Wright possessed the gun. The\nDistrict Court nonetheless applied its own predictions about\nwhat another jury may do when presented with the same\nevidence, emphasized the need for finality, and opined that the\neffect of prosecution on the defendant precluded a proper\nprosecution from proceeding. See id. at *5-6. Invoking its own\nnotions about the unfairness of requiring a defendant to face a\nretrial where the Government did not obtain a majority of the\njurors’ votes is an improper exercise of a court’s supervisory\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\nMoreover, there is no prejudice to a defendant simply because\nhe faces the anxiety and the normal stress of undergoing a trial.\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\n1975) (“[A]nxiety is present to some degree in virtually every\ncase. Something more than the normal anxiety that\naccompanies a trial is necessary to show a degree of\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\nonly real harm alleged is the general unfairness to these\ndefendants in having to go forward yet again with a lengthy\ntrial, in their being ‘ground down’ by the several months’ drain\non their mental, emotional, and financial resources. A lack of\nsuch fairness, however, does not alone violate due process.”).\nRather, prejudice sufficient for the District Court to intervene\nin a proper prosecution based upon its inherent authority occurs\nonly where the Government engages in actions that place a\ndefendant at a disadvantage in addressing the charges. That\nsort of prejudice is absent in this case.\n\n\n\n\n 15\n\n Unless there is some constitutional basis, such as a due\nprocess violation, it makes sense to limit a court’s authority to\nbar retrial to instances of prosecutorial misconduct and\nprejudice. First, it ensures that a judge’s personal preferences\nabout a case do not influence whether the case proceeds. See\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\n(“The judiciary may not impose its personal and private\nnotions of ‘fairness’ on law enforcement officials, but does\nhave a limited authority to affect prosecutorial actions when\nthose actions are taken in violation of the Constitution.”).\nSecond, as more fully discussed below, it guarantees that a\ncourt limits the Executive’s decision to prosecute only where\nthere is a constitutionally sound reason to do so. 9 This brings\nus to the second Dietz requirement.\n\n\n 9\n For these reasons, we find unpersuasive our dissenting\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\nobservation that a court has the inherent power to resolve a\ncase, as authority for allowing a court dismiss an indictment\nafter successive hung juries. As a general matter, there is no\ndoubt that a court has the authority to dismiss a case, but it may\nnot simply end a case because it decides that it should not be\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\ntheir progeny make clear, the court must point to evidentiary\ndeficiency, prejudicial misconduct, or a constitutional basis,\nsuch as double jeopardy or due process, to justify precluding a\nprosecution. If a court believed that the evidence was deficient,\nthe prosecutor engaged in prejudicial misconduct, or a retrial\nwould violate the constitution, then it has a basis to preclude a\nretrial. Requiring such reasons for barring a retrial ensures that\n\n\n\n\n 16\n\n 2\n\n The second Dietz requirement reminds a court that the\nexercise of its powers must be in accordance with the\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\nwith the Constitution, a court must be mindful of its role in our\ntripartite form of government and the doctrine of separation of\npowers. Separation-of-powers principles limit a court’s\ninherent authority. “Regardless of whether the supervisory\npower stems from the federal courts’ inherent power to check\nintrusions by other branches of government or whether it is a\nform of specialized federal common law, the separation-of-\npowers principle imposes significant limits on it,” and\n“[p]roper regard for judicial integrity does not justify a\n‘chancellor’s foot veto’ over activities of coequal branches of\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\nCir. 1985) (internal quotation marks omitted) (quoting United\nStates v. Russell, 411 U.S. 423, 435 (1973)).\n\n In the criminal context, the Executive Branch has\n“broad discretion as to whom to prosecute,” and this discretion\n“rests largely on the recognition that the decision to prosecute\nis particularly ill-suited to judicial review.” Wayte v. United\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\nquotation marks omitted). A court is not equipped to evaluate\n\n [s]uch factors as . . . the prosecution’s general\n deterrence value, the Government’s enforcement\n priorities, and the case’s relationship to the\n\n\nthe ruling is not based on a court’s own personal sense of\nwhether a case is worthy of prosecution.\n\n\n\n\n 17\n\n Government’s overall enforcement plan . . . .\n Judicial supervision in this area, moreover,\n entails systemic costs of particular concern.\n Examining the basis of a prosecution delays the\n criminal proceeding, threatens to chill law\n enforcement by subjecting the prosecutor’s\n motives and decisionmaking to outside inquiry,\n and may undermine prosecutorial effectiveness\n by revealing the Government’s enforcement\n policy. All of these are substantial concerns that\n make the courts properly hesitant to examine the\n decision whether to prosecute.\n\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\n(echoing similar sentiments with respect to Rule 48(a)\ndismissals). Thus, absent constitutional concerns, the decision\nto try or retry a case is at the discretion of the prosecutor.\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\nas superprosecutors, second-guessing the legitimate exercise of\ncore elements of prosecutorial discretion, but rather as neutral\narbiters of the law” (citation and internal quotation marks\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\n1994) (“[T]he choice to forego permanently a prosecution is\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\n676 (“In maintaining order in our own house, we should not\nneedlessly trample on the interest of the prosecutor and of the\npublic in securing proper, lasting convictions.”); Isgro, 974\nF.2d at 1097 (stating that the doctrine of separation of powers\n“mandates judicial respect for the independence of the\nprosecutor,” and “[d]ismissal of an indictment with prejudice\n\n\n\n\n 18\n\nis the most severe sanction possible”). 10 Accordingly,\nseparation-of-powers principles preclude a court from\nterminating a prosecution absent misconduct and prejudice to\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\n974 F.2d at 1094.\n\n In short, a court’s power to preclude a prosecution is\nlimited by the separation of powers and, specifically, the\nExecutive’s law-enforcement and prosecutorial prerogative.\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\nhere to dismiss an indictment in the absence of misconduct and\nprejudice and based only on the fact that two juries could not\nreach a verdict intrudes on the Executive’s domain and thereby\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\nat 138; Isgro, 974 F.2d 1091.\n\n 10\n Several state courts have also refused to recognize\nany inherent authority to dismiss an indictment to prevent a\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\n(Fla. Dist. Ct. App. 1980). Other states, however, have\nrecognized a court’s authority to dismiss an indictment sua\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\n712; Witt, 572 S.W.2d at 917. These latter cases are\nunpersuasive because they give too little weight to the\nseparation of powers, a crucial constitutional principle in the\nfederal system.\n\n\n\n\n 19\n\n Finally, there is no statute or procedural rule that\npermits a court to bar a retrial in the absence of misconduct and\nprejudice. First, a court may not dismiss an indictment as a\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\n505. Second, a court’s inherent power does not “include the\npower to develop rules that circumvent or conflict with the\nFederal Rules of Criminal Procedure.” Carlisle v. United\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\nexercise of inherent authority circumvents the absence of\npower of the district court to dismiss an indictment in Rule\n31(b). As stated above, courts have inherent authority to\ndismiss indictments, including, for instance, for prosecutorial\nmisconduct if the defendant was prejudiced, Bank of Nova\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\nnor our Court has extended a court’s inherent authority to allow\n\n 11\n In Chambers, for example, the Supreme Court\nrecognized a court’s authority to impose silence, respect, and\ndecorum based on its authority to manage its own affairs. 501\nU.S. at 43. This authority has been exercised by controlling\nadmission to the bar and disciplining its members; punishing\nfor contempt, which penalizes disruption to proceedings and\ndisobedience to court orders; disallowing fraud on the courts;\nensuring the proceedings move forward; and curtailing\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\ncivil case for failure to prosecute to prevent delays and court\ncongestion as part of a court’s inherent power to manage its\nown affairs). Chambers and Link address how a court may\nmanage its own proceedings, but they do not address how the\ncourt must also account for issues of separation of powers in\nthe context of a criminal case.\n\n\n\n\n 20\n\nthe sua sponte dismissal of an indictment solely to preclude\nmultiple mistrials following hung juries, see Chambers, 501\nU.S. at 47; HSBC, 863 F.3d at 136. 12\n\n 12\n Most cases concerning a court’s inherent authority\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\n(noting a court’s inherent powers to rescind a jury discharge\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\n(recognizing a court’s authority to vacate a judgment upon\nproof that a fraud was perpetrated on the court, and, in\nparticular, to assess as a sanction the entire amount of the\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\n(authority to dismiss a civil case sua sponte for failure to\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\n(1947) (dismissing an action based on the doctrine of forum\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\n(citing cases involving the scope of a district court’s inherent\npower); Eash, 757 F.2d at 561-64 (same).\n There are other circumstances in which district courts\nlack the inherent authority to act, and most of those situations\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\n433 (holding that a court does not have authority to grant a\npost-verdict motion for judgment of acquittal, filed one day\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\n45-50, 55 (holding that a district court does not have inherent\nauthority to dismiss an indictment because the Government\nfailed to disclose to the grand jury substantial exculpatory\nevidence; “[b]ecause the grand jury is an institution separate\nfrom the courts, over whose functioning the courts do not\npreside, we think it clear that, as a general matter at least, no\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\nat 129, 135-37 (holding that the district court violated\nseparation-of-powers principles by sua sponte invoking its\n\n\n\n\n 21\n\n Thus, the District Court abused its discretion in barring\na retrial and dismissing the indictment. 13\n\n III\n\n For the foregoing reasons, we will reverse and remand\nfor further proceedings.\n\n\n\n\nsupervisory power to oversee the government’s entry into and\nimplementation of a deferred prosecution agreement).\n 13\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Appellant v. Raymont WRIGHT\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-17\\nOpinion type: majority\\nHas dissenting opinion: Yes\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-1972\\n _____________\\n\\n UNITED STATES OF AMERICA,\\n\\n Appellant\\n\\n v.\\n\\n RAYMONT WRIGHT\\n\\n ______________\\n\\n ON APPEAL FROM THE\\n UNITED STATES DISTRICT COURT\\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\\n (D.C. No. 2-14-cr-00292-001)\\n District Judge: Hon. Cathy Bissoon\\n ______________\\n\\n Argued May 24, 2018\\n ______________\\n\\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\\n Judges.\\n\\n (Opinion Filed: January 17, 2019)\\n\\n ______________\\n\\n OPINION OF THE COURT\\n ________________\\n\\nDonovan J. Cocas, Esq. [ARGUED]\\nJane M. Datttilo, Esq.\\nLaura S. Irwin, Esq.\\nOffice of the United States Attorney\\n700 Grant Street\\nSuite 4000\\nPittsburgh, PA 15219\\n\\n Attorney for Appellant\\n\\nRenee Pietropaolo, Esq. [ARGUED]\\nLisa B. Freeland, Esq.\\nAkin Adepoju, Esq.\\nOffice of the Federal Public Defender\\n1001 Liberty Avenue\\n1500 Liberty Center\\nPittsburgh, PA 15222\\n\\n Attorneys for Appellee Raymont Wright\\n\\nLawrence S. Lustberg, Esq. [ARGUED]\\nGibbons, P.C.\\nOne Gateway Center\\nNewark, NJ 07102\\n\\n Attorney for Amicus Appellee National Association of\\n Criminal Defense Lawyers\\n\\n\\n\\n\\n 2\\n\\nSHWARTZ, Circuit Judge.\\n\\n The District Court barred a retrial of and dismissed the\\nindictment against Defendant Raymont Wright with prejudice\\nafter two juries failed to reach a verdict. The Court did so\\nrelying on its inherent authority, but without finding that any\\nmisconduct had occurred or that Wright would suffer any\\nprejudice beyond the general anxiety and inconvenience of\\nfacing a retrial. Under such circumstances, the Court lacked\\nthe inherent authority to bar the retrial and dismiss the\\nindictment. Therefore, we will reverse the order dismissing the\\nindictment and remand for further proceedings.\\n\\n I\\n\\n In December 2014, Wright was charged with being a\\nfelon in possession of a firearm, in violation of 18 U.S.C.\\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\\nMay 2016. The jury was unable to reach a verdict. A second\\ntrial was held in March 2017, and that jury was also unable to\\nreach a verdict.\\n\\n During both trials, the jury heard evidence from police\\nofficers about Wright’s actions on July 24, 2014. 1 That\\nevening, five Pittsburgh Police detectives were patrolling in\\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\\nwere in the lead car, and Detectives Fallert and Goob were in\\nthe second car. Around 8:30 p.m. (when it was still daylight),\\nFallert and Goob saw a man, later identified as Wright, driving\\n\\n 1\\n The following facts are drawn largely from the\\nevidence presented at the first trial.\\n\\n\\n\\n\\n 3\\n\\na car in the opposite direction well above the 25-mile-per-hour\\nspeed limit. The detectives turned around to follow Wright,\\nand Wright sped up and turned onto a loop-shaped road. The\\ndetectives pursued Wright, who fled at a high speed and ran at\\nleast four stop signs. The lead car lost sight of Wright shortly\\nthereafter and discontinued pursuit.\\n\\n Officers in the lead car then noticed skid marks\\nsuggesting that a car had intended but failed to make a left turn\\nat the end of a street. Officers thereafter came upon Wright’s\\ncar in a parking lot below. The car had gone through a fence,\\nover a hillside, and into the lot. The car hit two unoccupied\\nparked cars, its tires blew out, and its windows were down.\\n\\n Detectives Baker and Henson exited the vehicle at the\\ntop of the hill and remained where Wright’s car broke through\\nthe fence, and Detective Kennedy drove his car down to the\\nparking lot’s entrance. Baker and Henson testified that they\\nsaw Wright search around the rear passenger seat of the car,\\nback out of the vehicle with a black semi-automatic handgun\\nin his right hand, and try to “rack the slide,” which can insert\\nor remove a round from the chamber. App. 118-19. They had\\ntheir weapons drawn and told Wright to drop the gun. At first,\\nWright merely stepped back, but he eventually tossed the gun\\nto the side, backed away, and lied on the ground. Pittsburgh\\npolice officer Elliott and his partner, who heard of the crash on\\nthe radio, were the first to reach Wright, and saw him lying on\\nthe ground with a handgun next to him. Henson stated that\\nwhen he made it down to the parking lot, he heard Wright say\\nto him, “Hey, big guy. You won this time or you won this\\nround, something of that nature. He [Wright] said: You feel\\nme? You won this time,” which Henson understood to mean\\nthat he had just avoided a shootout or that he caught Wright\\n\\n\\n\\n\\n 4\\n\\nafter the pursuit. App. 125. Henson subsequently took custody\\nof the gun and noticed the slide lever was bent, and when he\\nstraightened it, saw the gun was loaded with eight rounds, and\\none in the chamber. 2\\n\\n At the close of the Government’s case, Wright moved\\nfor a directed verdict, arguing that no reasonable juror could\\nfind beyond a reasonable doubt that Wright possessed the\\nfirearm. The District Court denied the motion because “the\\nevidence does thus far demonstrate that a reasonable juror\\ncould most certainly find the Defendant guilty of the charge in\\nthis case.” App. 171. Wright did not present a case.\\n\\n The jury deliberated for approximately five hours and\\nthen reported to the Court that it was deadlocked. After polling\\nthe jurors to confirm they were deadlocked and further\\ndeliberations would not bring them closer to a unanimous\\nverdict, the District Court declared a mistrial.\\n\\n At Wright’s March 2017 retrial, the Government\\npresented substantially the same evidence. The Government\\nalso called Detective Kennedy and Lieutenant Palermo, who\\nwere at the scene after Wright was arrested, as well as experts\\nwho testified regarding the collection of DNA and fingerprint\\nevidence from firearms to respond to Wright’s argument at the\\nfirst trial that investigators chose not to test the gun for forensic\\nevidence in an effort to cover up that they had planted the gun\\nat the scene.\\n\\n\\n 2\\n The parties stipulated Wright had been convicted of a\\nqualifying felony, and an ATF Special Agent testified about\\nthe gun’s interstate nexus.\\n\\n\\n\\n\\n 5\\n\\n At the close of the Government’s case, Wright again\\nmoved for a judgment of acquittal, which the Court denied\\nbecause “there is sufficient evidence in the record to establish\\nbeyond a reasonable doubt that Mr. Wright possessed the\\nfirearm in the case,” App. 650. Wright did not put on a case.\\n\\n The second jury deliberated for approximately three\\nhours and then reported that it was hopelessly deadlocked. The\\nCourt polled the jury to confirm the deadlock and then\\ndismissed the jury. 3\\n\\n After the Government notified the Court that it intended\\nto retry the case, the Court required the parties to brief\\n“whether the Court, through an exercise of its inherent\\nauthority, should prohibit or permit a second re-trial in this\\ncase.” App. 26. After considering the parties’ arguments, the\\nDistrict Court dismissed the indictment with prejudice, holding\\nthat it “ha[d] the inherent authority, under some circumstances,\\nto dismiss an indictment following multiple mistrials.” United\\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\\nunderlying the Double Jeopardy Clause also applied to a\\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\\n(2) other courts had dismissed indictments in similar\\n\\n 3\\n Wright asserted that in the first trial, jurors voted 8-4\\nfor acquittal, and in the second trial, the jury was evenly split.\\nThe Government asserted that in the first trial, jurors voted 7-\\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\\nnot explain how he obtained these numbers, the Government\\nsaid it obtained them by speaking with the jurors.\\n\\n\\n\\n\\n 6\\n\\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\\nexpressly allows the Government to retry a case after a mistrial,\\nnothing in the rule “limits a court’s inherent supervisory\\nauthority to dismiss an indictment in the interests of\\nfundamental fairness,” id. at *4; and (4) if the Court were to\\nadopt the Government’s position that there are no limit to the\\nnumber of times the Government can retry a defendant, it\\nwould be tantamount to a “type of jury shopping” that a court\\nshould not permit, id. at *4. The District Court also considered\\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\\nconcluded that most factors supported dismissal. 4\\n\\n 4\\n The Abbati factors are\\n\\n (1) the number of prior mistrials and the\\n outcome of the juries’ deliberations, so far as is\\n known; (2) the character of prior trials in terms\\n of length, complexity, and similarity of evidence\\n presented; (3) the likelihood of any substantial\\n difference in a subsequent trial, if allowed;\\n (4) the trial court’s own evaluation of the relative\\n strength of each party’s case; and (5) the\\n professional conduct and diligence of respective\\n counsel, particularly of the prosecuting attorney.\\n The court must also give due weight to the\\n prosecutor’s decision to reprosecute, assessing\\n the reasons for that decision, such as the gravity\\n\\n\\n\\n\\n 7\\n\\n The Government appeals.\\n\\n II 5\\n\\n We review the District Court’s order dismissing the\\nindictment based on the Court’s inherent power for abuse of\\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\\n\\n of the criminal charges and the public’s concern\\n in the effective and definitive conclusion of\\n criminal prosecutions. Conversely, the court\\n should accord careful consideration to the status\\n of the individual defendant and the impact of a\\n retrial upon the defendant in terms of untoward\\n hardship and unfairness.\\n\\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\\nat 521-22). For the reasons set forth herein, we would not\\nadopt Abbati, but even if we were to consider the Abbati\\nfactors, we would conclude that they do not support dismissal\\nin this case.\\n 5\\n The District Court had jurisdiction pursuant to 18\\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\\n§ 3731.\\n 6\\n The phrases “inherent power,” “inherent authority,”\\n“supervisory power,” and “supervisory authority” are all used\\nto describe the basis for a court action seeking to maintain the\\nintegrity of the proceedings that is not directly tethered to a\\nspecific rule, statute, or constitutional provision. See, e.g.,\\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\\n43 (1991) (inherent power); Bank of Nova Scotia v. United\\n\\n\\n\\n\\n 8\\n\\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\\nindictment for abuse of discretion); cf. Chambers v. NASCO,\\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\\nsanctions under its inherent power for abuse of discretion);\\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\\n2005) (“A trial court’s remedy for a discovery violation under\\nits supervisory powers is reviewed for abuse of discretion.”).\\nA district court abuses its discretion when it makes an errant\\nconclusion of law, an improper application of law to fact, or a\\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\\n\\n A\\n\\n Federal Rule of Criminal Procedure 31 allows the\\nGovernment to retry a case if the court declares a mistrial after\\na jury announces it is unable to reach a verdict. Specifically,\\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\\non one or more counts, the court may declare a mistrial on\\nthose counts. The government may retry any defendant on any\\ncount on which the jury could not agree.” Fed. R. Crim. P.\\n31(b)(3). The word “may” means that the Government has the\\n\\n\\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(supervisory power); United States v. Payner, 447 U.S. 727,\\n733-36 (1980) (supervisory power); United States v. Nobles,\\n422 U.S. 225, 231 (1975) (inherent power).\\n Even if we accepted the distinctions our dissenting\\ncolleague has drawn between inherent judicial powers,\\nlegislatively granted judicial powers, and supervisory powers,\\neach category must operate within the constitutional\\nframework, including the separation of powers.\\n\\n\\n\\n\\n 9\\n\\ndiscretion to retry a case, and nothing in the rule or its\\ncommentary provides or even suggests a limit on the number\\nof retrials it may conduct. See United States v. Wqas Khan,\\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\\n\\n 7\\n While Rule 31 does not limit the Government’s\\nauthority to retry a case, a handful of district courts have\\ndismissed indictments following a second hung jury, but those\\ndecisions are not persuasive. In Ingram, the district court\\ndismissed the indictment sua sponte (without any initial\\nobjection by the Government) after two mistrials—in which\\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\\njailed during the pendency of the trials, and “[t]he Government\\nha[d] no new proof; it simply want[ed] another chance.” 412\\nF. Supp. at 385. The court concluded that to permit a retrial\\nwould be “to ignore the reasonable doubt standard,” and so\\n“[t]he Court’s intervention [was] required in the interest of\\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\\n(McGowan, J., dissenting)). The Ingram court, however, relied\\nin part on the dissent in De Diego. Cases since Ingram have\\napplied the De Diego majority’s view concerning a court’s\\nlimited authority to dismiss an indictment. See, e.g., United\\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\\nDe Diego and reversing the district court’s dismissal of the\\nindictment where the district court found it would be\\n“unconscionable” to retry to the defendant); United States v.\\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\\nDiego and its dissent and holding a district court does not have\\nauthority to sua sponte dismiss an indictment based on the\\n\\n\\n\\n\\n 10\\n\\ndefendant’s poor health); United States v. Mussehl, 453 F.\\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\\nto dismiss the indictment based on alleged errors at trial, and\\nciting De Diego for the proposition that “[t]he duty [to\\nadminister justice] encompasses the concept of review of the\\nquestion whether the United States Attorney, in making his\\ndecision to prosecute, complied with the law, but does not\\nallow the Court to question a United States Attorney’s\\njudgment decision to prosecute, when lawfully made”).\\n The District Court also relied on Rossoff, where the\\ncourt denied the Government’s motion to dismiss the\\nindictment under Federal Rule of Criminal Procedure 48(a),\\nbut still dismissed the indictment with prejudice. 806 F. Supp.\\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\\nbeen two trials, and the Government sought to dismiss the\\nindictment and refile the charges in a different judicial district.\\nId. The court determined it had authority to dismiss an\\nindictment with prejudice if a retrial was “against the concept\\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\\nSupp. 384), and did so because, among other reasons, the\\ndefendant was in poor health, was under significant strain, and\\na majority of jurors at both trials found him not guilty, id. at\\n203. Rossoff, however, is distinguishable from Wright’s case\\nbecause in Rossoff, the Government sought to dismiss the\\nindictment so that it could refile charges in a different judicial\\ndistrict, which caused the court to question the Government’s\\ngood faith. In Wright’s case, the District Court made no\\nfinding that the Government’s desire to retry Wright was for\\nan improper purpose.\\n In addition, and significantly, neither Ingram nor\\nRossoff addressed the doctrine of separation of powers.\\nRather, each essentially relied on a general concept of fairness\\n\\n\\n\\n\\n 11\\n\\nthe text that empowers a court to prohibit the Government from\\nretrying a case. 8\\n B\\n\\n Apparently aware that Rule 31 did not provide it with a\\nbasis to preclude a retrial in these circumstances, the District\\nCourt concluded that it had the inherent authority to forbid the\\nretrial and dismiss the indictment. The District Court erred.\\n\\n The exercise of inherent authority must satisfy two\\nrequirements: (1) it “must be a reasonable response to the\\n\\n\\nto the defendant in deciding to dismiss an indictment. See\\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\\nIn this Circuit, however, “[t]he judiciary may not impose its\\npersonal and private notions of ‘fairness’ on law enforcement\\nofficials, but does have a limited authority to affect\\nprosecutorial actions when those actions are taken in violation\\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\\n596 (3d Cir. 1992) (citations omitted).\\n 8\\n Rule 31 differs from other Federal Rules of Criminal\\nProcedure because it makes no mention of the court’s\\nauthority. For instance, Rule 48(b) states that a court has\\nauthority to dismiss an indictment “if unnecessary delay occurs\\nin: (1) presenting a charge to the grand jury; (2) filing an\\ninformation against a defendant; or (3) bringing a defendant to\\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\\ngrounds on which a district court could also dismiss an\\nindictment, but each would be triggered by a motion, such as a\\nmotion to dismiss for failure to comply with Rule 16’s\\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\\n16(d)(2)(D), or a motion asserting a defect in the indictment,\\nFed. R. Crim. P. 12(b)(3)(B).\\n\\n\\n\\n\\n 12\\n\\nproblems and needs confronting the court’s fair administration\\nof justice,” and (2) it “cannot be contrary to any express grant\\nof or limitation on the district court’s power contained in a rule\\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\\n(citations and internal quotation marks omitted). We will\\nexamine each of these requirements in turn.\\n\\n 1\\n\\n As to the first Dietz requirement, “[g]uided by\\nconsiderations of justice, and in the exercise of supervisory\\npowers, federal courts may, within limits, formulate procedural\\nrules not specifically required by the Constitution or the\\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(internal quotation marks and citation omitted). Such rules\\nmust be imposed (1) “to implement a remedy for violation of\\nrecognized rights,” (2) “to preserve judicial integrity by\\nensuring that a conviction rests on appropriate considerations\\nvalidly before the jury,” and (3) “as a remedy designed to deter\\nillegal conduct.” Id. (citations omitted). Thus, a court may\\nexercise its inherent authority only when it is necessary to\\naddress improper conduct and ensure respect for the\\nproceedings.\\n\\n Under these principles, a court may dismiss an\\nindictment based upon its inherent authority only if the\\nGovernment engaged in misconduct, the defendant was\\nprejudiced, and no less severe remedy was available to address\\nthe prejudice. See Bank of Nova Scotia v. United States, 487\\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\\n(stating that “[a] court may dismiss an indictment under its\\nsupervisory powers only when the defendant suffers\\nsubstantial prejudice and where no lesser remedial action is\\n\\n\\n\\n\\n 13\\n\\navailable” (citations and internal quotation marks omitted));\\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\\n(observing that “a district court may not, in the management of\\nits docket, exercise its discretion to dismiss an indictment with\\nprejudice, either under Rule 48(b) or under its supervisory\\npower, unless the violation caused prejudice to the defendant\\nor posed a substantial threat thereof” (emphasis omitted));\\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\\n(holding that an indictment may not be dismissed for\\nprosecutorial misconduct absent a showing that the misconduct\\nprejudiced the defendants, and stating that “virtually every\\nother circuit to consider the issue post-Hasting and Nova Scotia\\nhas also held that an indictment may not be dismissed based on\\nprosecutorial misconduct, absent a showing of prejudice to the\\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\\n(7th Cir. 1993) (“A federal judge is not authorized to punish\\nthe misconduct of a prosecutor by letting the defendant walk,\\nunless the misconduct not only violated the defendant’s rights\\nbut also prejudiced his defense . . . .”); United States v. Tucker,\\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\\nexercise its supervisory authority to reverse a conviction or\\ndismiss an indictment absent prejudice to the defendant.”);\\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\\nHasting, and Bank of Nova Scotia form a trilogy admonishing\\nfederal courts to refrain from using the supervisory power to\\nconform executive conduct to judicially preferred norms by\\ndismissing charges, absent cognizable prejudice to a particular\\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\\nCir. 1992) (“Before it may invoke this [supervisory] power [to\\ndismiss an indictment], a court must first find that the\\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\\n1480 (9th Cir. 1994).\\n\\n\\n\\n\\n 14\\n\\n In this case, there has been no misconduct. Indeed, the\\nDistrict Court noted that the Government performed diligently\\nand professionally in both trials, Wright, 2017 WL 1179006,\\nat *4, and found that the evidence was sufficient to prove\\nbeyond a reasonable doubt that Wright possessed the gun. The\\nDistrict Court nonetheless applied its own predictions about\\nwhat another jury may do when presented with the same\\nevidence, emphasized the need for finality, and opined that the\\neffect of prosecution on the defendant precluded a proper\\nprosecution from proceeding. See id. at *5-6. Invoking its own\\nnotions about the unfairness of requiring a defendant to face a\\nretrial where the Government did not obtain a majority of the\\njurors’ votes is an improper exercise of a court’s supervisory\\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\nMoreover, there is no prejudice to a defendant simply because\\nhe faces the anxiety and the normal stress of undergoing a trial.\\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975) (“[A]nxiety is present to some degree in virtually every\\ncase. Something more than the normal anxiety that\\naccompanies a trial is necessary to show a degree of\\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\\nonly real harm alleged is the general unfairness to these\\ndefendants in having to go forward yet again with a lengthy\\ntrial, in their being ‘ground down’ by the several months’ drain\\non their mental, emotional, and financial resources. A lack of\\nsuch fairness, however, does not alone violate due process.”).\\nRather, prejudice sufficient for the District Court to intervene\\nin a proper prosecution based upon its inherent authority occurs\\nonly where the Government engages in actions that place a\\ndefendant at a disadvantage in addressing the charges. That\\nsort of prejudice is absent in this case.\\n\\n\\n\\n\\n 15\\n\\n Unless there is some constitutional basis, such as a due\\nprocess violation, it makes sense to limit a court’s authority to\\nbar retrial to instances of prosecutorial misconduct and\\nprejudice. First, it ensures that a judge’s personal preferences\\nabout a case do not influence whether the case proceeds. See\\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\\n(“The judiciary may not impose its personal and private\\nnotions of ‘fairness’ on law enforcement officials, but does\\nhave a limited authority to affect prosecutorial actions when\\nthose actions are taken in violation of the Constitution.”).\\nSecond, as more fully discussed below, it guarantees that a\\ncourt limits the Executive’s decision to prosecute only where\\nthere is a constitutionally sound reason to do so. 9 This brings\\nus to the second Dietz requirement.\\n\\n\\n 9\\n For these reasons, we find unpersuasive our dissenting\\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\\nobservation that a court has the inherent power to resolve a\\ncase, as authority for allowing a court dismiss an indictment\\nafter successive hung juries. As a general matter, there is no\\ndoubt that a court has the authority to dismiss a case, but it may\\nnot simply end a case because it decides that it should not be\\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\\ntheir progeny make clear, the court must point to evidentiary\\ndeficiency, prejudicial misconduct, or a constitutional basis,\\nsuch as double jeopardy or due process, to justify precluding a\\nprosecution. If a court believed that the evidence was deficient,\\nthe prosecutor engaged in prejudicial misconduct, or a retrial\\nwould violate the constitution, then it has a basis to preclude a\\nretrial. Requiring such reasons for barring a retrial ensures that\\n\\n\\n\\n\\n 16\\n\\n 2\\n\\n The second Dietz requirement reminds a court that the\\nexercise of its powers must be in accordance with the\\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\\nwith the Constitution, a court must be mindful of its role in our\\ntripartite form of government and the doctrine of separation of\\npowers. Separation-of-powers principles limit a court’s\\ninherent authority. “Regardless of whether the supervisory\\npower stems from the federal courts’ inherent power to check\\nintrusions by other branches of government or whether it is a\\nform of specialized federal common law, the separation-of-\\npowers principle imposes significant limits on it,” and\\n“[p]roper regard for judicial integrity does not justify a\\n‘chancellor’s foot veto’ over activities of coequal branches of\\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\\nCir. 1985) (internal quotation marks omitted) (quoting United\\nStates v. Russell, 411 U.S. 423, 435 (1973)).\\n\\n In the criminal context, the Executive Branch has\\n“broad discretion as to whom to prosecute,” and this discretion\\n“rests largely on the recognition that the decision to prosecute\\nis particularly ill-suited to judicial review.” Wayte v. United\\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\\nquotation marks omitted). A court is not equipped to evaluate\\n\\n [s]uch factors as . . . the prosecution’s general\\n deterrence value, the Government’s enforcement\\n priorities, and the case’s relationship to the\\n\\n\\nthe ruling is not based on a court’s own personal sense of\\nwhether a case is worthy of prosecution.\\n\\n\\n\\n\\n 17\\n\\n Government’s overall enforcement plan . . . .\\n Judicial supervision in this area, moreover,\\n entails systemic costs of particular concern.\\n Examining the basis of a prosecution delays the\\n criminal proceeding, threatens to chill law\\n enforcement by subjecting the prosecutor’s\\n motives and decisionmaking to outside inquiry,\\n and may undermine prosecutorial effectiveness\\n by revealing the Government’s enforcement\\n policy. All of these are substantial concerns that\\n make the courts properly hesitant to examine the\\n decision whether to prosecute.\\n\\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\\n(echoing similar sentiments with respect to Rule 48(a)\\ndismissals). Thus, absent constitutional concerns, the decision\\nto try or retry a case is at the discretion of the prosecutor.\\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\\nas superprosecutors, second-guessing the legitimate exercise of\\ncore elements of prosecutorial discretion, but rather as neutral\\narbiters of the law” (citation and internal quotation marks\\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\\n1994) (“[T]he choice to forego permanently a prosecution is\\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\\n676 (“In maintaining order in our own house, we should not\\nneedlessly trample on the interest of the prosecutor and of the\\npublic in securing proper, lasting convictions.”); Isgro, 974\\nF.2d at 1097 (stating that the doctrine of separation of powers\\n“mandates judicial respect for the independence of the\\nprosecutor,” and “[d]ismissal of an indictment with prejudice\\n\\n\\n\\n\\n 18\\n\\nis the most severe sanction possible”). 10 Accordingly,\\nseparation-of-powers principles preclude a court from\\nterminating a prosecution absent misconduct and prejudice to\\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\\n974 F.2d at 1094.\\n\\n In short, a court’s power to preclude a prosecution is\\nlimited by the separation of powers and, specifically, the\\nExecutive’s law-enforcement and prosecutorial prerogative.\\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\\nhere to dismiss an indictment in the absence of misconduct and\\nprejudice and based only on the fact that two juries could not\\nreach a verdict intrudes on the Executive’s domain and thereby\\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\\nat 138; Isgro, 974 F.2d 1091.\\n\\n 10\\n Several state courts have also refused to recognize\\nany inherent authority to dismiss an indictment to prevent a\\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\\n(Fla. Dist. Ct. App. 1980). Other states, however, have\\nrecognized a court’s authority to dismiss an indictment sua\\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\\n712; Witt, 572 S.W.2d at 917. These latter cases are\\nunpersuasive because they give too little weight to the\\nseparation of powers, a crucial constitutional principle in the\\nfederal system.\\n\\n\\n\\n\\n 19\\n\\n Finally, there is no statute or procedural rule that\\npermits a court to bar a retrial in the absence of misconduct and\\nprejudice. First, a court may not dismiss an indictment as a\\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\\n505. Second, a court’s inherent power does not “include the\\npower to develop rules that circumvent or conflict with the\\nFederal Rules of Criminal Procedure.” Carlisle v. United\\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\\nexercise of inherent authority circumvents the absence of\\npower of the district court to dismiss an indictment in Rule\\n31(b). As stated above, courts have inherent authority to\\ndismiss indictments, including, for instance, for prosecutorial\\nmisconduct if the defendant was prejudiced, Bank of Nova\\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\\nnor our Court has extended a court’s inherent authority to allow\\n\\n 11\\n In Chambers, for example, the Supreme Court\\nrecognized a court’s authority to impose silence, respect, and\\ndecorum based on its authority to manage its own affairs. 501\\nU.S. at 43. This authority has been exercised by controlling\\nadmission to the bar and disciplining its members; punishing\\nfor contempt, which penalizes disruption to proceedings and\\ndisobedience to court orders; disallowing fraud on the courts;\\nensuring the proceedings move forward; and curtailing\\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\\ncivil case for failure to prosecute to prevent delays and court\\ncongestion as part of a court’s inherent power to manage its\\nown affairs). Chambers and Link address how a court may\\nmanage its own proceedings, but they do not address how the\\ncourt must also account for issues of separation of powers in\\nthe context of a criminal case.\\n\\n\\n\\n\\n 20\\n\\nthe sua sponte dismissal of an indictment solely to preclude\\nmultiple mistrials following hung juries, see Chambers, 501\\nU.S. at 47; HSBC, 863 F.3d at 136. 12\\n\\n 12\\n Most cases concerning a court’s inherent authority\\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\\n(noting a court’s inherent powers to rescind a jury discharge\\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\\n(recognizing a court’s authority to vacate a judgment upon\\nproof that a fraud was perpetrated on the court, and, in\\nparticular, to assess as a sanction the entire amount of the\\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\\n(authority to dismiss a civil case sua sponte for failure to\\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\\n(1947) (dismissing an action based on the doctrine of forum\\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\\n(citing cases involving the scope of a district court’s inherent\\npower); Eash, 757 F.2d at 561-64 (same).\\n There are other circumstances in which district courts\\nlack the inherent authority to act, and most of those situations\\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\\n433 (holding that a court does not have authority to grant a\\npost-verdict motion for judgment of acquittal, filed one day\\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\\n45-50, 55 (holding that a district court does not have inherent\\nauthority to dismiss an indictment because the Government\\nfailed to disclose to the grand jury substantial exculpatory\\nevidence; “[b]ecause the grand jury is an institution separate\\nfrom the courts, over whose functioning the courts do not\\npreside, we think it clear that, as a general matter at least, no\\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\\nat 129, 135-37 (holding that the district court violated\\nseparation-of-powers principles by sua sponte invoking its\\n\\n\\n\\n\\n 21\\n\\n Thus, the District Court abused its discretion in barring\\na retrial and dismissing the indictment. 13\\n\\n III\\n\\n For the foregoing reasons, we will reverse and remand\\nfor further proceedings.\\n\\n\\n\\n\\nsupervisory power to oversee the government’s entry into and\\nimplementation of a deferred prosecution agreement).\\n 13\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":65,"cells":{"id":{"kind":"number","value":4582984,"string":"4,582,984"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"United States v. Raymont Wright"},"decision_date":{"kind":"string","value":"2019-01-18"},"docket_number":{"kind":"string","value":"17-1972"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before: MCKEE, SHWARTZ, and NYGAARD, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-1972\\n _____________\\n\\n UNITED STATES OF AMERICA,\\n\\n Appellant\\n\\n v.\\n\\n RAYMONT WRIGHT\\n\\n ______________\\n\\n ON APPEAL FROM THE\\n UNITED STATES DISTRICT COURT\\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\\n (D.C. No. 2-14-cr-00292-001)\\n District Judge: Hon. Cathy Bissoon\\n ______________\\n\\n Argued May 24, 2018\\n ______________\\n\\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\\n Judges.\\n\\n (Opinion Filed: January 17, 2019)\\n\\n ______________\\n\\n OPINION OF THE COURT\\n ________________\\n\\nDonovan J. Cocas, Esq. [ARGUED]\\nJane M. Datttilo, Esq.\\nLaura S. Irwin, Esq.\\nOffice of the United States Attorney\\n700 Grant Street\\nSuite 4000\\nPittsburgh, PA 15219\\n\\n Attorney for Appellant\\n\\nRenee Pietropaolo, Esq. [ARGUED]\\nLisa B. Freeland, Esq.\\nAkin Adepoju, Esq.\\nOffice of the Federal Public Defender\\n1001 Liberty Avenue\\n1500 Liberty Center\\nPittsburgh, PA 15222\\n\\n Attorneys for Appellee Raymont Wright\\n\\nLawrence S. Lustberg, Esq. [ARGUED]\\nGibbons, P.C.\\nOne Gateway Center\\nNewark, NJ 07102\\n\\n Attorney for Amicus Appellee National Association of\\n Criminal Defense Lawyers\\n\\n\\n\\n\\n 2\\n\\nSHWARTZ, Circuit Judge.\\n\\n The District Court barred a retrial of and dismissed the\\nindictment against Defendant Raymont Wright with prejudice\\nafter two juries failed to reach a verdict. The Court did so\\nrelying on its inherent authority, but without finding that any\\nmisconduct had occurred or that Wright would suffer any\\nprejudice beyond the general anxiety and inconvenience of\\nfacing a retrial. Under such circumstances, the Court lacked\\nthe inherent authority to bar the retrial and dismiss the\\nindictment. Therefore, we will reverse the order dismissing the\\nindictment and remand for further proceedings.\\n\\n I\\n\\n In December 2014, Wright was charged with being a\\nfelon in possession of a firearm, in violation of 18 U.S.C.\\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\\nMay 2016. The jury was unable to reach a verdict. A second\\ntrial was held in March 2017, and that jury was also unable to\\nreach a verdict.\\n\\n During both trials, the jury heard evidence from police\\nofficers about Wright’s actions on July 24, 2014.1 That\\nevening, five Pittsburgh Police detectives were patrolling in\\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\\nwere in the lead car, and Detectives Fallert and Goob were in\\nthe second car. Around 8:30 p.m. (when it was still daylight),\\nFallert and Goob saw a man, later identified as Wright, driving\\n\\n 1\\n The following facts are drawn largely from the\\nevidence presented at the first trial.\\n\\n\\n\\n\\n 3\\n\\na car in the opposite direction well above the 25-mile-per-hour\\nspeed limit. The detectives turned around to follow Wright,\\nand Wright sped up and turned onto a loop-shaped road. The\\ndetectives pursued Wright, who fled at a high speed and ran at\\nleast four stop signs. The lead car lost sight of Wright shortly\\nthereafter and discontinued pursuit.\\n\\n Officers in the lead car then noticed skid marks\\nsuggesting that a car had intended but failed to make a left turn\\nat the end of a street. Officers thereafter came upon Wright’s\\ncar in a parking lot below. The car had gone through a fence,\\nover a hillside, and into the lot. The car hit two unoccupied\\nparked cars, its tires blew out, and its windows were down.\\n\\n Detectives Baker and Henson exited the vehicle at the\\ntop of the hill and remained where Wright’s car broke through\\nthe fence, and Detective Kennedy drove his car down to the\\nparking lot’s entrance. Baker and Henson testified that they\\nsaw Wright search around the rear passenger seat of the car,\\nback out of the vehicle with a black semi-automatic handgun\\nin his right hand, and try to “rack the slide,” which can insert\\nor remove a round from the chamber. App. 118-19. They had\\ntheir weapons drawn and told Wright to drop the gun. At first,\\nWright merely stepped back, but he eventually tossed the gun\\nto the side, backed away, and lied on the ground. Pittsburgh\\npolice officer Elliott and his partner, who heard of the crash on\\nthe radio, were the first to reach Wright, and saw him lying on\\nthe ground with a handgun next to him. Henson stated that\\nwhen he made it down to the parking lot, he heard Wright say\\nto him, “Hey, big guy. You won this time or you won this\\nround, something of that nature. He [Wright] said: You feel\\nme? You won this time,” which Henson understood to mean\\nthat he had just avoided a shootout or that he caught Wright\\n\\n\\n\\n\\n 4\\n\\nafter the pursuit. App. 125. Henson subsequently took custody\\nof the gun and noticed the slide lever was bent, and when he\\nstraightened it, saw the gun was loaded with eight rounds, and\\none in the chamber. 2\\n\\n At the close of the Government’s case, Wright moved\\nfor a directed verdict, arguing that no reasonable juror could\\nfind beyond a reasonable doubt that Wright possessed the\\nfirearm. The District Court denied the motion because “the\\nevidence does thus far demonstrate that a reasonable juror\\ncould most certainly find the Defendant guilty of the charge in\\nthis case.” App. 171. Wright did not present a case.\\n\\n The jury deliberated for approximately five hours and\\nthen reported to the Court that it was deadlocked. After polling\\nthe jurors to confirm they were deadlocked and further\\ndeliberations would not bring them closer to a unanimous\\nverdict, the District Court declared a mistrial.\\n\\n At Wright’s March 2017 retrial, the Government\\npresented substantially the same evidence. The Government\\nalso called Detective Kennedy and Lieutenant Palermo, who\\nwere at the scene after Wright was arrested, as well as experts\\nwho testified regarding the collection of DNA and fingerprint\\nevidence from firearms to respond to Wright’s argument at the\\nfirst trial that investigators chose not to test the gun for forensic\\nevidence in an effort to cover up that they had planted the gun\\nat the scene.\\n\\n\\n 2\\n The parties stipulated Wright had been convicted of a\\nqualifying felony, and an ATF Special Agent testified about\\nthe gun’s interstate nexus.\\n\\n\\n\\n\\n 5\\n\\n At the close of the Government’s case, Wright again\\nmoved for a judgment of acquittal, which the Court denied\\nbecause “there is sufficient evidence in the record to establish\\nbeyond a reasonable doubt that Mr. Wright possessed the\\nfirearm in the case,” App. 650. Wright did not put on a case.\\n\\n The second jury deliberated for approximately three\\nhours and then reported that it was hopelessly deadlocked. The\\nCourt polled the jury to confirm the deadlock and then\\ndismissed the jury. 3\\n\\n After the Government notified the Court that it intended\\nto retry the case, the Court required the parties to brief\\n“whether the Court, through an exercise of its inherent\\nauthority, should prohibit or permit a second re-trial in this\\ncase.” App. 26. After considering the parties’ arguments, the\\nDistrict Court dismissed the indictment with prejudice, holding\\nthat it “ha[d] the inherent authority, under some circumstances,\\nto dismiss an indictment following multiple mistrials.” United\\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\\nunderlying the Double Jeopardy Clause also applied to a\\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\\n(2) other courts had dismissed indictments in similar\\n\\n 3\\n Wright asserted that in the first trial, jurors voted 8-4\\nfor acquittal, and in the second trial, the jury was evenly split.\\nThe Government asserted that in the first trial, jurors voted 7-\\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\\nnot explain how he obtained these numbers, the Government\\nsaid it obtained them by speaking with the jurors.\\n\\n\\n\\n\\n 6\\n\\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\\nexpressly allows the Government to retry a case after a mistrial,\\nnothing in the rule “limits a court’s inherent supervisory\\nauthority to dismiss an indictment in the interests of\\nfundamental fairness,” id. at *4; and (4) if the Court were to\\nadopt the Government’s position that there are no limit to the\\nnumber of times the Government can retry a defendant, it\\nwould be tantamount to a “type of jury shopping” that a court\\nshould not permit, id. at *4. The District Court also considered\\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\\nconcluded that most factors supported dismissal. 4\\n\\n 4\\n The Abbati factors are\\n\\n (1) the number of prior mistrials and the\\n outcome of the juries’ deliberations, so far as is\\n known; (2) the character of prior trials in terms\\n of length, complexity, and similarity of evidence\\n presented; (3) the likelihood of any substantial\\n difference in a subsequent trial, if allowed;\\n (4) the trial court’s own evaluation of the relative\\n strength of each party’s case; and (5) the\\n professional conduct and diligence of respective\\n counsel, particularly of the prosecuting attorney.\\n The court must also give due weight to the\\n prosecutor’s decision to reprosecute, assessing\\n the reasons for that decision, such as the gravity\\n\\n\\n\\n\\n 7\\n\\n The Government appeals.\\n\\n II 5\\n\\n We review the District Court’s order dismissing the\\nindictment based on the Court’s inherent power for abuse of\\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\\n\\n of the criminal charges and the public’s concern\\n in the effective and definitive conclusion of\\n criminal prosecutions. Conversely, the court\\n should accord careful consideration to the status\\n of the individual defendant and the impact of a\\n retrial upon the defendant in terms of untoward\\n hardship and unfairness.\\n\\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\\nat 521-22). For the reasons set forth herein, we would not\\nadopt Abbati, but even if we were to consider the Abbati\\nfactors, we would conclude that they do not support dismissal\\nin this case.\\n 5\\n The District Court had jurisdiction pursuant to 18\\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\\n§ 3731.\\n 6\\n The phrases “inherent power,” “inherent authority,”\\n“supervisory power,” and “supervisory authority” are all used\\nto describe the basis for a court action seeking to maintain the\\nintegrity of the proceedings that is not directly tethered to a\\nspecific rule, statute, or constitutional provision. See, e.g.,\\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\\n43 (1991) (inherent power); Bank of Nova Scotia v. United\\n\\n\\n\\n\\n 8\\n\\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\\nindictment for abuse of discretion); cf. Chambers v. NASCO,\\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\\nsanctions under its inherent power for abuse of discretion);\\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\\n2005) (“A trial court’s remedy for a discovery violation under\\nits supervisory powers is reviewed for abuse of discretion.”).\\nA district court abuses its discretion when it makes an errant\\nconclusion of law, an improper application of law to fact, or a\\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\\n\\n A\\n\\n Federal Rule of Criminal Procedure 31 allows the\\nGovernment to retry a case if the court declares a mistrial after\\na jury announces it is unable to reach a verdict. Specifically,\\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\\non one or more counts, the court may declare a mistrial on\\nthose counts. The government may retry any defendant on any\\ncount on which the jury could not agree.” Fed. R. Crim. P.\\n31(b)(3). The word “may” means that the Government has the\\n\\n\\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(supervisory power); United States v. Payner, 447 U.S. 727,\\n733-36 (1980) (supervisory power); United States v. Nobles,\\n422 U.S. 225, 231 (1975) (inherent power).\\n Even if we accepted the distinctions our dissenting\\ncolleague has drawn between inherent judicial powers,\\nlegislatively granted judicial powers, and supervisory powers,\\neach category must operate within the constitutional\\nframework, including the separation of powers.\\n\\n\\n\\n\\n 9\\n\\ndiscretion to retry a case, and nothing in the rule or its\\ncommentary provides or even suggests a limit on the number\\nof retrials it may conduct. See United States v. Wqas Khan,\\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\\n\\n 7\\n While Rule 31 does not limit the Government’s\\nauthority to retry a case, a handful of district courts have\\ndismissed indictments following a second hung jury, but those\\ndecisions are not persuasive. In Ingram, the district court\\ndismissed the indictment sua sponte (without any initial\\nobjection by the Government) after two mistrials—in which\\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\\njailed during the pendency of the trials, and “[t]he Government\\nha[d] no new proof; it simply want[ed] another chance.” 412\\nF. Supp. at 385. The court concluded that to permit a retrial\\nwould be “to ignore the reasonable doubt standard,” and so\\n“[t]he Court’s intervention [was] required in the interest of\\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\\n(McGowan, J., dissenting)). The Ingram court, however, relied\\nin part on the dissent in De Diego. Cases since Ingram have\\napplied the De Diego majority’s view concerning a court’s\\nlimited authority to dismiss an indictment. See, e.g., United\\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\\nDe Diego and reversing the district court’s dismissal of the\\nindictment where the district court found it would be\\n“unconscionable” to retry to the defendant); United States v.\\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\\nDiego and its dissent and holding a district court does not have\\nauthority to sua sponte dismiss an indictment based on the\\n\\n\\n\\n\\n 10\\n\\ndefendant’s poor health); United States v. Mussehl, 453 F.\\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\\nto dismiss the indictment based on alleged errors at trial, and\\nciting De Diego for the proposition that “[t]he duty [to\\nadminister justice] encompasses the concept of review of the\\nquestion whether the United States Attorney, in making his\\ndecision to prosecute, complied with the law, but does not\\nallow the Court to question a United States Attorney’s\\njudgment decision to prosecute, when lawfully made”).\\n The District Court also relied on Rossoff, where the\\ncourt denied the Government’s motion to dismiss the\\nindictment under Federal Rule of Criminal Procedure 48(a),\\nbut still dismissed the indictment with prejudice. 806 F. Supp.\\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\\nbeen two trials, and the Government sought to dismiss the\\nindictment and refile the charges in a different judicial district.\\nId. The court determined it had authority to dismiss an\\nindictment with prejudice if a retrial was “against the concept\\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\\nSupp. 384), and did so because, among other reasons, the\\ndefendant was in poor health, was under significant strain, and\\na majority of jurors at both trials found him not guilty, id. at\\n203. Rossoff, however, is distinguishable from Wright’s case\\nbecause in Rossoff, the Government sought to dismiss the\\nindictment so that it could refile charges in a different judicial\\ndistrict, which caused the court to question the Government’s\\ngood faith. In Wright’s case, the District Court made no\\nfinding that the Government’s desire to retry Wright was for\\nan improper purpose.\\n In addition, and significantly, neither Ingram nor\\nRossoff addressed the doctrine of separation of powers.\\nRather, each essentially relied on a general concept of fairness\\n\\n\\n\\n\\n 11\\n\\nthe text that empowers a court to prohibit the Government from\\nretrying a case. 8\\n B\\n\\n Apparently aware that Rule 31 did not provide it with a\\nbasis to preclude a retrial in these circumstances, the District\\nCourt concluded that it had the inherent authority to forbid the\\nretrial and dismiss the indictment. The District Court erred.\\n\\n The exercise of inherent authority must satisfy two\\nrequirements: (1) it “must be a reasonable response to the\\n\\n\\nto the defendant in deciding to dismiss an indictment. See\\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\\nIn this Circuit, however, “[t]he judiciary may not impose its\\npersonal and private notions of ‘fairness’ on law enforcement\\nofficials, but does have a limited authority to affect\\nprosecutorial actions when those actions are taken in violation\\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\\n596 (3d Cir. 1992) (citations omitted).\\n 8\\n Rule 31 differs from other Federal Rules of Criminal\\nProcedure because it makes no mention of the court’s\\nauthority. For instance, Rule 48(b) states that a court has\\nauthority to dismiss an indictment “if unnecessary delay occurs\\nin: (1) presenting a charge to the grand jury; (2) filing an\\ninformation against a defendant; or (3) bringing a defendant to\\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\\ngrounds on which a district court could also dismiss an\\nindictment, but each would be triggered by a motion, such as a\\nmotion to dismiss for failure to comply with Rule 16’s\\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\\n16(d)(2)(D), or a motion asserting a defect in the indictment,\\nFed. R. Crim. P. 12(b)(3)(B).\\n\\n\\n\\n\\n 12\\n\\nproblems and needs confronting the court’s fair administration\\nof justice,” and (2) it “cannot be contrary to any express grant\\nof or limitation on the district court’s power contained in a rule\\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\\n(citations and internal quotation marks omitted). We will\\nexamine each of these requirements in turn.\\n\\n 1\\n\\n As to the first Dietz requirement, “[g]uided by\\nconsiderations of justice, and in the exercise of supervisory\\npowers, federal courts may, within limits, formulate procedural\\nrules not specifically required by the Constitution or the\\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(internal quotation marks and citation omitted). Such rules\\nmust be imposed (1) “to implement a remedy for violation of\\nrecognized rights,” (2) “to preserve judicial integrity by\\nensuring that a conviction rests on appropriate considerations\\nvalidly before the jury,” and (3) “as a remedy designed to deter\\nillegal conduct.” Id. (citations omitted). Thus, a court may\\nexercise its inherent authority only when it is necessary to\\naddress improper conduct and ensure respect for the\\nproceedings.\\n\\n Under these principles, a court may dismiss an\\nindictment based upon its inherent authority only if the\\nGovernment engaged in misconduct, the defendant was\\nprejudiced, and no less severe remedy was available to address\\nthe prejudice. See Bank of Nova Scotia v. United States, 487\\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\\n(stating that “[a] court may dismiss an indictment under its\\nsupervisory powers only when the defendant suffers\\nsubstantial prejudice and where no lesser remedial action is\\n\\n\\n\\n\\n 13\\n\\navailable” (citations and internal quotation marks omitted));\\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\\n(observing that “a district court may not, in the management of\\nits docket, exercise its discretion to dismiss an indictment with\\nprejudice, either under Rule 48(b) or under its supervisory\\npower, unless the violation caused prejudice to the defendant\\nor posed a substantial threat thereof” (emphasis omitted));\\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\\n(holding that an indictment may not be dismissed for\\nprosecutorial misconduct absent a showing that the misconduct\\nprejudiced the defendants, and stating that “virtually every\\nother circuit to consider the issue post-Hasting and Nova Scotia\\nhas also held that an indictment may not be dismissed based on\\nprosecutorial misconduct, absent a showing of prejudice to the\\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\\n(7th Cir. 1993) (“A federal judge is not authorized to punish\\nthe misconduct of a prosecutor by letting the defendant walk,\\nunless the misconduct not only violated the defendant’s rights\\nbut also prejudiced his defense . . . .”); United States v. Tucker,\\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\\nexercise its supervisory authority to reverse a conviction or\\ndismiss an indictment absent prejudice to the defendant.”);\\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\\nHasting, and Bank of Nova Scotia form a trilogy admonishing\\nfederal courts to refrain from using the supervisory power to\\nconform executive conduct to judicially preferred norms by\\ndismissing charges, absent cognizable prejudice to a particular\\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\\nCir. 1992) (“Before it may invoke this [supervisory] power [to\\ndismiss an indictment], a court must first find that the\\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\\n1480 (9th Cir. 1994).\\n\\n\\n\\n\\n 14\\n\\n In this case, there has been no misconduct. Indeed, the\\nDistrict Court noted that the Government performed diligently\\nand professionally in both trials, Wright, 2017 WL 1179006,\\nat *4, and found that the evidence was sufficient to prove\\nbeyond a reasonable doubt that Wright possessed the gun. The\\nDistrict Court nonetheless applied its own predictions about\\nwhat another jury may do when presented with the same\\nevidence, emphasized the need for finality, and opined that the\\neffect of prosecution on the defendant precluded a proper\\nprosecution from proceeding. See id. at *5-6. Invoking its own\\nnotions about the unfairness of requiring a defendant to face a\\nretrial where the Government did not obtain a majority of the\\njurors’ votes is an improper exercise of a court’s supervisory\\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\nMoreover, there is no prejudice to a defendant simply because\\nhe faces the anxiety and the normal stress of undergoing a trial.\\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975) (“[A]nxiety is present to some degree in virtually every\\ncase. Something more than the normal anxiety that\\naccompanies a trial is necessary to show a degree of\\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\\nonly real harm alleged is the general unfairness to these\\ndefendants in having to go forward yet again with a lengthy\\ntrial, in their being ‘ground down’ by the several months’ drain\\non their mental, emotional, and financial resources. A lack of\\nsuch fairness, however, does not alone violate due process.”).\\nRather, prejudice sufficient for the District Court to intervene\\nin a proper prosecution based upon its inherent authority occurs\\nonly where the Government engages in actions that place a\\ndefendant at a disadvantage in addressing the charges. That\\nsort of prejudice is absent in this case.\\n\\n\\n\\n\\n 15\\n\\n Unless there is some constitutional basis, such as a due\\nprocess violation, it makes sense to limit a court’s authority to\\nbar retrial to instances of prosecutorial misconduct and\\nprejudice. First, it ensures that a judge’s personal preferences\\nabout a case do not influence whether the case proceeds. See\\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\\n(“The judiciary may not impose its personal and private\\nnotions of ‘fairness’ on law enforcement officials, but does\\nhave a limited authority to affect prosecutorial actions when\\nthose actions are taken in violation of the Constitution.”).\\nSecond, as more fully discussed below, it guarantees that a\\ncourt limits the Executive’s decision to prosecute only where\\nthere is a constitutionally sound reason to do so. 9 This brings\\nus to the second Dietz requirement.\\n\\n\\n 9\\n For these reasons, we find unpersuasive our dissenting\\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\\nobservation that a court has the inherent power to resolve a\\ncase, as authority for allowing a court dismiss an indictment\\nafter successive hung juries. As a general matter, there is no\\ndoubt that a court has the authority to dismiss a case, but it may\\nnot simply end a case because it decides that it should not be\\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\\ntheir progeny make clear, the court must point to evidentiary\\ndeficiency, prejudicial misconduct, or a constitutional basis,\\nsuch as double jeopardy or due process, to justify precluding a\\nprosecution. If a court believed that the evidence was deficient,\\nthe prosecutor engaged in prejudicial misconduct, or a retrial\\nwould violate the constitution, then it has a basis to preclude a\\nretrial. Requiring such reasons for barring a retrial ensures that\\n\\n\\n\\n\\n 16\\n\\n 2\\n\\n The second Dietz requirement reminds a court that the\\nexercise of its powers must be in accordance with the\\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\\nwith the Constitution, a court must be mindful of its role in our\\ntripartite form of government and the doctrine of separation of\\npowers. Separation-of-powers principles limit a court’s\\ninherent authority. “Regardless of whether the supervisory\\npower stems from the federal courts’ inherent power to check\\nintrusions by other branches of government or whether it is a\\nform of specialized federal common law, the separation-of-\\npowers principle imposes significant limits on it,” and\\n“[p]roper regard for judicial integrity does not justify a\\n‘chancellor’s foot veto’ over activities of coequal branches of\\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\\nCir. 1985) (internal quotation marks omitted) (quoting United\\nStates v. Russell, 411 U.S. 423, 435 (1973)).\\n\\n In the criminal context, the Executive Branch has\\n“broad discretion as to whom to prosecute,” and this discretion\\n“rests largely on the recognition that the decision to prosecute\\nis particularly ill-suited to judicial review.” Wayte v. United\\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\\nquotation marks omitted). A court is not equipped to evaluate\\n\\n [s]uch factors as . . . the prosecution’s general\\n deterrence value, the Government’s enforcement\\n priorities, and the case’s relationship to the\\n\\n\\nthe ruling is not based on a court’s own personal sense of\\nwhether a case is worthy of prosecution.\\n\\n\\n\\n\\n 17\\n\\n Government’s overall enforcement plan . . . .\\n Judicial supervision in this area, moreover,\\n entails systemic costs of particular concern.\\n Examining the basis of a prosecution delays the\\n criminal proceeding, threatens to chill law\\n enforcement by subjecting the prosecutor’s\\n motives and decisionmaking to outside inquiry,\\n and may undermine prosecutorial effectiveness\\n by revealing the Government’s enforcement\\n policy. All of these are substantial concerns that\\n make the courts properly hesitant to examine the\\n decision whether to prosecute.\\n\\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\\n(echoing similar sentiments with respect to Rule 48(a)\\ndismissals). Thus, absent constitutional concerns, the decision\\nto try or retry a case is at the discretion of the prosecutor.\\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\\nas superprosecutors, second-guessing the legitimate exercise of\\ncore elements of prosecutorial discretion, but rather as neutral\\narbiters of the law” (citation and internal quotation marks\\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\\n1994) (“[T]he choice to forego permanently a prosecution is\\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\\n676 (“In maintaining order in our own house, we should not\\nneedlessly trample on the interest of the prosecutor and of the\\npublic in securing proper, lasting convictions.”); Isgro, 974\\nF.2d at 1097 (stating that the doctrine of separation of powers\\n“mandates judicial respect for the independence of the\\nprosecutor,” and “[d]ismissal of an indictment with prejudice\\n\\n\\n\\n\\n 18\\n\\nis the most severe sanction possible”). 10 Accordingly,\\nseparation-of-powers principles preclude a court from\\nterminating a prosecution absent misconduct and prejudice to\\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\\n974 F.2d at 1094.\\n\\n In short, a court’s power to preclude a prosecution is\\nlimited by the separation of powers and, specifically, the\\nExecutive’s law-enforcement and prosecutorial prerogative.\\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\\nhere to dismiss an indictment in the absence of misconduct and\\nprejudice and based only on the fact that two juries could not\\nreach a verdict intrudes on the Executive’s domain and thereby\\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\\nat 138; Isgro, 974 F.2d 1091.\\n\\n 10\\n Several state courts have also refused to recognize\\nany inherent authority to dismiss an indictment to prevent a\\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\\n(Fla. Dist. Ct. App. 1980). Other states, however, have\\nrecognized a court’s authority to dismiss an indictment sua\\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\\n712; Witt, 572 S.W.2d at 917. These latter cases are\\nunpersuasive because they give too little weight to the\\nseparation of powers, a crucial constitutional principle in the\\nfederal system.\\n\\n\\n\\n\\n 19\\n\\n Finally, there is no statute or procedural rule that\\npermits a court to bar a retrial in the absence of misconduct and\\nprejudice. First, a court may not dismiss an indictment as a\\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\\n505. Second, a court’s inherent power does not “include the\\npower to develop rules that circumvent or conflict with the\\nFederal Rules of Criminal Procedure.” Carlisle v. United\\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\\nexercise of inherent authority circumvents the absence of\\npower of the district court to dismiss an indictment in Rule\\n31(b). As stated above, courts have inherent authority to\\ndismiss indictments, including, for instance, for prosecutorial\\nmisconduct if the defendant was prejudiced, Bank of Nova\\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\\nnor our Court has extended a court’s inherent authority to allow\\n\\n 11\\n In Chambers, for example, the Supreme Court\\nrecognized a court’s authority to impose silence, respect, and\\ndecorum based on its authority to manage its own affairs. 501\\nU.S. at 43. This authority has been exercised by controlling\\nadmission to the bar and disciplining its members; punishing\\nfor contempt, which penalizes disruption to proceedings and\\ndisobedience to court orders; disallowing fraud on the courts;\\nensuring the proceedings move forward; and curtailing\\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\\ncivil case for failure to prosecute to prevent delays and court\\ncongestion as part of a court’s inherent power to manage its\\nown affairs). Chambers and Link address how a court may\\nmanage its own proceedings, but they do not address how the\\ncourt must also account for issues of separation of powers in\\nthe context of a criminal case.\\n\\n\\n\\n\\n 20\\n\\nthe sua sponte dismissal of an indictment solely to preclude\\nmultiple mistrials following hung juries, see Chambers, 501\\nU.S. at 47; HSBC, 863 F.3d at 136. 12\\n\\n 12\\n Most cases concerning a court’s inherent authority\\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\\n(noting a court’s inherent powers to rescind a jury discharge\\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\\n(recognizing a court’s authority to vacate a judgment upon\\nproof that a fraud was perpetrated on the court, and, in\\nparticular, to assess as a sanction the entire amount of the\\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\\n(authority to dismiss a civil case sua sponte for failure to\\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\\n(1947) (dismissing an action based on the doctrine of forum\\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\\n(citing cases involving the scope of a district court’s inherent\\npower); Eash, 757 F.2d at 561-64 (same).\\n There are other circumstances in which district courts\\nlack the inherent authority to act, and most of those situations\\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\\n433 (holding that a court does not have authority to grant a\\npost-verdict motion for judgment of acquittal, filed one day\\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\\n45-50, 55 (holding that a district court does not have inherent\\nauthority to dismiss an indictment because the Government\\nfailed to disclose to the grand jury substantial exculpatory\\nevidence; “[b]ecause the grand jury is an institution separate\\nfrom the courts, over whose functioning the courts do not\\npreside, we think it clear that, as a general matter at least, no\\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\\nat 129, 135-37 (holding that the district court violated\\nseparation-of-powers principles by sua sponte invoking its\\n\\n\\n\\n\\n 21\\n\\n Thus, the District Court abused its discretion in barring\\na retrial and dismissing the indictment. 13\\n\\n III\\n\\n For the foregoing reasons, we will reverse and remand\\nfor further proceedings.\\n\\n\\n\\n\\nsupervisory power to oversee the government’s entry into and\\nimplementation of a deferred prosecution agreement).\\n 13\", \"author\": \"SHWARTZ, Circuit Judge.\"}, {\"type\": \"dissent\", \"author\": \"Our\", \"text\": \"Our dissenting colleague says that our approach\\ndeprives the court from taking action “when warranted to\\nprotect the institutional integrity of the judiciary.” Dissent at\\n3. We disagree. This approach recognizes a court’s role in our\\ntripartite system of government and ensures that a court\\nintercedes when proceeding would violate the Constitution.\\nFurthermore, our approach does not preclude a court from\\nending a case where the evidence is insufficient or the conduct\\nof the prosecution is improper.\\n\\n\\n\\n\\n 22\\n\\nNo. 17-1972, United States of America v. Raymont Wright\"}, {\"author\": \"NYGAARD, Circuit Judge, dissenting\", \"type\": \"dissent\", \"text\": \"NYGAARD, Circuit Judge, dissenting\\n\\n This appeal presents us with two issues: First, does a\\ndistrict court possess the inherent power to dismiss an\\nindictment after serial hung juries, and second, did the\\nDistrict Court here abuse its discretion by dismissing this\\nindictment after two of them. I answer yes to the first and no\\nto the second. Because I view this to be a matter of\\nsubstantial importance, I must respectfully dissent. 1\\n\\n As the majority notes, twice now, the Government has\\ntried Raymont Wright for a violation of federal law: being a\\nfelon in possession of a firearm. 2 Twice now, the\\nGovernment has done so on the basis of essentially the same\\nevidence at trials presided over by the same District Court.\\nAnd twice now, two different juries could not reach a verdict.\\nThus, when the Government announced its intention to put\\nWright on trial for the third time, the District Court was\\nskeptical. It asked for briefing on whether it possessed the\\ninherent power to prohibit the Government from taking a\\n\\n1\\n Whether the District Court had the inherent power to\\ndismiss the indictment is a legal question. We employ a\\nplenary standard of review to that issue. See United States v.\\nSchiff, 602 F.3d 152, 161 (3d Cir. 2010) (citing United States\\nv. Scott, 223 F.3d 208, 210 (3d Cir. 2000)). Whether the\\nDistrict Court appropriately exercised this power is reviewed\\nfor an abuse of discretion. Link v. Wabash R.R. Co., 370 U.S.\\n626, 633 (1962).\\n2\\n See 18 U.S.C. § 922(g).\\n\\nthird turn, and if it did, whether the court should use that\\npower. 3 After hearing from both sides, the District Court\\nconcluded that its inherent power applied to this\\ncircumstance. It then exercised its discretion to dismiss the\\nindictment.\\n\\n Neither the Government nor the majority disputes that\\ndistrict courts have the inherent authority to dismiss\\nindictments under at least some circumstances. Citing to\\nUnited States v. Hasting, 4 however, the majority cabins that\\nauthority to those instances in which there is evidence of\\nprosecutorial misconduct. In my view, in so doing, the\\nmajority conflates and confuses the various powers of the\\ncourt. And it also hobbles the court’s discretion to probe the\\nimpact on the fair administration of justice of those\\nprosecutorial decisions that sit outside the definition of bad\\nconduct but still pose—or threaten to pose—real institutional\\nharm.\\n\\n The executive office inheres prosecutors with the\\npower to bring a case to trial. The judicial office, on the other\\nhand, inheres the court with the power to end a case. 5 Both\\n\\n3\\n The District Court ordered the parties to “file cross briefs\\nstating their position regarding whether the Court, through an\\nexercise of its inherent authority, should prohibit or permit a\\nsecond re-trial in this case.” United States v. Wright, No. 14-\\ncr-292, 2017 WL 1179006, at *1 (W.D. Pa. 2017).\\n4\\n 461 U.S. 499, 505 (1983).\\n5\\n See Young v. U.S. ex rel. Vuitton et Fils S.A., 481 U.S. 787,\\n816 (1987)(Scalia, J. concurring)(“The judicial power is the\\npower to decide, in accordance with law, who should prevail\\nin a case or controversy. See Art. III, § 2. . . . [S]ince the\\n\\n\\n\\n\\n 2\\n\\noffices share a responsibility to safeguard the overall integrity\\nof the judicial process. But when a prosecutor decides to\\nproceed with another trial in the aftermath of multiple\\nmistrials, who but the court is empowered to question the\\nimpact of the prosecutor’s discretion on the fair\\nadministration of justice, particularly when the court has\\nconcerns that the proceedings—and the institution—will be\\ntainted by the abuse of jury shopping? It could be argued that\\ntwo mistrials may not in some instances be enough to inflict\\nserious institutional damage. But, the majority’s combined\\nreliance on Dietz v. Bouldin 6 and Fed. R. Crim. P. 31(b)(3) to\\nallow the prosecutor to bring an unlimited number of retrials,\\nso long as she or he does not stray into the realm of “illegal\\nconduct,” provides the prosecutor with an unchecked power.\\nThis poses a threat to the integrity of the judiciary and\\ncontradicts the inherent responsibility and authority vested in\\nthe judiciary by the framers of the Constitution. Thus, it is\\nthe majority’s decision—and not the District Court’s exercise\\nof its inherent authority—that violates the separation of\\npower principles on which the majority relies. We must\\naffirm that our trial court judges have the discretion,\\noriginating in the court’s inherent power, to take proper\\naction when warranted to protect the institutional integrity of\\nthe judiciary.\\n\\n Here, the District Court mindfully struck the balance\\nthat is necessary anytime the power of the court and the\\n\\n\\nprosecution of law violators is part of the implementation of\\nthe laws, it is—at least to the extent that it is publicly\\nexercised—executive power, vested by the Constitution in the\\nPresident.”) (footnote omitted)).\\n6\\n 136 S. Ct. 1885, 1892 (2016).\\n\\n\\n\\n\\n 3\\n\\npower of the prosecutor intersect. Drawing from factors set\\nout in State v. Abbati, 7 the District Court identified and\\ninvestigated a circumstance that it identified as harmful to the\\ninstitution and to the defendant: jury shopping. It also took\\nnote of the impact of serial retrials on the defendant. It then\\nproperly dismissed the indictment. Its use of the court’s\\ninherent discretion did not violate the separation of powers\\ndoctrine. To the contrary, it gave definition and substance to\\nit.\\n\\n I.\\n\\n Some review is appropriate to illuminate how and\\npossibly why I believe the majority confuses the court’s\\nvarious powers.\\n\\n A.\\n\\n Federal courts operate within a constitutional system\\nthat enumerates the powers of each branch of government, as\\nset forth in the founding document. Article I restrains\\ncongressional power to those “legislative Powers granted\\nherein.” 8 By comparison, Article II vests the President with\\n“the executive Power” without further description, limitation,\\nor restriction. 9 Analogous to Article II, Article III conveys\\nwithout restriction or limitation the “judicial Power” to\\nfederal courts. 10 Accordingly, the Supreme Court has—since\\nat least 1812—recognized that “[c]ertain implied powers must\\n\\n7\\n 493 A.2d 513, 521-22 (N.J. 1985).\\n8\\n U.S. Const. art. I, § 1.\\n9\\n U.S. Const. art. II, § 1.\\n10\\n U.S. Const. art. III, § 1.\\n\\n\\n\\n\\n 4\\n\\nnecessarily result to our Courts of justice from the nature of\\ntheir institution.” 11 “The moment the courts of the United\\nStates were called into existence and invested with\\njurisdiction over any subject, they became possessed of”\\ninherent authority. 12\\n\\n Moreover, two bedrock purposes of the Constitution—\\nchecking the actions of the states and ensuring that Congress\\nand the Executive do not overstep their boundaries—require a\\nfederal judiciary that exercises its own independent judicial\\npower. That is, it would be impossible for federal courts to\\ndischarge these vital duties if they lacked some inherent\\npower beyond the reach of the Executive or the legislature. I\\nthink of it this way: the elaborate measures set out in the\\nConstitution to protect the independence of the judiciary (life\\ntenure, removal from office only through impeachment, no\\ndecrease in salary during a judge’s tenure, for example)\\nwould be meaningless if there were not some inherent,\\nunimpeachable power vested solely in the federal courts.\\n\\n In Eash v. Riggins Trucking Inc., 13 we defined inherent\\npower as vesting in federal courts upon their creation and as\\nnot deriving from any statute. In this sense, the “judicial\\npower” given to the federal courts by Article III of the\\nConstitution is the “power to decide, in accordance with law,\\nwho should prevail in a case or controversy.” 14 No matter the\\ndescription, this power is intrinsic to the judicial office and\\n\\n11\\n United States v. Hudson, 11 U.S. (7 Cranch) 32, 34 (1812).\\n12\\n Ex parte Robinson, 86 U.S. 505, 510 (1873) (speaking of\\nthe inherent contempt power).\\n13\\n 757 F.2d 557, 561 (3d Cir. 1985) (en banc).\\n14\\n Young, 481 U.S. at 816 (Scalia, J., concurring).\\n\\n\\n\\n\\n 5\\n\\ncannot be inhibited by any rule or act of Congress. As we\\nhave recognized, the boundaries of this power are often\\n“nebulous” and “shadowy,” 15 and “it is not always possible to\\ncategorize inherent power.” 16 Yet, we have an outline.\\n\\n In Eash, we identified three main classes or categories\\nof inherent power: 1) inherent powers based in Article III,\\nthat is, the power of a lower federal court to decide a case\\nover which it has jurisdiction; 2) those powers “necessary to\\nthe exercise of all others,” 17 and 3) powers that include those\\nreasonably useful to achieve justice, which are “necessary\\nonly in the practical sense of being useful.” 18 Focusing on the\\nfirst category, the inherent power to decide a case is “so\\nfundamental to the essence of a court as a constitutional\\ntribunal that to divest the court of absolute command within\\nthis sphere is really to render practically meaningless the\\nterms ‘court’ and ‘judicial power.’” 19 In other words, powers\\n\\n15\\n Eash, 757 F.2d at 561 (citation omitted).\\n16\\n Id. at 562.\\n17\\n Id. (quoting Roadway Express, Inc., v. Piper, 447 U.S. 752,\\n764 (1980)).\\n18\\n Id. at 563; see also Am. Civil Liberties Union v. Holder,\\n673 F.3d 245, 255-56 (4th Cir. 2011) (applying Eash factors);\\nIn re Stone, 986 F.2d 898, 901-02 (5th Cir. 1993) (per\\ncuriam) (adopting Eash factors). In Chambers v. NASCO\\nInc., the Supreme Court was urged to adopt our approach to\\ninherent powers. But the Court held that it “ha[d] never so\\nclassified the inherent powers and . . . ha[d] no need to do so\\nnow.” 501 U.S. 32, 47 n.12 (1991).\\n19\\n Eash, 757 F.2d at 562. The third aspect of a court’s\\ninherent power is its authority to employ persons or\\ninstruments not connected with the court, such as experts and\\n\\n\\n\\n\\n 6\\n\\nin this category make a court a court; they are encoded into\\nthe judiciary’s DNA. Courts have referred to this power as a\\ncourt’s “irreducible inherent authority” 20 and “the core\\nArticle III power.” 21 It is nothing less than our ability to\\ndecide a case over which we have jurisdiction, without\\ninterference by Congress or the Executive. 22\\n\\n Drawing from this, when I refer to a district court’s\\ninherent power, I mean a ‘“[c]ertain implied power[] [that]\\nmust necessarily result to our Courts of justice from the\\nnature of their institution,’ [a] power[] ‘which cannot be\\ndispensed with in a Court, because they are necessary to the\\nexercise of all others.’” 23 It is “grounded in the separation of\\npowers concept,” since to deny it and yet maintain an\\nindependent judiciary “is a self-contradiction.” 24\\n\\n However, that is not to say that the court operates\\nsolely outside the realm of legislatively granted judicial\\n\\n\\nauditors, to assist in its decision-making function. This facet\\nof inherent power is not in play here.\\n20\\n Id.\\n21\\n Am. Civil Liberties Union v. Holder, 673 F.3d at 256.\\n22\\n United States v. Klein, 80 U.S. (13 Wall.) 128, 147 (1871),\\nEash, 757 F.2d at 562 (noting that courts may exercise this\\ntype of inherent power despite legislation to the contrary); see\\nalso Michaelson v. United States ex rel. Chicago, St. P., M. &\\nO. Ry. Co., 266 U.S. 42, 64 (1924) (acknowledging that the\\nConstitution vests courts with some powers unalterable by\\nlegislation).\\n23\\n Chambers, 501 U.S. at 43 (quoting Hudson, 11 U.S. (7\\nCranch) at 34.).\\n24\\n Eash, 757 F.2d at 562.\\n\\n\\n\\n\\n 7\\n\\npowers. 25 In fact, the categorization scheme in Eash was\\nintended largely as a means of explaining the relationship\\nbetween inherent judicial powers and legislatively granted\\njudicial powers. 26 It is here that I believe the majority’s\\nanalysis strays.\\n\\n B.\\n\\n The majority, the briefs, and the discussion at oral\\nargument reveal what has become a commonplace but\\nimprecise conflation of the terms “inherent power” and\\n“supervisory power.” 27 The Government, while referencing\\nthe District Court’s “inherent power,” also referred to the\\ncourt’s “supervisory power,” and its “inherent supervisory\\njudicial authority.” 28 The Appellee covers the entire panoply,\\nciting the District Court’s “supervisory authority,” its\\n\\n\\n25\\n See Hudson, 11 U.S. (7 Cranch) at 33.\\n26\\n See In re Tutu Wells Contamination Litig., 120 F.3d 368,\\n384 n.14 (3d Cir. 1997), overruled on other grounds by\\nCunningham v. Hamilton County, Ohio, 527 U.S. 198 (1999).\\n27\\n In Eash, we noted that “[t]he conceptual and definitional\\nproblems regarding inherent power . . . have bedeviled\\ncommentators for years,” 757 F.2d at 561, and that “those\\ncases that have employed inherent power appear to use that\\ngeneric term to describe several distinguishable court\\npowers,” id. at 562. We also noted that “this lack of\\nspecificity [has been compounded by courts] rel[ying] . . . on\\nprecedents involving one form of power to support the court’s\\nuse of another.” Id.\\n28\\n E.g., Appellant’s Br. at 13, 16; Appellant’s Reply Br. at 2,\\n14.\\n\\n\\n\\n\\n 8\\n\\n“supervisory power,” and its “inherent power.” 29 At times,\\nwe too have been guilty of adding to the confusion. 30 The\\nerroneous interchangeability of these terms clouds an\\nimportant distinction that is crucial to this appeal: the\\ndifference between inherent judicial powers and legislatively\\ngranted judicial powers. 31 As noted supra, inherent “judicial\\npower” is given to the federal courts by Article III of the\\nConstitution. 32 Through this grant, federal courts receive the\\n“power to decide, in accordance with law, who should prevail\\nin a case or controversy.” 33 The merging of the terms\\n“inherent” and “supervisory” likely has its genesis in the fact\\nthat some inherent powers are supervisory in function, such\\nas a federal court’s inherent power “to supervise the\\nadministration of criminal justice.” 34\\n\\n29\\n E.g., Appellee’s Br. at 22, 26.\\n30\\n See, e.g., United States v. Accetturo, 783 F.2d 382, 396 (3d\\nCir. 1986) (Sloviter, J., dissenting) (speaking of our “inherent\\nsupervisory power”); see also United States v. Watkins, 339\\nF.3d 167, 180 (3d Cir. 2003) (Nygaard, J., concurring)\\n(referring to both a court’s supervisory power and inherent\\npower to dismiss a case under Fed. R. Crim. P. 48(b)).\\n31\\n In re Tutu Wells Litig., 120 F.3d at 384 n. 14.\\n32\\n See U.S. Const. art. III, § 1.\\n33\\n Young, 481 U.S. at 816 (Scalia, J., concurring).\\n34\\n United States v. Payner, 447 U.S. 727, 735 n.7 (1980)\\n(quotation marks omitted); see also Sara Sun Beale,\\nReconsidering Supervisory Power in Criminal Cases;\\nConstitutional and Statutory Limits of the Federal Courts, 84\\nColum. L. Rev. 1433, 1433-34, 1465, 1470 (1984)\\n(identification of Article III “judicial power,” not\\ncongressional acts, as the source of the Supreme Court’s\\nsupervisory authority).\\n\\n\\n\\n\\n 9\\n\\n However, unlike inherent powers, a court’s\\nsupervisory authority may come from, and can be limited by,\\nacts of Congress or a court’s own rules. 35 Supervisory power\\noften speaks to the power “to mandate ‘procedures deemed\\ndesirable from the viewpoint of sound judicial practice.’” 36 A\\ncourt’s use of supervisory power can usually be classified in\\none of three ways. First, supervisory power can refer to an\\nappellate court’s supervision of a district court, through the\\nimposition of procedures in addition to those already imposed\\nby federal statute or constitutional provision. 37 We have, for\\nexample, relied on our supervisory power over district courts\\nto review the application of local rules of practice and\\nprocedure. 38 We have also used our supervisory power to\\n\\n\\n\\n\\n35\\n See, e.g., McNabb v. United States, 318 U.S. 332, 340-41\\n(1943); Hasting, 461 U.S. at 505.\\n36\\n United States v. Moreno, 809 F.3d 766, 780 (3d Cir. 2016)\\n(quoting Thomas v. Arn, 474 U.S. 140, 146-47 (1985)).\\n37\\n See, e.g., Castro v. United States, 540 U.S. 375, 384 (2003)\\n(instructing district courts to notify pro se litigants about\\nconsequences of re-characterizing motions as ones seeking\\nrelief under 28 U.S.C. § 2255); Thiel v. S. Pac. Co., 328 U.S.\\n217, 225 (1946) (announcing a new rule for the composition\\nof federal juries); Dunbar v. Triangle Lumber & Supply Co.,\\n816 F.2d 126, 129 (3d Cir. 1987) (prescribing procedures for\\nmotions to dismiss based on the conduct of a litigant’s\\ncounsel); United States v. Bazzano, 570 F.2d 1120, 1137-38\\n(3d Cir. 1977) (requiring district courts to state reasons for a\\ncriminal sentence).\\n38\\n See United States v. Wecht, 484 F.3d 194, 204-05 (3d Cir.\\n2007).\\n\\n\\n\\n\\n 10\\n\\nprohibit certain jury instructions in the district courts 39 and to\\nreview attorney-client fee arrangements. 40 Second, Courts—\\nboth trial and appellate—also refer to their “supervisory\\npower” when meaning their power to supervise pending\\nlitigation. 41 They can, for example, seal and unseal records, 42\\nreassign a case to a different judge on remand, 43 or disqualify\\nan attorney on ethical grounds. 44 Lastly, the power of a\\nfederal court to supervise law enforcement officials can also\\nbe what a court intends when it speaks of its “supervisory\\n\\n\\n\\n\\n39\\n See United States v. E. Med. Billing Inc., 230 F.3d 600,\\n607-12 (3d Cir. 2000).\\n40\\n See Ryan v. Butera, Beausang, Cohen & Brennan, 193 F.3d\\n210, 214 (3d Cir. 1999).\\n41\\n See, e.g., Carlisle v. United States, 517 U.S. 416, 425-26\\n(1996) (acknowledging “supervisory power” of district courts\\nover litigation before them).\\n42\\n See, e.g., Hagestad v. Tragesser, 49 F.3d 1430, 1434 (9th\\nCir. 1995).\\n43\\n See Gov’t of the Virgin Islands v. Walker, 261 F.3d 370,\\n376 (3d Cir. 2001) (noting that, “[a]lthough it is the standard\\npractice in the district courts and in this circuit that a case on\\nremand is assigned to the judge who originally heard it, we\\ncan, in the exercise of our supervisory power, reassign this\\ncase to a different judge upon remand.”) (quotation marks\\nomitted).\\n44\\n In re Grand Jury Investigation, 447 F. Supp. 2d 453, 456-\\n57 (E.D. Pa. 2006) (collecting cases); see also United States\\nv. Moreno, 809 F.3d at 780 (summarizing supervisory\\nauthority).\\n\\n\\n\\n\\n 11\\n\\npower.” 45 These powers broadly ensure that pending cases\\nare managed uniformly and efficiently.\\n\\n I concede that the boundary between supervisory\\nauthority that is inherent to the court and that which is granted\\nby the legislature can, at times, be difficult to identify.\\nHowever, these difficulties are irrelevant to this case because\\nI conclude that the District Court here acted pursuant to its\\ninherent power and not to any authority conferred by any\\nstatute or rule. The District Court’s action was not\\nundertaken in supervision of pending litigation—two trials\\nwere already concluded and a potential third trial had not yet\\nbegun. Nor was it exercised according to a rule of procedure\\nor practice newly announced by an appellate tribunal.\\nMoreover, its action was not a response to any prosecutorial\\nmisconduct or request from Wright to dismiss the indictment.\\nThere is simply no basis to conclude that the inherent power\\nthat the District Court exercised in this case derived from any\\nlegislative grant.\\n\\n To the contrary, the specific power under review here\\nis the power to dismiss an indictment after two mistrials\\nbecause of deadlocked juries in each instance. This power\\nfalls within Eash’s first category of power because it is an\\ninherent power to resolve a case. A court, by its nature, must\\nbe able to dismiss with prejudice actions brought before it,\\njust as it must have the power to decide cases and enter\\n\\n45\\n See, e.g., United States v. Thompson, 772 F.3d 752, 763 (3d\\nCir. 2014). For a comprehensive discussion of the origins\\nand uses of supervisory power, see Amy Coney Barrett, The\\nSupervisory Power of the Supreme Court, 106 Colum. L. Rev.\\n324, 330 (2006).\\n\\n\\n\\n\\n 12\\n\\njudgments. 46 Such exercises of power are fundamental to the\\nessence of a court. Were they not, the judicial system simply\\ncould not function. 47\\n\\n The inherent power to dismiss is “of ancient origin,\\nhaving its roots in judgments of nonsuit and non prosequitur\\nentered at common law,” and so is a power that is part of the\\nvery nature of the judicial institution. 48 It is incidental and\\nnecessary to the fair and efficient operation of the courts. 49\\nIndeed, “the power to dismiss exists in many situations. For\\nexample, a district court has the inherent power to dismiss sua\\nsponte for lack of jurisdiction, or under the doctrine of forum\\nnon conveniens.” 50 Because the power to resolve a case by\\ndismissing an indictment (in a criminal action) or a complaint\\n(in a civil action) is fundamental to the essence of a court of\\njustice, it cannot be interfered with. Indeed, as two\\ncommentators have explained, “McNabb, other Supreme\\n\\n46\\n We have also noted that our power to remand is a subset of\\nthe inherent power to dismiss a case. See Bradgate Assocs.,\\nInc. v. Fellows, Read & Assocs., Inc., 999 F.2d. 745, 750 n.4\\n(3d Cir. 1993).\\n47\\n See, e.g., Fitzgerald v. First E. Seventh St. Tenants Corp.,\\n221 F.3d 362, 363-364 (2d Cir. 2000) (holding a district court\\nhas the inherent power to dismiss a case, sua sponte, if it\\ndetermines that the action is frivolous or the court lacks\\njurisdiction over the matter).\\n48\\n Link, 370 U.S. at 630.\\n49\\n See, e.g., Bowers v. Nat’l Collegiate Athletic Ass’n, 564 F.\\nSupp. 2d 322, 333 (D.N.J. 2008) (citing Derzack v. County of\\nAllegheny, 173 F.R.D. 400, 411 (W.D. Pa. 1996), aff’d\\nwithout op., 118 F.3d 1575 (3d Cir. 1997)).\\n50\\n In re Prevot, 59 F.3d 556, 565-66 (6th Cir. 1995).\\n\\n\\n\\n\\n 13\\n\\nCourt cases, and an analysis of several lower court opinions\\naddressing this precise issue should sufficiently dispel any\\nnotion that the federal courts lack the power to bar repeated\\nattempts to obtain a conviction” following serial mistrials.51\\nThus, the District Court’s action here was well within the\\nboundaries of its inherent power.\\n\\n Therefore, the majority’s conclusion that “inherent\\nauthority,” “supervisory power,” and “supervisory authority”\\nall refer to the same thing (while understandable given the\\nrampant muddled references that persist) ultimately misses\\nthe point. The power at issue here is the inherent power of\\nthe court to decide a case: a power that is limited by the\\nboundaries of reason and discretion and is subject to appellate\\nreview for abuse. It is not subject to the power of Congress\\nor the Executive.\\n\\n II.\\n\\n There is no dispute that district courts have the\\ninherent power to dismiss indictments in at least some\\ncircumstance. The majority nevertheless concludes that the\\nDistrict Court lacked the power to do so in this case. The\\nmajority reaches that conclusion for three principal reasons,\\nbut none withstands scrutiny.\\n\\n A.\\n\\n51\\n Michael A. Berch & Rebecca White Berch, The Power of\\nthe Judiciary to Dismiss Criminal Charges After Several\\nHung Juries: A Proposed Rule to Control Judicial Discretion,\\n30 Loy. L.A. L. Rev. 535, 543 & nn. 42-43 (1997) (collecting\\ncases).\\n\\n\\n\\n\\n 14\\n\\n First, the majority agrees with the Government’s\\nargument that the District Court’s dismissal violated the\\nSeparation of Powers Doctrine. I agree that the District\\nCourt’s dismissal implicates the separation of powers. But its\\nactions were in furtherance—not in violation—of the\\ndoctrine. The separation of powers doctrine refers to the\\nbalance among the branches of Government which prevents\\none branch from disrupting the constitutional functions of\\nanother. 52\\n\\n Here, the majority concludes that, in dismissing the\\nindictment after two hung juries, the District Court\\nencroached on the independence of the Executive because it\\nprohibited the prosecution from exercising its constitutional\\nduty to enforce the laws of the United States. Certainly, the\\nUnited States Attorney, as a member of the Executive Branch,\\nhas such a responsibility. 53 And, just as certainly, the\\ndecision to prosecute “is soundly within the discretion of the\\nprosecutor, not the courts.” 54 The Government’s authority\\nnot to prosecute a case is clear as well. 55 But we see no sign\\nthat the District Court did anything to prevent the\\nGovernment from fulfilling its duty. To the contrary, the\\nGovernment was twice given a full and fair opportunity to\\n\\n52\\n See, e.g., Clinton v. Jones, 520 U.S. 681, 699-700 (1997);\\nMorrison v. Olson, 487 U.S. 654, 696 (1988); Nixon v. Adm’r\\nof Gen. Servs., 433 U.S. 425, 442-43 (1977); Baraka v.\\nMcGreevey, 481 F.3d 187, 201 (3d Cir. 2007).\\n53\\n See, e.g., In re Grand Jury, 286 F.3d 153, 163 (3d Cir.\\n2002).\\n54\\n United States v. Talley, 164 F.3d 989, 997 (6th Cir. 1999).\\n55\\n See, e.g., United States v. Quinn, 728 F.3d 243, 255-56 (3d\\nCir. 2013).\\n\\n\\n\\n\\n 15\\n\\npresent its case and makes no claim that the District Court\\never prevented it from doing so. Having had those\\nopportunities, the Government had no absolute right as a\\nmatter of separation of powers or otherwise to try again. As\\ntwo commentators have explained, a district court’s use of its\\ninherent power to dismiss an indictment after serial mistrials\\ndoes not raise “significant separation of powers concerns”\\nbecause the nature of that inherent power means that federal\\ncourts “need not automatically defer to a prosecutor’s\\ndecision to retry a defendant” in this situation. 56\\n\\n The majority nevertheless concludes that prosecutors\\nhave the unimpeded right to try persons for violating federal\\nlaw based on an indictment as many times as they wish and\\nthat the separation of powers doctrine prohibits a federal court\\nfrom interfering. This position is untenable because it is not a\\ntrue reflection of the separation of powers. It is axiomatic\\nthat no one branch of government is completely divorced\\nfrom the other two. In reality, “our constitutional system\\nimposes on the Branches a degree of overlapping\\nresponsibility, a duty of interdependence as well as\\nindependence.” 57 This overlap becomes problematic, of\\ncourse, when it results in an encroachment (when an action of\\none branch might undermine the independence of another\\nbranch) or an aggrandizement (where one branch seeks\\n“powers more appropriately diffused among separate\\nBranches”). 58\\n\\n\\n56\\n Berch & Berch, supra note 51, at 544.\\n57\\n Mistretta v. United States, 488 U.S. 361, 381 (1989).\\n58\\n Id. at 381; see also In re Tribune Media Co., 799 F.3d 272,\\n285 (3d Cir. 2015) (Ambro, J., concurring).\\n\\n\\n\\n\\n 16\\n\\n But recognizing a district court’s right to prohibit a\\nretrial following serial mistrials does not implicate these\\nconcerns. To the contrary, and putting the shoe on the other\\nfoot, the Government’s position that nothing limits its\\nopportunity to try and retry a defendant as many times as it\\nchooses violates the judicial branch’s constitutional mandate\\nto exercise its judicial power. Just as the filing of an\\nindictment is an exercise of executive power, the dismissal of\\none is an exercise of judicial power. The unlimited serial\\nprosecutions that the Government advocates for, and that the\\nmajority permits, would limit a court’s authority to dismiss an\\nindictment to only those instances in which the prosecutor\\nsteps outside the bounds of professional conduct. But our\\nindependence as an institution of government must include an\\nability to adjudicate, and thus dismiss with prejudice,\\nindividual cases when a district court, in its discretion, has\\nconcerns about the impact of serial retrials on the institution\\nand the defendant. We view the prosecution of a defendant\\nafter deadlocked juries as a tipping point in balancing the\\nseparation of powers. As the repeated prosecutions increase,\\nso too does the judiciary’s power to limit them. As we stated\\nin Eash, and as we said supra, a court’s exercise of its\\ninherent power to dismiss an indictment after retrials does not\\nviolate the separation of powers but is grounded in it. 59\\n\\n B.\\n\\n Second, and relatedly, the majority concludes that the\\nDistrict Court’s dismissal was in violation of Fed. R. Crim. P.\\n31(b)(3), which the majority claims confers on prosecutors\\nthe unlimited discretion to retry defendants following serial\\n\\n59\\n See Eash, 757 F.2d at 562.\\n\\n\\n\\n\\n 17\\n\\nmistrials. Rule 31 does nothing of the kind. Rule 31 provides\\nin relevant part that “if a jury cannot agree on a verdict on one\\nor more counts, the court may declare a mistrial on those\\ncounts. The government may retry any defendant on any\\ncounts on which the jury could not agree.” 60 The Supreme\\nCourt adopted this rule in its original form in 1944 as a\\n“restatement of existing law.” 61 The Supreme Court itself\\nappears never to have cited Rule 31(b)(3), and neither the few\\nCourts of Appeals to have done so 62 nor its Advisory\\nCommittee Notes have discussed its history or purpose in any\\ndetail. Arguably, the rule’s reference to the prosecutor’s\\ngeneral ability to retry a defendant following a mistrial may\\nbe nothing more than a recognition of the longstanding\\nprinciple that retrials following mistrials are not prohibited by\\nthe Double Jeopardy Clause, 63 which is not at issue here.\\n\\n In any event, this rule does not by its terms prohibit\\ndistrict courts from dismissing indictments following serial\\nmistrials. District courts have the inherent power to do so as\\nexplained above. A district court’s exercise of that power\\ncould be contrary to Rule 31(b)(3) only if the rule contained\\nan “express grant of or limitation on” that power. 64 It does\\nnot. The rule does not mandate a retrial after a mistrial. Nor\\n\\n60\\n Fed. R. Crim. P. 31(b)(3).\\n61\\n Id. advisory committee’s note to 1944 adoption.\\n62\\n See United States v. Melendez, 775 F.3d 50, 57 (1st Cir.\\n2014); United States v. Warren, 593 F.3d 540, 546 (7th Cir.\\n2010); United States v. Fort, 472 F.3d 1106, 1111 n.3 (9th\\nCir. 2007); United States v. Gotti, 451 F.3d 133, 137 (2d Cir.\\n2006).\\n63\\n See United States v. Perez, 22 U.S. 579, 580 (1824).\\n64\\n Dietz, 136 S. Ct. at 1892.\\n\\n\\n\\n\\n 18\\n\\ndoes it contain any other limitation on the district court’s\\npower to prohibit one. In fact, the rule does not even mention\\nthat issue. 65 Thus, as the Supreme Court has noted in\\naddressing other rules of court, “[i]t would require a much\\nclearer expression of purpose than [this rule] provides for us\\nto assume that it was intended to abrogate” the district courts’\\ninherent power. 66 Put simply, when there have been multiple\\nmistrials and the prosecutor seeks to try the case again, Rule\\n31(b)(3) does not purport to reduce the role of the district\\ncourts to that of a rubber stamp.\\n\\n C.\\n\\n Finally, the majority claims that a district court can\\nexercise its inherent power to dismiss an indictment only if\\nthere is evidence of willful bad faith or prosecutorial\\nmisconduct on the part of the government and resultant\\nprejudice to the defendant. It cites to numerous decisions that\\nit says supports this position. 67 But none of these cases deals\\n\\n65\\n The majority claims that Rule 31(b)(3)’s silence on this\\nissue supports the proposition that district courts lack the\\nauthority to dismiss an indictment following serial mistrials.\\nBut because district courts have the inherent power to do so\\nas explained above, the question is not whether Rule 31(b)(3)\\npermits district courts to dismiss an indictment in that\\ncircumstance. The question instead is whether Rule 31(b)(3)\\nprohibits them from doing so. It does not.\\n66\\n Link, 370 U.S. at 631-32.\\n67\\n See Bank of Nova Scotia v. United States, 487 U.S. 250,\\n254-56, 263 (1988); United States v. Chapman, 524 F.3d\\n1073, 1087 (9th Cir. 2008); United States v. Goodson, 204\\nF.3d 508, 514 (4th Cir. 2000); United States v. Derrick, 163\\n\\n\\n\\n\\n 19\\n\\nwith the particular circumstance we face here: the decision to\\nretry a defendant after serial mistrials. 68 In fact, many are\\ndismissals due to prosecutorial misconduct. The majority’s\\nreliance on such decisions is misplaced because it ignores the\\nfact that the dismissal in this case was not punitive in nature;\\nit was not a sanction for misconduct. 69 As two commentators\\nhave explained, “[a]lthough the inherent power principle has\\nusually involved cases of misconduct by the parties or a\\nvindication of statutory principles, the doctrine is not so\\nlimited.” 70 To the contrary, courts may use their inherent\\nauthority to dismiss indictments whenever necessary to\\nvindicate “principles of fairness to the defendant and the\\ninterests of the public in the effective administration of\\njustice.” 71\\n\\n That is just what the District Court did here. The\\nGovernment asked the District Court to dismiss without\\nprejudice “[e]ven if this court were inclined to dismiss the\\ncase.” 72 Yet the Government proffered no additional\\n\\n\\nF.3d 799, 808 (4th Cir. 1998); United States v. Tucker, 8 F.3d\\n673, 674 (9th Cir. 1993) (en banc); United States v. Van\\nEngel, 15 F.3d 623, 631-32 (7th Cir. 1993); United States v.\\nSantana, 6 F.3d 1, 11 (1st Cir. 1993); United States v. Isgro,\\n974 F.2d 1091, 1094 (9th Cir. 1992).\\n68\\n Derrick does deal with a dismissal of the indictment after\\nan initial grant of a retrial, but the circumstance differs from\\nthis case because the mistrials were not due to deadlocked\\nverdicts. See 163 F.3d at 803\\n69\\n Cf., e.g., Isgro, 974 F.2d at 1097.\\n70\\n Berch & Berch, supra note 51, at 548.\\n71\\n Id.\\n72\\n Wright, 2017 WL 1179006, at *7.\\n\\n\\n\\n\\n 20\\n\\nevidence it would present if Wright was re-indicted. It asked\\nto try the same case again before a third jury, merely hoping\\nfor a different result. The District Court’s dismissal of the\\nindictment with prejudice was based on the merits, or lack\\nthereof, of the Government’s request, no more and no less.\\n\\n Moreover, the dismissal was not, as the majority\\ncontends, a general declaration of unfairness simply because\\nthe government failed to obtain a conviction. 73 Nor was it\\nmerely an attempt to shield the defendant from the anxiety of\\na retrial. 74 Reference to Miller and Shepherd misconstrues\\nnot only the circumstance of this case, but also the gravity of\\nthe District Court’s concern. As I discuss next, the District\\nCourt weighed many factors, mindful of the importance of\\neach, before making its decision. From all of this—even\\ntaking into account the separation of powers and Rule\\n31(b)(3)—it is evident to me that the District Court correctly\\nconcluded it had the inherent authority to act upon the\\nprosecutor’s decision to retry this case in the wake of two\\nmistrials. 75\\n\\n73\\n See United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\n74\\n See United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975); see also Arizona v. Washington, 434 U.S. 497, 503-04\\n(1978).\\n75\\n Although we conclude that the District Court appropriately\\nexercised its inherent power as a court of law to dismiss an\\nindictment, thus placing its actions within Eash’s first\\ncategory, the District Court appeared at one point to tether its\\ndismissal to its “inherent authority to effectuate . . . the\\nspeedy and orderly administration of justice and to ensure\\nfundamental fairness.” Wright, 2017 WL 1179006, at *2.\\nThese actions are typically associated with the second\\n\\n\\n\\n\\n 21\\n\\n III.\\n\\n Before moving to the actual merits of the District\\nCourt’s decision, a word of caution is in order. Just because a\\ncourt has inherent power to dismiss an indictment after a\\nretrial does not mean it should always be exercised. 76 My\\ndissenting opinion today should not be interpreted as an\\nendorsement of unchecked and ungrounded judicial power.\\nNor should it be interpreted as permitting district courts in\\nthis Circuit to dismiss indictments without a significant basis\\nfor doing so. Moreover, nothing in this opinion should be\\nread as limiting reprosecution to two trials. Cases no doubt\\nexist where a third or fourth trial on the same indictment may\\nbe appropriate where the evidence so indicates. It is simply\\nmy conclusion that, in some cases, and in the proper exercise\\nof its discretion, a district court has the inherent power to\\nprohibit continued re-prosecution by dismissing an\\nindictment.\\n\\n IV.\\n\\n This is such a case. The District Court here rightly\\nproceeded with the Government’s request for another trial\\nwith deliberate caution. Recognizing the lack of guidance\\n\\n\\nclassification of Eash’s powers. See Eash, 757 F.2d at 562-\\n563. Nonetheless, it invoked the inherent power of the court\\nand dismissed the case and it is on this basis that I conclude\\nthe District Court did not reach the boundaries of its power.\\n76\\n See Lopez v. United States 373 U.S. 427, 440 (1963); see\\nalso Chambers, 501 U.S. at 44 (“Because of their very\\npotency and discretion, inherent powers must be exercised\\nwith restraint and discretion.”).\\n\\n\\n\\n\\n 22\\n\\nfrom this Court, the District Court turned to a decision of the\\nSupreme Court of New Jersey. In State v. Abbati, 77 that court\\nlisted several factors a trial court should consider before\\ndismissing an indictment after several hung juries. These\\nfactors are valid inquiries and include\\n\\n • the number of previous mistrials and the\\n outcome of the juries’ deliberations, as far as\\n can be determined;\\n • the character or nature of the previous trials,\\n considering their length, complexity of issues,\\n and similarities in evidence;\\n • the probability that any subsequent trial will be\\n much different from the previous ones;\\n • the relative strength of the party’s case, as\\n determined by the trial court;\\n • the conduct of counsel during the previous\\n trials. 78\\n\\nIn considering these factors, a district court must also accord\\nappropriate weight to the Government’s decision to continue\\nprosecution, giving deliberate consideration to the reasons for\\nthat choice. 79\\n\\n Other considerations might include the seriousness of\\nthe crimes charged, the public’s interest in the effective\\nresolution of criminal charges, and the criminal defendant’s\\ncircumstances, including the impact that continued\\nprosecution might have on him or her and the potential for\\n\\n77\\n 493 A.2d 513.\\n78\\n Id. at 521-22.\\n79\\n See id.\\n\\n\\n\\n\\n 23\\n\\nunfairness or unnecessary hardship. 80 The factors just\\noutlined are not an exhaustive list and district courts could\\nconsider other things that are reasonably useful in answering\\nwhether further prosecutions after deadlocked juries should\\nbe permitted. Moreover, all of these elements of inquiry\\nenable the court to assess the impact that a serial retrial has on\\nthe integrity of the judiciary as an institution.\\n\\n These avenues of inquiry make sense to me. Take\\ndifferences in evidence, for example. If the evidence would\\nbe different at a retrial, then there seems little chance that\\ncontinued prosecution should be curtailed. If, on the other\\nhand, there would be no substantial difference in evidence,\\nconcern about re-prosecution is appropriate. So too the\\nnumber of deadlocked juries is an important consideration.\\nContinued prosecution after two, three, or even four\\ndeadlocked juries could unbalance the scale. By inquiring\\ninto the seriousness of the charges, a district court could\\ncompare the crime being prosecuted to other cases when a\\ncourt dismissed an indictment after deadlocked juries. In\\nother words, a district court must make sufficient findings and\\nestablish a sufficient record supporting its decision, thus\\nenabling a court of appeals to accurately assess whether the\\ndistrict court abused its discretion or not. That is what the\\nDistrict Court did here.\\n\\n I see no abuse of discretion in the District Court’s\\nexercise of its inherent powers. The District Court’s ruling\\nwas not arbitrary and instead was based on a thorough,\\ncareful, and balanced consideration of the above factors. The\\nDistrict Court first acknowledged the weight of its actions\\n\\n80\\n See id.\\n\\n\\n\\n\\n 24\\n\\nwithin our constitutional scheme. It then found that the\\nevidence suggested that the deadlock was not the result of a\\nlone holdout. As to the character of the preceding trials, the\\nDistrict Court noted the Government’s position that this was a\\n“simple” case. It also stated that both previous trials were\\n“virtual duplicates” and that counsel on both sides was the\\nsame for both prosecutions. The District Court further\\nobserved the lack of any allegation of jury nullification or\\nbias. Instead, it found that “there is every indication that the\\ntwo juries engaged in deliberations in good faith, and, despite\\ntheir best efforts, were unable to reach a verdict.”\\n\\n The District Court also considered the strength of the\\nparties’ respective cases and determined that its opinion on\\nthis factor was irrelevant, given that two separate juries had\\nconcluded that the Government failed to meet its burden of\\nproof. It commended the professionalism and hence the\\neffectiveness of counsel on all sides, which it weighted as\\nfavoring disallowing any further prosecution. The District\\nCourt specifically considered the seriousness of the crime\\ncharged, and it noted that other courts had dismissed\\nindictments when the charges were far graver. 81 Lastly, the\\nDistrict Court thoroughly balanced the Government’s\\nauthority to prosecute against the effect of continued\\nprosecution on Wright. Recognizing that Wright has been on\\nbond since July of 2014, and on home detention for nearly\\ntwo years, the District Court concluded that this inquiry\\ntipped in his favor.\\n\\n81\\n Wright, 2017 WL 1179006, at *6 (citing United States v.\\nIngram, 412 F. Supp. 384, 385 (D.D.C. 1976); State v.\\nMoriwake, 647 P.2d 705, 708 (Haw. 1982); Abbati, 493 A.2d\\nat 517; and State v. Witt, 572 S.W.2d 913, 914 (Tenn. 1978)).\\n\\n\\n\\n\\n 25\\n\\n V.\\n\\n In conclusion, I see no abuse of discretion in the\\nDistrict Court’s careful and thorough balancing of relevant\\nfactors, a balancing which led it to invoke its inherent power\\nand to dismiss the Government’s indictment of Wright. For\\nall of these reasons, I respectfully dissent from my esteemed\\ncolleagues in the majority. I would affirm.\\n\\n\\n\\n\\n 26\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360237/\", \"author_raw\": \"NYGAARD, Circuit Judge, dissenting\"}, {\"author\": \"McKEE, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"McKEE, Circuit Judge, concurring in the judgment.\\n\\n As I shall explain, I am sympathetic to what the District\\nCourt was trying to do in this case and I think I understand why\\nthe court acted as it did. Moreover, I agree with Judge Nygaard\\ninsofar as he posits in dissent that a District Court can step in\\nat some point and bar a retrial without infringing on the\\nseparation of powers. Nevertheless, despite my belief that the\\nseparation of powers doctrine is not necessarily violated by a\\ntrial court barring a retrial after successive mistrials, and\\ndespite my belief that the District Court was trying to act in a\\nmanner that would assure a measure of justice for Wright, I\\nconcur in the judgment reversing the District Court. I simply\\ndo not believe that the current state of the law supports the\\nDistrict Court’s action in the absence of prosecutorial\\nmisconduct, bad faith, or more than two unsuccessful trials.\\nSince the record is clear that the District Court found neither\\nprosecutorial misconduct nor bad faith, I concur in the\\njudgment reversing the court’s order but feel compelled to\\nwrite separately to explain why.\\n I.\\n At the outset, it is important to note that I do not believe\\nthat a trial court lacks the power to, at some point, call a halt to\\nsuccessive prosecutions following deadlocked juries, and I do\\nnot read Judge Shwartz’s opinion as standing for that principle.\\nThe Government even conceded at oral argument that there\\ncould come a point where successive prosecutions become so\\nonerous and burdensome that additional trials rise to the level\\nof a Due Process violation which a trial court is clearly\\nempowered to prevent. Moreover, in Barkus v. Illinois, 1 the\\nSupreme Court noted that there “may” come a point where\\nmultiple prosecutions become so harassing that they violate the\\nDue Process Clause. 2\\n\\n Here the evidence in both trials consisted solely of\\npolice testimony. According to the officers’ testimony, some\\nresidents of the community witnessed crucial parts of Wright’s\\nencounter with the police, but they did not testify. Similarly,\\nWright did not testify on his own behalf, nor did the defense\\nput on a case. His theory was that he had no way of knowing\\n\\n1\\n 359 U.S. 121 (1959).\\n2\\n Id. at 127.\\n 1\\n\\nthat the men in plain clothes and unmarked cars who began\\npursuing him were police; he panicked, sped away, and\\ncrashed; and police subsequently planted the gun at the scene.\\nWright also asserted that the officers chose not to test the gun\\nfor DNA or fingerprints because they knew the results would\\ncontradict their story. In an effort to counter Wright’s\\nargument from the first trial that police decided not to test the\\ngun for fingerprints and DNA in order to hide their\\nmalfeasance, the Government called experts at the second trial\\n“who testified about the difficulty of retrieving DNA and\\nfingerprint evidence from firearms.” 3\\n\\n Nevertheless, the Government’s case depended entirely\\non the testimony of police officers who had worked together\\nfor many years and/or knew one another. Over the span of ten\\nmonths, the District Court twice listened to the police\\ntestimony during the trials. That testimony was at times\\ncontradictory and at other times strained credulity.\\n\\n At the first trial, Detective Fallert, who first noticed\\nWright speeding, testified that Wright was travelling at 90\\nmph, but he did not note that in his police paperwork nor did\\nhe note it at the pretrial hearing. His contemporaneously\\nprepared investigative report also did not claim that Wright\\nwas initially speeding. Detective Henson, who took over the\\nchase, testified that he saw Wright holding a handgun, but\\nconceded that he had no way of knowing whether Wright knew\\nhe was a police officer when the pursuit began. Lastly,\\nDetective Baker testified similarly to Henson, yet guessed that\\nWright had been going at a speed of 60 mph and accelerated.\\nThis is a very substantial discrepancy, especially for seasoned\\npolice officers who can be expected to have some expertise and\\nexperience in estimating the speed of an automobile.\\n\\n In the second trial, the Government called the same\\nwitnesses, with the exception of Detective Fallert. Notably,\\nthis time Detective Henson testified he actually did not see\\nWright speeding. Two different juries found themselves\\ndeadlocked—unable to convict or acquit.\\n II.\\n The majority opinion suggests that the District Court’s\\n\\n3\\n Appellant Br. at 11.\\n 2\\n\\ndecision to dismiss the indictment with prejudice\\nimpermissibly infringed upon the jury’s role. Judge Shwartz\\nstates: “[t]he District Court nonetheless applied its own\\npredictions about what another jury may do when presented\\nwith the same evidence,” and concluded that was “an improper\\nexercise of a court’s supervisory power.” 4 However, it is\\ndifficult to know whether the District Court ruled as it did\\nbased upon a belief that a third jury presented with the same\\nevidence would be unable to reach a verdict or whether it\\nsimply shared the doubts that some of the jurors obviously had\\nabout the veracity of police officers’ testimony.\\n\\n In any event, either scenario poses exactly the same\\nissue about a court overstepping its bounds and infringing on\\nthe role of a jury as well as prosecutorial discretion. As I stated\\nat the beginning, to the extent that a trial judge can intervene\\nand dismiss an indictment, I am skeptical that this record\\nsupports such an assertion of judicial authority. Nevertheless,\\nthere is more support for the judge’s actions here than our\\nreversal suggests.\\n\\n It is not a novel proposition that a trial judge must\\n“ensure that any and all . . . evidence is not only relevant, but\\nalso reliable.” 5 “The trial judge’s role is to preside over the\\ntrial; passively if possible but aggressively when indicated.” 6\\nThus, the law allows for trial courts to channel the jury’s\\njudgment in certain circumstances. Here, the court’s decision\\nwould prevent another jury from hearing the same evidence\\nthat has failed to convict Wright on two prior occasions.\\n\\n There are situations in which judges must act as\\n“gatekeepers” and ensure the reliability of evidence before a\\njury is able to consider it. Accordingly, in an admittedly very\\ndifferent context, the Supreme Court has described trial judges\\nas gatekeepers of evidence. 7 “[A] gatekeeping role for the\\n\\n4\\n Maj. Op. 13–14.\\n5\\n Kannankeril v. Terminix Int’l, Inc., 128 F.3d 802, 806 (3d\\nCir. 1997) (citing Daubert v. Merrill Dow Pharms., 509 U.S.\\n579, 589 (1993)).\\n6\\n Holdnrook v. Lykes Bros. Steamship Co., 80 F.3d 777, 788\\n(3d Cir. 1996).\\n7\\n Daubert, 509 U.S. at 597.\\n 3\\n\\njudge, no matter how flexible, inevitably on occasion will\\nprevent the jury from learning of authentic insights and\\ninnovations.” 8\\n\\n Despite the importance of the jury system, and the faith\\nwe place in juries, the law has thus traditionally recognized the\\ndanger that jurors may not be able to restrict their deliberations\\nto admissible evidence and that they may return a verdict based\\non factors other than the evidence presented at trial. For\\nexample, Federal Rule of Evidence 403 allows courts to\\nprevent jurors from learning of certain testimony (even\\nuncontradicted testimony) if the court concludes that the\\ntestimony could cause a jury to reach a verdict based more on\\nemotion or prejudice than on evidence. 9\\n\\n The best known example of how courts are empowered\\nto limit what a jury can consider may well be the body of law\\nthat has developed in the wake of the Supreme Court’s decision\\nin Daubert. In Daubert, the Court stated: “the trial judge must\\nensure that any and all scientific testimony or evidence\\nadmitted is not only relevant, but reliable.” 10 We certainly\\ncould, but do not, allow the jury to determine whether the\\nscientific evidence is reliable in the first instance based upon\\ntestimony at trial. Instead, that preliminary factual\\ndetermination rests solely with the trial court if the reliability\\nis challenged.\\n\\n The difficulty with relying on this body of law here is,\\nof course, the fact that the trial court’s dismissal of Wright’s\\nindictment was not limited to an intrusion into the jury-box.\\nMore fundamentally, and more importantly, it also trespassed\\non the separation of powers, and concomitantly, on the\\nprosecutorial discretion that is endemic in that concept.\\n\\n Despite Judge Nygaard’s thoughtful attempt to address\\nthat issue and the jury’s obvious concerns regarding the\\n\\n8\\n Id.\\n9\\n See, e.g., United States v. Bailey, 840 F.3d 99, 117, 121–23,\\n(3d Cir. 2016) (finding that the probative value of video\\nevidence of murder committed by coconspirators was\\nsubstantially outweighed by risk of unfair prejudice).\\n10\\n Daubert, 509 U.S. at 589.\\n 4\\n\\ntestimony of police officers in this case, I am not convinced\\nthat the United States Supreme Court would agree that the\\ninherent powers of a trial court are broad enough to justify what\\nhappened here.\\n\\n The Government clearly has the inherent authority to\\ndecide not to retry Wright given all of the circumstances in this\\ncase, including the seemingly improbable account of what\\nhappened, 11 the conflicting nature of the police testimony and\\nthe jurors’ apparent trouble with it, the fact that there is no\\nadditional evidence to offer at a third trial, and Wright’s\\napparent steps toward rehabilitation since the offense which\\ndisqualified him from lawfully owning a firearm, as well as any\\nother factors that the Government might appropriately\\nconsider. 12 However, I can find no authority that convinces me\\nthat the United States Supreme Court would agree that a trial\\ncourt’s inherent authority allows it to dismiss an indictment\\nwith prejudice on this record.\\n\\n III.\\n\\n\\n\\n11\\n According to the officers’ accounts, they watched (in the\\nopen and without cover) as Wright fumbled in the back of a\\ncar with tinted windows and came out holding a gun. They\\nthen continued to stand and watch from approximately 25\\nyards away—without cover and without taking any actions to\\nprotect themselves—as he attempted to rack the slide which\\nwould have placed a bullet in the chamber.\\n12\\n Appellee argues without contradiction that:\\n\\n [f]ollowing early involvement with the criminal\\n justice system, Mr. Wright began to turn his life\\n around, returning to school and earning his\\n Associates degree in Computer Management-\\n Networking Engineering Technology[,] . . . a\\n Bachelor of Science degree in Information\\n Technology and Management . . . graduating\\n cum laude[,] . . . and . . . a Master of Science\\n degree.\\n\\nAppellee Br. at 52.\\n 5\\n\\n As I noted at the outset, the Government agrees that\\nsuccessive prosecutions can rise to the level of a Due Process\\nviolation, which a court clearly could remedy by dismissing an\\nindictment. However, the Government strenuously argues\\nWright’s prosecution has not yet reached that point. The\\nGovernment’s position inherently argues that the court’s action\\nhere is also not justified by any concept of fundamental\\nfairness. In Ake v. Oklahoma, 13 the Supreme Court observed\\nthat the right to Due Process includes the “guarantee of\\nfundamental fairness.” 14 As has been discussed by Judge\\nShwartz, the District Court here relied on the decision of the\\nNew Jersey Supreme Court in State v. Abbati. 15 There, the\\nNew Jersey Supreme Court affirmed a trial court’s dismissal of\\nan indictment with prejudice after two juries deadlocked,\\nresulting in mistrials. 16 That situation is on “all fours” with the\\ncircumstances here and the District Court relied heavily on that\\ndecision to justify its action and fashion a rule that would\\nproperly allow a trial court to dismiss an indictment with\\nprejudice under certain circumstances. 17\\n\\n However, the New Jersey Supreme Court based its\\ndecision on the inherent authority of state courts under the New\\nJersey Constitution. 18 It did not purport to rest its decision on\\nthe U.S. Constitution and, with very limited exception, it cited\\nto state judicial decisions—not federal ones—in discussing\\nwhen consecutive hung juries justified dismissing an\\nindictment with prejudice. 19 The holding of the Court is\\n\\n13\\n 470 U.S. 68 (1985).\\n14\\n Id. at 76.\\n15\\n 493 A.2d 513 (N.J. 1985).\\n16\\n Id. at 522.\\n17\\n See United States v. Wright, Crim A No. 14-292, 2017 WL\\n1179006, at *3, *4 (W.D. Pa. Mar. 30, 2017).\\n18\\n Abbati, 493 A.3d at 517–18.\\n19\\n Abbati cited to Ake, for the general proposition that the\\n“requirement of fundamental fairness [is] grounded in [the]\\nfourteenth amendment’s due process guarantee.” 493 A.2d at\\n518. However, with the exception of a single District Court\\ncase, the Court cited numerous state court cases for the\\nproposition that a trial court had the inherent authority to\\ndismiss an indictment with prejudice after two juries\\ndeadlocked. Id. at 519–20. It concluded by finding “[t]hese\\n 6\\n\\nsummarized in its statement that the “judicial responsibility for\\nthe proper administration of criminal justice also gives rise to\\nthe inherent power to dismiss an indictment in appropriate\\ncircumstances.” 20\\n\\n The Abbati standard has not been discussed by this\\nCourt (aside from in the instant case), let alone adopted by it.\\nAlthough some of the factors used by the New Jersey Supreme\\nCourt are analogous to considerations federal courts have made\\nin similar federal cases, such as United States v. Ingram 21 and\\nUnited States v. Rossoff, 22 Abbati has no real corollary in\\nfederal case law. 23\\n\\nexamples of the courts’ exercise of their power to administer\\nthe criminal justice system assist in answering the further\\nargument of the State that recognition of an inherent judicial\\npower to dismiss an indictment with prejudice would overstep\\nthe separation of powers.” Id. at 520. Abbati dismissed that\\nargument based upon its belief that “[t]he separation of\\npowers is not an end in itself, but a general principle intended\\nto ensure that the system of checks and balances remains\\nvital.” Id. at 521 (citing State v. Leonardis, 375 A.2d 607, 612\\n(N.J. 1977)).\\n20\\n Id. at 520.\\n21\\n 412 F. Supp. 384 (D.D.C. 1976). The District Court of the\\nDistrict of Columbia dismissed an indictment after two trials\\nin which twenty-one of twenty-four jurors voted to acquit.\\nThe court found no prosecutorial misconduct. Id. at 386. It\\ninstead considered the issue a “matter of fair play,”\\nemphasizing that “[t]he Government has no new proof; it\\nsimply wants another chance” and “simply wishes to keep\\npressing so long as juries disagree in the hope that a\\nconviction eventually will result.” Id. at 385.\\n22\\n 806 F. Supp. 200 (C.D. Ill. 1992).\\n23\\n For example, the first prong of Abbati’s analysis concerns\\nthe number of mistrials and the outcome of the juries’\\ndeliberations. 493 A.2d at 521. Both Rossoff and Ingram took\\nthis into account in dismissing indictments. See Rossoff, 806\\nF. Supp. at 203 (naming, as “additional compelling\\ncircumstances: 1) the majority of jurors in both cases found\\nDr. Rossoff Not Guilty; 2) if not for the allegedly biased juror\\nin the second trial, Dr. Rossoff would have been acquitted on\\nall counts; 3) the two trials have taken over one solid month\\n 7\\n\\n Accordingly, as I noted at the outset, I am sympathetic\\nto the District Court’s efforts given the totality of the\\ncircumstances here. However, until Congress or the United\\nStates Supreme Court determines otherwise, I agree that we\\nhave no alternative but to enter judgment reversing the District\\nCourt. I therefore concur in the judgment reversing the District\\nCourt’s order.\\n\\n\\n\\n\\nof the Court’s time”); Ingram, 412 F. Supp. at 385 (“The\\nproof was legally sufficient to support a conviction in each\\ninstance but the juries simply did not credit the witnesses,\\nvoting 10–2 and 11–1 for acquittal.”).\\n The Abbati standard is also based on the likelihood of\\nany substantial difference in a subsequent trial, which the\\nIngram decision also considered. See Ingram, 412 F. Supp. at\\n385 (“If another trial takes place there is every reason to\\nbelieve the jury will again be divided or will acquit.”).\\n Finally, Rossoff and Ingram both made determinations\\nsimilar to Abbati’s seventh prong, the status of the individual\\nand the impact of a retrial upon the defendant in terms of\\nuntoward hardship and unfairness. 483 A.2d at 422; see\\nIngram, 412 F. Supp. at 385–86 (“Here is a man in jail now\\nmore than seven months primarily because of an offense\\nwhich the Government is unable to convince a jury he\\ncommitted. . . . To permit a retrial, after 21 of 24 jurors have\\nalready refused to convict, is to ignore the reasonable doubt\\nstandard.”); Rossoff, 806 F. Supp. at 203 (“Dr. Rossoff is 71\\nyears of age and in poor health. He has had heart surgery,\\nsuffers from severe anemia and at the time of the second trial\\nwas on experimental treatment. He has been under great\\nphysical and emotional strain as the result of these repeated\\ntrials and was even hospitalized immediately following the\\nsecond trial.”).\\n\\n 8\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360237/\", \"author_raw\": \"McKEE, Circuit Judge, concurring\"}]}"},"judge1":{"kind":"string","value":"MCKEE"},"judge2":{"kind":"string","value":"SHWARTZ"},"judge3":{"kind":"string","value":"NYGAARD"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"MCKEE\": \", Circuit\", \"SHWARTZ\": \", Circuit\", \"NYGAARD\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":4,"string":"4"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":2,"string":"2"},"concurrence_count":{"kind":"number","value":1,"string":"1"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4582984/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: United States v. Raymont Wright\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-18\nOpinion type: majority\nHas dissenting opinion: Yes\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-1972\n _____________\n\n UNITED STATES OF AMERICA,\n\n Appellant\n\n v.\n\n RAYMONT WRIGHT\n\n ______________\n\n ON APPEAL FROM THE\n UNITED STATES DISTRICT COURT\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\n (D.C. No. 2-14-cr-00292-001)\n District Judge: Hon. Cathy Bissoon\n ______________\n\n Argued May 24, 2018\n ______________\n\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\n Judges.\n\n (Opinion Filed: January 17, 2019)\n\n ______________\n\n OPINION OF THE COURT\n ________________\n\nDonovan J. Cocas, Esq. [ARGUED]\nJane M. Datttilo, Esq.\nLaura S. Irwin, Esq.\nOffice of the United States Attorney\n700 Grant Street\nSuite 4000\nPittsburgh, PA 15219\n\n Attorney for Appellant\n\nRenee Pietropaolo, Esq. [ARGUED]\nLisa B. Freeland, Esq.\nAkin Adepoju, Esq.\nOffice of the Federal Public Defender\n1001 Liberty Avenue\n1500 Liberty Center\nPittsburgh, PA 15222\n\n Attorneys for Appellee Raymont Wright\n\nLawrence S. Lustberg, Esq. [ARGUED]\nGibbons, P.C.\nOne Gateway Center\nNewark, NJ 07102\n\n Attorney for Amicus Appellee National Association of\n Criminal Defense Lawyers\n\n\n\n\n 2\n\nSHWARTZ, Circuit Judge.\n\n The District Court barred a retrial of and dismissed the\nindictment against Defendant Raymont Wright with prejudice\nafter two juries failed to reach a verdict. The Court did so\nrelying on its inherent authority, but without finding that any\nmisconduct had occurred or that Wright would suffer any\nprejudice beyond the general anxiety and inconvenience of\nfacing a retrial. Under such circumstances, the Court lacked\nthe inherent authority to bar the retrial and dismiss the\nindictment. Therefore, we will reverse the order dismissing the\nindictment and remand for further proceedings.\n\n I\n\n In December 2014, Wright was charged with being a\nfelon in possession of a firearm, in violation of 18 U.S.C.\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\nMay 2016. The jury was unable to reach a verdict. A second\ntrial was held in March 2017, and that jury was also unable to\nreach a verdict.\n\n During both trials, the jury heard evidence from police\nofficers about Wright’s actions on July 24, 2014.1 That\nevening, five Pittsburgh Police detectives were patrolling in\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\nwere in the lead car, and Detectives Fallert and Goob were in\nthe second car. Around 8:30 p.m. (when it was still daylight),\nFallert and Goob saw a man, later identified as Wright, driving\n\n 1\n The following facts are drawn largely from the\nevidence presented at the first trial.\n\n\n\n\n 3\n\na car in the opposite direction well above the 25-mile-per-hour\nspeed limit. The detectives turned around to follow Wright,\nand Wright sped up and turned onto a loop-shaped road. The\ndetectives pursued Wright, who fled at a high speed and ran at\nleast four stop signs. The lead car lost sight of Wright shortly\nthereafter and discontinued pursuit.\n\n Officers in the lead car then noticed skid marks\nsuggesting that a car had intended but failed to make a left turn\nat the end of a street. Officers thereafter came upon Wright’s\ncar in a parking lot below. The car had gone through a fence,\nover a hillside, and into the lot. The car hit two unoccupied\nparked cars, its tires blew out, and its windows were down.\n\n Detectives Baker and Henson exited the vehicle at the\ntop of the hill and remained where Wright’s car broke through\nthe fence, and Detective Kennedy drove his car down to the\nparking lot’s entrance. Baker and Henson testified that they\nsaw Wright search around the rear passenger seat of the car,\nback out of the vehicle with a black semi-automatic handgun\nin his right hand, and try to “rack the slide,” which can insert\nor remove a round from the chamber. App. 118-19. They had\ntheir weapons drawn and told Wright to drop the gun. At first,\nWright merely stepped back, but he eventually tossed the gun\nto the side, backed away, and lied on the ground. Pittsburgh\npolice officer Elliott and his partner, who heard of the crash on\nthe radio, were the first to reach Wright, and saw him lying on\nthe ground with a handgun next to him. Henson stated that\nwhen he made it down to the parking lot, he heard Wright say\nto him, “Hey, big guy. You won this time or you won this\nround, something of that nature. He [Wright] said: You feel\nme? You won this time,” which Henson understood to mean\nthat he had just avoided a shootout or that he caught Wright\n\n\n\n\n 4\n\nafter the pursuit. App. 125. Henson subsequently took custody\nof the gun and noticed the slide lever was bent, and when he\nstraightened it, saw the gun was loaded with eight rounds, and\none in the chamber. 2\n\n At the close of the Government’s case, Wright moved\nfor a directed verdict, arguing that no reasonable juror could\nfind beyond a reasonable doubt that Wright possessed the\nfirearm. The District Court denied the motion because “the\nevidence does thus far demonstrate that a reasonable juror\ncould most certainly find the Defendant guilty of the charge in\nthis case.” App. 171. Wright did not present a case.\n\n The jury deliberated for approximately five hours and\nthen reported to the Court that it was deadlocked. After polling\nthe jurors to confirm they were deadlocked and further\ndeliberations would not bring them closer to a unanimous\nverdict, the District Court declared a mistrial.\n\n At Wright’s March 2017 retrial, the Government\npresented substantially the same evidence. The Government\nalso called Detective Kennedy and Lieutenant Palermo, who\nwere at the scene after Wright was arrested, as well as experts\nwho testified regarding the collection of DNA and fingerprint\nevidence from firearms to respond to Wright’s argument at the\nfirst trial that investigators chose not to test the gun for forensic\nevidence in an effort to cover up that they had planted the gun\nat the scene.\n\n\n 2\n The parties stipulated Wright had been convicted of a\nqualifying felony, and an ATF Special Agent testified about\nthe gun’s interstate nexus.\n\n\n\n\n 5\n\n At the close of the Government’s case, Wright again\nmoved for a judgment of acquittal, which the Court denied\nbecause “there is sufficient evidence in the record to establish\nbeyond a reasonable doubt that Mr. Wright possessed the\nfirearm in the case,” App. 650. Wright did not put on a case.\n\n The second jury deliberated for approximately three\nhours and then reported that it was hopelessly deadlocked. The\nCourt polled the jury to confirm the deadlock and then\ndismissed the jury. 3\n\n After the Government notified the Court that it intended\nto retry the case, the Court required the parties to brief\n“whether the Court, through an exercise of its inherent\nauthority, should prohibit or permit a second re-trial in this\ncase.” App. 26. After considering the parties’ arguments, the\nDistrict Court dismissed the indictment with prejudice, holding\nthat it “ha[d] the inherent authority, under some circumstances,\nto dismiss an indictment following multiple mistrials.” United\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\nunderlying the Double Jeopardy Clause also applied to a\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\n(2) other courts had dismissed indictments in similar\n\n 3\n Wright asserted that in the first trial, jurors voted 8-4\nfor acquittal, and in the second trial, the jury was evenly split.\nThe Government asserted that in the first trial, jurors voted 7-\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\nnot explain how he obtained these numbers, the Government\nsaid it obtained them by speaking with the jurors.\n\n\n\n\n 6\n\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\nexpressly allows the Government to retry a case after a mistrial,\nnothing in the rule “limits a court’s inherent supervisory\nauthority to dismiss an indictment in the interests of\nfundamental fairness,” id. at *4; and (4) if the Court were to\nadopt the Government’s position that there are no limit to the\nnumber of times the Government can retry a defendant, it\nwould be tantamount to a “type of jury shopping” that a court\nshould not permit, id. at *4. The District Court also considered\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\nconcluded that most factors supported dismissal. 4\n\n 4\n The Abbati factors are\n\n (1) the number of prior mistrials and the\n outcome of the juries’ deliberations, so far as is\n known; (2) the character of prior trials in terms\n of length, complexity, and similarity of evidence\n presented; (3) the likelihood of any substantial\n difference in a subsequent trial, if allowed;\n (4) the trial court’s own evaluation of the relative\n strength of each party’s case; and (5) the\n professional conduct and diligence of respective\n counsel, particularly of the prosecuting attorney.\n The court must also give due weight to the\n prosecutor’s decision to reprosecute, assessing\n the reasons for that decision, such as the gravity\n\n\n\n\n 7\n\n The Government appeals.\n\n II 5\n\n We review the District Court’s order dismissing the\nindictment based on the Court’s inherent power for abuse of\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\n\n of the criminal charges and the public’s concern\n in the effective and definitive conclusion of\n criminal prosecutions. Conversely, the court\n should accord careful consideration to the status\n of the individual defendant and the impact of a\n retrial upon the defendant in terms of untoward\n hardship and unfairness.\n\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\nat 521-22). For the reasons set forth herein, we would not\nadopt Abbati, but even if we were to consider the Abbati\nfactors, we would conclude that they do not support dismissal\nin this case.\n 5\n The District Court had jurisdiction pursuant to 18\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\n§ 3731.\n 6\n The phrases “inherent power,” “inherent authority,”\n“supervisory power,” and “supervisory authority” are all used\nto describe the basis for a court action seeking to maintain the\nintegrity of the proceedings that is not directly tethered to a\nspecific rule, statute, or constitutional provision. See, e.g.,\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\n43 (1991) (inherent power); Bank of Nova Scotia v. United\n\n\n\n\n 8\n\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\nindictment for abuse of discretion); cf. Chambers v. NASCO,\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\nsanctions under its inherent power for abuse of discretion);\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\n2005) (“A trial court’s remedy for a discovery violation under\nits supervisory powers is reviewed for abuse of discretion.”).\nA district court abuses its discretion when it makes an errant\nconclusion of law, an improper application of law to fact, or a\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\n\n A\n\n Federal Rule of Criminal Procedure 31 allows the\nGovernment to retry a case if the court declares a mistrial after\na jury announces it is unable to reach a verdict. Specifically,\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\non one or more counts, the court may declare a mistrial on\nthose counts. The government may retry any defendant on any\ncount on which the jury could not agree.” Fed. R. Crim. P.\n31(b)(3). The word “may” means that the Government has the\n\n\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\n(supervisory power); United States v. Payner, 447 U.S. 727,\n733-36 (1980) (supervisory power); United States v. Nobles,\n422 U.S. 225, 231 (1975) (inherent power).\n Even if we accepted the distinctions our dissenting\ncolleague has drawn between inherent judicial powers,\nlegislatively granted judicial powers, and supervisory powers,\neach category must operate within the constitutional\nframework, including the separation of powers.\n\n\n\n\n 9\n\ndiscretion to retry a case, and nothing in the rule or its\ncommentary provides or even suggests a limit on the number\nof retrials it may conduct. See United States v. Wqas Khan,\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\n\n 7\n While Rule 31 does not limit the Government’s\nauthority to retry a case, a handful of district courts have\ndismissed indictments following a second hung jury, but those\ndecisions are not persuasive. In Ingram, the district court\ndismissed the indictment sua sponte (without any initial\nobjection by the Government) after two mistrials—in which\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\njailed during the pendency of the trials, and “[t]he Government\nha[d] no new proof; it simply want[ed] another chance.” 412\nF. Supp. at 385. The court concluded that to permit a retrial\nwould be “to ignore the reasonable doubt standard,” and so\n“[t]he Court’s intervention [was] required in the interest of\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\n(McGowan, J., dissenting)). The Ingram court, however, relied\nin part on the dissent in De Diego. Cases since Ingram have\napplied the De Diego majority’s view concerning a court’s\nlimited authority to dismiss an indictment. See, e.g., United\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\nDe Diego and reversing the district court’s dismissal of the\nindictment where the district court found it would be\n“unconscionable” to retry to the defendant); United States v.\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\nDiego and its dissent and holding a district court does not have\nauthority to sua sponte dismiss an indictment based on the\n\n\n\n\n 10\n\ndefendant’s poor health); United States v. Mussehl, 453 F.\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\nto dismiss the indictment based on alleged errors at trial, and\nciting De Diego for the proposition that “[t]he duty [to\nadminister justice] encompasses the concept of review of the\nquestion whether the United States Attorney, in making his\ndecision to prosecute, complied with the law, but does not\nallow the Court to question a United States Attorney’s\njudgment decision to prosecute, when lawfully made”).\n The District Court also relied on Rossoff, where the\ncourt denied the Government’s motion to dismiss the\nindictment under Federal Rule of Criminal Procedure 48(a),\nbut still dismissed the indictment with prejudice. 806 F. Supp.\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\nbeen two trials, and the Government sought to dismiss the\nindictment and refile the charges in a different judicial district.\nId. The court determined it had authority to dismiss an\nindictment with prejudice if a retrial was “against the concept\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\nSupp. 384), and did so because, among other reasons, the\ndefendant was in poor health, was under significant strain, and\na majority of jurors at both trials found him not guilty, id. at\n203. Rossoff, however, is distinguishable from Wright’s case\nbecause in Rossoff, the Government sought to dismiss the\nindictment so that it could refile charges in a different judicial\ndistrict, which caused the court to question the Government’s\ngood faith. In Wright’s case, the District Court made no\nfinding that the Government’s desire to retry Wright was for\nan improper purpose.\n In addition, and significantly, neither Ingram nor\nRossoff addressed the doctrine of separation of powers.\nRather, each essentially relied on a general concept of fairness\n\n\n\n\n 11\n\nthe text that empowers a court to prohibit the Government from\nretrying a case. 8\n B\n\n Apparently aware that Rule 31 did not provide it with a\nbasis to preclude a retrial in these circumstances, the District\nCourt concluded that it had the inherent authority to forbid the\nretrial and dismiss the indictment. The District Court erred.\n\n The exercise of inherent authority must satisfy two\nrequirements: (1) it “must be a reasonable response to the\n\n\nto the defendant in deciding to dismiss an indictment. See\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\nIn this Circuit, however, “[t]he judiciary may not impose its\npersonal and private notions of ‘fairness’ on law enforcement\nofficials, but does have a limited authority to affect\nprosecutorial actions when those actions are taken in violation\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\n596 (3d Cir. 1992) (citations omitted).\n 8\n Rule 31 differs from other Federal Rules of Criminal\nProcedure because it makes no mention of the court’s\nauthority. For instance, Rule 48(b) states that a court has\nauthority to dismiss an indictment “if unnecessary delay occurs\nin: (1) presenting a charge to the grand jury; (2) filing an\ninformation against a defendant; or (3) bringing a defendant to\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\ngrounds on which a district court could also dismiss an\nindictment, but each would be triggered by a motion, such as a\nmotion to dismiss for failure to comply with Rule 16’s\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\n16(d)(2)(D), or a motion asserting a defect in the indictment,\nFed. R. Crim. P. 12(b)(3)(B).\n\n\n\n\n 12\n\nproblems and needs confronting the court’s fair administration\nof justice,” and (2) it “cannot be contrary to any express grant\nof or limitation on the district court’s power contained in a rule\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\n(citations and internal quotation marks omitted). We will\nexamine each of these requirements in turn.\n\n 1\n\n As to the first Dietz requirement, “[g]uided by\nconsiderations of justice, and in the exercise of supervisory\npowers, federal courts may, within limits, formulate procedural\nrules not specifically required by the Constitution or the\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\n(internal quotation marks and citation omitted). Such rules\nmust be imposed (1) “to implement a remedy for violation of\nrecognized rights,” (2) “to preserve judicial integrity by\nensuring that a conviction rests on appropriate considerations\nvalidly before the jury,” and (3) “as a remedy designed to deter\nillegal conduct.” Id. (citations omitted). Thus, a court may\nexercise its inherent authority only when it is necessary to\naddress improper conduct and ensure respect for the\nproceedings.\n\n Under these principles, a court may dismiss an\nindictment based upon its inherent authority only if the\nGovernment engaged in misconduct, the defendant was\nprejudiced, and no less severe remedy was available to address\nthe prejudice. See Bank of Nova Scotia v. United States, 487\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\n(stating that “[a] court may dismiss an indictment under its\nsupervisory powers only when the defendant suffers\nsubstantial prejudice and where no lesser remedial action is\n\n\n\n\n 13\n\navailable” (citations and internal quotation marks omitted));\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\n(observing that “a district court may not, in the management of\nits docket, exercise its discretion to dismiss an indictment with\nprejudice, either under Rule 48(b) or under its supervisory\npower, unless the violation caused prejudice to the defendant\nor posed a substantial threat thereof” (emphasis omitted));\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\n(holding that an indictment may not be dismissed for\nprosecutorial misconduct absent a showing that the misconduct\nprejudiced the defendants, and stating that “virtually every\nother circuit to consider the issue post-Hasting and Nova Scotia\nhas also held that an indictment may not be dismissed based on\nprosecutorial misconduct, absent a showing of prejudice to the\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\n(7th Cir. 1993) (“A federal judge is not authorized to punish\nthe misconduct of a prosecutor by letting the defendant walk,\nunless the misconduct not only violated the defendant’s rights\nbut also prejudiced his defense . . . .”); United States v. Tucker,\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\nexercise its supervisory authority to reverse a conviction or\ndismiss an indictment absent prejudice to the defendant.”);\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\nHasting, and Bank of Nova Scotia form a trilogy admonishing\nfederal courts to refrain from using the supervisory power to\nconform executive conduct to judicially preferred norms by\ndismissing charges, absent cognizable prejudice to a particular\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\nCir. 1992) (“Before it may invoke this [supervisory] power [to\ndismiss an indictment], a court must first find that the\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\n1480 (9th Cir. 1994).\n\n\n\n\n 14\n\n In this case, there has been no misconduct. Indeed, the\nDistrict Court noted that the Government performed diligently\nand professionally in both trials, Wright, 2017 WL 1179006,\nat *4, and found that the evidence was sufficient to prove\nbeyond a reasonable doubt that Wright possessed the gun. The\nDistrict Court nonetheless applied its own predictions about\nwhat another jury may do when presented with the same\nevidence, emphasized the need for finality, and opined that the\neffect of prosecution on the defendant precluded a proper\nprosecution from proceeding. See id. at *5-6. Invoking its own\nnotions about the unfairness of requiring a defendant to face a\nretrial where the Government did not obtain a majority of the\njurors’ votes is an improper exercise of a court’s supervisory\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\nMoreover, there is no prejudice to a defendant simply because\nhe faces the anxiety and the normal stress of undergoing a trial.\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\n1975) (“[A]nxiety is present to some degree in virtually every\ncase. Something more than the normal anxiety that\naccompanies a trial is necessary to show a degree of\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\nonly real harm alleged is the general unfairness to these\ndefendants in having to go forward yet again with a lengthy\ntrial, in their being ‘ground down’ by the several months’ drain\non their mental, emotional, and financial resources. A lack of\nsuch fairness, however, does not alone violate due process.”).\nRather, prejudice sufficient for the District Court to intervene\nin a proper prosecution based upon its inherent authority occurs\nonly where the Government engages in actions that place a\ndefendant at a disadvantage in addressing the charges. That\nsort of prejudice is absent in this case.\n\n\n\n\n 15\n\n Unless there is some constitutional basis, such as a due\nprocess violation, it makes sense to limit a court’s authority to\nbar retrial to instances of prosecutorial misconduct and\nprejudice. First, it ensures that a judge’s personal preferences\nabout a case do not influence whether the case proceeds. See\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\n(“The judiciary may not impose its personal and private\nnotions of ‘fairness’ on law enforcement officials, but does\nhave a limited authority to affect prosecutorial actions when\nthose actions are taken in violation of the Constitution.”).\nSecond, as more fully discussed below, it guarantees that a\ncourt limits the Executive’s decision to prosecute only where\nthere is a constitutionally sound reason to do so. 9 This brings\nus to the second Dietz requirement.\n\n\n 9\n For these reasons, we find unpersuasive our dissenting\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\nobservation that a court has the inherent power to resolve a\ncase, as authority for allowing a court dismiss an indictment\nafter successive hung juries. As a general matter, there is no\ndoubt that a court has the authority to dismiss a case, but it may\nnot simply end a case because it decides that it should not be\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\ntheir progeny make clear, the court must point to evidentiary\ndeficiency, prejudicial misconduct, or a constitutional basis,\nsuch as double jeopardy or due process, to justify precluding a\nprosecution. If a court believed that the evidence was deficient,\nthe prosecutor engaged in prejudicial misconduct, or a retrial\nwould violate the constitution, then it has a basis to preclude a\nretrial. Requiring such reasons for barring a retrial ensures that\n\n\n\n\n 16\n\n 2\n\n The second Dietz requirement reminds a court that the\nexercise of its powers must be in accordance with the\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\nwith the Constitution, a court must be mindful of its role in our\ntripartite form of government and the doctrine of separation of\npowers. Separation-of-powers principles limit a court’s\ninherent authority. “Regardless of whether the supervisory\npower stems from the federal courts’ inherent power to check\nintrusions by other branches of government or whether it is a\nform of specialized federal common law, the separation-of-\npowers principle imposes significant limits on it,” and\n“[p]roper regard for judicial integrity does not justify a\n‘chancellor’s foot veto’ over activities of coequal branches of\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\nCir. 1985) (internal quotation marks omitted) (quoting United\nStates v. Russell, 411 U.S. 423, 435 (1973)).\n\n In the criminal context, the Executive Branch has\n“broad discretion as to whom to prosecute,” and this discretion\n“rests largely on the recognition that the decision to prosecute\nis particularly ill-suited to judicial review.” Wayte v. United\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\nquotation marks omitted). A court is not equipped to evaluate\n\n [s]uch factors as . . . the prosecution’s general\n deterrence value, the Government’s enforcement\n priorities, and the case’s relationship to the\n\n\nthe ruling is not based on a court’s own personal sense of\nwhether a case is worthy of prosecution.\n\n\n\n\n 17\n\n Government’s overall enforcement plan . . . .\n Judicial supervision in this area, moreover,\n entails systemic costs of particular concern.\n Examining the basis of a prosecution delays the\n criminal proceeding, threatens to chill law\n enforcement by subjecting the prosecutor’s\n motives and decisionmaking to outside inquiry,\n and may undermine prosecutorial effectiveness\n by revealing the Government’s enforcement\n policy. All of these are substantial concerns that\n make the courts properly hesitant to examine the\n decision whether to prosecute.\n\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\n(echoing similar sentiments with respect to Rule 48(a)\ndismissals). Thus, absent constitutional concerns, the decision\nto try or retry a case is at the discretion of the prosecutor.\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\nas superprosecutors, second-guessing the legitimate exercise of\ncore elements of prosecutorial discretion, but rather as neutral\narbiters of the law” (citation and internal quotation marks\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\n1994) (“[T]he choice to forego permanently a prosecution is\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\n676 (“In maintaining order in our own house, we should not\nneedlessly trample on the interest of the prosecutor and of the\npublic in securing proper, lasting convictions.”); Isgro, 974\nF.2d at 1097 (stating that the doctrine of separation of powers\n“mandates judicial respect for the independence of the\nprosecutor,” and “[d]ismissal of an indictment with prejudice\n\n\n\n\n 18\n\nis the most severe sanction possible”). 10 Accordingly,\nseparation-of-powers principles preclude a court from\nterminating a prosecution absent misconduct and prejudice to\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\n974 F.2d at 1094.\n\n In short, a court’s power to preclude a prosecution is\nlimited by the separation of powers and, specifically, the\nExecutive’s law-enforcement and prosecutorial prerogative.\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\nhere to dismiss an indictment in the absence of misconduct and\nprejudice and based only on the fact that two juries could not\nreach a verdict intrudes on the Executive’s domain and thereby\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\nat 138; Isgro, 974 F.2d 1091.\n\n 10\n Several state courts have also refused to recognize\nany inherent authority to dismiss an indictment to prevent a\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\n(Fla. Dist. Ct. App. 1980). Other states, however, have\nrecognized a court’s authority to dismiss an indictment sua\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\n712; Witt, 572 S.W.2d at 917. These latter cases are\nunpersuasive because they give too little weight to the\nseparation of powers, a crucial constitutional principle in the\nfederal system.\n\n\n\n\n 19\n\n Finally, there is no statute or procedural rule that\npermits a court to bar a retrial in the absence of misconduct and\nprejudice. First, a court may not dismiss an indictment as a\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\n505. Second, a court’s inherent power does not “include the\npower to develop rules that circumvent or conflict with the\nFederal Rules of Criminal Procedure.” Carlisle v. United\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\nexercise of inherent authority circumvents the absence of\npower of the district court to dismiss an indictment in Rule\n31(b). As stated above, courts have inherent authority to\ndismiss indictments, including, for instance, for prosecutorial\nmisconduct if the defendant was prejudiced, Bank of Nova\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\nnor our Court has extended a court’s inherent authority to allow\n\n 11\n In Chambers, for example, the Supreme Court\nrecognized a court’s authority to impose silence, respect, and\ndecorum based on its authority to manage its own affairs. 501\nU.S. at 43. This authority has been exercised by controlling\nadmission to the bar and disciplining its members; punishing\nfor contempt, which penalizes disruption to proceedings and\ndisobedience to court orders; disallowing fraud on the courts;\nensuring the proceedings move forward; and curtailing\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\ncivil case for failure to prosecute to prevent delays and court\ncongestion as part of a court’s inherent power to manage its\nown affairs). Chambers and Link address how a court may\nmanage its own proceedings, but they do not address how the\ncourt must also account for issues of separation of powers in\nthe context of a criminal case.\n\n\n\n\n 20\n\nthe sua sponte dismissal of an indictment solely to preclude\nmultiple mistrials following hung juries, see Chambers, 501\nU.S. at 47; HSBC, 863 F.3d at 136. 12\n\n 12\n Most cases concerning a court’s inherent authority\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\n(noting a court’s inherent powers to rescind a jury discharge\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\n(recognizing a court’s authority to vacate a judgment upon\nproof that a fraud was perpetrated on the court, and, in\nparticular, to assess as a sanction the entire amount of the\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\n(authority to dismiss a civil case sua sponte for failure to\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\n(1947) (dismissing an action based on the doctrine of forum\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\n(citing cases involving the scope of a district court’s inherent\npower); Eash, 757 F.2d at 561-64 (same).\n There are other circumstances in which district courts\nlack the inherent authority to act, and most of those situations\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\n433 (holding that a court does not have authority to grant a\npost-verdict motion for judgment of acquittal, filed one day\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\n45-50, 55 (holding that a district court does not have inherent\nauthority to dismiss an indictment because the Government\nfailed to disclose to the grand jury substantial exculpatory\nevidence; “[b]ecause the grand jury is an institution separate\nfrom the courts, over whose functioning the courts do not\npreside, we think it clear that, as a general matter at least, no\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\nat 129, 135-37 (holding that the district court violated\nseparation-of-powers principles by sua sponte invoking its\n\n\n\n\n 21\n\n Thus, the District Court abused its discretion in barring\na retrial and dismissing the indictment. 13\n\n III\n\n For the foregoing reasons, we will reverse and remand\nfor further proceedings.\n\n\n\n\nsupervisory power to oversee the government’s entry into and\nimplementation of a deferred prosecution agreement).\n 13\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: United States v. Raymont Wright\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-18\\nOpinion type: majority\\nHas dissenting opinion: Yes\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-1972\\n _____________\\n\\n UNITED STATES OF AMERICA,\\n\\n Appellant\\n\\n v.\\n\\n RAYMONT WRIGHT\\n\\n ______________\\n\\n ON APPEAL FROM THE\\n UNITED STATES DISTRICT COURT\\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\\n (D.C. No. 2-14-cr-00292-001)\\n District Judge: Hon. Cathy Bissoon\\n ______________\\n\\n Argued May 24, 2018\\n ______________\\n\\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\\n Judges.\\n\\n (Opinion Filed: January 17, 2019)\\n\\n ______________\\n\\n OPINION OF THE COURT\\n ________________\\n\\nDonovan J. Cocas, Esq. [ARGUED]\\nJane M. Datttilo, Esq.\\nLaura S. Irwin, Esq.\\nOffice of the United States Attorney\\n700 Grant Street\\nSuite 4000\\nPittsburgh, PA 15219\\n\\n Attorney for Appellant\\n\\nRenee Pietropaolo, Esq. [ARGUED]\\nLisa B. Freeland, Esq.\\nAkin Adepoju, Esq.\\nOffice of the Federal Public Defender\\n1001 Liberty Avenue\\n1500 Liberty Center\\nPittsburgh, PA 15222\\n\\n Attorneys for Appellee Raymont Wright\\n\\nLawrence S. Lustberg, Esq. [ARGUED]\\nGibbons, P.C.\\nOne Gateway Center\\nNewark, NJ 07102\\n\\n Attorney for Amicus Appellee National Association of\\n Criminal Defense Lawyers\\n\\n\\n\\n\\n 2\\n\\nSHWARTZ, Circuit Judge.\\n\\n The District Court barred a retrial of and dismissed the\\nindictment against Defendant Raymont Wright with prejudice\\nafter two juries failed to reach a verdict. The Court did so\\nrelying on its inherent authority, but without finding that any\\nmisconduct had occurred or that Wright would suffer any\\nprejudice beyond the general anxiety and inconvenience of\\nfacing a retrial. Under such circumstances, the Court lacked\\nthe inherent authority to bar the retrial and dismiss the\\nindictment. Therefore, we will reverse the order dismissing the\\nindictment and remand for further proceedings.\\n\\n I\\n\\n In December 2014, Wright was charged with being a\\nfelon in possession of a firearm, in violation of 18 U.S.C.\\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\\nMay 2016. The jury was unable to reach a verdict. A second\\ntrial was held in March 2017, and that jury was also unable to\\nreach a verdict.\\n\\n During both trials, the jury heard evidence from police\\nofficers about Wright’s actions on July 24, 2014.1 That\\nevening, five Pittsburgh Police detectives were patrolling in\\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\\nwere in the lead car, and Detectives Fallert and Goob were in\\nthe second car. Around 8:30 p.m. (when it was still daylight),\\nFallert and Goob saw a man, later identified as Wright, driving\\n\\n 1\\n The following facts are drawn largely from the\\nevidence presented at the first trial.\\n\\n\\n\\n\\n 3\\n\\na car in the opposite direction well above the 25-mile-per-hour\\nspeed limit. The detectives turned around to follow Wright,\\nand Wright sped up and turned onto a loop-shaped road. The\\ndetectives pursued Wright, who fled at a high speed and ran at\\nleast four stop signs. The lead car lost sight of Wright shortly\\nthereafter and discontinued pursuit.\\n\\n Officers in the lead car then noticed skid marks\\nsuggesting that a car had intended but failed to make a left turn\\nat the end of a street. Officers thereafter came upon Wright’s\\ncar in a parking lot below. The car had gone through a fence,\\nover a hillside, and into the lot. The car hit two unoccupied\\nparked cars, its tires blew out, and its windows were down.\\n\\n Detectives Baker and Henson exited the vehicle at the\\ntop of the hill and remained where Wright’s car broke through\\nthe fence, and Detective Kennedy drove his car down to the\\nparking lot’s entrance. Baker and Henson testified that they\\nsaw Wright search around the rear passenger seat of the car,\\nback out of the vehicle with a black semi-automatic handgun\\nin his right hand, and try to “rack the slide,” which can insert\\nor remove a round from the chamber. App. 118-19. They had\\ntheir weapons drawn and told Wright to drop the gun. At first,\\nWright merely stepped back, but he eventually tossed the gun\\nto the side, backed away, and lied on the ground. Pittsburgh\\npolice officer Elliott and his partner, who heard of the crash on\\nthe radio, were the first to reach Wright, and saw him lying on\\nthe ground with a handgun next to him. Henson stated that\\nwhen he made it down to the parking lot, he heard Wright say\\nto him, “Hey, big guy. You won this time or you won this\\nround, something of that nature. He [Wright] said: You feel\\nme? You won this time,” which Henson understood to mean\\nthat he had just avoided a shootout or that he caught Wright\\n\\n\\n\\n\\n 4\\n\\nafter the pursuit. App. 125. Henson subsequently took custody\\nof the gun and noticed the slide lever was bent, and when he\\nstraightened it, saw the gun was loaded with eight rounds, and\\none in the chamber. 2\\n\\n At the close of the Government’s case, Wright moved\\nfor a directed verdict, arguing that no reasonable juror could\\nfind beyond a reasonable doubt that Wright possessed the\\nfirearm. The District Court denied the motion because “the\\nevidence does thus far demonstrate that a reasonable juror\\ncould most certainly find the Defendant guilty of the charge in\\nthis case.” App. 171. Wright did not present a case.\\n\\n The jury deliberated for approximately five hours and\\nthen reported to the Court that it was deadlocked. After polling\\nthe jurors to confirm they were deadlocked and further\\ndeliberations would not bring them closer to a unanimous\\nverdict, the District Court declared a mistrial.\\n\\n At Wright’s March 2017 retrial, the Government\\npresented substantially the same evidence. The Government\\nalso called Detective Kennedy and Lieutenant Palermo, who\\nwere at the scene after Wright was arrested, as well as experts\\nwho testified regarding the collection of DNA and fingerprint\\nevidence from firearms to respond to Wright’s argument at the\\nfirst trial that investigators chose not to test the gun for forensic\\nevidence in an effort to cover up that they had planted the gun\\nat the scene.\\n\\n\\n 2\\n The parties stipulated Wright had been convicted of a\\nqualifying felony, and an ATF Special Agent testified about\\nthe gun’s interstate nexus.\\n\\n\\n\\n\\n 5\\n\\n At the close of the Government’s case, Wright again\\nmoved for a judgment of acquittal, which the Court denied\\nbecause “there is sufficient evidence in the record to establish\\nbeyond a reasonable doubt that Mr. Wright possessed the\\nfirearm in the case,” App. 650. Wright did not put on a case.\\n\\n The second jury deliberated for approximately three\\nhours and then reported that it was hopelessly deadlocked. The\\nCourt polled the jury to confirm the deadlock and then\\ndismissed the jury. 3\\n\\n After the Government notified the Court that it intended\\nto retry the case, the Court required the parties to brief\\n“whether the Court, through an exercise of its inherent\\nauthority, should prohibit or permit a second re-trial in this\\ncase.” App. 26. After considering the parties’ arguments, the\\nDistrict Court dismissed the indictment with prejudice, holding\\nthat it “ha[d] the inherent authority, under some circumstances,\\nto dismiss an indictment following multiple mistrials.” United\\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\\nunderlying the Double Jeopardy Clause also applied to a\\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\\n(2) other courts had dismissed indictments in similar\\n\\n 3\\n Wright asserted that in the first trial, jurors voted 8-4\\nfor acquittal, and in the second trial, the jury was evenly split.\\nThe Government asserted that in the first trial, jurors voted 7-\\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\\nnot explain how he obtained these numbers, the Government\\nsaid it obtained them by speaking with the jurors.\\n\\n\\n\\n\\n 6\\n\\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\\nexpressly allows the Government to retry a case after a mistrial,\\nnothing in the rule “limits a court’s inherent supervisory\\nauthority to dismiss an indictment in the interests of\\nfundamental fairness,” id. at *4; and (4) if the Court were to\\nadopt the Government’s position that there are no limit to the\\nnumber of times the Government can retry a defendant, it\\nwould be tantamount to a “type of jury shopping” that a court\\nshould not permit, id. at *4. The District Court also considered\\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\\nconcluded that most factors supported dismissal. 4\\n\\n 4\\n The Abbati factors are\\n\\n (1) the number of prior mistrials and the\\n outcome of the juries’ deliberations, so far as is\\n known; (2) the character of prior trials in terms\\n of length, complexity, and similarity of evidence\\n presented; (3) the likelihood of any substantial\\n difference in a subsequent trial, if allowed;\\n (4) the trial court’s own evaluation of the relative\\n strength of each party’s case; and (5) the\\n professional conduct and diligence of respective\\n counsel, particularly of the prosecuting attorney.\\n The court must also give due weight to the\\n prosecutor’s decision to reprosecute, assessing\\n the reasons for that decision, such as the gravity\\n\\n\\n\\n\\n 7\\n\\n The Government appeals.\\n\\n II 5\\n\\n We review the District Court’s order dismissing the\\nindictment based on the Court’s inherent power for abuse of\\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\\n\\n of the criminal charges and the public’s concern\\n in the effective and definitive conclusion of\\n criminal prosecutions. Conversely, the court\\n should accord careful consideration to the status\\n of the individual defendant and the impact of a\\n retrial upon the defendant in terms of untoward\\n hardship and unfairness.\\n\\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\\nat 521-22). For the reasons set forth herein, we would not\\nadopt Abbati, but even if we were to consider the Abbati\\nfactors, we would conclude that they do not support dismissal\\nin this case.\\n 5\\n The District Court had jurisdiction pursuant to 18\\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\\n§ 3731.\\n 6\\n The phrases “inherent power,” “inherent authority,”\\n“supervisory power,” and “supervisory authority” are all used\\nto describe the basis for a court action seeking to maintain the\\nintegrity of the proceedings that is not directly tethered to a\\nspecific rule, statute, or constitutional provision. See, e.g.,\\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\\n43 (1991) (inherent power); Bank of Nova Scotia v. United\\n\\n\\n\\n\\n 8\\n\\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\\nindictment for abuse of discretion); cf. Chambers v. NASCO,\\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\\nsanctions under its inherent power for abuse of discretion);\\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\\n2005) (“A trial court’s remedy for a discovery violation under\\nits supervisory powers is reviewed for abuse of discretion.”).\\nA district court abuses its discretion when it makes an errant\\nconclusion of law, an improper application of law to fact, or a\\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\\n\\n A\\n\\n Federal Rule of Criminal Procedure 31 allows the\\nGovernment to retry a case if the court declares a mistrial after\\na jury announces it is unable to reach a verdict. Specifically,\\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\\non one or more counts, the court may declare a mistrial on\\nthose counts. The government may retry any defendant on any\\ncount on which the jury could not agree.” Fed. R. Crim. P.\\n31(b)(3). The word “may” means that the Government has the\\n\\n\\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(supervisory power); United States v. Payner, 447 U.S. 727,\\n733-36 (1980) (supervisory power); United States v. Nobles,\\n422 U.S. 225, 231 (1975) (inherent power).\\n Even if we accepted the distinctions our dissenting\\ncolleague has drawn between inherent judicial powers,\\nlegislatively granted judicial powers, and supervisory powers,\\neach category must operate within the constitutional\\nframework, including the separation of powers.\\n\\n\\n\\n\\n 9\\n\\ndiscretion to retry a case, and nothing in the rule or its\\ncommentary provides or even suggests a limit on the number\\nof retrials it may conduct. See United States v. Wqas Khan,\\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\\n\\n 7\\n While Rule 31 does not limit the Government’s\\nauthority to retry a case, a handful of district courts have\\ndismissed indictments following a second hung jury, but those\\ndecisions are not persuasive. In Ingram, the district court\\ndismissed the indictment sua sponte (without any initial\\nobjection by the Government) after two mistrials—in which\\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\\njailed during the pendency of the trials, and “[t]he Government\\nha[d] no new proof; it simply want[ed] another chance.” 412\\nF. Supp. at 385. The court concluded that to permit a retrial\\nwould be “to ignore the reasonable doubt standard,” and so\\n“[t]he Court’s intervention [was] required in the interest of\\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\\n(McGowan, J., dissenting)). The Ingram court, however, relied\\nin part on the dissent in De Diego. Cases since Ingram have\\napplied the De Diego majority’s view concerning a court’s\\nlimited authority to dismiss an indictment. See, e.g., United\\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\\nDe Diego and reversing the district court’s dismissal of the\\nindictment where the district court found it would be\\n“unconscionable” to retry to the defendant); United States v.\\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\\nDiego and its dissent and holding a district court does not have\\nauthority to sua sponte dismiss an indictment based on the\\n\\n\\n\\n\\n 10\\n\\ndefendant’s poor health); United States v. Mussehl, 453 F.\\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\\nto dismiss the indictment based on alleged errors at trial, and\\nciting De Diego for the proposition that “[t]he duty [to\\nadminister justice] encompasses the concept of review of the\\nquestion whether the United States Attorney, in making his\\ndecision to prosecute, complied with the law, but does not\\nallow the Court to question a United States Attorney’s\\njudgment decision to prosecute, when lawfully made”).\\n The District Court also relied on Rossoff, where the\\ncourt denied the Government’s motion to dismiss the\\nindictment under Federal Rule of Criminal Procedure 48(a),\\nbut still dismissed the indictment with prejudice. 806 F. Supp.\\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\\nbeen two trials, and the Government sought to dismiss the\\nindictment and refile the charges in a different judicial district.\\nId. The court determined it had authority to dismiss an\\nindictment with prejudice if a retrial was “against the concept\\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\\nSupp. 384), and did so because, among other reasons, the\\ndefendant was in poor health, was under significant strain, and\\na majority of jurors at both trials found him not guilty, id. at\\n203. Rossoff, however, is distinguishable from Wright’s case\\nbecause in Rossoff, the Government sought to dismiss the\\nindictment so that it could refile charges in a different judicial\\ndistrict, which caused the court to question the Government’s\\ngood faith. In Wright’s case, the District Court made no\\nfinding that the Government’s desire to retry Wright was for\\nan improper purpose.\\n In addition, and significantly, neither Ingram nor\\nRossoff addressed the doctrine of separation of powers.\\nRather, each essentially relied on a general concept of fairness\\n\\n\\n\\n\\n 11\\n\\nthe text that empowers a court to prohibit the Government from\\nretrying a case. 8\\n B\\n\\n Apparently aware that Rule 31 did not provide it with a\\nbasis to preclude a retrial in these circumstances, the District\\nCourt concluded that it had the inherent authority to forbid the\\nretrial and dismiss the indictment. The District Court erred.\\n\\n The exercise of inherent authority must satisfy two\\nrequirements: (1) it “must be a reasonable response to the\\n\\n\\nto the defendant in deciding to dismiss an indictment. See\\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\\nIn this Circuit, however, “[t]he judiciary may not impose its\\npersonal and private notions of ‘fairness’ on law enforcement\\nofficials, but does have a limited authority to affect\\nprosecutorial actions when those actions are taken in violation\\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\\n596 (3d Cir. 1992) (citations omitted).\\n 8\\n Rule 31 differs from other Federal Rules of Criminal\\nProcedure because it makes no mention of the court’s\\nauthority. For instance, Rule 48(b) states that a court has\\nauthority to dismiss an indictment “if unnecessary delay occurs\\nin: (1) presenting a charge to the grand jury; (2) filing an\\ninformation against a defendant; or (3) bringing a defendant to\\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\\ngrounds on which a district court could also dismiss an\\nindictment, but each would be triggered by a motion, such as a\\nmotion to dismiss for failure to comply with Rule 16’s\\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\\n16(d)(2)(D), or a motion asserting a defect in the indictment,\\nFed. R. Crim. P. 12(b)(3)(B).\\n\\n\\n\\n\\n 12\\n\\nproblems and needs confronting the court’s fair administration\\nof justice,” and (2) it “cannot be contrary to any express grant\\nof or limitation on the district court’s power contained in a rule\\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\\n(citations and internal quotation marks omitted). We will\\nexamine each of these requirements in turn.\\n\\n 1\\n\\n As to the first Dietz requirement, “[g]uided by\\nconsiderations of justice, and in the exercise of supervisory\\npowers, federal courts may, within limits, formulate procedural\\nrules not specifically required by the Constitution or the\\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(internal quotation marks and citation omitted). Such rules\\nmust be imposed (1) “to implement a remedy for violation of\\nrecognized rights,” (2) “to preserve judicial integrity by\\nensuring that a conviction rests on appropriate considerations\\nvalidly before the jury,” and (3) “as a remedy designed to deter\\nillegal conduct.” Id. (citations omitted). Thus, a court may\\nexercise its inherent authority only when it is necessary to\\naddress improper conduct and ensure respect for the\\nproceedings.\\n\\n Under these principles, a court may dismiss an\\nindictment based upon its inherent authority only if the\\nGovernment engaged in misconduct, the defendant was\\nprejudiced, and no less severe remedy was available to address\\nthe prejudice. See Bank of Nova Scotia v. United States, 487\\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\\n(stating that “[a] court may dismiss an indictment under its\\nsupervisory powers only when the defendant suffers\\nsubstantial prejudice and where no lesser remedial action is\\n\\n\\n\\n\\n 13\\n\\navailable” (citations and internal quotation marks omitted));\\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\\n(observing that “a district court may not, in the management of\\nits docket, exercise its discretion to dismiss an indictment with\\nprejudice, either under Rule 48(b) or under its supervisory\\npower, unless the violation caused prejudice to the defendant\\nor posed a substantial threat thereof” (emphasis omitted));\\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\\n(holding that an indictment may not be dismissed for\\nprosecutorial misconduct absent a showing that the misconduct\\nprejudiced the defendants, and stating that “virtually every\\nother circuit to consider the issue post-Hasting and Nova Scotia\\nhas also held that an indictment may not be dismissed based on\\nprosecutorial misconduct, absent a showing of prejudice to the\\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\\n(7th Cir. 1993) (“A federal judge is not authorized to punish\\nthe misconduct of a prosecutor by letting the defendant walk,\\nunless the misconduct not only violated the defendant’s rights\\nbut also prejudiced his defense . . . .”); United States v. Tucker,\\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\\nexercise its supervisory authority to reverse a conviction or\\ndismiss an indictment absent prejudice to the defendant.”);\\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\\nHasting, and Bank of Nova Scotia form a trilogy admonishing\\nfederal courts to refrain from using the supervisory power to\\nconform executive conduct to judicially preferred norms by\\ndismissing charges, absent cognizable prejudice to a particular\\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\\nCir. 1992) (“Before it may invoke this [supervisory] power [to\\ndismiss an indictment], a court must first find that the\\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\\n1480 (9th Cir. 1994).\\n\\n\\n\\n\\n 14\\n\\n In this case, there has been no misconduct. Indeed, the\\nDistrict Court noted that the Government performed diligently\\nand professionally in both trials, Wright, 2017 WL 1179006,\\nat *4, and found that the evidence was sufficient to prove\\nbeyond a reasonable doubt that Wright possessed the gun. The\\nDistrict Court nonetheless applied its own predictions about\\nwhat another jury may do when presented with the same\\nevidence, emphasized the need for finality, and opined that the\\neffect of prosecution on the defendant precluded a proper\\nprosecution from proceeding. See id. at *5-6. Invoking its own\\nnotions about the unfairness of requiring a defendant to face a\\nretrial where the Government did not obtain a majority of the\\njurors’ votes is an improper exercise of a court’s supervisory\\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\nMoreover, there is no prejudice to a defendant simply because\\nhe faces the anxiety and the normal stress of undergoing a trial.\\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975) (“[A]nxiety is present to some degree in virtually every\\ncase. Something more than the normal anxiety that\\naccompanies a trial is necessary to show a degree of\\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\\nonly real harm alleged is the general unfairness to these\\ndefendants in having to go forward yet again with a lengthy\\ntrial, in their being ‘ground down’ by the several months’ drain\\non their mental, emotional, and financial resources. A lack of\\nsuch fairness, however, does not alone violate due process.”).\\nRather, prejudice sufficient for the District Court to intervene\\nin a proper prosecution based upon its inherent authority occurs\\nonly where the Government engages in actions that place a\\ndefendant at a disadvantage in addressing the charges. That\\nsort of prejudice is absent in this case.\\n\\n\\n\\n\\n 15\\n\\n Unless there is some constitutional basis, such as a due\\nprocess violation, it makes sense to limit a court’s authority to\\nbar retrial to instances of prosecutorial misconduct and\\nprejudice. First, it ensures that a judge’s personal preferences\\nabout a case do not influence whether the case proceeds. See\\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\\n(“The judiciary may not impose its personal and private\\nnotions of ‘fairness’ on law enforcement officials, but does\\nhave a limited authority to affect prosecutorial actions when\\nthose actions are taken in violation of the Constitution.”).\\nSecond, as more fully discussed below, it guarantees that a\\ncourt limits the Executive’s decision to prosecute only where\\nthere is a constitutionally sound reason to do so. 9 This brings\\nus to the second Dietz requirement.\\n\\n\\n 9\\n For these reasons, we find unpersuasive our dissenting\\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\\nobservation that a court has the inherent power to resolve a\\ncase, as authority for allowing a court dismiss an indictment\\nafter successive hung juries. As a general matter, there is no\\ndoubt that a court has the authority to dismiss a case, but it may\\nnot simply end a case because it decides that it should not be\\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\\ntheir progeny make clear, the court must point to evidentiary\\ndeficiency, prejudicial misconduct, or a constitutional basis,\\nsuch as double jeopardy or due process, to justify precluding a\\nprosecution. If a court believed that the evidence was deficient,\\nthe prosecutor engaged in prejudicial misconduct, or a retrial\\nwould violate the constitution, then it has a basis to preclude a\\nretrial. Requiring such reasons for barring a retrial ensures that\\n\\n\\n\\n\\n 16\\n\\n 2\\n\\n The second Dietz requirement reminds a court that the\\nexercise of its powers must be in accordance with the\\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\\nwith the Constitution, a court must be mindful of its role in our\\ntripartite form of government and the doctrine of separation of\\npowers. Separation-of-powers principles limit a court’s\\ninherent authority. “Regardless of whether the supervisory\\npower stems from the federal courts’ inherent power to check\\nintrusions by other branches of government or whether it is a\\nform of specialized federal common law, the separation-of-\\npowers principle imposes significant limits on it,” and\\n“[p]roper regard for judicial integrity does not justify a\\n‘chancellor’s foot veto’ over activities of coequal branches of\\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\\nCir. 1985) (internal quotation marks omitted) (quoting United\\nStates v. Russell, 411 U.S. 423, 435 (1973)).\\n\\n In the criminal context, the Executive Branch has\\n“broad discretion as to whom to prosecute,” and this discretion\\n“rests largely on the recognition that the decision to prosecute\\nis particularly ill-suited to judicial review.” Wayte v. United\\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\\nquotation marks omitted). A court is not equipped to evaluate\\n\\n [s]uch factors as . . . the prosecution’s general\\n deterrence value, the Government’s enforcement\\n priorities, and the case’s relationship to the\\n\\n\\nthe ruling is not based on a court’s own personal sense of\\nwhether a case is worthy of prosecution.\\n\\n\\n\\n\\n 17\\n\\n Government’s overall enforcement plan . . . .\\n Judicial supervision in this area, moreover,\\n entails systemic costs of particular concern.\\n Examining the basis of a prosecution delays the\\n criminal proceeding, threatens to chill law\\n enforcement by subjecting the prosecutor’s\\n motives and decisionmaking to outside inquiry,\\n and may undermine prosecutorial effectiveness\\n by revealing the Government’s enforcement\\n policy. All of these are substantial concerns that\\n make the courts properly hesitant to examine the\\n decision whether to prosecute.\\n\\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\\n(echoing similar sentiments with respect to Rule 48(a)\\ndismissals). Thus, absent constitutional concerns, the decision\\nto try or retry a case is at the discretion of the prosecutor.\\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\\nas superprosecutors, second-guessing the legitimate exercise of\\ncore elements of prosecutorial discretion, but rather as neutral\\narbiters of the law” (citation and internal quotation marks\\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\\n1994) (“[T]he choice to forego permanently a prosecution is\\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\\n676 (“In maintaining order in our own house, we should not\\nneedlessly trample on the interest of the prosecutor and of the\\npublic in securing proper, lasting convictions.”); Isgro, 974\\nF.2d at 1097 (stating that the doctrine of separation of powers\\n“mandates judicial respect for the independence of the\\nprosecutor,” and “[d]ismissal of an indictment with prejudice\\n\\n\\n\\n\\n 18\\n\\nis the most severe sanction possible”). 10 Accordingly,\\nseparation-of-powers principles preclude a court from\\nterminating a prosecution absent misconduct and prejudice to\\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\\n974 F.2d at 1094.\\n\\n In short, a court’s power to preclude a prosecution is\\nlimited by the separation of powers and, specifically, the\\nExecutive’s law-enforcement and prosecutorial prerogative.\\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\\nhere to dismiss an indictment in the absence of misconduct and\\nprejudice and based only on the fact that two juries could not\\nreach a verdict intrudes on the Executive’s domain and thereby\\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\\nat 138; Isgro, 974 F.2d 1091.\\n\\n 10\\n Several state courts have also refused to recognize\\nany inherent authority to dismiss an indictment to prevent a\\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\\n(Fla. Dist. Ct. App. 1980). Other states, however, have\\nrecognized a court’s authority to dismiss an indictment sua\\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\\n712; Witt, 572 S.W.2d at 917. These latter cases are\\nunpersuasive because they give too little weight to the\\nseparation of powers, a crucial constitutional principle in the\\nfederal system.\\n\\n\\n\\n\\n 19\\n\\n Finally, there is no statute or procedural rule that\\npermits a court to bar a retrial in the absence of misconduct and\\nprejudice. First, a court may not dismiss an indictment as a\\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\\n505. Second, a court’s inherent power does not “include the\\npower to develop rules that circumvent or conflict with the\\nFederal Rules of Criminal Procedure.” Carlisle v. United\\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\\nexercise of inherent authority circumvents the absence of\\npower of the district court to dismiss an indictment in Rule\\n31(b). As stated above, courts have inherent authority to\\ndismiss indictments, including, for instance, for prosecutorial\\nmisconduct if the defendant was prejudiced, Bank of Nova\\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\\nnor our Court has extended a court’s inherent authority to allow\\n\\n 11\\n In Chambers, for example, the Supreme Court\\nrecognized a court’s authority to impose silence, respect, and\\ndecorum based on its authority to manage its own affairs. 501\\nU.S. at 43. This authority has been exercised by controlling\\nadmission to the bar and disciplining its members; punishing\\nfor contempt, which penalizes disruption to proceedings and\\ndisobedience to court orders; disallowing fraud on the courts;\\nensuring the proceedings move forward; and curtailing\\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\\ncivil case for failure to prosecute to prevent delays and court\\ncongestion as part of a court’s inherent power to manage its\\nown affairs). Chambers and Link address how a court may\\nmanage its own proceedings, but they do not address how the\\ncourt must also account for issues of separation of powers in\\nthe context of a criminal case.\\n\\n\\n\\n\\n 20\\n\\nthe sua sponte dismissal of an indictment solely to preclude\\nmultiple mistrials following hung juries, see Chambers, 501\\nU.S. at 47; HSBC, 863 F.3d at 136. 12\\n\\n 12\\n Most cases concerning a court’s inherent authority\\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\\n(noting a court’s inherent powers to rescind a jury discharge\\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\\n(recognizing a court’s authority to vacate a judgment upon\\nproof that a fraud was perpetrated on the court, and, in\\nparticular, to assess as a sanction the entire amount of the\\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\\n(authority to dismiss a civil case sua sponte for failure to\\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\\n(1947) (dismissing an action based on the doctrine of forum\\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\\n(citing cases involving the scope of a district court’s inherent\\npower); Eash, 757 F.2d at 561-64 (same).\\n There are other circumstances in which district courts\\nlack the inherent authority to act, and most of those situations\\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\\n433 (holding that a court does not have authority to grant a\\npost-verdict motion for judgment of acquittal, filed one day\\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\\n45-50, 55 (holding that a district court does not have inherent\\nauthority to dismiss an indictment because the Government\\nfailed to disclose to the grand jury substantial exculpatory\\nevidence; “[b]ecause the grand jury is an institution separate\\nfrom the courts, over whose functioning the courts do not\\npreside, we think it clear that, as a general matter at least, no\\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\\nat 129, 135-37 (holding that the district court violated\\nseparation-of-powers principles by sua sponte invoking its\\n\\n\\n\\n\\n 21\\n\\n Thus, the District Court abused its discretion in barring\\na retrial and dismissing the indictment. 13\\n\\n III\\n\\n For the foregoing reasons, we will reverse and remand\\nfor further proceedings.\\n\\n\\n\\n\\nsupervisory power to oversee the government’s entry into and\\nimplementation of a deferred prosecution agreement).\\n 13\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":66,"cells":{"id":{"kind":"number","value":4582985,"string":"4,582,985"},"name":{"kind":"string","value":"Carlyle BRYAN ; Julie Beberman; Charles Francis, Appellants v. UNITED STATES of America; Unknown Officers of the Department of Homeland Security; Bureau of Customs & Border Protection; Customs and Border Protection Officers John Mazur; Jamie Demarais; Obed Torres; William Santiago ; Orlando Baez; Timothy Ogg; Andres Vazquez ; Joel Osorio; Juan Gracia; Gregory Defelice"},"name_abbreviation":{"kind":"string","value":"Carlyle Bryan v. United States"},"decision_date":{"kind":"string","value":"2019-01-18"},"docket_number":{"kind":"string","value":"17-1519"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Krause, Roth, Fisher\", \"parties\": \"\", \"opinions\": [{\"author\": \"ROTH, Circuit Judge\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n ________________\\n\\n No. 17-1519\\n ________________\\n\\n CARLYLE BRYAN; JULIE BEBERMAN;\\n CHARLES FRANCIS,\\n\\n Appellants\\n\\n v.\\n\\nUNITED STATES OF AMERICA; UNKNOWN OFFICERS OF THE DEPARTMENT\\nOF HOMELAND SECURITY; BUREAU OF CUSTOMS & BORDER PROTECTION;\\n CUSTOMS AND BORDER PROTECTION OFFICERS JOHN MAZUR;\\n JAMIE DEMARAIS; OBED TORRES; WILLIAM SANTIAGO;\\n ORLANDO BAEZ; TIMOTHY OGG; ANDRES VAZQUEZ;\\n JOEL OSORIO; JUAN GRACIA; GREGORY DEFELICE\\n ________________\\n\\n Appeal from the District Court of the Virgin Islands\\n (Division of St. Croix)\\n (D.C. Civil Action No. 1-10-cv-00066)\\n District Judge: Honorable Wilma A. Lewis\\n ________________\\n\\n Argued on May 22, 2018\\n\\n Before: KRAUSE, ROTH and FISHER, Circuit Judges\\n\\n (Opinion filed: January 18, 2019)\\n\\n\\nDavid M. Nissman, (Argued)\\nMcChain Nissman Law Group\\n53A Company Street\\nChristiansted, VI 00820\\n\\n Counsel for Appellants\\n\\fSamantha L. Chaifetz (Argued)\\nJoycelyn Hewett\\nChad A. Readler\\nMark B. Stern\\nUnited States Department of Justice\\nAppellate Section\\nRoom 7248\\n950 Pennsylvania Avenue, N.W.\\nWashington, DC 20530\\n\\nJeffrey E. Sandberg\\nUnited States Department of Justice\\nCivil Division\\nRoom 7214\\n950 Pennsylvania Avenue, N.W.\\nWashington, DC 20530\\n\\n Counsel for Appellee\\n\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\nROTH, Circuit Judge\\n\\n In 2008, Carlyle Bryan, Julie Beberman, and Charles Francis (the travelers),\\nresidents of St. Croix in the U.S. Virgin Islands, embarked on a Caribbean cruise aboard\\nthe Adventure of the Seas. Their trip took them to a number of foreign ports before they\\nreturned to the United States. During their trip, U.S. Customs and Border Protection\\n(CBP) officers searched their cabins on suspicion of drug-smuggling activity. Those\\nsearches yielded no contraband and prompted the three travelers to assert Bivens claims1\\nagainst the officers for allegedly violating their Fourth Amendment rights. They also\\nasserted tort claims against the United States government under the Federal Tort Claims\\nAct (FTCA or the Act). The District Court of the Virgin Islands granted summary\\njudgment in favor of the officers and the government.\\n\\n\\n\\n1 Bivens provides for private rights of action against federal officials for certain\\nconstitutional violations. Bivens v. Six Unknown Named Agents of Federal Bureau of\\nNarcotics, 403 U.S. 388 (1971).\\n 2\\n\\f Because we conclude that the officers are entitled to qualified immunity and the\\nUnited States government is shielded from liability under the FTCA’s discretionary\\nfunction exception, we will affirm.\\n\\n I.\\n\\n The Cruise\\n\\n The cruise lasted from August 31 to September 7, 2008. Beberman had booked\\ntwo cabins for the three travelers: one for Bryan and herself, and a second for Francis.\\nThe cruise began in the United States. They sailed from San Juan, Puerto Rico, stopped\\nat several foreign ports, including Antigua, Barbados, St. Lucia, and St. Maarten,\\nproceeded to St. Thomas in the U.S. Virgin Islands, and returned to San Juan.\\n\\n The travelers had to pass through a CBP checkpoint in San Juan before boarding\\nthe ship. Bryan and Beberman went through without incident. Francis’s trip through the\\ncheckpoint was not so smooth. When a CBP officer asked Francis what his occupation\\nwas, he hesitated and then said “oil change.” (Francis worked with automobiles and\\nchanged motor oil.) CBP officers then inspected Francis’s bag. There was a very full\\ncanister of shaving powder in the bag. When a CBP officer opened the canister, the\\npowder dispersed through the room and coated the officer. Bryan laughed. They contend\\nnow that the inspection of their cabins was in retaliation for Bryan’s laughing at the CBP\\nofficer. The officers found nothing unlawful in Francis’s bags. CBP Officer Baez made\\na notation in the Treasury Enforcement Communications System (TECS) database that\\nFrancis had appeared “disoriented and nervous” and that it took him some time to state\\nhis employment, but that the examination of his bag did not uncover anything.2\\n\\n The Creation of “Lookout” Entries by Officer Timothy Ogg (September 5, 2008)\\n\\n CBP Officer Timothy Ogg, stationed in San Juan, was routinely assigned the task\\nof reviewing passenger manifests for the Adventure of the Seas to identify passengers\\nworthy of further scrutiny. Around September 1, he compared the names on the\\npassenger manifest against the names on reports logged onto TECS. Both Bryan’s and\\nFrancis’s names yielded matches; both had TECS entries related to drug smuggling.\\n\\n Officer Ogg found two entries on Bryan. The first, dated May 17, 2000, was\\nauthored by Immigration & Customs Enforcement (ICE) Agent Hillary Hodge. Referring\\nto Bryan, the entry read: “Subject is associate[d] with suspected drug smugglers within\\nthe US Virgin Islands. Subject is also suspected of smuggling narcotics within the Virgin\\nIslands. If encountered, conduct 100% exam . . ..”3 Officer Ogg later testified that he\\n\\n2 JA 8.\\n3 JA 9.\\n 3\\n\\fhad previously worked with Agent Hodge and credited his entry in part because he\\nregarded Hodge as an excellent worker. The second TECS entry, from 2004, referred to\\nthe prior entry, characterized Bryan as a “suspect in USVI drug smuggling,” and\\nencouraged agents to “document [his] co-travelers, employment and reason for travel.”4\\n\\n As for Francis, Officer Ogg uncovered two TECS reports from 2006 identifying\\nFrancis as the “Subject of [a Drug Enforcement Administration] indictment.” The first\\nreport was authored while the Drug Enforcement Administration investigation was going\\non and characterized Francis as a “subject of current interest”; the second was authored\\nafter the investigation had ended and referred to him as a “Previous Suspect.”5 Both\\nreports urged personnel to alert special agents if they encountered Francis.\\n\\n According to Officer Ogg’s subsequent deposition testimony, another factor\\naroused his suspicion: CBP officers had previously made narcotics seizures on the\\nAdventure of the Seas on the same route. A number of islands along the route were\\nknown to be sources of narcotics smuggled into the United States. Officer Ogg\\ncharacterized them as high-risk islands.\\n\\n On September 5, primarily on the strength of the TECS records concerning Bryan\\nand Francis, Officer Ogg created “lookout” entries for Bryan and Francis in the TECS\\ndatabase. A “lookout” is a TECS entry that alerts CBP officers to specific passengers and\\nrecommends certain investigative steps when they are encountered. In the case of Bryan\\nand Francis, the “lookout entries” noted their connection to “drug smuggling” and\\nrecommended, in the standard TECS shorthand (i.e., “100% exam”), that their cabins be\\ninspected before their return to San Juan on September 7. 6\\n\\n Officer Ogg also entered a separate “lookout” for Beberman. Except for the co-\\ntravelers listed, the “lookout” entry for Beberman mirrored Bryan’s. At his deposition,\\nOfficer Ogg gave two reasons for the Beberman “lookout.” First, she was traveling with\\ntwo individuals about whom there were independent TECS entries predicated on drug-\\nsmuggling concerns. Second, as a practical matter, Officer Ogg stated that he had to\\nenter a lookout for Beberman to ensure that Bryan and Francis did not use her to evade\\n\\n\\n\\n\\n4 JA 9-10.\\n5 JA 10.\\n6 Id.\\n\\n\\n 4\\n\\fdetection and inspection by having her submit a single customs declaration form for the\\nthree of them, but in her name only.7\\n\\n The St. Thomas Cabin Searches (September 6, 2008)\\n\\n On the morning of September 6, 2008, after the travelers had returned to United\\nStates waters and had docked in St. Thomas, CBP Officers DeFelice, Demarais, Mazur,\\nSantiago, and Torres (collectively, the St. Thomas Officers) inspected Bryan and\\nBeberman’s cabin, along with Francis’s.\\n\\n The cabin searches each lasted between five and ten minutes.8 The St. Thomas\\nofficers knocked on the cabin doors before opening them. The occupants were asked to\\nget dressed without using the bathroom, and in at least partial view of the officers. They\\nwere then asked to leave their cabins and stand against a wall in the hallway. They\\nwaited in the hallway for between two and five minutes, while officers with a drug-\\nsniffing dog inspected their cabins. Neither cabin search yielded any contraband; the St.\\nThomas Officers created TECS entries to that effect.9\\n\\n II.\\n\\n As a result of the searches, Beberman, Bryan, and Francis filed suit in the District\\nCourt for the Virgin Islands, asserting Fourth Amendment Bivens claims against Officer\\nOgg, who had recommended, but not participated in, the cabin searches and against the\\nSt. Thomas officers, who had executed the cabin searches. The travelers also asserted\\ntort claims against the United States under the FTCA for invasion of privacy, false\\nimprisonment, and intentional infliction of emotional distress.\\n\\n\\n7 Ogg testified at his deposition that passengers traveling together were allowed to submit\\na single customs declaration form without identifying every passenger. Because\\nsecondary inspections were triggered by the names included on declaration forms, Bryan\\nand Francis could have attempted to evade detection by having Beberman submit a form\\nin her name only. Officer Ogg explained that he had entered three separate “lookouts” to\\nguard against that possibility.\\n8 The cabin inspections differed in two respects: The occupants found themselves in\\n\\ndifferent states of undress (i.e., Francis was naked, while Bryan and Beberman were\\npartially clothed) and the occupants were observed to different extents while they dressed\\n(i.e., Bryan and Beberman dressed with their cabin door ajar and the officers outside,\\nwhile Francis dressed in full view of the officers).\\n9 On September 7, when the ship reached San Juan, a different set of CBP officers began\\n\\nto inspect the travelers’ cabins but cut short the searches when they learned of the St.\\nThomas searches. The San Juan searches are not implicated in this appeal. The travelers\\nvoluntarily dismissed their Bivens claims against the San Juan officers.\\n 5\\n\\f At the close of discovery, the officers and the United States moved for summary\\njudgment. The District Court granted their motion on all claims.\\n\\n As for the officers, the District Court reasoned that neither Officer Ogg’s entry of\\n“lookouts” nor the St. Thomas cabin searches violated the travelers’ Fourth Amendment\\nrights. Further, it held that the officers were entitled to qualified immunity because their\\nconduct did not violate clearly established Fourth Amendment rights.\\n\\n As for the United States, the District Court held that the FTCA claims were barred\\nby the Act’s discretionary function exception.\\n\\n We review the District Court’s grant of summary judgment de novo, applying the\\nsame decisional principle.10 The District Court exercised subject matter jurisdiction\\nunder 28 U.S.C. §§ 1331 and 1346(b). We have appellate jurisdiction under 28 U.S.C. §\\n1291.\\n\\n III.\\n\\n The Fourth Amendment protects the public “against unreasonable searches and\\nseizures.”11 Whether a search is reasonable turns on “all of the circumstances\\nsurrounding the search,” including where the search took place. 12\\n\\n The search here took place at the border. The border serves a unique gate-keeping\\nfunction. Our controlling Fourth Amendment precedent is attuned to that reality. The\\nSupreme Court has stressed the border’s role in protecting our territorial sovereignty,\\nalong with the need to curb the inflow of drugs at the border. 13 For those reasons, we\\nextend the government special latitude at the border and strike “the Fourth Amendment\\nbalance between the interests of the Government and the privacy right of the individual”\\nin the government’s favor.14\\n\\n10 Summary judgment should be granted when, “after drawing all reasonable inferences\\nfrom the underlying facts in the light most favorable to the nonmoving party, the court\\nconcludes that there is no genuine issue of material fact to be resolved at trial and the\\nmoving party is entitled to judgment as a matter of law.” Petruzzi’s IGA Supermarkets,\\nInc. v. Darling-Delaware Co., 998 F.2d 1224, 1230 (3d Cir. 1993).\\n11 U.S. Const. amend. IV.\\n12 United States v. Montoya de Hernandez, 473 U.S. 531, 537 (1985).\\n13 See Montoya, 473 U.S. at 538 (highlighting a “longstanding concern for the protection\\n\\nof the integrity of the border. This concern is, if anything, heightened by the veritable\\nnational crisis in law enforcement caused by smuggling of illicit narcotics . . ..”) (citation\\nomitted); see also Bradley v. United States, 299 F.3d 197, 201-02 (3d Cir. 2002).\\n14 Montoya, 473 U.S. at 539-40; see also United States v. Hyde, 37 F.3d 116, 119-20 (3d\\n\\nCir. 1994).\\n 6\\n\\f In view of the government’s interests, we “have long held that routine searches at\\nour nation’s borders are presumed to be reasonable under the Fourth Amendment.” 15\\nIndeed, “[r]outine searches of the persons and effects of entrants are not subject to any\\nrequirement of reasonable suspicion, probable cause, or warrant . . ..”16 In contrast,\\n“nonroutine searches . . . require reasonable suspicion.”17 This approach to border\\nsearches applies with equal force at “the functional equivalent” of the border,18 such as a\\nship’s first port of call in the United States. 19 Under this standard, the search here was a\\nborder search.\\n\\n On September 4, 2008, a day before Officer Ogg entered “lookouts” for the\\ntravelers and two days before the cabin searches, we ruled for the first time on the\\nconstitutional propriety of border searches in the same context presented in this appeal —\\nin remarkable coincidence, searches of cabins aboard the Adventure of the Seas. 20 In\\nUnited States v. Whitted, we acknowledged “the surprising dearth of authority” on\\nwhether a search of a cruise ship cabin at the border is a routine search requiring no\\nsuspicion, or a non-routine search requiring “reasonable suspicion” (i.e., a “particularized\\nand objective basis” to suspect criminal activity).21 We held for the first time that\\nbecause of a passenger’s “high expectation of privacy” and the “level of intrusiveness,” a\\nsearch of a cruise ship cabin at the border is non-routine and requires reasonable\\nsuspicion.22 We also held that unsubstantiated information from TECS can establish\\nreasonable suspicion.23\\n\\n IV.\\n\\n In considering whether a government official is entitled to qualified immunity, a\\ncourt can determine whether a constitutional right was violated or in the alternative,\\nwhether that right was clearly established.24 Following that precedent, we will not opine\\nas to whether there were underlying Fourth Amendment violations involved in the search\\nhere. We will instead determine whether the Whitted standard, that a search of a cabin on\\na cruise ship required reasonable suspicion, was clearly established when Officer Ogg\\nincluded in his entry of “lookouts” in the TECS System that 100 % examination of the\\n\\n15 Bradley, 299 F.3d at 201 (citations omitted).\\n16 Montoya, 473 U.S. at 538 (footnote omitted).\\n17 Bradley, 299 F.3d at 204 n.8 (citation omitted).\\n18 Almeida-Sanchez v. United States, 413 U.S. 266, 272-73 (1973).\\n19 United States v. Smith, 273 F.3d 629, 633 n.8 (5th Cir. 2001) (citation omitted).\\n20 United States v. Whitted, 541 F.3d 480 (3d Cir. 2008).\\n21 Whitted, 541 F.3d at 486, 489.\\n22 Id. at 489.\\n23 Id. at 490.\\n24 Pearson v. Callahan, 555 U.S. 223, 236 (2009).\\n\\n\\n 7\\n\\fthree travelers, i.e., examination of their cabins, was recommended and the next day\\nwhen the St. Thomas officers searched the travelers’ cabins.\\n\\n The doctrine of qualified immunity shields government officials from Bivens\\nclaims and money damages, unless a plaintiff can establish that the official violated a\\nstatutory or constitutional right, and that the right was “clearly established at the time of\\nthe challenged conduct.”25 To be clearly established, a right’s contours must be\\n“sufficiently definite that any reasonable official in the defendant’s shoes would have\\nunderstood that he was violating it” and that “existing precedent . . . placed the statutory\\nor constitutional question confronted by the official beyond debate.” 26\\n\\n Further, as the Supreme Court recently reiterated, “clearly established law should\\nnot be defined at a high level of generality” but must instead “be particularized to the\\nfacts of the case.”27 The doctrine is designed to “give[] government officials breathing\\nroom to make reasonable but mistaken judgments by protect[ing] all but the plainly\\nincompetent or those who knowingly violate the law.”28\\n\\n Supreme Court discussion of searches has emphasized the threats posed at borders\\nand the government’s compelling interests in searches there. 29 Because the government’s\\ninterest in preventing the entry of unwarranted persons and effects is at its zenith at the\\nborder,30 Congress “has granted the Executive plenary authority to conduct routine\\nsearches and seizures at the border, without probable cause or a warrant . . ..”31 Until\\nSeptember 4, 2008, there had been no ruling in the Third Circuit as to what constituted a\\n“routine search.” As for Officer Ogg, he was located in San Juan, Puerto Rico, in the\\nFirst Circuit. There had not been any such ruling in the First Circuit, and the First Circuit\\ncourts would not be bound by Whitted, a Third Circuit case.\\n\\n When such a ruling is made, a ruling which affects the procedures used in border\\nsearches, it is beyond belief that within two days the government could determine what\\nwas “reasonable suspicion” and what new policy was required to conform to the ruling,\\nmuch less communicate that new policy to the CBP officers. We can only conclude that\\nas of September 5, 2008, it was not clearly established in either the Third Circuit or the\\nFirst Circuit that a search of a cruise ship cabin at the border had to be supported by\\n\\n25 Ashcroft v. al-Kidd, 563 U.S. 731, 735 (2011) (citing Harlow v. Fitzgerald, 457 U.S.\\n800, 818 (1982)).\\n26 Plumhoff v. Rickard, 134 S. Ct. 2012, 2023 (2014) (quoting Ashcroft, 563 U.S. at 741).\\n27 White v. Pauly, 137 S. Ct. 548, 552 (2017) (per curiam) (citation omitted); see also\\n\\nL.R. v. Sch. Dist. of Phila., 836 F.3d 235, 248 (3d Cir. 2016).\\n28 City & Cty. of S.F. v. Sheehan, 135 S. Ct. 1765, 1774 (2015) (citation omitted).\\n29 See, e.g., Montoya, 473 U.S. at 539-40.\\n30 United States v. Flores-Montano, 541 U.S. 149, 152-53 (2004).\\n31 Id. at 153.\\n\\n\\n 8\\n\\freasonable suspicion. Accordingly, under the circumstances that Officer Ogg confronted,\\nhe did not violate clearly established law by entering lookouts for the three passengers the\\nday after we issued our decision in Whitted. He is entitled to qualified immunity.\\n\\n We conclude that the same situation applies to the St. Thomas officers. On\\nSeptember 6, the Whitted standard was no more clearly established than it had been the\\nday before. Moreover, if the St. Thomas officers had been aware of Whitted, they would\\nhave known that Whitted held that unsubstantiated information from TECS can establish\\nreasonable suspicion.32\\n\\n For these reasons, we conclude that the Whitted standard was not clearly\\nestablished in the Third Circuit, or the First Circuit, on September 5 or 6. Within one or\\ntwo days, neither Officer Ogg nor the St. Thomas officers could reasonably be expected\\nto have learned of this development in our Fourth Amendment jurisprudence. At that\\ntime, it would not have been beyond debate that, absent reasonable suspicion, the Fourth\\nAmendment prohibited the search of the travelers’ cabins. For purposes of qualified\\nimmunity, a legal principle does not become “clearly established” the day we announce a\\ndecision, or even one or two days later.\\n\\n This holding is informed by the overarching aim of the qualified immunity\\ndoctrine to insulate from civil liability “all but the plainly incompetent or those who\\nknowingly violate the law,”33 and the need to ensure that the relevant legal principle is\\nframed with particularity34 and settled “beyond debate.”35 We are, however, deciding\\nonly this case. For that reason, we decline to draw a bright line demarcating when a legal\\nprinciple becomes “clearly established.” We leave that exercise for another day.\\n\\n Finally, the tort claims against the United States also fail because of the FTCA’s\\ndiscretionary function exception. The FTCA provides a limited waiver of sovereign\\nimmunity in certain tort actions against the United States for money damages.36 That\\nwaiver does not extend to various types of government conduct enumerated in 28 U.S.C.\\n\\n\\n\\n\\n32 541 F.3d at 490.\\n33 White, 137 S. Ct. at 552.\\n34 Id.\\n35 Plumhoff, 134 S. Ct. at 2023.\\n36 28 U.S.C. § 1346(b)(1).\\n\\n\\n 9\\n\\f§ 2680, including “the exercise or performance or the failure to exercise or perform a\\ndiscretionary function or duty . . . whether or not the discretion involved be abused.”37\\n\\n The travelers do not dispute that Officer Ogg’s entry of “lookouts” and the\\nsearches that followed were discretionary acts under the “discretionary function”\\nexception.38 Rather, they argue that the United States is not shielded from liability\\nbecause the officers in this case, though exercising their discretion, violated “clearly\\nestablished . . . constitutional rights of which a reasonable person would have known.” 39\\n\\n Because, for the reasons set out above, the CBP officers did not violate clearly\\nestablished constitutional rights, the FTCA claims also fail.\\n\\n V.\\n\\n For the reasons stated above, we will affirm the judgment of the District Court.\\n\\n\\n\\n\\n37 28 U.S.C. § 2680(a). Discretionary acts and omissions “involv[e] an element of\\njudgment or choice.” Conduct is non-discretionary only if a “federal statute, regulation,\\nor policy specifically prescribes a course of action for an employee to follow” and the\\ngovernment “employee has no rightful option but to adhere to the directive.” United\\nStates v. Gaubert, 499 U.S. 315, 322 (1991) (quoting Berkovitz ex rel. Berkovitz v. United\\nStates, 486 U.S. 531, 536 (1988)).\\n38 Br. at 63-64.\\n39 Harlow, 457 U.S. at 818.\\n\\n\\n 10\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360238/\", \"author_raw\": \"ROTH, Circuit Judge\"}]}"},"judge1":{"kind":"string","value":"KRAUSE"},"judge2":{"kind":"string","value":"ROTH"},"judge3":{"kind":"string","value":"FISHER"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4582985/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Carlyle BRYAN ; Julie Beberman; Charles Francis, Appellants v. UNITED STATES of America; Unknown Officers of the Department of Homeland Security; Bureau of Customs & Border Protection; Customs and Border Protection Officers John Mazur; Jamie Demarais; Obed Torres; William Santiago ; Orlando Baez; Timothy Ogg; Andres Vazquez ; Joel Osorio; Juan Gracia; Gregory Defelice\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-18\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n ________________\n\n No. 17-1519\n ________________\n\n CARLYLE BRYAN; JULIE BEBERMAN;\n CHARLES FRANCIS,\n\n Appellants\n\n v.\n\nUNITED STATES OF AMERICA; UNKNOWN OFFICERS OF THE DEPARTMENT\nOF HOMELAND SECURITY; BUREAU OF CUSTOMS & BORDER PROTECTION;\n CUSTOMS AND BORDER PROTECTION OFFICERS JOHN MAZUR;\n JAMIE DEMARAIS; OBED TORRES; WILLIAM SANTIAGO;\n ORLANDO BAEZ; TIMOTHY OGG; ANDRES VAZQUEZ;\n JOEL OSORIO; JUAN GRACIA; GREGORY DEFELICE\n ________________\n\n Appeal from the District Court of the Virgin Islands\n (Division of St. Croix)\n (D.C. Civil Action No. 1-10-cv-00066)\n District Judge: Honorable Wilma A. Lewis\n ________________\n\n Argued on May 22, 2018\n\n Before: KRAUSE, ROTH and FISHER, Circuit Judges\n\n (Opinion filed: January 18, 2019)\n\n\nDavid M. Nissman, (Argued)\nMcChain Nissman Law Group\n53A Company Street\nChristiansted, VI 00820\n\n Counsel for Appellants\n\fSamantha L. Chaifetz (Argued)\nJoycelyn Hewett\nChad A. Readler\nMark B. Stern\nUnited States Department of Justice\nAppellate Section\nRoom 7248\n950 Pennsylvania Avenue, N.W.\nWashington, DC 20530\n\nJeffrey E. Sandberg\nUnited States Department of Justice\nCivil Division\nRoom 7214\n950 Pennsylvania Avenue, N.W.\nWashington, DC 20530\n\n Counsel for Appellee\n\n\n ________________\n\n OPINION\n ________________\n\nROTH, Circuit Judge\n\n In 2008, Carlyle Bryan, Julie Beberman, and Charles Francis (the travelers),\nresidents of St. Croix in the U.S. Virgin Islands, embarked on a Caribbean cruise aboard\nthe Adventure of the Seas. Their trip took them to a number of foreign ports before they\nreturned to the United States. During their trip, U.S. Customs and Border Protection\n(CBP) officers searched their cabins on suspicion of drug-smuggling activity. Those\nsearches yielded no contraband and prompted the three travelers to assert Bivens claims1\nagainst the officers for allegedly violating their Fourth Amendment rights. They also\nasserted tort claims against the United States government under the Federal Tort Claims\nAct (FTCA or the Act). The District Court of the Virgin Islands granted summary\njudgment in favor of the officers and the government.\n\n\n\n1 Bivens provides for private rights of action against federal officials for certain\nconstitutional violations. Bivens v. Six Unknown Named Agents of Federal Bureau of\nNarcotics, 403 U.S. 388 (1971).\n 2\n\f Because we conclude that the officers are entitled to qualified immunity and the\nUnited States government is shielded from liability under the FTCA’s discretionary\nfunction exception, we will affirm.\n\n I.\n\n The Cruise\n\n The cruise lasted from August 31 to September 7, 2008. Beberman had booked\ntwo cabins for the three travelers: one for Bryan and herself, and a second for Francis.\nThe cruise began in the United States. They sailed from San Juan, Puerto Rico, stopped\nat several foreign ports, including Antigua, Barbados, St. Lucia, and St. Maarten,\nproceeded to St. Thomas in the U.S. Virgin Islands, and returned to San Juan.\n\n The travelers had to pass through a CBP checkpoint in San Juan before boarding\nthe ship. Bryan and Beberman went through without incident. Francis’s trip through the\ncheckpoint was not so smooth. When a CBP officer asked Francis what his occupation\nwas, he hesitated and then said “oil change.” (Francis worked with automobiles and\nchanged motor oil.) CBP officers then inspected Francis’s bag. There was a very full\ncanister of shaving powder in the bag. When a CBP officer opened the canister, the\npowder dispersed through the room and coated the officer. Bryan laughed. They contend\nnow that the inspection of their cabins was in retaliation for Bryan’s laughing at the CBP\nofficer. The officers found nothing unlawful in Francis’s bags. CBP Officer Baez made\na notation in the Treasury Enforcement Communications System (TECS) database that\nFrancis had appeared “disoriented and nervous” and that it took him some time to state\nhis employment, but that the examination of his bag did not uncover anything.2\n\n The Creation of “Lookout” Entries by Officer Timothy Ogg (September 5, 2008)\n\n CBP Officer Timothy Ogg, stationed in San Juan, was routinely assigned the task\nof reviewing passenger manifests for the Adventure of the Seas to identify passengers\nworthy of further scrutiny. Around September 1, he compared the names on the\npassenger manifest against the names on reports logged onto TECS. Both Bryan’s and\nFrancis’s names yielded matches; both had TECS entries related to drug smuggling.\n\n Officer Ogg found two entries on Bryan. The first, dated May 17, 2000, was\nauthored by Immigration & Customs Enforcement (ICE) Agent Hillary Hodge. Referring\nto Bryan, the entry read: “Subject is associate[d] with suspected drug smugglers within\nthe US Virgin Islands. Subject is also suspected of smuggling narcotics within the Virgin\nIslands. If encountered, conduct 100% exam . . ..”3 Officer Ogg later testified that he\n\n2 JA 8.\n3 JA 9.\n 3\n\fhad previously worked with Agent Hodge and credited his entry in part because he\nregarded Hodge as an excellent worker. The second TECS entry, from 2004, referred to\nthe prior entry, characterized Bryan as a “suspect in USVI drug smuggling,” and\nencouraged agents to “document [his] co-travelers, employment and reason for travel.”4\n\n As for Francis, Officer Ogg uncovered two TECS reports from 2006 identifying\nFrancis as the “Subject of [a Drug Enforcement Administration] indictment.” The first\nreport was authored while the Drug Enforcement Administration investigation was going\non and characterized Francis as a “subject of current interest”; the second was authored\nafter the investigation had ended and referred to him as a “Previous Suspect.”5 Both\nreports urged personnel to alert special agents if they encountered Francis.\n\n According to Officer Ogg’s subsequent deposition testimony, another factor\naroused his suspicion: CBP officers had previously made narcotics seizures on the\nAdventure of the Seas on the same route. A number of islands along the route were\nknown to be sources of narcotics smuggled into the United States. Officer Ogg\ncharacterized them as high-risk islands.\n\n On September 5, primarily on the strength of the TECS records concerning Bryan\nand Francis, Officer Ogg created “lookout” entries for Bryan and Francis in the TECS\ndatabase. A “lookout” is a TECS entry that alerts CBP officers to specific passengers and\nrecommends certain investigative steps when they are encountered. In the case of Bryan\nand Francis, the “lookout entries” noted their connection to “drug smuggling” and\nrecommended, in the standard TECS shorthand (i.e., “100% exam”), that their cabins be\ninspected before their return to San Juan on September 7. 6\n\n Officer Ogg also entered a separate “lookout” for Beberman. Except for the co-\ntravelers listed, the “lookout” entry for Beberman mirrored Bryan’s. At his deposition,\nOfficer Ogg gave two reasons for the Beberman “lookout.” First, she was traveling with\ntwo individuals about whom there were independent TECS entries predicated on drug-\nsmuggling concerns. Second, as a practical matter, Officer Ogg stated that he had to\nenter a lookout for Beberman to ensure that Bryan and Francis did not use her to evade\n\n\n\n\n4 JA 9-10.\n5 JA 10.\n6 Id.\n\n\n 4\n\fdetection and inspection by having her submit a single customs declaration form for the\nthree of them, but in her name only.7\n\n The St. Thomas Cabin Searches (September 6, 2008)\n\n On the morning of September 6, 2008, after the travelers had returned to United\nStates waters and had docked in St. Thomas, CBP Officers DeFelice, Demarais, Mazur,\nSantiago, and Torres (collectively, the St. Thomas Officers) inspected Bryan and\nBeberman’s cabin, along with Francis’s.\n\n The cabin searches each lasted between five and ten minutes.8 The St. Thomas\nofficers knocked on the cabin doors before opening them. The occupants were asked to\nget dressed without using the bathroom, and in at least partial view of the officers. They\nwere then asked to leave their cabins and stand against a wall in the hallway. They\nwaited in the hallway for between two and five minutes, while officers with a drug-\nsniffing dog inspected their cabins. Neither cabin search yielded any contraband; the St.\nThomas Officers created TECS entries to that effect.9\n\n II.\n\n As a result of the searches, Beberman, Bryan, and Francis filed suit in the District\nCourt for the Virgin Islands, asserting Fourth Amendment Bivens claims against Officer\nOgg, who had recommended, but not participated in, the cabin searches and against the\nSt. Thomas officers, who had executed the cabin searches. The travelers also asserted\ntort claims against the United States under the FTCA for invasion of privacy, false\nimprisonment, and intentional infliction of emotional distress.\n\n\n7 Ogg testified at his deposition that passengers traveling together were allowed to submit\na single customs declaration form without identifying every passenger. Because\nsecondary inspections were triggered by the names included on declaration forms, Bryan\nand Francis could have attempted to evade detection by having Beberman submit a form\nin her name only. Officer Ogg explained that he had entered three separate “lookouts” to\nguard against that possibility.\n8 The cabin inspections differed in two respects: The occupants found themselves in\n\ndifferent states of undress (i.e., Francis was naked, while Bryan and Beberman were\npartially clothed) and the occupants were observed to different extents while they dressed\n(i.e., Bryan and Beberman dressed with their cabin door ajar and the officers outside,\nwhile Francis dressed in full view of the officers).\n9 On September 7, when the ship reached San Juan, a different set of CBP officers began\n\nto inspect the travelers’ cabins but cut short the searches when they learned of the St.\nThomas searches. The San Juan searches are not implicated in this appeal. The travelers\nvoluntarily dismissed their Bivens claims against the San Juan officers.\n 5\n\f At the close of discovery, the officers and the United States moved for summary\njudgment. The District Court granted their motion on all claims.\n\n As for the officers, the District Court reasoned that neither Officer Ogg’s entry of\n“lookouts” nor the St. Thomas cabin searches violated the travelers’ Fourth Amendment\nrights. Further, it held that the officers were entitled to qualified immunity because their\nconduct did not violate clearly established Fourth Amendment rights.\n\n As for the United States, the District Court held that the FTCA claims were barred\nby the Act’s discretionary function exception.\n\n We review the District Court’s grant of summary judgment de novo, applying the\nsame decisional principle.10 The District Court exercised subject matter jurisdiction\nunder 28 U.S.C. §§ 1331 and 1346(b). We have appellate jurisdiction under 28 U.S.C. §\n1291.\n\n III.\n\n The Fourth Amendment protects the public “against unreasonable searches and\nseizures.”11 Whether a search is reasonable turns on “all of the circumstances\nsurrounding the search,” including where the search took place. 12\n\n The search here took place at the border. The border serves a unique gate-keeping\nfunction. Our controlling Fourth Amendment precedent is attuned to that reality. The\nSupreme Court has stressed the border’s role in protecting our territorial sovereignty,\nalong with the need to curb the inflow of drugs at the border. 13 For those reasons, we\nextend the government special latitude at the border and strike “the Fourth Amendment\nbalance between the interests of the Government and the privacy right of the individual”\nin the government’s favor.14\n\n10 Summary judgment should be granted when, “after drawing all reasonable inferences\nfrom the underlying facts in the light most favorable to the nonmoving party, the court\nconcludes that there is no genuine issue of material fact to be resolved at trial and the\nmoving party is entitled to judgment as a matter of law.” Petruzzi’s IGA Supermarkets,\nInc. v. Darling-Delaware Co., 998 F.2d 1224, 1230 (3d Cir. 1993).\n11 U.S. Const. amend. IV.\n12 United States v. Montoya de Hernandez, 473 U.S. 531, 537 (1985).\n13 See Montoya, 473 U.S. at 538 (highlighting a “longstanding concern for the protection\n\nof the integrity of the border. This concern is, if anything, heightened by the veritable\nnational crisis in law enforcement caused by smuggling of illicit narcotics . . ..”) (citation\nomitted); see also Bradley v. United States, 299 F.3d 197, 201-02 (3d Cir. 2002).\n14 Montoya, 473 U.S. at 539-40; see also United States v. Hyde, 37 F.3d 116, 119-20 (3d\n\nCir. 1994).\n 6\n\f In view of the government’s interests, we “have long held that routine searches at\nour nation’s borders are presumed to be reasonable under the Fourth Amendment.” 15\nIndeed, “[r]outine searches of the persons and effects of entrants are not subject to any\nrequirement of reasonable suspicion, probable cause, or warrant . . ..”16 In contrast,\n“nonroutine searches . . . require reasonable suspicion.”17 This approach to border\nsearches applies with equal force at “the functional equivalent” of the border,18 such as a\nship’s first port of call in the United States. 19 Under this standard, the search here was a\nborder search.\n\n On September 4, 2008, a day before Officer Ogg entered “lookouts” for the\ntravelers and two days before the cabin searches, we ruled for the first time on the\nconstitutional propriety of border searches in the same context presented in this appeal —\nin remarkable coincidence, searches of cabins aboard the Adventure of the Seas. 20 In\nUnited States v. Whitted, we acknowledged “the surprising dearth of authority” on\nwhether a search of a cruise ship cabin at the border is a routine search requiring no\nsuspicion, or a non-routine search requiring “reasonable suspicion” (i.e., a “particularized\nand objective basis” to suspect criminal activity).21 We held for the first time that\nbecause of a passenger’s “high expectation of privacy” and the “level of intrusiveness,” a\nsearch of a cruise ship cabin at the border is non-routine and requires reasonable\nsuspicion.22 We also held that unsubstantiated information from TECS can establish\nreasonable suspicion.23\n\n IV.\n\n In considering whether a government official is entitled to qualified immunity, a\ncourt can determine whether a constitutional right was violated or in the alternative,\nwhether that right was clearly established.24 Following that precedent, we will not opine\nas to whether there were underlying Fourth Amendment violations involved in the search\nhere. We will instead determine whether the Whitted standard, that a search of a cabin on\na cruise ship required reasonable suspicion, was clearly established when Officer Ogg\nincluded in his entry of “lookouts” in the TECS System that 100 % examination of the\n\n15 Bradley, 299 F.3d at 201 (citations omitted).\n16 Montoya, 473 U.S. at 538 (footnote omitted).\n17 Bradley, 299 F.3d at 204 n.8 (citation omitted).\n18 Almeida-Sanchez v. United States, 413 U.S. 266, 272-73 (1973).\n19 United States v. Smith, 273 F.3d 629, 633 n.8 (5th Cir. 2001) (citation omitted).\n20 United States v. Whitted, 541 F.3d 480 (3d Cir. 2008).\n21 Whitted, 541 F.3d at 486, 489.\n22 Id. at 489.\n23 Id. at 490.\n24 Pearson v. Callahan, 555 U.S. 223, 236 (2009).\n\n\n 7\n\fthree travelers, i.e., examination of their cabins, was recommended and the next day\nwhen the St. Thomas officers searched the travelers’ cabins.\n\n The doctrine of qualified immunity shields government officials from Bivens\nclaims and money damages, unless a plaintiff can establish that the official violated a\nstatutory or constitutional right, and that the right was “clearly established at the time of\nthe challenged conduct.”25 To be clearly established, a right’s contours must be\n“sufficiently definite that any reasonable official in the defendant’s shoes would have\nunderstood that he was violating it” and that “existing precedent . . . placed the statutory\nor constitutional question confronted by the official beyond debate.” 26\n\n Further, as the Supreme Court recently reiterated, “clearly established law should\nnot be defined at a high level of generality” but must instead “be particularized to the\nfacts of the case.”27 The doctrine is designed to “give[] government officials breathing\nroom to make reasonable but mistaken judgments by protect[ing] all but the plainly\nincompetent or those who knowingly violate the law.”28\n\n Supreme Court discussion of searches has emphasized the threats posed at borders\nand the government’s compelling interests in searches there. 29 Because the government’s\ninterest in preventing the entry of unwarranted persons and effects is at its zenith at the\nborder,30 Congress “has granted the Executive plenary authority to conduct routine\nsearches and seizures at the border, without probable cause or a warrant . . ..”31 Until\nSeptember 4, 2008, there had been no ruling in the Third Circuit as to what constituted a\n“routine search.” As for Officer Ogg, he was located in San Juan, Puerto Rico, in the\nFirst Circuit. There had not been any such ruling in the First Circuit, and the First Circuit\ncourts would not be bound by Whitted, a Third Circuit case.\n\n When such a ruling is made, a ruling which affects the procedures used in border\nsearches, it is beyond belief that within two days the government could determine what\nwas “reasonable suspicion” and what new policy was required to conform to the ruling,\nmuch less communicate that new policy to the CBP officers. We can only conclude that\nas of September 5, 2008, it was not clearly established in either the Third Circuit or the\nFirst Circuit that a search of a cruise ship cabin at the border had to be supported by\n\n25 Ashcroft v. al-Kidd, 563 U.S. 731, 735 (2011) (citing Harlow v. Fitzgerald, 457 U.S.\n800, 818 (1982)).\n26 Plumhoff v. Rickard, 134 S. Ct. 2012, 2023 (2014) (quoting Ashcroft, 563 U.S. at 741).\n27 White v. Pauly, 137 S. Ct. 548, 552 (2017) (per curiam) (citation omitted); see also\n\nL.R. v. Sch. Dist. of Phila., 836 F.3d 235, 248 (3d Cir. 2016).\n28 City & Cty. of S.F. v. Sheehan, 135 S. Ct. 1765, 1774 (2015) (citation omitted).\n29 See, e.g., Montoya, 473 U.S. at 539-40.\n30 United States v. Flores-Montano, 541 U.S. 149, 152-53 (2004).\n31 Id. at 153.\n\n\n 8\n\freasonable suspicion. Accordingly, under the circumstances that Officer Ogg confronted,\nhe did not violate clearly established law by entering lookouts for the three passengers the\nday after we issued our decision in Whitted. He is entitled to qualified immunity.\n\n We conclude that the same situation applies to the St. Thomas officers. On\nSeptember 6, the Whitted standard was no more clearly established than it had been the\nday before. Moreover, if the St. Thomas officers had been aware of Whitted, they would\nhave known that Whitted held that unsubstantiated information from TECS can establish\nreasonable suspicion.32\n\n For these reasons, we conclude that the Whitted standard was not clearly\nestablished in the Third Circuit, or the First Circuit, on September 5 or 6. Within one or\ntwo days, neither Officer Ogg nor the St. Thomas officers could reasonably be expected\nto have learned of this development in our Fourth Amendment jurisprudence. At that\ntime, it would not have been beyond debate that, absent reasonable suspicion, the Fourth\nAmendment prohibited the search of the travelers’ cabins. For purposes of qualified\nimmunity, a legal principle does not become “clearly established” the day we announce a\ndecision, or even one or two days later.\n\n This holding is informed by the overarching aim of the qualified immunity\ndoctrine to insulate from civil liability “all but the plainly incompetent or those who\nknowingly violate the law,”33 and the need to ensure that the relevant legal principle is\nframed with particularity34 and settled “beyond debate.”35 We are, however, deciding\nonly this case. For that reason, we decline to draw a bright line demarcating when a legal\nprinciple becomes “clearly established.” We leave that exercise for another day.\n\n Finally, the tort claims against the United States also fail because of the FTCA’s\ndiscretionary function exception. The FTCA provides a limited waiver of sovereign\nimmunity in certain tort actions against the United States for money damages.36 That\nwaiver does not extend to various types of government conduct enumerated in 28 U.S.C.\n\n\n\n\n32 541 F.3d at 490.\n33 White, 137 S. Ct. at 552.\n34 Id.\n35 Plumhoff, 134 S. Ct. at 2023.\n36 28 U.S.C. § 1346(b)(1).\n\n\n 9\n\f§ 2680, including “the exercise or performance or the failure to exercise or perform a\ndiscretionary function or duty . . . whether or not the discretion involved be abused.”37\n\n The travelers do not dispute that Officer Ogg’s entry of “lookouts” and the\nsearches that followed were discretionary acts under the “discretionary function”\nexception.38 Rather, they argue that the United States is not shielded from liability\nbecause the officers in this case, though exercising their discretion, violated “clearly\nestablished . . . constitutional rights of which a reasonable person would have known.” 39\n\n Because, for the reasons set out above, the CBP officers did not violate clearly\nestablished constitutional rights, the FTCA claims also fail.\n\n V.\n\n For the reasons stated above, we will affirm the judgment of the District Court.\n\n\n\n\n37 28 U.S.C. § 2680(a). Discretionary acts and omissions “involv[e] an element of\njudgment or choice.” Conduct is non-discretionary only if a “federal statute, regulation,\nor policy specifically prescribes a course of action for an employee to follow” and the\ngovernment “employee has no rightful option but to adhere to the directive.” United\nStates v. Gaubert, 499 U.S. 315, 322 (1991) (quoting Berkovitz ex rel. Berkovitz v. United\nStates, 486 U.S. 531, 536 (1988)).\n38 Br. at 63-64.\n39 Harlow, 457 U.S. at 818.\n\n\n 10\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Carlyle BRYAN ; Julie Beberman; Charles Francis, Appellants v. UNITED STATES of America; Unknown Officers of the Department of Homeland Security; Bureau of Customs & Border Protection; Customs and Border Protection Officers John Mazur; Jamie Demarais; Obed Torres; William Santiago ; Orlando Baez; Timothy Ogg; Andres Vazquez ; Joel Osorio; Juan Gracia; Gregory Defelice\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-18\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n ________________\\n\\n No. 17-1519\\n ________________\\n\\n CARLYLE BRYAN; JULIE BEBERMAN;\\n CHARLES FRANCIS,\\n\\n Appellants\\n\\n v.\\n\\nUNITED STATES OF AMERICA; UNKNOWN OFFICERS OF THE DEPARTMENT\\nOF HOMELAND SECURITY; BUREAU OF CUSTOMS & BORDER PROTECTION;\\n CUSTOMS AND BORDER PROTECTION OFFICERS JOHN MAZUR;\\n JAMIE DEMARAIS; OBED TORRES; WILLIAM SANTIAGO;\\n ORLANDO BAEZ; TIMOTHY OGG; ANDRES VAZQUEZ;\\n JOEL OSORIO; JUAN GRACIA; GREGORY DEFELICE\\n ________________\\n\\n Appeal from the District Court of the Virgin Islands\\n (Division of St. Croix)\\n (D.C. Civil Action No. 1-10-cv-00066)\\n District Judge: Honorable Wilma A. Lewis\\n ________________\\n\\n Argued on May 22, 2018\\n\\n Before: KRAUSE, ROTH and FISHER, Circuit Judges\\n\\n (Opinion filed: January 18, 2019)\\n\\n\\nDavid M. Nissman, (Argued)\\nMcChain Nissman Law Group\\n53A Company Street\\nChristiansted, VI 00820\\n\\n Counsel for Appellants\\n\\fSamantha L. Chaifetz (Argued)\\nJoycelyn Hewett\\nChad A. Readler\\nMark B. Stern\\nUnited States Department of Justice\\nAppellate Section\\nRoom 7248\\n950 Pennsylvania Avenue, N.W.\\nWashington, DC 20530\\n\\nJeffrey E. Sandberg\\nUnited States Department of Justice\\nCivil Division\\nRoom 7214\\n950 Pennsylvania Avenue, N.W.\\nWashington, DC 20530\\n\\n Counsel for Appellee\\n\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\nROTH, Circuit Judge\\n\\n In 2008, Carlyle Bryan, Julie Beberman, and Charles Francis (the travelers),\\nresidents of St. Croix in the U.S. Virgin Islands, embarked on a Caribbean cruise aboard\\nthe Adventure of the Seas. Their trip took them to a number of foreign ports before they\\nreturned to the United States. During their trip, U.S. Customs and Border Protection\\n(CBP) officers searched their cabins on suspicion of drug-smuggling activity. Those\\nsearches yielded no contraband and prompted the three travelers to assert Bivens claims1\\nagainst the officers for allegedly violating their Fourth Amendment rights. They also\\nasserted tort claims against the United States government under the Federal Tort Claims\\nAct (FTCA or the Act). The District Court of the Virgin Islands granted summary\\njudgment in favor of the officers and the government.\\n\\n\\n\\n1 Bivens provides for private rights of action against federal officials for certain\\nconstitutional violations. Bivens v. Six Unknown Named Agents of Federal Bureau of\\nNarcotics, 403 U.S. 388 (1971).\\n 2\\n\\f Because we conclude that the officers are entitled to qualified immunity and the\\nUnited States government is shielded from liability under the FTCA’s discretionary\\nfunction exception, we will affirm.\\n\\n I.\\n\\n The Cruise\\n\\n The cruise lasted from August 31 to September 7, 2008. Beberman had booked\\ntwo cabins for the three travelers: one for Bryan and herself, and a second for Francis.\\nThe cruise began in the United States. They sailed from San Juan, Puerto Rico, stopped\\nat several foreign ports, including Antigua, Barbados, St. Lucia, and St. Maarten,\\nproceeded to St. Thomas in the U.S. Virgin Islands, and returned to San Juan.\\n\\n The travelers had to pass through a CBP checkpoint in San Juan before boarding\\nthe ship. Bryan and Beberman went through without incident. Francis’s trip through the\\ncheckpoint was not so smooth. When a CBP officer asked Francis what his occupation\\nwas, he hesitated and then said “oil change.” (Francis worked with automobiles and\\nchanged motor oil.) CBP officers then inspected Francis’s bag. There was a very full\\ncanister of shaving powder in the bag. When a CBP officer opened the canister, the\\npowder dispersed through the room and coated the officer. Bryan laughed. They contend\\nnow that the inspection of their cabins was in retaliation for Bryan’s laughing at the CBP\\nofficer. The officers found nothing unlawful in Francis’s bags. CBP Officer Baez made\\na notation in the Treasury Enforcement Communications System (TECS) database that\\nFrancis had appeared “disoriented and nervous” and that it took him some time to state\\nhis employment, but that the examination of his bag did not uncover anything.2\\n\\n The Creation of “Lookout” Entries by Officer Timothy Ogg (September 5, 2008)\\n\\n CBP Officer Timothy Ogg, stationed in San Juan, was routinely assigned the task\\nof reviewing passenger manifests for the Adventure of the Seas to identify passengers\\nworthy of further scrutiny. Around September 1, he compared the names on the\\npassenger manifest against the names on reports logged onto TECS. Both Bryan’s and\\nFrancis’s names yielded matches; both had TECS entries related to drug smuggling.\\n\\n Officer Ogg found two entries on Bryan. The first, dated May 17, 2000, was\\nauthored by Immigration & Customs Enforcement (ICE) Agent Hillary Hodge. Referring\\nto Bryan, the entry read: “Subject is associate[d] with suspected drug smugglers within\\nthe US Virgin Islands. Subject is also suspected of smuggling narcotics within the Virgin\\nIslands. If encountered, conduct 100% exam . . ..”3 Officer Ogg later testified that he\\n\\n2 JA 8.\\n3 JA 9.\\n 3\\n\\fhad previously worked with Agent Hodge and credited his entry in part because he\\nregarded Hodge as an excellent worker. The second TECS entry, from 2004, referred to\\nthe prior entry, characterized Bryan as a “suspect in USVI drug smuggling,” and\\nencouraged agents to “document [his] co-travelers, employment and reason for travel.”4\\n\\n As for Francis, Officer Ogg uncovered two TECS reports from 2006 identifying\\nFrancis as the “Subject of [a Drug Enforcement Administration] indictment.” The first\\nreport was authored while the Drug Enforcement Administration investigation was going\\non and characterized Francis as a “subject of current interest”; the second was authored\\nafter the investigation had ended and referred to him as a “Previous Suspect.”5 Both\\nreports urged personnel to alert special agents if they encountered Francis.\\n\\n According to Officer Ogg’s subsequent deposition testimony, another factor\\naroused his suspicion: CBP officers had previously made narcotics seizures on the\\nAdventure of the Seas on the same route. A number of islands along the route were\\nknown to be sources of narcotics smuggled into the United States. Officer Ogg\\ncharacterized them as high-risk islands.\\n\\n On September 5, primarily on the strength of the TECS records concerning Bryan\\nand Francis, Officer Ogg created “lookout” entries for Bryan and Francis in the TECS\\ndatabase. A “lookout” is a TECS entry that alerts CBP officers to specific passengers and\\nrecommends certain investigative steps when they are encountered. In the case of Bryan\\nand Francis, the “lookout entries” noted their connection to “drug smuggling” and\\nrecommended, in the standard TECS shorthand (i.e., “100% exam”), that their cabins be\\ninspected before their return to San Juan on September 7. 6\\n\\n Officer Ogg also entered a separate “lookout” for Beberman. Except for the co-\\ntravelers listed, the “lookout” entry for Beberman mirrored Bryan’s. At his deposition,\\nOfficer Ogg gave two reasons for the Beberman “lookout.” First, she was traveling with\\ntwo individuals about whom there were independent TECS entries predicated on drug-\\nsmuggling concerns. Second, as a practical matter, Officer Ogg stated that he had to\\nenter a lookout for Beberman to ensure that Bryan and Francis did not use her to evade\\n\\n\\n\\n\\n4 JA 9-10.\\n5 JA 10.\\n6 Id.\\n\\n\\n 4\\n\\fdetection and inspection by having her submit a single customs declaration form for the\\nthree of them, but in her name only.7\\n\\n The St. Thomas Cabin Searches (September 6, 2008)\\n\\n On the morning of September 6, 2008, after the travelers had returned to United\\nStates waters and had docked in St. Thomas, CBP Officers DeFelice, Demarais, Mazur,\\nSantiago, and Torres (collectively, the St. Thomas Officers) inspected Bryan and\\nBeberman’s cabin, along with Francis’s.\\n\\n The cabin searches each lasted between five and ten minutes.8 The St. Thomas\\nofficers knocked on the cabin doors before opening them. The occupants were asked to\\nget dressed without using the bathroom, and in at least partial view of the officers. They\\nwere then asked to leave their cabins and stand against a wall in the hallway. They\\nwaited in the hallway for between two and five minutes, while officers with a drug-\\nsniffing dog inspected their cabins. Neither cabin search yielded any contraband; the St.\\nThomas Officers created TECS entries to that effect.9\\n\\n II.\\n\\n As a result of the searches, Beberman, Bryan, and Francis filed suit in the District\\nCourt for the Virgin Islands, asserting Fourth Amendment Bivens claims against Officer\\nOgg, who had recommended, but not participated in, the cabin searches and against the\\nSt. Thomas officers, who had executed the cabin searches. The travelers also asserted\\ntort claims against the United States under the FTCA for invasion of privacy, false\\nimprisonment, and intentional infliction of emotional distress.\\n\\n\\n7 Ogg testified at his deposition that passengers traveling together were allowed to submit\\na single customs declaration form without identifying every passenger. Because\\nsecondary inspections were triggered by the names included on declaration forms, Bryan\\nand Francis could have attempted to evade detection by having Beberman submit a form\\nin her name only. Officer Ogg explained that he had entered three separate “lookouts” to\\nguard against that possibility.\\n8 The cabin inspections differed in two respects: The occupants found themselves in\\n\\ndifferent states of undress (i.e., Francis was naked, while Bryan and Beberman were\\npartially clothed) and the occupants were observed to different extents while they dressed\\n(i.e., Bryan and Beberman dressed with their cabin door ajar and the officers outside,\\nwhile Francis dressed in full view of the officers).\\n9 On September 7, when the ship reached San Juan, a different set of CBP officers began\\n\\nto inspect the travelers’ cabins but cut short the searches when they learned of the St.\\nThomas searches. The San Juan searches are not implicated in this appeal. The travelers\\nvoluntarily dismissed their Bivens claims against the San Juan officers.\\n 5\\n\\f At the close of discovery, the officers and the United States moved for summary\\njudgment. The District Court granted their motion on all claims.\\n\\n As for the officers, the District Court reasoned that neither Officer Ogg’s entry of\\n“lookouts” nor the St. Thomas cabin searches violated the travelers’ Fourth Amendment\\nrights. Further, it held that the officers were entitled to qualified immunity because their\\nconduct did not violate clearly established Fourth Amendment rights.\\n\\n As for the United States, the District Court held that the FTCA claims were barred\\nby the Act’s discretionary function exception.\\n\\n We review the District Court’s grant of summary judgment de novo, applying the\\nsame decisional principle.10 The District Court exercised subject matter jurisdiction\\nunder 28 U.S.C. §§ 1331 and 1346(b). We have appellate jurisdiction under 28 U.S.C. §\\n1291.\\n\\n III.\\n\\n The Fourth Amendment protects the public “against unreasonable searches and\\nseizures.”11 Whether a search is reasonable turns on “all of the circumstances\\nsurrounding the search,” including where the search took place. 12\\n\\n The search here took place at the border. The border serves a unique gate-keeping\\nfunction. Our controlling Fourth Amendment precedent is attuned to that reality. The\\nSupreme Court has stressed the border’s role in protecting our territorial sovereignty,\\nalong with the need to curb the inflow of drugs at the border. 13 For those reasons, we\\nextend the government special latitude at the border and strike “the Fourth Amendment\\nbalance between the interests of the Government and the privacy right of the individual”\\nin the government’s favor.14\\n\\n10 Summary judgment should be granted when, “after drawing all reasonable inferences\\nfrom the underlying facts in the light most favorable to the nonmoving party, the court\\nconcludes that there is no genuine issue of material fact to be resolved at trial and the\\nmoving party is entitled to judgment as a matter of law.” Petruzzi’s IGA Supermarkets,\\nInc. v. Darling-Delaware Co., 998 F.2d 1224, 1230 (3d Cir. 1993).\\n11 U.S. Const. amend. IV.\\n12 United States v. Montoya de Hernandez, 473 U.S. 531, 537 (1985).\\n13 See Montoya, 473 U.S. at 538 (highlighting a “longstanding concern for the protection\\n\\nof the integrity of the border. This concern is, if anything, heightened by the veritable\\nnational crisis in law enforcement caused by smuggling of illicit narcotics . . ..”) (citation\\nomitted); see also Bradley v. United States, 299 F.3d 197, 201-02 (3d Cir. 2002).\\n14 Montoya, 473 U.S. at 539-40; see also United States v. Hyde, 37 F.3d 116, 119-20 (3d\\n\\nCir. 1994).\\n 6\\n\\f In view of the government’s interests, we “have long held that routine searches at\\nour nation’s borders are presumed to be reasonable under the Fourth Amendment.” 15\\nIndeed, “[r]outine searches of the persons and effects of entrants are not subject to any\\nrequirement of reasonable suspicion, probable cause, or warrant . . ..”16 In contrast,\\n“nonroutine searches . . . require reasonable suspicion.”17 This approach to border\\nsearches applies with equal force at “the functional equivalent” of the border,18 such as a\\nship’s first port of call in the United States. 19 Under this standard, the search here was a\\nborder search.\\n\\n On September 4, 2008, a day before Officer Ogg entered “lookouts” for the\\ntravelers and two days before the cabin searches, we ruled for the first time on the\\nconstitutional propriety of border searches in the same context presented in this appeal —\\nin remarkable coincidence, searches of cabins aboard the Adventure of the Seas. 20 In\\nUnited States v. Whitted, we acknowledged “the surprising dearth of authority” on\\nwhether a search of a cruise ship cabin at the border is a routine search requiring no\\nsuspicion, or a non-routine search requiring “reasonable suspicion” (i.e., a “particularized\\nand objective basis” to suspect criminal activity).21 We held for the first time that\\nbecause of a passenger’s “high expectation of privacy” and the “level of intrusiveness,” a\\nsearch of a cruise ship cabin at the border is non-routine and requires reasonable\\nsuspicion.22 We also held that unsubstantiated information from TECS can establish\\nreasonable suspicion.23\\n\\n IV.\\n\\n In considering whether a government official is entitled to qualified immunity, a\\ncourt can determine whether a constitutional right was violated or in the alternative,\\nwhether that right was clearly established.24 Following that precedent, we will not opine\\nas to whether there were underlying Fourth Amendment violations involved in the search\\nhere. We will instead determine whether the Whitted standard, that a search of a cabin on\\na cruise ship required reasonable suspicion, was clearly established when Officer Ogg\\nincluded in his entry of “lookouts” in the TECS System that 100 % examination of the\\n\\n15 Bradley, 299 F.3d at 201 (citations omitted).\\n16 Montoya, 473 U.S. at 538 (footnote omitted).\\n17 Bradley, 299 F.3d at 204 n.8 (citation omitted).\\n18 Almeida-Sanchez v. United States, 413 U.S. 266, 272-73 (1973).\\n19 United States v. Smith, 273 F.3d 629, 633 n.8 (5th Cir. 2001) (citation omitted).\\n20 United States v. Whitted, 541 F.3d 480 (3d Cir. 2008).\\n21 Whitted, 541 F.3d at 486, 489.\\n22 Id. at 489.\\n23 Id. at 490.\\n24 Pearson v. Callahan, 555 U.S. 223, 236 (2009).\\n\\n\\n 7\\n\\fthree travelers, i.e., examination of their cabins, was recommended and the next day\\nwhen the St. Thomas officers searched the travelers’ cabins.\\n\\n The doctrine of qualified immunity shields government officials from Bivens\\nclaims and money damages, unless a plaintiff can establish that the official violated a\\nstatutory or constitutional right, and that the right was “clearly established at the time of\\nthe challenged conduct.”25 To be clearly established, a right’s contours must be\\n“sufficiently definite that any reasonable official in the defendant’s shoes would have\\nunderstood that he was violating it” and that “existing precedent . . . placed the statutory\\nor constitutional question confronted by the official beyond debate.” 26\\n\\n Further, as the Supreme Court recently reiterated, “clearly established law should\\nnot be defined at a high level of generality” but must instead “be particularized to the\\nfacts of the case.”27 The doctrine is designed to “give[] government officials breathing\\nroom to make reasonable but mistaken judgments by protect[ing] all but the plainly\\nincompetent or those who knowingly violate the law.”28\\n\\n Supreme Court discussion of searches has emphasized the threats posed at borders\\nand the government’s compelling interests in searches there. 29 Because the government’s\\ninterest in preventing the entry of unwarranted persons and effects is at its zenith at the\\nborder,30 Congress “has granted the Executive plenary authority to conduct routine\\nsearches and seizures at the border, without probable cause or a warrant . . ..”31 Until\\nSeptember 4, 2008, there had been no ruling in the Third Circuit as to what constituted a\\n“routine search.” As for Officer Ogg, he was located in San Juan, Puerto Rico, in the\\nFirst Circuit. There had not been any such ruling in the First Circuit, and the First Circuit\\ncourts would not be bound by Whitted, a Third Circuit case.\\n\\n When such a ruling is made, a ruling which affects the procedures used in border\\nsearches, it is beyond belief that within two days the government could determine what\\nwas “reasonable suspicion” and what new policy was required to conform to the ruling,\\nmuch less communicate that new policy to the CBP officers. We can only conclude that\\nas of September 5, 2008, it was not clearly established in either the Third Circuit or the\\nFirst Circuit that a search of a cruise ship cabin at the border had to be supported by\\n\\n25 Ashcroft v. al-Kidd, 563 U.S. 731, 735 (2011) (citing Harlow v. Fitzgerald, 457 U.S.\\n800, 818 (1982)).\\n26 Plumhoff v. Rickard, 134 S. Ct. 2012, 2023 (2014) (quoting Ashcroft, 563 U.S. at 741).\\n27 White v. Pauly, 137 S. Ct. 548, 552 (2017) (per curiam) (citation omitted); see also\\n\\nL.R. v. Sch. Dist. of Phila., 836 F.3d 235, 248 (3d Cir. 2016).\\n28 City & Cty. of S.F. v. Sheehan, 135 S. Ct. 1765, 1774 (2015) (citation omitted).\\n29 See, e.g., Montoya, 473 U.S. at 539-40.\\n30 United States v. Flores-Montano, 541 U.S. 149, 152-53 (2004).\\n31 Id. at 153.\\n\\n\\n 8\\n\\freasonable suspicion. Accordingly, under the circumstances that Officer Ogg confronted,\\nhe did not violate clearly established law by entering lookouts for the three passengers the\\nday after we issued our decision in Whitted. He is entitled to qualified immunity.\\n\\n We conclude that the same situation applies to the St. Thomas officers. On\\nSeptember 6, the Whitted standard was no more clearly established than it had been the\\nday before. Moreover, if the St. Thomas officers had been aware of Whitted, they would\\nhave known that Whitted held that unsubstantiated information from TECS can establish\\nreasonable suspicion.32\\n\\n For these reasons, we conclude that the Whitted standard was not clearly\\nestablished in the Third Circuit, or the First Circuit, on September 5 or 6. Within one or\\ntwo days, neither Officer Ogg nor the St. Thomas officers could reasonably be expected\\nto have learned of this development in our Fourth Amendment jurisprudence. At that\\ntime, it would not have been beyond debate that, absent reasonable suspicion, the Fourth\\nAmendment prohibited the search of the travelers’ cabins. For purposes of qualified\\nimmunity, a legal principle does not become “clearly established” the day we announce a\\ndecision, or even one or two days later.\\n\\n This holding is informed by the overarching aim of the qualified immunity\\ndoctrine to insulate from civil liability “all but the plainly incompetent or those who\\nknowingly violate the law,”33 and the need to ensure that the relevant legal principle is\\nframed with particularity34 and settled “beyond debate.”35 We are, however, deciding\\nonly this case. For that reason, we decline to draw a bright line demarcating when a legal\\nprinciple becomes “clearly established.” We leave that exercise for another day.\\n\\n Finally, the tort claims against the United States also fail because of the FTCA’s\\ndiscretionary function exception. The FTCA provides a limited waiver of sovereign\\nimmunity in certain tort actions against the United States for money damages.36 That\\nwaiver does not extend to various types of government conduct enumerated in 28 U.S.C.\\n\\n\\n\\n\\n32 541 F.3d at 490.\\n33 White, 137 S. Ct. at 552.\\n34 Id.\\n35 Plumhoff, 134 S. Ct. at 2023.\\n36 28 U.S.C. § 1346(b)(1).\\n\\n\\n 9\\n\\f§ 2680, including “the exercise or performance or the failure to exercise or perform a\\ndiscretionary function or duty . . . whether or not the discretion involved be abused.”37\\n\\n The travelers do not dispute that Officer Ogg’s entry of “lookouts” and the\\nsearches that followed were discretionary acts under the “discretionary function”\\nexception.38 Rather, they argue that the United States is not shielded from liability\\nbecause the officers in this case, though exercising their discretion, violated “clearly\\nestablished . . . constitutional rights of which a reasonable person would have known.” 39\\n\\n Because, for the reasons set out above, the CBP officers did not violate clearly\\nestablished constitutional rights, the FTCA claims also fail.\\n\\n V.\\n\\n For the reasons stated above, we will affirm the judgment of the District Court.\\n\\n\\n\\n\\n37 28 U.S.C. § 2680(a). Discretionary acts and omissions “involv[e] an element of\\njudgment or choice.” Conduct is non-discretionary only if a “federal statute, regulation,\\nor policy specifically prescribes a course of action for an employee to follow” and the\\ngovernment “employee has no rightful option but to adhere to the directive.” United\\nStates v. Gaubert, 499 U.S. 315, 322 (1991) (quoting Berkovitz ex rel. Berkovitz v. United\\nStates, 486 U.S. 531, 536 (1988)).\\n38 Br. at 63-64.\\n39 Harlow, 457 U.S. at 818.\\n\\n\\n 10\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":67,"cells":{"id":{"kind":"number","value":4583040,"string":"4,583,040"},"name":{"kind":"string","value":"UNITED STATES of America v. William HIRD, Appellant at No. 14-4754 United States of America v. Thomasine Tynes, Appellant at No. 14-4804 United States of America v. Robert Mulgrew, Appellant at No. 14-4812 United States of America v. Michael Lowry, Appellant at No. 15-1344 United States of America v. Willie Singletary, Appellant at No. 15-1739 United States of America v. Henry P. Alfano, AKA Ed, AKA Eddie, Henry P. Alfano, Appellant at No. 15-3765"},"name_abbreviation":{"kind":"string","value":"United States v. William Hird"},"decision_date":{"kind":"string","value":"2019-01-18"},"docket_number":{"kind":"string","value":"14-4754; 14-4804; 14-4812; 15-1344; 15-1739; 15-3765"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Greenaway, Nygaard, Fisher\", \"parties\": \"\", \"opinions\": [{\"author\": \"NYGAARD, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n\\n __________\\n\\nNos. 14-4754, 14-4804, 14-4812, 15-1344, 15-1739, 15-3765\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n WILLIAM HIRD,\\n Appellant at No. 14-4754\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n THOMASINE TYNES,\\n Appellant at No. 14-4804\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n ROBERT MULGREW,\\n Appellant at No. 14-4812\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n MICHAEL LOWRY,\\n Appellant at No. 15-1344\\n\\f __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n WILLIE SINGLETARY,\\n Appellant at No. 15-1739\\n ___________\\n\\n UNITED STATES OF AMERICA\\n v.\\n HENRY P. ALFANO,\\n aka Ed, aka Eddie,\\n\\n Henry P. Alfano,\\n Appellant at No. 15-3765\\n __________\\n\\n On Appeal from the United States District Court\\n for the Eastern District of Pennsylvania\\n\\n (District Court Criminal Nos. 2-13-cr-00039-007,\\n2-13-cr-00039-005, 2-13-cr-00039-003, 2-13-cr-00039-002,\\n 2-13-cr-00039-004, 2-13-cr-00039-008)\\n District Judge: Honorable Robert F. Kelly\\n District Judge: Honorable Lawrence F. Stengel\\n\\n Argued October 23, 2017\\n\\n BEFORE: GREENAWAY, JR., NYGAARD,\\n and FISHER, Circuit Judges\\n\\n\\n (Opinion Filed: January 18, 2019)\\n\\n\\n\\n\\n 2\\n\\fAngela Halim\\nHalim Drossner\\n1528 Walnut Street, Suite 1501\\nPhiladelphia, PA 19102\\n\\nGregory J. Pagano\\n1315 Walnut Street, 12th Floor\\nPhiladelphia, PA 19107\\n Counsel for Appellant in No. 14-4754\\n\\nLisa A. Mathewson [Argued]\\n123 South Broad Street, Suite 810\\nPhiladelphia, PA 19109\\n Counsel for Appellant No. 14-4804\\n\\nPeter Goldberger [Argued]\\nPamela A. Wilk\\n50 Rittenhouse Place\\nArdmore, PA 19003\\n Counsel for Appellant in No. 14-4812\\n\\nMichael J. Engle [Argued]\\nStradley Ronon Stevens & Young\\n2005 Market Street, Suite 2600\\nPhiladelphia, PA 19103\\n\\nMeredith A. Lowry\\n1528 Walnut Street, Suite 1501\\nPhiladelphia, PA 19102\\n Counsel for Appellant in No. 15-1344\\n\\n\\n\\n\\n 3\\n\\fWilliam J. Brennan\\n1600 Locust Street\\nPhiladelphia, PA 19103\\n Counsel for Appellant in No. 15-1739\\n\\nMark E. Cedrone [Argued]\\nCedrone & Mancano\\n123 South Broad Street, Suite 810\\nPhiladelphia, PA 19109\\n Counsel for Appellant in No. 15-3765\\n\\n\\nLouis D. Lappen\\nDenise S. Wolf\\nAnthony J. Wzorek\\nRobert A. Zauzmer [Argued]\\nOffice of United States Attorney\\n615 Chestnut Street, Suite 1250\\nPhiladelphia, PA 19106\\n Counsel for Appellee\\n\\n\\n\\n\\n __________\\n\\n OPINION OF THE COURT\\n __________\\n\\nNYGAARD, Circuit Judge.\\n\\n I.\\n\\n\\n\\n\\n 4\\n\\f In the run-up to a joint trial on a 77-count indictment\\nthat charged Appellants with operating a ticket-fixing scheme\\nin the Philadelphia Traffic Court, the District Court denied a\\nmotion, under Federal Rule of Criminal Procedure\\n12(b)(3)(B)(v), to dismiss charges of conspiracy (18 U.S.C. §\\n1349), mail fraud (18 U.S.C. § 1341), and wire fraud (18\\nU.S.C. § 1343). Appellants Henry Alfano (private citizen)\\nand William Hird (Traffic Court administrator) subsequently\\npleaded guilty to all counts against them. But now they\\nappeal the District Court’s decision on this motion,\\nquestioning whether the indictment properly alleged offenses\\nof mail fraud and wire fraud. 1\\n\\n Appellants Michael Lowry, Robert Mulgrew, and\\nThomasine Tynes (Traffic Court judges) proceeded to a joint\\ntrial and were acquitted on the fraud and conspiracy counts,\\nbut they were convicted of perjury for statements they made\\nbefore the Grand Jury. Lowry, Mulgrew, and Tynes dispute\\nthe sufficiency of the evidence on which they were convicted\\nby arguing that the prosecutor’s questions were vague, and\\nthat their answers were literally true. Lowry and Mulgrew\\ncontend alternatively that the jury was prejudiced by evidence\\npresented at trial on the fraud and conspiracy counts.\\nMulgrew also complains that the District Court erred by\\nruling that certain evidence was inadmissible.\\n\\n At the same trial, the jury convicted Willie Singletary\\n(Traffic Court judge) of making false statements during the\\ninvestigation. He claims the District Court made errors when\\n\\n\\n1\\n Alfano and Hird preserved their right to appeal. See infra\\nsubsection I.C.\\n\\n\\n\\n\\n 5\\n\\fit sentenced him. 2 The Government concurs with\\nSingletary’s challenge to his sentence.\\n\\n We have consolidated these appeals for efficiency and\\nhave grouped the arguments—to the extent that it is\\npossible—by common issues. We agree with Singletary and\\nthe Government that he should be resentenced. We will\\nreverse the judgment and remand his cause to the District\\nCourt for this purpose. We are not persuaded by the rest of\\nAppellants’ arguments and will affirm their judgments of\\nconviction. 3\\n\\n II.\\n\\n Appellants Alfano 4 and Hird 5\\n\\n\\n\\n2\\n Singletary also attempted to join additional arguments raised\\nby other appellants, but for reasons we explain later, see infra\\nnote 33, we focus only on his challenge to his sentence.\\n3\\n The District Court had jurisdiction pursuant to 18 U.S.C. §\\n3231. We have jurisdiction to review these claims under 28\\nU.S.C.§ 1291 and 18 U.S.C. § 3742(a).\\n4\\n Appellant Alfano pleaded guilty to Conspiracy (Count 1),\\nWire Fraud (Counts 2, 3, 4, 5, 6, 7) and Mail Fraud (Counts\\n51, 52, 53, 54, 55, 56).\\n5\\n Appellant Hird pleaded guilty to Conspiracy (Count 1),\\nWire Fraud (Counts 3, 4, 5, 6, 16, 17, 18, 19, 20, 22, 23) and\\nMail Fraud (Counts 58, 59, 60).\\n\\n\\n\\n\\n 6\\n\\f A.\\n\\n We begin with a brief look at the indictment’s\\ndescription of the Traffic Court and its operations to\\ncontextualize the arguments made by Alfano and Hird. The\\nPhiladelphia Traffic Court was part of the First Judicial\\nDistrict of Pennsylvania. App. 186 (Indictment ¶ 2). 6 It\\nadjudicated violations of the Pennsylvania Motor Vehicle\\nCode occurring in the City of Philadelphia, no matter whether\\nthe Philadelphia Police or the Pennsylvania State Police\\nissued the tickets. App. 187 (Indictment ¶5). When a person\\nwas cited for a violation he or she was required—within ten\\ndays—to enter a plea of guilty or not guilty. If the person\\nfailed to plead, the Traffic Court issued a notice that his or her\\nlicense was being suspended. App. 189 (Indictment ¶ 12). A\\nperson who pleaded not guilty proceeded to a hearing with a\\nTraffic Court judge presiding. App. 187 (Indictment ¶ 6).\\n\\n A guilty plea, or a determination of guilt by a Traffic\\nCourt judge after a hearing, resulted in a judgment ordering\\npayment of statutory fines and court costs. App. 188\\n(Indictment ¶ 8). 7 The Traffic Court was responsible for\\ncollecting these fines (sending them to the City and\\n\\n\\n6\\n Philadelphia Traffic Court was abolished and its jurisdiction\\nwas transferred to the Municipal Court in 2013 by an Act of\\nthe Pennsylvania General Assembly. 42 Pa.Con.Stat.\\n§1121(a)(2) (2013). The court is now known as the Traffic\\nDivision of the Municipal Court.\\n7\\n Although other penalties are prescribed by the Pennsylvania\\nMotor Vehicle Code (App. 188), this appeal is limited to the\\nmonetary fines and costs. App. 355.\\n\\n\\n\\n\\n 7\\n\\fCommonwealth) and costs (which it distributed to several\\npre-designated funds). App. 188-89 (Indictment ¶ 9).\\nFinally, it reported the disposition of each adjudication to the\\nPennsylvania Department of Transportation (PennDOT).\\nApp. 189 (Indictment ¶ 11).\\n\\n B.\\n\\n The indictment charged that, at the behest of Alfano\\n(App. 193 (Indictment ¶ 25)) and others, the Traffic Court\\nadministrator and judges operated an “extra-judicial system,\\nnot sanctioned by the Pennsylvania court system” that\\nignored court procedure and gave preferential treatment\\n(“consideration”) to select individuals with connections to the\\ncourt who had been cited for motor vehicle violations. App.\\n196 (Indictment ¶ 31). The special treatment included:\\n\\n (1) dismissing tickets outright; (2)\\n finding the ticketholder not guilty\\n after a “show” hearing; (3)\\n adjudicating the ticket in a\\n manner to reduce fines and avoid\\n assignment of points to a driver’s\\n record; and (4) obtaining\\n continuances of trial dates to\\n “judge-shop,” that is find a Traffic\\n Court judge who would accede to\\n a request for preferential\\n treatment.\\n\\nApp. 195-196 (Indictment ¶ 30). All of this was “not\\navailable to the rest of the citizenry.” App. 196 (Indictment ¶\\n32). It also alleged that Appellants cooperated with each\\n\\n\\n\\n\\n 8\\n\\fother to fulfill requests they and their staffs received. App.\\n194-95 (Indictment ¶ 27). Finally, it charged that “[i]n\\nacceding to requests for ‘consideration,’ defendants were\\ndepriving the City of Philadelphia and the Commonwealth of\\nPennsylvania of money which would have been properly due\\nas fines and costs.” App. 197 (Indictment ¶ 38). 8\\n After extending consideration to favored individuals,\\nTraffic Court judges would report the final adjudication to\\n“various authorities, including PennDOT, as if there had been\\na fair and open review of the circumstances.” App. 197\\n(Indictment ¶ 34). Appellant Hird provided a printout to\\nAppellant Alfano showing citations that had been “dismissed\\nor otherwise disposed of.” App. 198-99 (Indictment ¶ 42).\\nSuch “receipts” were not routinely issued in cases.\\n\\n C.\\n\\n Hird and Alfano pleaded guilty to all the charges\\nagainst them in the indictment. But, in their plea agreement\\nthey reserved the right to appeal “whether the Indictment\\n\\n\\n8\\n An example of the many allegations involving Alfano and\\nHird is: A.S. requested assistance from Appellant Alfano and\\nAppellant Hird on Citation Number P1J0PK568L4 on or\\naround February 17, 2010. The citation charged A.S. with\\ndriving a tractor-trailer from which snow and ice fell, striking\\nvehicles on Interstate 95. The violation carried a $300 fine\\nand costs of $142. Appellant Hird promised that he would\\n“stop all action” on the citation and instructed A.S. to ignore\\nthe ticket. Although A.S. did not appear at the hearing, the\\nTraffic Court judge (who is not an appellant here) ruled A.S.\\nnot guilty. App. 210-12 (Indictment ¶¶ 25-34).\\n\\n\\n\\n\\n 9\\n\\fsufficiently alleged that the defendants engaged in a scheme\\nto defraud the Commonwealth of Pennsylvania and the City\\nof Philadelphia of money in costs and fees.” App. 355 (Plea\\nAgreement ¶ 9(b)(4)). So they now appeal the District\\nCourt’s order denying the motion to dismiss, asserting that\\nthe indictment failed to allege violations of mail fraud and\\nwire fraud.\\n\\n “To be sufficient, an indictment must allege that the\\ndefendant performed acts which, if proven, constitute a\\nviolation of the law that he is charged with violating.” United\\nStates v. Small, 793 F.3d 350, 352 (3d Cir. 2015). We\\nassume in our review that the allegations in the indictment are\\ntrue. United States v. Hedaithy, 392 F.3d 580, 583 (3d Cir.\\n2004). “The question of whether the . . . indictments alleged\\nfacts that are within the ambit of the mail fraud statute is a\\nquestion of statutory interpretation subject to plenary review.”\\nId. at 590 n.10.\\n\\n To indict on mail or wire fraud, the Government must\\nallege that defendants “devised or intend[ed] to devise any\\nscheme or artifice to defraud, or for obtaining money or\\nproperty by means of false or fraudulent pretenses,\\nrepresentations, or promises” and used mail or wire to effect\\nthe scheme. 18 U.S.C. §§ 1341, 1343. Alfano and Hird claim\\nthe Government failed to allege that the scheme to commit\\nwire and mail fraud had an objective of “obtaining money or\\nproperty.” 9\\n\\n9\\n In the context of mail fraud (§ 1341) and wire fraud (§1343)\\nthe term “money” has the same meaning. The same is true\\nfor the term “property.” Carpenter v. United States, 484 U.S.\\n19, 25 n. 6 (1987).\\n\\n\\n\\n\\n 10\\n\\f The District Court ruled that the indictment\\nsufficiently alleged that the scheme “involved defrauding the\\nCommonwealth and the City of money.” App. 20. It noted,\\namong others, allegations that:\\n\\n The conspirators used the\\n Philadelphia Traffic Court\\n (“Traffic Court”) to give\\n preferential treatment to certain\\n ticketholders, most commonly by\\n “fixing” tickets for those with\\n whom they were politically and\\n socially connected. By doing so,\\n the conspirators defrauded the\\n Commonwealth of Pennsylvania\\n and the City of Philadelphia of\\n funds to which the\\n Commonwealth and the City were\\n entitled.\\n\\nId. at 18; see also id. at 185 (Indictment ¶ 1). Similarly, it\\nreferred to the following.\\n\\n In acceding to requests for\\n “consideration,” defendants were\\n depriving the City of Philadelphia\\n and the Commonwealth of\\n Pennsylvania of money which\\n would have been properly due as\\n fines and costs.\\n\\n\\n\\n\\n 11\\n\\fId. at 9; see also id. at 197 (quoting Indictment ¶ 38).\\nHighlighting the references to “funds” and “money,” and that\\nthe monetary amounts of the fines are specifically pleaded,\\nthe District Court cited to a case from the Court of Appeals\\nfor the Eighth Circuit which concluded succinctly that\\n“[m]oney is money.” United States v. Sullivan, No. 2:13-cr-\\n00039, 2013 WL 3305217, at *7 (E.D. Pa. July 1, 2013)\\n(quoting United States v. Granberry, 908 F.2d 278, 280 (8th\\nCir. 1990)). The District Court was satisfied that the\\nindictment alleged enough.\\n\\n “Money, of course, is a form of property.” Reiter v.\\nSonotone Corp., 442 U.S. 330, 338 (1979). But Alfano and\\nHird argue that the mere mention of money in an indictment\\nis not enough. They point to a string of Supreme Court and\\nCourt of Appeals decisions analyzing Section 1341 and\\nSection 1343 which reinforce the point that crimes of mail\\nfraud and wire fraud are “limited in scope to the protection of\\nproperty rights.” McNally v. United States, 483 U.S. 350, 360\\n(1987). 10 The Supreme Court said that “[a]ny benefit which\\nthe government derives from the [mail fraud] statute must be\\nlimited to the Government’s interests as a property holder.”\\nId. at 359 n.8 (emphasis added). Appellants are convinced\\nthat money in the form of traffic fines and costs cannot be\\nregarded as the Government’s “property” for purposes of mail\\nor wire fraud, and they identify two decisions as particularly\\nsupportive of their position: Cleveland v. United States, 531\\n\\n10\\n The District Court cited to a number of cases that came\\nafter McNally: Carpenter v. United States, 484 U.S. 19\\n(1987); Cleveland v. United States, 531 U.S. 12 (2000);\\nPasquantino v. United States, 544 U.S. 349 (2005).\\n\\n\\n\\n\\n 12\\n\\fU.S. 12 (2000); and United States v. Henry¸ 29 F.3d 112 (3d\\nCir. 1994).\\n\\n The Court in Cleveland examined the mail fraud\\nconvictions of individuals who received a state video poker\\nlicense by submitting a license application that withheld\\nimportant information. Cleveland, 531 U.S. 12. 11 The Court\\nnoted that the video poker licenses were part of a state\\nprogram that was “purely regulatory.” Id. at 22 (citation\\nomitted). 12 It ruled that licenses are a “paradigmatic\\nexercise[] of the States’ traditional police powers.” Id. at 23.\\nThe Court went on to say that the state’s regulatory powers\\ninvolving “intangible rights of allocation, exclusion, and\\ncontrol” (which are embodied in a license) are not interests\\nthat traditionally have been recognized as property. Id.\\nTherefore, even though appellants may have obtained the\\nlicense through deception, this was not mail fraud because the\\nlicense—at least while still in the hands of the state—was not\\n\\n\\n\\n11\\n The licenses were part of a regulatory scheme that had as\\nits purpose to increase public confidence in the honesty of\\ngaming activities that are free of criminal involvement.\\nCleveland, 531 U.S. at 20–21 (quoting La. Rev. Stat. Ann. §\\n27:306(A)(1) (2000) (repealed 2012)).\\n12\\n The Court rebuffed the Government’s attempts to analogize\\nlicenses to other forms of property like patents and franchise\\nrights. As for likening licenses to franchise rights, the Court\\nobserved that the Government did not enter the video poker\\nbusiness, but rather decided to “permit, regulate, and tax\\nprivate operators of the games.” Id. at 24.\\n\\n\\n\\n\\n 13\\n\\fproperty. Id. at 26-27. It was a purely administrative tool\\nused to achieve regulatory objectives. Id. at 21.\\n\\n The state responded to the Court’s concerns by\\nagreeing that the licenses served a regulatory purpose, but it\\ndirected attention to the revenue it received from fees\\ncollected for license applications and renewals, as well as\\ndevice fees. Id. at 21-22. It argued that this revenue is a\\nproperty interest. Id. The Court was not convinced:\\n\\n Tellingly, as to the character of\\n Louisiana’s stake in its video\\n poker licenses, the Government\\n nowhere alleges that Cleveland\\n defrauded the State of any money\\n to which the State was entitled by\\n law. Indeed, there is no dispute\\n that TSG paid the State of\\n Louisiana its proper share of\\n revenue, which totaled more than\\n $1.2 million, between 1993 and\\n 1995. If Cleveland defrauded the\\n State of “property,” the nature of\\n that property cannot be economic.\\n\\nId. at 22 (emphasis added). It concluded that “[e]ven when\\ntied to an expected stream of revenue, the State’s right of\\ncontrol does not create a property interest any more than a\\nlaw licensing liquor sales in a State that levies a sales tax on\\n\\n\\n\\n\\n 14\\n\\fliquor.” Id. at 23. 13 The money collected from application\\nand processing fees was an integral part of the state\\nregulatory program and it did not create any property interest.\\nSee id.\\n\\n The purpose of the Pennsylvania Motor Vehicle Code\\nis to “promote the safety of persons and property within the\\nstate.” Mauer v. Boardman, 7 A.2d 466, 472 (Pa. 1939).\\nMoreover, issuing traffic tickets is a crucial element in the\\nenforcement of the Motor Vehicle Code: it is a quintessential\\nexercise of state police power. Alfano and Hird conclude,\\nmuch like Cleveland, that no property interest could arise\\nfrom revenue generated from the state’s exercise of its police\\npower in the form of a traffic-ticket fine. They see nothing\\nbut a regulatory program here. But this ignores crucial\\naspects of the case before us that make it different.\\n\\n Simply stated, fees charged to obtain a license cannot\\nbe equated with fines and costs that result from a traffic\\nticket. The license fee was imposed, adjusted, and collected\\nsolely by the state’s exercise of its regulatory authority. In\\ncontrast, here the state’s police power is exercised when a\\ncitation is issued, but this ticket merely establishes the\\nsummary violation with which the person is charged. Once a\\nperson has been charged, it is judicial power (not the state’s\\npolice power) that is exercised to determine whether the\\n\\n\\n\\n\\n13\\n Cleveland also held that Government-issued licenses have\\nno intrinsic economic worth before they are given to\\napplicants. Id. at 23.\\n\\n\\n\\n\\n 15\\n\\fperson is guilty and, if guilty, to impose the fine and costs. 14\\nThese fines and costs, although specified by the Motor\\nVehicle Code, cannot be cabined as a product of the state’s\\nregulatory authority. They are part and parcel of the\\njudgment of the court. With this in mind, it is significant that\\nthe indictment does not focus on how the citations were\\nissued (which would implicate police power), but rather\\nalleges that the judicial process was rigged to produce only\\njudgments that imposed lower fines—or most often—no fines\\nand costs at all. 15\\n\\n But this raises a further question: can a criminal\\njudgment held by the government ever be “property?” The\\nCourt in Cleveland offered a critique in its analysis of a\\n\\n14\\n The Traffic Court was not an administrative tribunal.\\nRather, it was part of the First Judicial District of\\nPennsylvania. App. 186 (Indictment ¶ 2). See also supra\\nnote 6 and accompanying text.\\n15\\n On this point, it is noteworthy that the Supreme Court also\\nsaid the following: “We resist . . . [any invitation] to approve\\na sweeping expansion of federal criminal jurisdiction in the\\nabsence of a clear statement by Congress. . . . ‘[U]nless\\nCongress conveys its purpose clearly, it will not be deemed to\\nhave significantly changed the federal-state balance’ in the\\nprosecution of crimes.” Cleveland, 531 U.S. at 24-25\\n(quoting Jones v. United States, 529 U.S. 848, 858 (2000)).\\nAs we discuss later, the legal tradition of understanding\\njudgments as property is long-established. Consequently, the\\nconcern about expanding the reach of federal fraud statutes to\\nnew classes of property that was present in the deliberation of\\nstate licenses in Cleveland is not at issue here.\\n\\n\\n\\n\\n 16\\n\\fdifferent issue (whether licenses were analogous to patents)\\nthat is apropos to answering this question.\\n\\n [W]hile a patent holder may sell\\n her patent, see 35 U.S.C. § 261 . .\\n . “patents shall have the attributes\\n of personal property” . . . the State\\n may not sell its licensing\\n authority. Instead of a patent\\n holder’s interest in an unlicensed\\n patent, the better analogy is to the\\n Federal Government’s interest in\\n an unissued patent. That interest,\\n like the State’s interest in\\n licensing video poker operations,\\n surely implicates the\\n Government’s role as sovereign,\\n not as property holder.\\n\\nCleveland, 531 U.S. at 23–24. Fines imposed by judges are\\ncriminal penalties that “implicate[] the Government’s role as\\nsovereign.” Id. at 24. Judgments ordering traffic fines and\\ncosts cannot be sold and, in the logic of Cleveland, would\\nseem then to have no intrinsic economic value. Indeed, the\\npenal (non-economic) nature of the fine is undeniable because\\nthe failure to pay a fine can result in the imposition of\\nsentences of greater consequence, including imprisonment.\\nSee Pa. R. Crim. P. 706 cmt. But Cleveland is not the last\\nword. As we will discuss below, a Supreme Court opinion\\nissued five years later, Pasquantino v. United States, 544 U.S.\\n349 (2005), forecloses the defendants’ argument.\\n\\n\\n\\n\\n 17\\n\\f Finally, we note a dissimilarity between this case and\\nCleveland, highlighted by the District Court, on the\\nsignificance of the monetary interest that the Government\\nassociates with the fraud. The Cleveland Court regarded the\\nlicensing fees as integral to the regulatory effort and collateral\\nto the matter at hand. The indictment there centered on the\\nscheme to obtain liceneses, and did not even raise the\\nlicensing fees. See Cleveland, 531 U.S. at 22. Indeed, those\\ncharged with the fraud paid all the appropriate fees; there was\\nno evidence that the government suffered any economic\\ndetriment. Id.\\n\\n In contrast, the indictment here explicitly states that\\nthe scheme deprived the City and the Commonwealth of\\nmoney, and it describes the object of the scheme as obviating\\njudgments of guilt that imposed the fines and costs. Unlike\\nCleveland, the fines and costs play a central role in the\\nscheme as alleged.\\n\\n Alfano and Hird next focus on our decision in Henry\\nto argue that the Government cannot claim to have a property\\nright because the Government never had a legal claim to the\\nfines and costs at any point in the scheme. In Henry, we\\nexamined convictions for wire fraud arising from a\\ncompetitive bidding process among banks to receive deposits\\nof a public agency’s bridge tolls. Henry v. United States, 29\\nF.3d 112 (3d Cir. 1994). Appellants—public employees—\\nwere convicted of mail fraud for giving one bank confidential\\ninformation about bids from other banks. Id. at 113. We\\nidentified several problems, 16 but Alfano and Hird highlight\\n\\n16\\n The Supreme Court had already made clear that “a\\ngovernment official’s breach of his or her obligations to the\\n\\n\\n\\n\\n 18\\n\\four observation in Henry that the object of the mail and wire\\nfraud must be something to which the victim could claim a\\nright of entitlement. Id. at 115 (“a grant of a right of\\nexclusion”) (citing Carpenter, 484 U.S. at 26-27)). 17 Indeed,\\nwe noted that a bank’s property right to the tolls would attach\\nonly after the funds were deposited. Id. at 114. So the banks\\nthat lost the bidding process never had a basis to claim any\\nlegally recognized entitlement to the toll deposits. 18 Id. at\\n115. A fraud claim cannot rest on the bidders being cheated\\nout of an opportunity to receive the deposits. For these\\nreasons, we concluded that the indictment did not allege a\\nscheme to obtain fraudulently someone’s “property.” Id. at\\n116.\\n\\n Here, the Government alleged that the defendants\\n“were depriving . . . Philadelphia and . . . Pennsylvania of\\nmoney which would have been properly due as fines and\\ncosts” by making it possible for certain well-connected\\nindividuals to avoid a judgment of guilt that imposed an\\nobligation to pay appropriate statutory fines. App. 197\\n\\n\\npublic or an employee’s breach of his or her obligations to an\\nemployer” did not fall within the scope of Section 1343.\\nHenry, 29 F.3d at 114 (citing Carpenter, 484 U.S. at 25).\\n17\\n To assess whether a particular claim is a legal entitlement,\\n“we look to whether the law traditionally has recognized and\\nenforced [the entitlement] as a property right.” Henry, 29\\nF.3d at 115.\\n18\\n They were, no doubt, robbed of a fair process, but we could\\nnot identify any legal tradition that recognized this\\ndeprivation as a property right. Id. at 115.\\n\\n\\n\\n\\n 19\\n\\f(Indictment ¶ 38). But Appellants stress that, like the\\ndeposits in Henry, the indictment here alleged an entitlement\\nthat does not yet exist because a person must be adjudicated\\n(or plead) guilty before they must pay any fines or costs.\\nNone of the cases directly associated with Alfano and Hird\\nresulted in a guilty judgment. As a result, they argue, the\\nGovernment cannot claim here that it was cheated of an\\nentitlement, because they were only fines and costs that the\\npeople might have owed if they had been found guilty.\\n\\n The District Court said it well. Accepting this\\nargument “would permit the alleged conspirators” to take\\nadvantage of their “unique position” in this case “to enter into\\na scheme to commit fraud and then hide behind the argument\\nthat the success of their fraud precludes prosecution under the\\n‘money or property interest’ requirement of the mail and wire\\nfraud statutes.” Sullivan, 2013 WL 3305217, at *7.\\nAppellants cannot rest on the very object of their scheme (to\\nwork on behalf of favored individuals to obviate judgments of\\nguilt and the imposition of fines and costs) as the basis to\\nclaim that there is no fraud. Indeed, the not-guilty judgments\\nthat Alfano and Hird worked to obtain through the\\nextrajudicial system were alleged in the indictment as\\nevidence of the scheme itself.\\n\\n Even if some of the cases in the extra-judicial system\\nwould have been judged not guilty in a real adjudication it is\\n(as the District Court correctly noted) the intent of the\\nscheme, not the successful execution of it, that is the basis for\\ncriminal liability. See Neder v. United States, 527 U.S. 1, 25\\n(1999) (In the criminal context, the court focuses on the\\nobjective of the scheme rather than its actual outcome; what\\noperatives intended to do, not whether they were successful in\\n\\n\\n\\n\\n 20\\n\\fdoing it.); United States v. Rowe, 56 F.2d 747, 749 (2d Cir.)\\n(“Civilly of course the [mail fraud statute]would fail without\\nproof of damage, but that has no application to criminal\\nliability.”), cert. denied 286 U.S. 554 (1932). The indictment\\ngenerally alleges not just that Appellants operated a system\\nthat operated outside the bounds of Traffic Court procedures,\\nbut that it did so for the purpose of obviating judgments of\\nguilt imposing fines and costs in those selected cases. See,\\ne.g., supra note 8. Moreover, we note that in one case not\\ndirectly involving either Alfano or Hird, the indictment\\nalleged that fines and costs were not just obviated, but were\\nactually erased by an alleged co-conspirator traffic court\\njudge who ignored the conviction, backdated a continuance,\\nand “adjudicated” the person not-guilty. App. 228-29\\n(Indictment ¶¶ 108-113). This episode serves to highlight\\nthat the entire scheme was centered on keeping (or taking)\\njudgments out of the hands of the Government to prevent the\\nimposition of fines and costs. As a result, Appellants’\\nreliance on our justice system’s presumption of innocence as\\na basis to argue against the existence of a governmental\\nproperty interest is a red herring that is properly disregarded\\nhere.\\n\\n Accordingly, we conclude that the indictment’s\\nallegation that the scheme had an objective of depriving\\n“Philadelphia and . . . Pennsylvania of money which would\\nhave been properly due as fines and costs” is not undermined\\nby the lack of guilty verdicts. App. 197 (Indictment ¶38\\n(emphasis added)).\\n\\n Alfano and Hird next highlight that, in Henry, our\\nproperty interest analysis centered on “whether the law\\ntraditionally has recognized and enforced [the entitlement in\\n\\n\\n\\n\\n 21\\n\\fquestion] as a property right.” 29 F.3d at 115. Appellants\\nassert that traffic fines and costs typically have not been\\nconsidered economic property and are unsupported by any\\nlegal tradition sufficient to ground charges of wire and mail\\nfraud. As we have already noted we disagree with any\\nconclusion that the fines and costs at issue have no intrinsic\\neconomic value. But we turn to another decision of the\\nSupreme Court that came after Cleveland to address squarely\\nwhether jurisprudence supports our conclusion.\\n\\n In 2005 the Supreme Court reviewed convictions\\narising from a scheme to smuggle large quantities of liquor\\nfrom the United States into Canada, evading Canadian taxes.\\nSee Pasquantino v. United States, 544 U.S. 349, 353 (2005).\\nThe Court noted that the right to be paid has been routinely\\nrecognized as property, id. at 355–56, 19 observing that there is\\nan equivalence between “money in hand and money legally\\ndue,” id. at 356. Affirming the conviction, the Court said:\\n“Had petitioners complied with this legal obligation, they\\nwould have paid money to Canada. Petitioners’ tax evasion\\ndeprived Canada of that money, inflicting an economic injury\\nno less than had they embezzled funds from the Canadian\\ntreasury.” Id. It concluded that: “[t]he object of petitioners’\\nscheme was to deprive Canada of money legally due, and\\ntheir scheme thereby had as its object the deprivation of\\nCanada’s ‘property.’” Id. Under Pasquantino, then, traffic\\ntickets (or more precisely, judgments arising from them) are\\nconsidered an “entitlement to collect money from individuals,\\n\\n\\n19\\n The Court cited 3 W. Blackstone, Commentaries on the\\nLaws of England 153–155 (1768), which classified the right\\nto sue on a debt as personal property.\\n\\n\\n\\n\\n 22\\n\\fthe possession of which is ‘something of value.’” 544 U.S. at\\n355 (quoting McNally, 483 U.S. at 358). 20 We conclude that\\na scheme to obviate judgments imposing fines, effectively\\npreventing the government from holding and collecting on\\nsuch judgments imposes an economic injury that is the\\nequivalent of unlawfully taking money from fines paid out of\\nthe Government’s accounts. See id. at 358.\\n\\n Alfano and Hird focus, finally, on the role that a\\njudge’s discretion plays in the adjudication of a case,\\nasserting that the uncertainty this creates about outcomes in\\nany given case undermines any argument that a judgment in a\\nTraffic Court case can be claimed as an entitlement to\\nproperty. To the extent that this merely rephrases the issue of\\nguilt or innocence on particular charges, we have already\\n\\n20\\n We also note that Pennsylvania law permits the government\\nto remedy the nonpayment of fines and costs as an unpaid\\ndebt through civil process, enabling the government to\\nbecome a judgment creditor. Pa. R. Crim. P. 706 cmt.\\n(“Nothing in this rule [concerning criminal fines] is intended\\nto abridge any rights the Commonwealth may have in a civil\\nproceeding to collect a fine or costs.”). Because of this, a\\nseparate legal tradition is implicated that recognizes the\\njudgment itself as property. See, e.g., Armada (Singapore)\\nPTE Ltd. v. Amcol International Corp., 885 F.3d 1090, 1094\\n(7th Cir. 2018). This long, stable legal tradition of\\nrecognizing civil judgments for money as property supports\\nthe conclusion that the fines arising from judgments in traffic\\ncourt cannot be regarded merely as implicating the act of a\\nsovereign imposing a criminal penalty. They can be collected\\nby civil process as a debt and are, thus, a property interest.\\n\\n\\n\\n\\n 23\\n\\faddressed it above. To the degree that it refers to a judge’s\\ndiscretion in sentencing, as the District Court noted, there is\\nno such discretion here. 21 The Motor Vehicle Code imposes\\nfines and costs for each violation, eliminating any judicial\\ndiscretion in this regard.\\n\\n D.\\n\\n All of this leads us to conclude that the District Court\\ndid not err by denying the motion to dismiss. We conclude\\nthat, as alleged, this scheme had the objective of preventing\\nthe City of Philadelphia and the Commonwealth of\\nPennsylvania from possessing a lawful entitlement to collect\\nmoney in the form of fines and costs—a property interest—\\nfrom individuals who Alfano and Hird assisted. We will thus\\naffirm the convictions of Appellants Alfano and Hird.\\n\\n III.\\n\\n Appellants Tynes, Lowry, and Mulgrew\\n\\n A.\\n\\n\\n\\n\\n21\\n We question, in general, the relevance of an entity’s\\nauthority to relinquish a just entitlement or to forbear an\\nobligation that an entitlement imposes upon another, as a\\nbasis to call into doubt the legitimacy of, or the very existence\\nof the entitlement. But see United States v. Mariani, 90 F.\\nSupp. 2d 574, 583 (M.D. Pa. 2000) (Discretionary civil fines\\nand penalties “may be too speculative to constitute a valid\\nproperty interest.”) (internal citation omitted).\\n\\n\\n\\n\\n 24\\n\\f In 2011, the United States Attorney presented to the\\nGrand Jury evidence arising from the Federal Bureau of\\nInvestigation’s inquiry into the Traffic Court. Appellants\\nLowry, Mulgrew, and Tynes testified and the Government\\nbrought perjury charges against them for statements they\\nmade to the Grand Jury. After Hird and Alfano pleaded\\nguilty, the rest of the Appellants went to trial. The jury\\nacquitted Lowry, Mulgrew, and Tynes of all counts against\\nthem on wire fraud, mail fraud, and conspiracy. But it found\\nthem guilty of perjury. Tynes, Lowry, and Mulgrew\\nchallenge their convictions by raising similar legal arguments\\nabout the sufficiency of the evidence.\\n As with all challenges to the sufficiency of the\\nevidence, we use a highly deferential standard of review. See\\nUnited States v. Caraballo-Rodriguez, 726 F.3d 418, 430 (3d\\nCir. 2013) (en banc). We examine the record in a light most\\nfavorable to the prosecution, and will not disturb the verdict if\\n“any rational trier of fact could have found the essential\\nelements of the crime beyond a reasonable doubt.” United\\nStates v. McGee, 763 F.3d 304, 316 (3d Cir. 2014) (emphasis\\nin original) (quoting Jackson v. Virginia, 443 U.S. 307, 319\\n(1979)). Tynes, Lowry, and Mulgrew argue that the\\nquestions asked of them at trial were fatally vague and/or that\\ntheir answers were truthful. As a result, they contend that\\nthese questions and answers are an inadequate basis for a\\nperjury conviction.\\n\\n A conviction for perjury before a grand jury requires\\nthe Government to prove that the defendant took an oath\\nbefore the grand jury and then knowingly made a “false\\nmaterial declaration.” 18 U.S.C. § 1623. But we recognized\\n(in the context of a sentencing enhancement for perjury) that\\nsometimes “confusion, mistake, or faulty memory” results in\\n\\n\\n\\n\\n 25\\n\\finaccuracies that cannot be categorized as a “willful attempt\\nto obstruct justice” under perjury statutes. United States v.\\nMiller, 527 F.3d 54, 75 (3d Cir. 2008) (quoting U.S.\\nSentencing Guidelines Manual § 3C1.1 cmt. n.2 (U.S.\\nSentencing Comm’n 2003). So we do understand that\\n“[p]recise questioning is imperative as a predicate for the\\noffense of perjury.” Bronston v. United States, 409 U.S. 352,\\n362 (1973).\\n\\n Precision, however, is assessed in context. An\\nexaminer’s line of questioning should, at a minimum,\\nestablish the factual basis grounding an accusation that an\\nanswer to a particular question is false. Miller, 527 F.3d at\\n78. So a perjury conviction is supported by the record “when\\nthe defendant’s testimony ‘can reasonably be inferred to be\\nknowingly untruthful and intentionally misleading, even\\nthough the specific question to which the response is given\\nmay itself be imprecise.’” United States v. Serafini, 167 F.3d\\n812, 823 (3d Cir. 1999) (quoting United States v. DeZarn,\\n157 F.3d 1042, 1043 (6th Cir. 1998)).\\n\\n Challenges to the clarity of a question are typically left\\nto the jury, which has the responsibility of determining\\nwhether the defendant understood the question to be\\nconfusing or subject to many interpretations. United States v.\\nSlawik, 548 F.2d 75, 86 (3d Cir. 1977). Moreover, consistent\\nwith our standard of review, we will not disturb a jury’s\\ndetermination that a response under oath constitutes perjury\\nunless “it is ‘entirely unreasonable to expect that the\\ndefendant understood the question posed to him.’” Serafini,\\n167 F.3d at 820 (quoting United States v. Ryan, 828 F.2d\\n1010, 1015 (3d Cir. 1987), abrogated on other grounds by\\n\\n\\n\\n\\n 26\\n\\fUnited States v. Wells, 519 U.S. 482 (1997)). 22 On appeal,\\nwe review every aspect of the record pertinent to both the\\nquestion and answer to reach a conclusion about whether, in\\ncontext, the witness understood the question well enough to\\ngive an answer that he or she knew to be false. See Miller,\\n527 F.3d at 78. Our review, however, is focused on glaring\\ninstances of vagueness or double-speak by the examiner at the\\ntime of questioning (rather than artful post-hoc interpretations\\nof the questions) that—by the lights of any reasonable fact-\\nfinder—would mislead or confuse a witness into making a\\nresponse that later becomes the basis of a perjury conviction.\\nQuestions that breach this threshold are “fundamentally\\nambiguous” and cannot legitimately ground a perjury\\nconviction. Id. at 77. 23\\n\\n\\n22\\n The Court of Appeals for the Second Circuit underscored\\nthe high bar this establishes for appellants by noting that a\\nfundamentally ambiguous question is “not a phrase with a\\nmeaning about which men of ordinary intellect could agree,\\nnor one which could be used with mutual understanding by a\\nquestioner and answerer unless it were defined at the time it\\nwere sought and offered as testimony.” United States v.\\nLighte, 782 F.2d 367, 375 (2d Cir. 1986) (quoting United\\nStates v. Lattimore, 127 F. Supp. 405, 410 (D. D.C.), aff’d,\\n232 F.2d. 334 (D.C. Cir. 1955)).\\n23\\n The rule of fundamental ambiguity is intended to\\n“preclude convictions that are grounded on little more than\\nsurmise or conjecture, and . . . prevent witnesses . . . from\\nunfairly bearing the risks associated with the inadequacies of\\ntheir examiners.” Ryan, 828 F.2d at 1015.\\n\\n\\n\\n\\n 27\\n\\f That is the law applicable to the claims raised by\\nTynes, Lowry and Mulgrew. But, because our review is fact-\\ndependent, and because each raises some unique issues, we\\nwill address each of their claims individually. 24\\n B.\\n\\n\\n\\n\\n24\\n Adopting the arguments made by Alfano and Hird,\\nAppellants Lowry, Mulgrew and Tynes assert that the\\nGovernment improperly charged them with conspiracy, wire\\nfraud, and mail fraud. Therefore, they assert, their joint trial\\non these counts of the indictment prejudiced the jury’s\\ndeliberation on the charges of perjury. They claim such\\nevidence would have been excluded under Federal Rule of\\nEvidence. 403. They also contend that, without a charge of\\nconspiracy, the joinder of their cases would have been\\nimpermissible under Federal Rule of Criminal Evidence 8(b)\\nor, at the very least, severance of their cases would have been\\nwarranted under Federal Rule of Criminal Procedure 14(a).\\nCertainly, where there is evidence of prejudice resulting from\\n“spillover” evidence from counts that should have been\\ndismissed, reversal is warranted. See United States v. Wright,\\n665 F.3d 560, 575-577 (3d Cir. 2012). But we have\\nconcluded that the District Court did not err by denying the\\nmotion, under Federal Rule of Civil Procedure 12(b)(3), to\\ndismiss the conspiracy, wire fraud and mail fraud counts of\\nthe indictment. Thus, Appellants’ spillover argument has\\nbeen nullified. Likewise, Appellants have no basis to claim\\nthat the Court unfairly prejudiced them by not granting\\nseparate trials.\\n\\n\\n\\n\\n 28\\n\\f Appellant Tynes 25\\n\\n Appellant Tynes claims her convictions for perjury at\\nCount 71 and Count 72 lack sufficient evidence because she\\nwas responding to questions that were fundamentally\\nambiguous. The perjury charged at Count 71 arises from the\\nfollowing exchange.\\n\\n Q. In all the years\\n you’ve been [at Traffic\\n Court] have you\\n ever been asked to give\\n\\n\\n25\\n Tynes filed a separate motion to dismiss. App. 291-99.\\nThe record also contains Tynes’ proposed order to join\\nSullivan’s motion to dismiss. App. 290. However, Tynes’\\nmotion contains no such request. Moreover, the\\nGovernment’s response to the motions notes that Lowry and\\nMulgrew moved to join (without argument), and makes no\\nmention of Tynes. The District Court’s ruling on Tynes’\\nmotion to dismiss relates only to the arguments she made\\nseparately in her brief. As a result, we cannot consider\\nTynes’ arguments on appeal that relate to those raised in\\nSullivan’s motion. Moreover, since she failed to raise any of\\nthe arguments she made in her separate motion to dismiss,\\nthese arguments are waived. With that said, we will affirm\\nthe District Court’s ruling on the Motion raised by Sullivan\\nand joined by the five Appellants. Therefore, we need not\\naddress Tynes’ assertion that the District Court’s mishandled\\nher joinder motion because it does not prejudice the outcome\\nof her appeal.\\n\\n\\n\\n\\n 29\\n\\f favorable treatment on\\n a case to anybody?\\n\\n A. No, not favorable\\n treatment. People basically\\n know me. The lawyers\\n know me. The court\\n officers know me. I have\\n been called a nononsense\\n person because I’m just not\\n that way. I take my\\n position seriously, and the\\n cards fall where they may.\\n\\nApp. 255, 5720. 26 Tynes contends that the Government\\npursued a novel theory here (applying federal fraud statutes to\\nallegations of ticket fixing) and used the vague term\\n“favorable treatment” to gloss over its uncertainty about what,\\nultimately, would constitute an illegal act. She points out that\\nthe term had not been used before in reference to this case\\nand that the Government offered no explanation or definition\\nof the term to alert Tynes to the intent of the question.\\n\\n Also, from Tynes’ perspective, every litigant\\nappearing before a court seeks an outcome that is favorable,\\nthus making “favorable treatment” a term that essentially\\nreferred to “how litigation works.” She claims that its use\\namounted to a fishing expedition designed to capture unfairly\\n\\n26\\n We cite to the testimony quoted in the indictment and the\\nGrand Jury that was used at trial. We note that there are some\\ntypographical inconsistencies between these sources and in\\nthose instances we have quoted the Grand Jury testimony.\\n\\n\\n\\n\\n 30\\n\\fthe entirety of her conduct in the courtroom. She warns that\\nthis is precisely the type of “open-ended construction” in\\nquestioning that we found unacceptable in Serafini. 167 F.3d\\nat 822.\\n\\n Tynes makes a related argument against her perjury\\nconviction for Count 72. That conviction is based on this\\nexchange.\\n Q. You’ve never taken\\n action on a request?\\n\\n A. No.\\n\\nApp. 257, 5722. She maintains that the word “request” was\\npresented to the jury as a follow-on to the question grounding\\nCount 71, requiring a person to link the term “favorable\\ntreatment” and the word “request” to make sense of it. She\\nargues that the Government took advantage of the ambiguity\\nof “favorable treatment,” forcing the jury to speculate that\\nTynes interpreted “request” as “favorable treatment.” This\\nreliance on “sequential referents” is, from her perspective,\\nexactly what we criticized in Serafini. 167 F.3d at 821. But\\nshe misconstrues our holding.\\n\\n In Serafini, the surrounding questions focused on a\\ndifferent topic. This bolstered appellant’s argument in that\\ncase that the question on which the perjury conviction rested\\nwas fundamentally ambiguous. Id. The appellant said the\\nmultiplicity of topics in surrounding questions caused the jury\\nto speculate improperly on how he understood the question at\\nissue. We said: “The meaning of individual questions and\\nanswers is not determined by ‘lifting a statement . . . out of its\\nimmediate context,’ when it is that very context which fixes\\n\\n\\n\\n\\n 31\\n\\fthe meaning of the question.” Serafini, 167 F.3d at 821\\n(quoting United States v. Tonelli, 577 F.3d 194, 198 (3d Cir.\\n1978)). In the case of Serafini, the context made the\\nconfusing nature of the question apparent. The various topics\\nin surrounding questions created sufficient ambiguity to\\nundermine the conviction. Id.\\n\\n Here, however, even though the terms used by the\\nexaminer changed, we conclude that the line of questioning—\\nincluding both questions that ground Count 71 and 72—have\\nan obvious, consistent focus.\\n\\n Q. In all the years\\n you’ve been [at Traffic\\n Court] have you\\n ever been asked to give\\n favorable treatment on\\n a case to anybody?\\n\\n A. No, not favorable\\n treatment. People basically\\n know me. The lawyers\\n know me. The court\\n officers know me. I have\\n been called a nononsense\\n person because I’m just not\\n that way. I take my\\n position seriously and the\\n cards fall where they\\n may. Most of the time . . .\\n the people in my Court\\n plea bargain. They know\\n that most of the time,\\n\\n\\n\\n\\n 32\\n\\fninety percent of the time,\\nsay 90 percent, I go with\\nthe police officer’s\\nrecommendation. . . .\\n\\nQ. So, in all those years\\nno one has ever asked you\\nto find somebody not\\nguilty--\\n\\nA. No.\\n\\nQ. --or to find a lesser\\nviolation; find a lesser fine;\\nanything along those lines?\\n\\nA. No. I will say to\\npeople go to court, go to\\ntrial and see what\\nhappens. . . .\\n\\nQ. Ward leaders,\\npoliticians has anyone\\ncalled you and said I\\nhave Johnny Jones coming\\nup next week and I\\nwould appreciate it if -- if\\nyou would look\\nfavorably on him when he\\ncomes through? Has\\nanything like that ever\\nhappened?\\n\\n\\n\\n\\n 33\\n\\f A. Throughout the\\n years ward leaders and\\n people have called all the\\n time and asked me\\n questions. The only thing I\\n will say to them is they\\n need to go to court. If you\\n think it’s a problem, they\\n need to hire a lawyer, or\\n make sure you bring all\\n your evidence to court. If\\n it’s something like\\n inspection, make sure you\\n bring your -- papers and\\n things like that. That’s\\n what I would tell them to\\n do. I give advice that\\n way. I don’t know if that’s\\n wrong or not, but I do.\\n\\n Q. You’ve never taken\\n action on a request?\\n\\n A. No.\\n\\nApp. 528-29, 530; 5720-22. This broader context would give\\nany reasonable fact-finder more than enough basis to\\nconclude that the witness knew the point of reference for both\\nthe term “favorable treatment” and “request” was ticket\\nfixing. In fact, Tynes is asking us to do precisely the thing we\\ncriticized in Serafini, to lift a phrase or statement out of its\\ncontext. Serafini, 167 F.3d at 821. Tynes has not persuaded\\nus that the question harbors any fatal ambiguity.\\n\\n\\n\\n\\n 34\\n\\f Tynes next contends that her responses to questions\\ngrounding Count 71 and Count 72 cannot support convictions\\nfor perjury because they were literally true. Of course,\\nperjury arises only from making knowingly false material\\ndeclarations. 18 U.S.C. § 1623. Therefore, a witness who\\nanswers an ambiguous question with a non-responsive answer\\nthat the witness believes is true—even if the answer is\\nmisleading—does not commit perjury. See Bronston, 409\\nU.S. at 361-62; see also United States v. Reilly, 33 F.3d 1396,\\n1416 (3d Cir. 1994).\\n Tynes argues that, because she regarded the question\\nabout favorable treatment as vague, she interpreted it as\\nasking whether she accepted any bribes in exchange for a\\njudgment of not guilty or a reduced punishment. Her\\nresponse of “no” (grounding Count 71) is literally true—she\\nsays—because there is no evidence that she accepted any\\nbribes in return for giving preferential outcomes in the\\nadjudication of some individuals who were cited for breaking\\nthe law. Under this theory, the same argument can also\\nnegate the charges at Count 72 since she says she did not\\naccept any “requests” (bribes) in exchange for preferential\\ntreatment.\\n\\n Although the jury is permitted reasonable inferences\\ndrawn from the record about the witness’ understanding of\\nthe truth or falsity of the answer, it is not (as we noted above)\\npermitted to reach conclusions based merely on speculation\\nor conjecture. See Bronston, 409 U.S. at 359. Tynes’\\nassertion of literal truth is undermined because the trial record\\nsupports no reasonable inference that the Government was\\nasking her about matters outside of the alleged bribes, nor\\n\\n\\n\\n\\n 35\\n\\fdoes it provide any reason why Tynes would interpret the\\nquestion in this way.\\n\\n Finally, Tynes contends that the evidence was not\\nsufficient to support her conviction. However, the jury heard\\nTynes’ personal assistant, Medaglia “Dolly” Warren, testify\\nthat she received from personal assistants of other judges\\nthree to four cards per week requesting consideration. Each\\ncard had the name of a person who was appearing before\\nTynes on that day. She passed these to Tynes’ court officer,\\nwho was present during the proceedings. App. 4593-95.\\nTynes also instructed Warren to give similar cards to the staff\\nof other judges. App. 4598. Warren knew to act discreetly\\nwhen she was transferring the cards. App. 4599. The jury\\nalso heard testimony from those who actually received\\nconsideration from Tynes. For example, Timothy Blong was\\ncited for reckless driving and driving without a license. He\\nadmitted in testimony that he did not have a license when he\\nwas cited. App. 3150. He also testified that he requested\\nconsideration through a Traffic Court employee (Danielle\\nCzerniakowski, who worked as a personal assistant to a\\nTraffic Court judge) with whom he was acquainted. When he\\nappeared in court, he was simply told that his case was\\ndismissed. He did not have to say anything, App. 3159-60.\\nBlong testified he was told his case was dismissed because\\nthe police officer did not appear (App. 3160-61), but the\\ngovernment produced evidence that an officer was present.\\nApp. 3193-96. The Government also showed that Tynes was\\nthe presiding judge in Blong’s case. App. 3193. Richard\\nCarrigan—who admitted in testimony that he drove through a\\nred light—described a similar experience in which, after\\nrequesting favorable treatment through Judge Lowry’s\\npersonal assistant, Kevin O’Donnell, his case was dismissed\\n\\n\\n\\n\\n 36\\n\\fby Judge Tynes without ever having to say a word. App.\\n3178-82.\\n\\n Tynes does not challenge any of this in her appeal.\\nInstead she focuses on the weight of other evidence and\\nperceived gaps in testimony. We conclude that all of this\\nprovides more than a sufficient basis to support a reasonable\\njury’s conclusion that Tynes did “give favorable treatment on\\na case,” and did “take[] action on a request.” App. 528-30.\\n\\n For all of these reasons, we will affirm the judgment of\\nconviction on perjury as to Appellant Tynes.\\n C.\\n\\n Appellant Lowry 27\\n\\n Like Tynes, Appellant Lowry advances arguments of\\nfundamental ambiguity and literal truth. His perjury\\nconviction centered on one question and answer.\\n\\n\\n Q. So if I understand\\n your testimony, you’re\\n saying you don’t give out\\n special favors; is that right?\\n\\n A. No, I treat\\n everybody in that\\n courtroom the same.\\n\\n\\n27\\n Lowry was charged with perjury in Count 69 of the\\nindictment.\\n\\n\\n\\n\\n 37\\n\\fApp. 489. Lowry attacks the Government’s use of the term\\n“special favors” as one with many potential meanings.\\nHowever, as we noted above in our reference to Serafini, we\\nreject arguments that lift individual questions or answers—or\\nindividual phrases embedded in either—from the context of\\nsurrounding questions that help fix their meaning. Serafini,\\n167 F.3d at 821. The larger context for the question asked of\\nLowry is as follows.\\n\\n Q. So if I understand\\n your testimony, you’re\\n saying you don’t give out\\n special favors; is that right?\\n\\n A. Well, I know it\\n appears that way; and it’s\\n hard for me to prove to\\n you . . .\\n\\n Q. I’m just asking,\\n your testimony is you don’t\\n give out special favors, is\\n that right?\\n\\n A. No, I treat\\n everybody in that\\n courtroom the same.\\n\\n Q. You treat everybody\\n fairly?\\n\\n A. I’m a lenient judge.\\n I will admit to that.\\n\\n\\n\\n\\n 38\\n\\f Q. You treat everybody\\n fairly?\\n\\n A. Yes, I do.\\n\\n Q. And these notices\\n that you get from your\\n personal or from other\\n people, they don’t affect\\n you in any way; is that\\n right?\\n\\n A. Virtually no effect\\n at all.\\n\\n\\nApp. 489-90.\\n\\n Lowry’s assertion that the phrase “special favors” is\\nsubject to many interpretations is unconvincing. We note two\\nthings. First, the line of questioning reasonably supports a\\nconclusion that this inquiry referenced conduct associated\\nwith allegations of ticket fixing. Second, Lowry answered as\\nif his understanding of the question was consistent with this\\ninterpretation. He said that he was aware it may “appear” that\\nhe gave special favors. He also defended himself by saying\\nthat such requests did not affect his conduct in the courtroom\\nat all. If—as he says—he understood “special favors” to\\nmean fair treatment, his answer makes no sense.\\n\\n Lowry next claims that, since the question was\\nstructured to elicit a negative response, his answer cannot be\\n\\n\\n\\n\\n 39\\n\\fused as the basis of a perjury charge. Relatedly, he contends\\nthat the question was merely a summation of an answer that\\nhe gave just before this question. In essence he argues that\\nthis was a leading question. We have concluded, in the\\ncontext of a trial, that the propriety of leading questions in\\ndirect examinations is a matter left to the sound discretion of\\nthe trial judge. See United States v. Montgomery, 126 F.2d\\n151, 153 (3d Cir. 1942). We extend the same deference here\\nto the District Court’s decision to admit this portion of the\\nGrand Jury transcript. We do not regard the question as\\nfundamentally unfair or unclear, or something outside the\\nnorm of questions typically employed on direct examination.\\nFor these reasons, we conclude that the District Court did not\\nabuse its discretion here.\\n\\n Alternatively, Lowry argues that—if the term is\\nunderstood to reference fixing tickets—there is no evidence\\nto contradict his response that requests for special favors did\\nnot impact any of his adjudications. We do not agree. The\\nrecord contains the following testimony.\\n\\n Kevin O’Donnell, who was Lowry’s personal\\nassistant, testified about Lowry’s involvement with requesting\\nand giving consideration. He said that Lowry made four to\\nfive requests each month for consideration and that\\nO’Donnell transmitted them to the personal assistants of other\\nTraffic Court judges. App. 1854. Likewise, he said other\\njudges transmitted requests for consideration to Lowry\\nthrough their personal assistants. App. 1812-13. Appellant\\nHird and various politicians also made requests of Lowry for\\nconsideration. App. 1827-28, 1832-33. O’Donnell said he\\nwould give the requests to Lowry on the day scheduled for\\nhearing on the citation. App. 1818-19. The requests were for\\n\\n\\n\\n\\n 40\\n\\fpreferential treatment in the adjudication of particular\\ncitations: typically the requests were for “removing points”\\nand obtaining a “not guilty” judgment. App. 1819.\\nO’Donnell said he sometimes had to signal Lowry in the\\ncourtroom to remind him that a particular case was supposed\\nto receive consideration. App. 1822-23. He testified from\\nhis own observation that Lowry typically honored requests\\nfor consideration. App. 1829. He also declared if Lowry\\nclaimed he never gave consideration or asked it of others, this\\nwould not be truthful. App. 1813. The same assistant\\ntestified that if Lowry testified that he ignored requests for\\nconsideration, or that he never honored requests for\\nconsideration, that testimony would not be true. App. 1855.\\nThe Government also asked: “If [Lowry] claimed that . . .\\nconsideration requests had no impact when he disposed of\\ncases, would that be true?” The assistant responded,\\n“probably not.” Id.\\n\\n Another witness, Walt Smaczylo, employed as a court\\nofficer in the Traffic Court, provided an example of how\\n“consideration” worked in the courtroom.\\n\\n When someone comes in,\\n for example, for a reckless\\n driving ticket and that\\n judge normally comes\\n down pretty hard and finds\\n that defendant guilty and\\n then the same type cases\\n come in and you see a\\n defendant walk out either\\n not guilty or a significantly\\n reduced charge.\\n\\n\\n\\n\\n 41\\n\\fApp. 1912. The Government asked Smaczylo if he saw\\nLowry preside over such instances, and he answered: “That’s\\ncorrect, yes.” Id. Smaczylo testified that requests for\\nconsideration were written on small note cards or “sticky”\\nnotes and that he saw Lowry in possession of these cards and\\nnotes. App. 1914. He also provided a generalized example\\nof consideration, based on his observation and understanding,\\nin which a reckless driving citation would be reduced to\\ncareless driving. In such instances, he indicated that a $300\\nto $400 fine would be cut in half. He said: “So, that money\\nwas not collected, obviously, by the state. If that ticket was\\nfixed then I saw it as stealing.” App. 1919. Smaczylo was\\nasked: “[I]f Judge Lowry testified at the [G]rand [J]ury he\\ndidn’t give consideration would that be a truth or would that\\nbe a lie?” He responded: “That would not be the truth.”\\nApp. 1921.\\n\\n All of this testimony provides more than a sufficient\\nbasis to support a reasonable jury’s conclusion that Lowry\\nwas not truthful when he responded to the Government’s\\nquestion about special favors. 28\\n\\n28\\n Lowry points to the cross-examination of both witnesses in\\nwhich they seem to equivocate on some of their observations\\nand responses to the Government. For instance O’Donnell\\nstated his view that giving consideration was no different\\nfrom the leniency that Lowry extended to every other person\\nwho pleaded not guilty and appeared at the hearing.\\nHowever, we do not weigh the credibility of evidence in the\\nrecord. We only judge whether there is sufficient evidence in\\nthe record to support a reasonable fact-finder’s determination\\nthat the record supported conviction of Lowry on a charge of\\n\\n\\n\\n\\n 42\\n\\f Finally, Lowry argues that the Government’s question\\nsought a dispositive response from him on the charges of\\nconspiracy and fraud. He says an affirmative answer to\\nwhether he gave “special favors” to certain individuals would\\nhave been enough to convict him of conspiracy and fraud.\\nThus, he maintains that his acquittal on charges of mail fraud,\\nwire fraud, and conspiracy is res judicata as to the perjury\\ncharges that are based on his answer. He said he did not\\ncommit fraud and the jury agreed with him. Therefore, he\\nsays, he did not perjure himself. However, even if we\\naccepted Lowry’s characterization of the question, we reject\\nthis argument.\\n\\n First, a jury’s determination that Lowry’s ticket-fixing\\nconduct did not constitute wire fraud, mail fraud, and\\nconspiracy does not preclude its determination that he lied\\nabout this conduct before the Grand Jury. Moreover, as the\\nSupreme Court has articulated, a verdict on one count that\\nseems to be at odds with another “shows that either in the\\nacquittal or the conviction the jury did not speak their real\\nconclusions, but that does not show that they were not\\nconvinced of the defendant’s guilt.” United States v. Powell,\\n469 U.S. 57, 63 (1984) (quoting Dunn v. United States, 284\\nU.S. 390, 393 (1932)). It is impossible to know in such cases\\nwhether the verdicts were an exercise of lenity by the jury or\\noutright error.\\n\\n Nonetheless, as the Powell Court noted, any\\nassessment of the jury’s rationale for its verdicts “would be\\n\\n\\nperjury. See United States v. Richardson, 658 F.3d 333, 337\\n(3d Cir. 2011).\\n\\n\\n\\n\\n 43\\n\\fbased either on pure speculation or would require inquiries\\ninto the jury’s deliberations that courts generally will not\\nundertake.” Id. at 58. So, even if Lowry was correct that the\\nacquittal is relevant to his response to the question grounding\\nhis perjury conviction, we are not convinced that his perjury\\nconviction is unfounded. Given the substantial body of\\nevidence presented to the jury, nothing here demands that we\\nabandon the deference we traditionally give to the collective\\njudgment of the jury. For all these reasons, we will affirm the\\njury’s verdict as to Lowry.\\n\\n D.\\n\\n Appellant Mulgrew 29\\n\\n Mulgrew does not argue that the question asked at the\\nGrand Jury was ambiguous, he simply maintains that his\\nstatement was truthful. 30 The questions and answers\\ngrounding his perjury conviction are as follows.\\n\\n Q. How about your\\n personal, has your personal\\n received any calls like that\\n from other judges, other\\n ward leaders that she’s\\n conveyed to you, saying\\n\\n29\\n Mulgrew was charged with perjury in Count 70 of the\\nindictment.\\n30\\n Mulgrew’s claims are reviewed for plain error because he\\ndid not make the same argument before the District Court.\\nUnited States v. Syme, 276 F.3d 131, 148 (3d Cir. 2002).\\n\\n\\n\\n\\n 44\\n\\f so-and-so has called about\\n this case?\\n\\n A. If she did, she didn’t\\n convey them to me.\\n\\n\\nApp. 432-33 (emphasis added). Shortly after this, the\\nfollowing exchange occurred:\\n\\n Q. Let me make sure as\\n well that if I got your\\n testimony correct [sic].\\n You’re saying that if other\\n people, whether they be\\n political leaders, friends\\n and family, anybody is\\n approaching your personal\\n and asking her specifically\\n to look out for a case, see\\n what she can do in a case,\\n give preferential treatment,\\n however you want to\\n phrase it, that she is not\\n relaying any of that\\n information on to you; is\\n that correct?\\n\\n A. No, she isn’t.\\n\\nApp. 438. As to the first exchange, Mulgrew claims that the\\nGovernment’s use of the word “call” referred exclusively to\\ntelephone calls. This mattered to him, he says, because others\\n\\n\\n\\n\\n 45\\n\\fhad testified that personal assistants of other Traffic Court\\njudges would give index cards to his personal assistant in his\\nchambers or robing room containing names of some\\nindividuals whose tickets were listed for hearing. Mulgrew\\nclaims that there is no evidence that he ever received any\\nphone calls asking that he act extrajudicially to give well-\\nconnected individuals preferential treatment. The implication\\nis that, had the Government asked him about receiving index\\ncards with such requests, his answer would have been\\ncompletely different.\\n As with Tynes and Lowry, our review of claims of\\nliteral truth drives us to examine the context of the question.\\n\\n Q. How about other\\n judges, have other judges\\n ever approached you or\\n called to you or get a\\n message to you either\\n themselves or through their\\n personals saying that\\n someone is going to be on\\n your list next week or next\\n Monday and can you could\\n some special way towards\\n the case?\\n\\n A. No, they haven’t.\\n\\n Q. Never?\\n\\n A. No.\\n\\n\\n\\n\\n 46\\n\\fQ. How about your\\npersonal, has your personal\\nreceived any calls like that\\nfrom other judges, other\\nward leaders that she’s\\nconveyed to you saying so\\nand so has called about this\\ncase?\\n\\nA. If she did, she didn’t\\nconvey them to me.\\n\\nQ. And your personal\\nis who?\\n\\nA. Gloria McNasby.\\n\\nQ. Have you ever seen\\non traffic court files --You\\nactually get a file when\\nsomeone’s case is called?\\n\\nA. Right.\\n\\nQ. So the case is called\\nand you get a file presented\\nto you; is that right?\\n\\nA. uh-huh.\\n\\nQ. Have you ever seen\\nany index cards or\\nnotations on the file\\n\\n\\n\\n\\n 47\\n\\f indicating that a person has\\n called or taken some\\n special interest in this\\n case?\\n\\n A. Nope.\\n\\nApp. 432-33 (emphasis added). The transcript makes it\\nobvious that Mulgrew’s singular reliance on the reference to a\\n“call” ignores the thrust of the Government’s line of\\nquestions. The questions focus on the substance of the\\ncommunications between Mulgrew’s personal assistant and\\nhimself, rather than the mode of those communications.\\n\\n Mulgrew also claims that he responded truthfully to\\nthe second question.\\n\\n Q. Let me make sure as\\n well that if I got your\\n testimony correct [sic].\\n You’re saying that if other\\n people whether they be\\n political leaders, friends\\n and family, anybody is\\n approaching your personal\\n and asking her specifically\\n to look out for a case, see\\n what she can do in a case,\\n give preferential treatment,\\n however you want to\\n phrase it, that she is not\\n relaying any of that\\n\\n\\n\\n\\n 48\\n\\f information on to you; is\\n that correct?\\n\\n A. No, she isn’t.\\n\\n Q. Wouldn’t you want\\n to know it?\\n\\n A. No, I don’t want to\\n know. Then I never have to\\n worry about what I do in\\n the courtroom.\\n\\nApp. 437-38 (emphasis added). Apparently focusing on the\\nwords “see what she can do,” he says that he answered\\ntruthfully by responding that his personal assistant did not tell\\nhim that people were approaching her and asking her to give\\nthem preferential treatment. But, as with the first question,\\nMulgrew cherry-picks a small part of the question out of\\ncontext, distorting it. The full text and follow up question\\nshow that the thrust of the inquiry was whether Mulgrew’s\\npersonal assistant was informing him of the names of those\\nrequesting preferential treatment from him. And Mulgrew’s\\nresponse to the follow-up question —saying that he did not\\nwant to know so that he did not have to worry about what he\\ndid in the courtroom—is consistent with one who understood\\nthis. App. 438.\\n\\n We conclude that, ultimately, the evidence is sufficient\\nfor a reasonable jury to conclude Mulgrew understood that\\nboth of these questions were focused on whether his personal\\nassistant informed him of requests for him to give preferential\\ntreatment, and that he answered in the negative to both.\\n\\n\\n\\n\\n 49\\n\\f Mulgrew alternatively asserts that the District Court\\nerred by refusing to admit additional testimony from the\\nGrand Jury that he claims is relevant to his perjury\\nconviction. 31 After the Government introduced Mulgrew’s\\nGrand Jury testimony, Mulgrew sought the admission of other\\nportions of his testimony. But the District Court sustained the\\nGovernment’s hearsay objection. The portion of the\\ntranscript supporting the perjury conviction is as follows:\\n\\n Q. [W]hether you have\\n ever been asked to provide,\\n what I’ll call, favorable\\n treatment for people in\\n traffic court or however\\n you define that, whether it\\n would be special handling,\\n keep an eye out for a\\n ticket, do me a favor.\\n Have you ever been asked\\n to provide any type of\\n treatment like that for\\n people in traffic court?\\n\\n A. People have asked\\n me for consideration, but I\\n give consideration to\\n everybody that comes in\\n my courtroom[,] so it\\n\\n31\\n We review the District Court’s ruling on the admissibility\\nof evidence for abuse of discretion. United States v. Green,\\n617 F.3d 233, 239 (3d Cir. 2010).\\n\\n\\n\\n\\n 50\\n\\f doesn’t make a difference\\n to me.\\n\\n\\nApp. 422-23. The basis for the Government’s hearsay\\nobjection to this portion of the testimony was that it raised an\\nout-of-court statement not offered by a party opponent.\\n\\n Mulgrew first contends that the District Court erred by\\nruling that this was hearsay because it was not offered for the\\ntruth of the matter asserted. He says that the testimony was\\ninstead offered to show his state of mind later in his\\ntestimony. See United States v. Hoffecker, 530 F.3d 137,\\n191-92 (3d Cir. 2008). However, we conclude that it was not\\nan abuse of discretion for the District Court to sustain the\\nGovernment’s hearsay objection. It was reasonable for the\\nDistrict Court to conclude here that his response relied on\\nout-of-court statements offered to assert his innocence since\\nhis response conveys a declaration that he treated no person\\ndifferent from another.\\n\\n Mulgrew also argues that this portion of the transcript\\nis admissible under Federal Rule of Evidence 106: “[i]f a\\nparty introduces all or part of a writing or recorded statement,\\nan adverse party may require the introduction, at that time, of\\nany other part—or any other writing or recorded statement—\\nthat in fairness ought to be considered at the same time.”\\nMulgrew maintains that this question and answer provides\\ncontext showing that he did not commit perjury. He also\\nmaintains that the “doctrine of completeness” applies here:\\nfairness demanded the admission of the statements. See\\n\\n\\n\\n\\n 51\\n\\fUnited States v. Soures, 736 F.2d 87, 91 (3d Cir. 1984). 32 We\\nare not convinced.\\n\\n The excerpt at issue occurs many pages before the\\ntestimony regarded as perjurious. It is unrelated in the overall\\nsequence of questions and to the answers grounding his\\nconviction. Moreover, as the intervening pages suggest, it\\nwas separated by the passage of time during questioning. We\\nalso fail to see how Mulgrew’s equivocation over the term\\n“consideration” gives helpful context to his later denial of\\nreceiving requests for consideration. For these reasons, we\\nconclude the District Court did not abuse its discretion by\\nsustaining the Government’s hearsay objection.\\n\\n IV.\\n\\n Appellant Singletary 33\\n\\n\\n32\\n “Under this doctrine of completeness, a second writing may\\nbe required to be read if it is necessary to (1) explain the\\nadmitted portion, (2) place the admitted portion in context, (3)\\navoid misleading the trier of fact, or (4) insure a fair and\\nimpartial understanding.” Soures, 736 F.2d at 91.\\n33\\n Appellant Singletary was charged with making false\\nstatements in Counts 73 and 74 of the indictment. He states\\nin his brief that he ‘joins all arguments on behalf of co-\\nappellants pursuant to Federal Rules of Appellate Procedure\\n28(i).” Singletary Br. 19. To the extent that he joins the\\nargument of prejudice resulting from the trial on the fraud and\\nconspiracy charges, we already have determined that the\\nindictment was proper and no prejudice resulted from\\n\\n\\n\\n\\n 52\\n\\f During the investigation of the Traffic Court by the\\nFederal Bureau of Investigation, Appellant Singletary was\\namong those interviewed. The jury acquitted Singletary of all\\ncounts of wire fraud, mail fraud, and conspiracy. It found\\nhim guilty of false statements made to the Federal Bureau of\\nInvestigation. At sentencing, over Singletary’s objection, the\\nDistrict Court sentenced Singletary using the Guideline on\\nobstruction.\\n\\n The Government agrees that the single count on which\\nhe was convicted does not contain all of the elements of\\nobstruction. U.S.S.G. § 2J1.2. For this reason, the\\nGovernment agrees with Singletary that he is entitled to a\\nremand for resentencing. Accordingly, we will vacate the\\njudgment of sentence as to Singletary and remand to the\\nDistrict Court for resentencing.\\n\\n V.\\n\\n For all of these reasons, we will vacate the judgment of\\nsentence of the District Court with regard to Appellant\\nSingletary and remand for resentencing. We will affirm the\\njudgments of the District Court as to Appellants Alfano, Hird,\\nLowry, Mulgrew and Tynes.\\n\\n\\n\\nbringing these charges to trial. As for the challenges to\\nperjury in Counts 72 and 74, we note that Singletary was\\ncharged with a different crime: false statements in a federal\\ninvestigation pursuant to 18 U.S.C. § 1001. In addition, the\\nchallenges to all of such charges are inherently fact-intensive.\\nAs he did not provide a factual basis for such a challenge, we\\nregard the issue to be waived.\\n\\n\\n\\n\\n 53\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360293/\", \"author_raw\": \"NYGAARD, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"GREENAWAY"},"judge2":{"kind":"string","value":"NYGAARD"},"judge3":{"kind":"string","value":"FISHER"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583040/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America v. William HIRD, Appellant at No. 14-4754 United States of America v. Thomasine Tynes, Appellant at No. 14-4804 United States of America v. Robert Mulgrew, Appellant at No. 14-4812 United States of America v. Michael Lowry, Appellant at No. 15-1344 United States of America v. Willie Singletary, Appellant at No. 15-1739 United States of America v. Henry P. Alfano, AKA Ed, AKA Eddie, Henry P. Alfano, Appellant at No. 15-3765\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-18\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n\n __________\n\nNos. 14-4754, 14-4804, 14-4812, 15-1344, 15-1739, 15-3765\n __________\n\n UNITED STATES OF AMERICA\n v.\n WILLIAM HIRD,\n Appellant at No. 14-4754\n __________\n\n UNITED STATES OF AMERICA\n v.\n THOMASINE TYNES,\n Appellant at No. 14-4804\n __________\n\n UNITED STATES OF AMERICA\n v.\n ROBERT MULGREW,\n Appellant at No. 14-4812\n __________\n\n UNITED STATES OF AMERICA\n v.\n MICHAEL LOWRY,\n Appellant at No. 15-1344\n\f __________\n\n UNITED STATES OF AMERICA\n v.\n WILLIE SINGLETARY,\n Appellant at No. 15-1739\n ___________\n\n UNITED STATES OF AMERICA\n v.\n HENRY P. ALFANO,\n aka Ed, aka Eddie,\n\n Henry P. Alfano,\n Appellant at No. 15-3765\n __________\n\n On Appeal from the United States District Court\n for the Eastern District of Pennsylvania\n\n (District Court Criminal Nos. 2-13-cr-00039-007,\n2-13-cr-00039-005, 2-13-cr-00039-003, 2-13-cr-00039-002,\n 2-13-cr-00039-004, 2-13-cr-00039-008)\n District Judge: Honorable Robert F. Kelly\n District Judge: Honorable Lawrence F. Stengel\n\n Argued October 23, 2017\n\n BEFORE: GREENAWAY, JR., NYGAARD,\n and FISHER, Circuit Judges\n\n\n (Opinion Filed: January 18, 2019)\n\n\n\n\n 2\n\fAngela Halim\nHalim Drossner\n1528 Walnut Street, Suite 1501\nPhiladelphia, PA 19102\n\nGregory J. Pagano\n1315 Walnut Street, 12th Floor\nPhiladelphia, PA 19107\n Counsel for Appellant in No. 14-4754\n\nLisa A. Mathewson [Argued]\n123 South Broad Street, Suite 810\nPhiladelphia, PA 19109\n Counsel for Appellant No. 14-4804\n\nPeter Goldberger [Argued]\nPamela A. Wilk\n50 Rittenhouse Place\nArdmore, PA 19003\n Counsel for Appellant in No. 14-4812\n\nMichael J. Engle [Argued]\nStradley Ronon Stevens & Young\n2005 Market Street, Suite 2600\nPhiladelphia, PA 19103\n\nMeredith A. Lowry\n1528 Walnut Street, Suite 1501\nPhiladelphia, PA 19102\n Counsel for Appellant in No. 15-1344\n\n\n\n\n 3\n\fWilliam J. Brennan\n1600 Locust Street\nPhiladelphia, PA 19103\n Counsel for Appellant in No. 15-1739\n\nMark E. Cedrone [Argued]\nCedrone & Mancano\n123 South Broad Street, Suite 810\nPhiladelphia, PA 19109\n Counsel for Appellant in No. 15-3765\n\n\nLouis D. Lappen\nDenise S. Wolf\nAnthony J. Wzorek\nRobert A. Zauzmer [Argued]\nOffice of United States Attorney\n615 Chestnut Street, Suite 1250\nPhiladelphia, PA 19106\n Counsel for Appellee\n\n\n\n\n __________\n\n OPINION OF THE COURT\n __________\n\nNYGAARD, Circuit Judge.\n\n I.\n\n\n\n\n 4\n\f In the run-up to a joint trial on a 77-count indictment\nthat charged Appellants with operating a ticket-fixing scheme\nin the Philadelphia Traffic Court, the District Court denied a\nmotion, under Federal Rule of Criminal Procedure\n12(b)(3)(B)(v), to dismiss charges of conspiracy (18 U.S.C. §\n1349), mail fraud (18 U.S.C. § 1341), and wire fraud (18\nU.S.C. § 1343). Appellants Henry Alfano (private citizen)\nand William Hird (Traffic Court administrator) subsequently\npleaded guilty to all counts against them. But now they\nappeal the District Court’s decision on this motion,\nquestioning whether the indictment properly alleged offenses\nof mail fraud and wire fraud. 1\n\n Appellants Michael Lowry, Robert Mulgrew, and\nThomasine Tynes (Traffic Court judges) proceeded to a joint\ntrial and were acquitted on the fraud and conspiracy counts,\nbut they were convicted of perjury for statements they made\nbefore the Grand Jury. Lowry, Mulgrew, and Tynes dispute\nthe sufficiency of the evidence on which they were convicted\nby arguing that the prosecutor’s questions were vague, and\nthat their answers were literally true. Lowry and Mulgrew\ncontend alternatively that the jury was prejudiced by evidence\npresented at trial on the fraud and conspiracy counts.\nMulgrew also complains that the District Court erred by\nruling that certain evidence was inadmissible.\n\n At the same trial, the jury convicted Willie Singletary\n(Traffic Court judge) of making false statements during the\ninvestigation. He claims the District Court made errors when\n\n\n1\n Alfano and Hird preserved their right to appeal. See infra\nsubsection I.C.\n\n\n\n\n 5\n\fit sentenced him. 2 The Government concurs with\nSingletary’s challenge to his sentence.\n\n We have consolidated these appeals for efficiency and\nhave grouped the arguments—to the extent that it is\npossible—by common issues. We agree with Singletary and\nthe Government that he should be resentenced. We will\nreverse the judgment and remand his cause to the District\nCourt for this purpose. We are not persuaded by the rest of\nAppellants’ arguments and will affirm their judgments of\nconviction. 3\n\n II.\n\n Appellants Alfano 4 and Hird 5\n\n\n\n2\n Singletary also attempted to join additional arguments raised\nby other appellants, but for reasons we explain later, see infra\nnote 33, we focus only on his challenge to his sentence.\n3\n The District Court had jurisdiction pursuant to 18 U.S.C. §\n3231. We have jurisdiction to review these claims under 28\nU.S.C.§ 1291 and 18 U.S.C. § 3742(a).\n4\n Appellant Alfano pleaded guilty to Conspiracy (Count 1),\nWire Fraud (Counts 2, 3, 4, 5, 6, 7) and Mail Fraud (Counts\n51, 52, 53, 54, 55, 56).\n5\n Appellant Hird pleaded guilty to Conspiracy (Count 1),\nWire Fraud (Counts 3, 4, 5, 6, 16, 17, 18, 19, 20, 22, 23) and\nMail Fraud (Counts 58, 59, 60).\n\n\n\n\n 6\n\f A.\n\n We begin with a brief look at the indictment’s\ndescription of the Traffic Court and its operations to\ncontextualize the arguments made by Alfano and Hird. The\nPhiladelphia Traffic Court was part of the First Judicial\nDistrict of Pennsylvania. App. 186 (Indictment ¶ 2). 6 It\nadjudicated violations of the Pennsylvania Motor Vehicle\nCode occurring in the City of Philadelphia, no matter whether\nthe Philadelphia Police or the Pennsylvania State Police\nissued the tickets. App. 187 (Indictment ¶5). When a person\nwas cited for a violation he or she was required—within ten\ndays—to enter a plea of guilty or not guilty. If the person\nfailed to plead, the Traffic Court issued a notice that his or her\nlicense was being suspended. App. 189 (Indictment ¶ 12). A\nperson who pleaded not guilty proceeded to a hearing with a\nTraffic Court judge presiding. App. 187 (Indictment ¶ 6).\n\n A guilty plea, or a determination of guilt by a Traffic\nCourt judge after a hearing, resulted in a judgment ordering\npayment of statutory fines and court costs. App. 188\n(Indictment ¶ 8). 7 The Traffic Court was responsible for\ncollecting these fines (sending them to the City and\n\n\n6\n Philadelphia Traffic Court was abolished and its jurisdiction\nwas transferred to the Municipal Court in 2013 by an Act of\nthe Pennsylvania General Assembly. 42 Pa.Con.Stat.\n§1121(a)(2) (2013). The court is now known as the Traffic\nDivision of the Municipal Court.\n7\n Although other penalties are prescribed by the Pennsylvania\nMotor Vehicle Code (App. 188), this appeal is limited to the\nmonetary fines and costs. App. 355.\n\n\n\n\n 7\n\fCommonwealth) and costs (which it distributed to several\npre-designated funds). App. 188-89 (Indictment ¶ 9).\nFinally, it reported the disposition of each adjudication to the\nPennsylvania Department of Transportation (PennDOT).\nApp. 189 (Indictment ¶ 11).\n\n B.\n\n The indictment charged that, at the behest of Alfano\n(App. 193 (Indictment ¶ 25)) and others, the Traffic Court\nadministrator and judges operated an “extra-judicial system,\nnot sanctioned by the Pennsylvania court system” that\nignored court procedure and gave preferential treatment\n(“consideration”) to select individuals with connections to the\ncourt who had been cited for motor vehicle violations. App.\n196 (Indictment ¶ 31). The special treatment included:\n\n (1) dismissing tickets outright; (2)\n finding the ticketholder not guilty\n after a “show” hearing; (3)\n adjudicating the ticket in a\n manner to reduce fines and avoid\n assignment of points to a driver’s\n record; and (4) obtaining\n continuances of trial dates to\n “judge-shop,” that is find a Traffic\n Court judge who would accede to\n a request for preferential\n treatment.\n\nApp. 195-196 (Indictment ¶ 30). All of this was “not\navailable to the rest of the citizenry.” App. 196 (Indictment ¶\n32). It also alleged that Appellants cooperated with each\n\n\n\n\n 8\n\fother to fulfill requests they and their staffs received. App.\n194-95 (Indictment ¶ 27). Finally, it charged that “[i]n\nacceding to requests for ‘consideration,’ defendants were\ndepriving the City of Philadelphia and the Commonwealth of\nPennsylvania of money which would have been properly due\nas fines and costs.” App. 197 (Indictment ¶ 38). 8\n After extending consideration to favored individuals,\nTraffic Court judges would report the final adjudication to\n“various authorities, including PennDOT, as if there had been\na fair and open review of the circumstances.” App. 197\n(Indictment ¶ 34). Appellant Hird provided a printout to\nAppellant Alfano showing citations that had been “dismissed\nor otherwise disposed of.” App. 198-99 (Indictment ¶ 42).\nSuch “receipts” were not routinely issued in cases.\n\n C.\n\n Hird and Alfano pleaded guilty to all the charges\nagainst them in the indictment. But, in their plea agreement\nthey reserved the right to appeal “whether the Indictment\n\n\n8\n An example of the many allegations involving Alfano and\nHird is: A.S. requested assistance from Appellant Alfano and\nAppellant Hird on Citation Number P1J0PK568L4 on or\naround February 17, 2010. The citation charged A.S. with\ndriving a tractor-trailer from which snow and ice fell, striking\nvehicles on Interstate 95. The violation carried a $300 fine\nand costs of $142. Appellant Hird promised that he would\n“stop all action” on the citation and instructed A.S. to ignore\nthe ticket. Although A.S. did not appear at the hearing, the\nTraffic Court judge (who is not an appellant here) ruled A.S.\nnot guilty. App. 210-12 (Indictment ¶¶ 25-34).\n\n\n\n\n 9\n\fsufficiently alleged that the defendants engaged in a scheme\nto defraud the Commonwealth of Pennsylvania and the City\nof Philadelphia of money in costs and fees.” App. 355 (Plea\nAgreement ¶ 9(b)(4)). So they now appeal the District\nCourt’s order denying the motion to dismiss, asserting that\nthe indictment failed to allege violations of mail fraud and\nwire fraud.\n\n “To be sufficient, an indictment must allege that the\ndefendant performed acts which, if proven, constitute a\nviolation of the law that he is charged with violating.” United\nStates v. Small, 793 F.3d 350, 352 (3d Cir. 2015). We\nassume in our review that the allegations in the indictment are\ntrue. United States v. Hedaithy, 392 F.3d 580, 583 (3d Cir.\n2004). “The question of whether the . . . indictments alleged\nfacts that are within the ambit of the mail fraud statute is a\nquestion of statutory interpretation subject to plenary review.”\nId. at 590 n.10.\n\n To indict on mail or wire fraud, the Government must\nallege that defendants “devised or intend[ed] to devise any\nscheme or artifice to defraud, or for obtaining money or\nproperty by means of false or fraudulent pretenses,\nrepresentations, or promises” and used mail or wire to effect\nthe scheme. 18 U.S.C. §§ 1341, 1343. Alfano and Hird claim\nthe Government failed to allege that the scheme to commit\nwire and mail fraud had an objective of “obtaining money or\nproperty.” 9\n\n9\n In the context of mail fraud (§ 1341) and wire fraud (§1343)\nthe term “money” has the same meaning. The same is true\nfor the term “property.” Carpenter v. United States, 484 U.S.\n19, 25 n. 6 (1987).\n\n\n\n\n 10\n\f The District Court ruled that the indictment\nsufficiently alleged that the scheme “involved defrauding the\nCommonwealth and the City of money.” App. 20. It noted,\namong others, allegations that:\n\n The conspirators used the\n Philadelphia Traffic Court\n (“Traffic Court”) to give\n preferential treatment to certain\n ticketholders, most commonly by\n “fixing” tickets for those with\n whom they were politically and\n socially connected. By doing so,\n the conspirators defrauded the\n Commonwealth of Pennsylvania\n and the City of Philadelphia of\n funds to which the\n Commonwealth and the City were\n entitled.\n\nId. at 18; see also id. at 185 (Indictment ¶ 1). Similarly, it\nreferred to the following.\n\n In acceding to requests for\n “consideration,” defendants were\n depriving the City of Philadelphia\n and the Commonwealth of\n Pennsylvania of money which\n would have been properly due as\n fines and costs.\n\n\n\n\n 11\n\fId. at 9; see also id. at 197 (quoting Indictment ¶ 38).\nHighlighting the references to “funds” and “money,” and that\nthe monetary amounts of the fines are specifically pleaded,\nthe District Court cited to a case from the Court of Appeals\nfor the Eighth Circuit which concluded succinctly that\n“[m]oney is money.” United States v. Sullivan, No. 2:13-cr-\n00039, 2013 WL 3305217, at *7 (E.D. Pa. July 1, 2013)\n(quoting United States v. Granberry, 908 F.2d 278, 280 (8th\nCir. 1990)). The District Court was satisfied that the\nindictment alleged enough.\n\n “Money, of course, is a form of property.” Reiter v.\nSonotone Corp., 442 U.S. 330, 338 (1979). But Alfano and\nHird argue that the mere mention of money in an indictment\nis not enough. They point to a string of Supreme Court and\nCourt of Appeals decisions analyzing Section 1341 and\nSection 1343 which reinforce the point that crimes of mail\nfraud and wire fraud are “limited in scope to the protection of\nproperty rights.” McNally v. United States, 483 U.S. 350, 360\n(1987). 10 The Supreme Court said that “[a]ny benefit which\nthe government derives from the [mail fraud] statute must be\nlimited to the Government’s interests as a property holder.”\nId. at 359 n.8 (emphasis added). Appellants are convinced\nthat money in the form of traffic fines and costs cannot be\nregarded as the Government’s “property” for purposes of mail\nor wire fraud, and they identify two decisions as particularly\nsupportive of their position: Cleveland v. United States, 531\n\n10\n The District Court cited to a number of cases that came\nafter McNally: Carpenter v. United States, 484 U.S. 19\n(1987); Cleveland v. United States, 531 U.S. 12 (2000);\nPasquantino v. United States, 544 U.S. 349 (2005).\n\n\n\n\n 12\n\fU.S. 12 (2000); and United States v. Henry¸ 29 F.3d 112 (3d\nCir. 1994).\n\n The Court in Cleveland examined the mail fraud\nconvictions of individuals who received a state video poker\nlicense by submitting a license application that withheld\nimportant information. Cleveland, 531 U.S. 12. 11 The Court\nnoted that the video poker licenses were part of a state\nprogram that was “purely regulatory.” Id. at 22 (citation\nomitted). 12 It ruled that licenses are a “paradigmatic\nexercise[] of the States’ traditional police powers.” Id. at 23.\nThe Court went on to say that the state’s regulatory powers\ninvolving “intangible rights of allocation, exclusion, and\ncontrol” (which are embodied in a license) are not interests\nthat traditionally have been recognized as property. Id.\nTherefore, even though appellants may have obtained the\nlicense through deception, this was not mail fraud because the\nlicense—at least while still in the hands of the state—was not\n\n\n\n11\n The licenses were part of a regulatory scheme that had as\nits purpose to increase public confidence in the honesty of\ngaming activities that are free of criminal involvement.\nCleveland, 531 U.S. at 20–21 (quoting La. Rev. Stat. Ann. §\n27:306(A)(1) (2000) (repealed 2012)).\n12\n The Court rebuffed the Government’s attempts to analogize\nlicenses to other forms of property like patents and franchise\nrights. As for likening licenses to franchise rights, the Court\nobserved that the Government did not enter the video poker\nbusiness, but rather decided to “permit, regulate, and tax\nprivate operators of the games.” Id. at 24.\n\n\n\n\n 13\n\fproperty. Id. at 26-27. It was a purely administrative tool\nused to achieve regulatory objectives. Id. at 21.\n\n The state responded to the Court’s concerns by\nagreeing that the licenses served a regulatory purpose, but it\ndirected attention to the revenue it received from fees\ncollected for license applications and renewals, as well as\ndevice fees. Id. at 21-22. It argued that this revenue is a\nproperty interest. Id. The Court was not convinced:\n\n Tellingly, as to the character of\n Louisiana’s stake in its video\n poker licenses, the Government\n nowhere alleges that Cleveland\n defrauded the State of any money\n to which the State was entitled by\n law. Indeed, there is no dispute\n that TSG paid the State of\n Louisiana its proper share of\n revenue, which totaled more than\n $1.2 million, between 1993 and\n 1995. If Cleveland defrauded the\n State of “property,” the nature of\n that property cannot be economic.\n\nId. at 22 (emphasis added). It concluded that “[e]ven when\ntied to an expected stream of revenue, the State’s right of\ncontrol does not create a property interest any more than a\nlaw licensing liquor sales in a State that levies a sales tax on\n\n\n\n\n 14\n\fliquor.” Id. at 23. 13 The money collected from application\nand processing fees was an integral part of the state\nregulatory program and it did not create any property interest.\nSee id.\n\n The purpose of the Pennsylvania Motor Vehicle Code\nis to “promote the safety of persons and property within the\nstate.” Mauer v. Boardman, 7 A.2d 466, 472 (Pa. 1939).\nMoreover, issuing traffic tickets is a crucial element in the\nenforcement of the Motor Vehicle Code: it is a quintessential\nexercise of state police power. Alfano and Hird conclude,\nmuch like Cleveland, that no property interest could arise\nfrom revenue generated from the state’s exercise of its police\npower in the form of a traffic-ticket fine. They see nothing\nbut a regulatory program here. But this ignores crucial\naspects of the case before us that make it different.\n\n Simply stated, fees charged to obtain a license cannot\nbe equated with fines and costs that result from a traffic\nticket. The license fee was imposed, adjusted, and collected\nsolely by the state’s exercise of its regulatory authority. In\ncontrast, here the state’s police power is exercised when a\ncitation is issued, but this ticket merely establishes the\nsummary violation with which the person is charged. Once a\nperson has been charged, it is judicial power (not the state’s\npolice power) that is exercised to determine whether the\n\n\n\n\n13\n Cleveland also held that Government-issued licenses have\nno intrinsic economic worth before they are given to\napplicants. Id. at 23.\n\n\n\n\n 15\n\fperson is guilty and, if guilty, to impose the fine and costs. 14\nThese fines and costs, although specified by the Motor\nVehicle Code, cannot be cabined as a product of the state’s\nregulatory authority. They are part and parcel of the\njudgment of the court. With this in mind, it is significant that\nthe indictment does not focus on how the citations were\nissued (which would implicate police power), but rather\nalleges that the judicial process was rigged to produce only\njudgments that imposed lower fines—or most often—no fines\nand costs at all. 15\n\n But this raises a further question: can a criminal\njudgment held by the government ever be “property?” The\nCourt in Cleveland offered a critique in its analysis of a\n\n14\n The Traffic Court was not an administrative tribunal.\nRather, it was part of the First Judicial District of\nPennsylvania. App. 186 (Indictment ¶ 2). See also supra\nnote 6 and accompanying text.\n15\n On this point, it is noteworthy that the Supreme Court also\nsaid the following: “We resist . . . [any invitation] to approve\na sweeping expansion of federal criminal jurisdiction in the\nabsence of a clear statement by Congress. . . . ‘[U]nless\nCongress conveys its purpose clearly, it will not be deemed to\nhave significantly changed the federal-state balance’ in the\nprosecution of crimes.” Cleveland, 531 U.S. at 24-25\n(quoting Jones v. United States, 529 U.S. 848, 858 (2000)).\nAs we discuss later, the legal tradition of understanding\njudgments as property is long-established. Consequently, the\nconcern about expanding the reach of federal fraud statutes to\nnew classes of property that was present in the deliberation of\nstate licenses in Cleveland is not at issue here.\n\n\n\n\n 16\n\fdifferent issue (whether licenses were analogous to patents)\nthat is apropos to answering this question.\n\n [W]hile a patent holder may sell\n her patent, see 35 U.S.C. § 261 . .\n . “patents shall have the attributes\n of personal property” . . . the State\n may not sell its licensing\n authority. Instead of a patent\n holder’s interest in an unlicensed\n patent, the better analogy is to the\n Federal Government’s interest in\n an unissued patent. That interest,\n like the State’s interest in\n licensing video poker operations,\n surely implicates the\n Government’s role as sovereign,\n not as property holder.\n\nCleveland, 531 U.S. at 23–24. Fines imposed by judges are\ncriminal penalties that “implicate[] the Government’s role as\nsovereign.” Id. at 24. Judgments ordering traffic fines and\ncosts cannot be sold and, in the logic of Cleveland, would\nseem then to have no intrinsic economic value. Indeed, the\npenal (non-economic) nature of the fine is undeniable because\nthe failure to pay a fine can result in the imposition of\nsentences of greater consequence, including imprisonment.\nSee Pa. R. Crim. P. 706 cmt. But Cleveland is not the last\nword. As we will discuss below, a Supreme Court opinion\nissued five years later, Pasquantino v. United States, 544 U.S.\n349 (2005), forecloses the defendants’ argument.\n\n\n\n\n 17\n\f Finally, we note a dissimilarity between this case and\nCleveland, highlighted by the District Court, on the\nsignificance of the monetary interest that the Government\nassociates with the fraud. The Cleveland Court regarded the\nlicensing fees as integral to the regulatory effort and collateral\nto the matter at hand. The indictment there centered on the\nscheme to obtain liceneses, and did not even raise the\nlicensing fees. See Cleveland, 531 U.S. at 22. Indeed, those\ncharged with the fraud paid all the appropriate fees; there was\nno evidence that the government suffered any economic\ndetriment. Id.\n\n In contrast, the indictment here explicitly states that\nthe scheme deprived the City and the Commonwealth of\nmoney, and it describes the object of the scheme as obviating\njudgments of guilt that imposed the fines and costs. Unlike\nCleveland, the fines and costs play a central role in the\nscheme as alleged.\n\n Alfano and Hird next focus on our decision in Henry\nto argue that the Government cannot claim to have a property\nright because the Government never had a legal claim to the\nfines and costs at any point in the scheme. In Henry, we\nexamined convictions for wire fraud arising from a\ncompetitive bidding process among banks to receive deposits\nof a public agency’s bridge tolls. Henry v. United States, 29\nF.3d 112 (3d Cir. 1994). Appellants—public employees—\nwere convicted of mail fraud for giving one bank confidential\ninformation about bids from other banks. Id. at 113. We\nidentified several problems, 16 but Alfano and Hird highlight\n\n16\n The Supreme Court had already made clear that “a\ngovernment official’s breach of his or her obligations to the\n\n\n\n\n 18\n\four observation in Henry that the object of the mail and wire\nfraud must be something to which the victim could claim a\nright of entitlement. Id. at 115 (“a grant of a right of\nexclusion”) (citing Carpenter, 484 U.S. at 26-27)). 17 Indeed,\nwe noted that a bank’s property right to the tolls would attach\nonly after the funds were deposited. Id. at 114. So the banks\nthat lost the bidding process never had a basis to claim any\nlegally recognized entitlement to the toll deposits. 18 Id. at\n115. A fraud claim cannot rest on the bidders being cheated\nout of an opportunity to receive the deposits. For these\nreasons, we concluded that the indictment did not allege a\nscheme to obtain fraudulently someone’s “property.” Id. at\n116.\n\n Here, the Government alleged that the defendants\n“were depriving . . . Philadelphia and . . . Pennsylvania of\nmoney which would have been properly due as fines and\ncosts” by making it possible for certain well-connected\nindividuals to avoid a judgment of guilt that imposed an\nobligation to pay appropriate statutory fines. App. 197\n\n\npublic or an employee’s breach of his or her obligations to an\nemployer” did not fall within the scope of Section 1343.\nHenry, 29 F.3d at 114 (citing Carpenter, 484 U.S. at 25).\n17\n To assess whether a particular claim is a legal entitlement,\n“we look to whether the law traditionally has recognized and\nenforced [the entitlement] as a property right.” Henry, 29\nF.3d at 115.\n18\n They were, no doubt, robbed of a fair process, but we could\nnot identify any legal tradition that recognized this\ndeprivation as a property right. Id. at 115.\n\n\n\n\n 19\n\f(Indictment ¶ 38). But Appellants stress that, like the\ndeposits in Henry, the indictment here alleged an entitlement\nthat does not yet exist because a person must be adjudicated\n(or plead) guilty before they must pay any fines or costs.\nNone of the cases directly associated with Alfano and Hird\nresulted in a guilty judgment. As a result, they argue, the\nGovernment cannot claim here that it was cheated of an\nentitlement, because they were only fines and costs that the\npeople might have owed if they had been found guilty.\n\n The District Court said it well. Accepting this\nargument “would permit the alleged conspirators” to take\nadvantage of their “unique position” in this case “to enter into\na scheme to commit fraud and then hide behind the argument\nthat the success of their fraud precludes prosecution under the\n‘money or property interest’ requirement of the mail and wire\nfraud statutes.” Sullivan, 2013 WL 3305217, at *7.\nAppellants cannot rest on the very object of their scheme (to\nwork on behalf of favored individuals to obviate judgments of\nguilt and the imposition of fines and costs) as the basis to\nclaim that there is no fraud. Indeed, the not-guilty judgments\nthat Alfano and Hird worked to obtain through the\nextrajudicial system were alleged in the indictment as\nevidence of the scheme itself.\n\n Even if some of the cases in the extra-judicial system\nwould have been judged not guilty in a real adjudication it is\n(as the District Court correctly noted) the intent of the\nscheme, not the successful execution of it, that is the basis for\ncriminal liability. See Neder v. United States, 527 U.S. 1, 25\n(1999) (In the criminal context, the court focuses on the\nobjective of the scheme rather than its actual outcome; what\noperatives intended to do, not whether they were successful in\n\n\n\n\n 20\n\fdoing it.); United States v. Rowe, 56 F.2d 747, 749 (2d Cir.)\n(“Civilly of course the [mail fraud statute]would fail without\nproof of damage, but that has no application to criminal\nliability.”), cert. denied 286 U.S. 554 (1932). The indictment\ngenerally alleges not just that Appellants operated a system\nthat operated outside the bounds of Traffic Court procedures,\nbut that it did so for the purpose of obviating judgments of\nguilt imposing fines and costs in those selected cases. See,\ne.g., supra note 8. Moreover, we note that in one case not\ndirectly involving either Alfano or Hird, the indictment\nalleged that fines and costs were not just obviated, but were\nactually erased by an alleged co-conspirator traffic court\njudge who ignored the conviction, backdated a continuance,\nand “adjudicated” the person not-guilty. App. 228-29\n(Indictment ¶¶ 108-113). This episode serves to highlight\nthat the entire scheme was centered on keeping (or taking)\njudgments out of the hands of the Government to prevent the\nimposition of fines and costs. As a result, Appellants’\nreliance on our justice system’s presumption of innocence as\na basis to argue against the existence of a governmental\nproperty interest is a red herring that is properly disregarded\nhere.\n\n Accordingly, we conclude that the indictment’s\nallegation that the scheme had an objective of depriving\n“Philadelphia and . . . Pennsylvania of money which would\nhave been properly due as fines and costs” is not undermined\nby the lack of guilty verdicts. App. 197 (Indictment ¶38\n(emphasis added)).\n\n Alfano and Hird next highlight that, in Henry, our\nproperty interest analysis centered on “whether the law\ntraditionally has recognized and enforced [the entitlement in\n\n\n\n\n 21\n\fquestion] as a property right.” 29 F.3d at 115. Appellants\nassert that traffic fines and costs typically have not been\nconsidered economic property and are unsupported by any\nlegal tradition sufficient to ground charges of wire and mail\nfraud. As we have already noted we disagree with any\nconclusion that the fines and costs at issue have no intrinsic\neconomic value. But we turn to another decision of the\nSupreme Court that came after Cleveland to address squarely\nwhether jurisprudence supports our conclusion.\n\n In 2005 the Supreme Court reviewed convictions\narising from a scheme to smuggle large quantities of liquor\nfrom the United States into Canada, evading Canadian taxes.\nSee Pasquantino v. United States, 544 U.S. 349, 353 (2005).\nThe Court noted that the right to be paid has been routinely\nrecognized as property, id. at 355–56, 19 observing that there is\nan equivalence between “money in hand and money legally\ndue,” id. at 356. Affirming the conviction, the Court said:\n“Had petitioners complied with this legal obligation, they\nwould have paid money to Canada. Petitioners’ tax evasion\ndeprived Canada of that money, inflicting an economic injury\nno less than had they embezzled funds from the Canadian\ntreasury.” Id. It concluded that: “[t]he object of petitioners’\nscheme was to deprive Canada of money legally due, and\ntheir scheme thereby had as its object the deprivation of\nCanada’s ‘property.’” Id. Under Pasquantino, then, traffic\ntickets (or more precisely, judgments arising from them) are\nconsidered an “entitlement to collect money from individuals,\n\n\n19\n The Court cited 3 W. Blackstone, Commentaries on the\nLaws of England 153–155 (1768), which classified the right\nto sue on a debt as personal property.\n\n\n\n\n 22\n\fthe possession of which is ‘something of value.’” 544 U.S. at\n355 (quoting McNally, 483 U.S. at 358). 20 We conclude that\na scheme to obviate judgments imposing fines, effectively\npreventing the government from holding and collecting on\nsuch judgments imposes an economic injury that is the\nequivalent of unlawfully taking money from fines paid out of\nthe Government’s accounts. See id. at 358.\n\n Alfano and Hird focus, finally, on the role that a\njudge’s discretion plays in the adjudication of a case,\nasserting that the uncertainty this creates about outcomes in\nany given case undermines any argument that a judgment in a\nTraffic Court case can be claimed as an entitlement to\nproperty. To the extent that this merely rephrases the issue of\nguilt or innocence on particular charges, we have already\n\n20\n We also note that Pennsylvania law permits the government\nto remedy the nonpayment of fines and costs as an unpaid\ndebt through civil process, enabling the government to\nbecome a judgment creditor. Pa. R. Crim. P. 706 cmt.\n(“Nothing in this rule [concerning criminal fines] is intended\nto abridge any rights the Commonwealth may have in a civil\nproceeding to collect a fine or costs.”). Because of this, a\nseparate legal tradition is implicated that recognizes the\njudgment itself as property. See, e.g., Armada (Singapore)\nPTE Ltd. v. Amcol International Corp., 885 F.3d 1090, 1094\n(7th Cir. 2018). This long, stable legal tradition of\nrecognizing civil judgments for money as property supports\nthe conclusion that the fines arising from judgments in traffic\ncourt cannot be regarded merely as implicating the act of a\nsovereign imposing a criminal penalty. They can be collected\nby civil process as a debt and are, thus, a property interest.\n\n\n\n\n 23\n\faddressed it above. To the degree that it refers to a judge’s\ndiscretion in sentencing, as the District Court noted, there is\nno such discretion here. 21 The Motor Vehicle Code imposes\nfines and costs for each violation, eliminating any judicial\ndiscretion in this regard.\n\n D.\n\n All of this leads us to conclude that the District Court\ndid not err by denying the motion to dismiss. We conclude\nthat, as alleged, this scheme had the objective of preventing\nthe City of Philadelphia and the Commonwealth of\nPennsylvania from possessing a lawful entitlement to collect\nmoney in the form of fines and costs—a property interest—\nfrom individuals who Alfano and Hird assisted. We will thus\naffirm the convictions of Appellants Alfano and Hird.\n\n III.\n\n Appellants Tynes, Lowry, and Mulgrew\n\n A.\n\n\n\n\n21\n We question, in general, the relevance of an entity’s\nauthority to relinquish a just entitlement or to forbear an\nobligation that an entitlement imposes upon another, as a\nbasis to call into doubt the legitimacy of, or the very existence\nof the entitlement. But see United States v. Mariani, 90 F.\nSupp. 2d 574, 583 (M.D. Pa. 2000) (Discretionary civil fines\nand penalties “may be too speculative to constitute a valid\nproperty interest.”) (internal citation omitted).\n\n\n\n\n 24\n\f In 2011, the United States Attorney presented to the\nGrand Jury evidence arising from the Federal Bureau of\nInvestigation’s inquiry into the Traffic Court. Appellants\nLowry, Mulgrew, and Tynes testified and the Government\nbrought perjury charges against them for statements they\nmade to the Grand Jury. After Hird and Alfano pleaded\nguilty, the rest of the Appellants went to trial. The jury\nacquitted Lowry, Mulgrew, and Tynes of all counts against\nthem on wire fraud, mail fraud, and conspiracy. But it found\nthem guilty of perjury. Tynes, Lowry, and Mulgrew\nchallenge their convictions by raising similar legal arguments\nabout the sufficiency of the evidence.\n As with all challenges to the sufficiency of the\nevidence, we use a highly deferential standard of review. See\nUnited States v. Caraballo-Rodriguez, 726 F.3d 418, 430 (3d\nCir. 2013) (en banc). We examine the record in a light most\nfavorable to the prosecution, and will not disturb the verdict if\n“any rational trier of fact could have found the essential\nelements of the crime beyond a reasonable doubt.” United\nStates v. McGee, 763 F.3d 304, 316 (3d Cir. 2014) (emphasis\nin original) (quoting Jackson v. Virginia, 443 U.S. 307, 319\n(1979)). Tynes, Lowry, and Mulgrew argue that the\nquestions asked of them at trial were fatally vague and/or that\ntheir answers were truthful. As a result, they contend that\nthese questions and answers are an inadequate basis for a\nperjury conviction.\n\n A conviction for perjury before a grand jury requires\nthe Government to prove that the defendant took an oath\nbefore the grand jury and then knowingly made a “false\nmaterial declaration.” 18 U.S.C. § 1623. But we recognized\n(in the context of a sentencing enhancement for perjury) that\nsometimes “confusion, mistake, or faulty memory” results in\n\n\n\n\n 25\n\finaccuracies that cannot be categorized as a “willful attempt\nto obstruct justice” under perjury statutes. United States v.\nMiller, 527 F.3d 54, 75 (3d Cir. 2008) (quoting U.S.\nSentencing Guidelines Manual § 3C1.1 cmt. n.2 (U.S.\nSentencing Comm’n 2003). So we do understand that\n“[p]recise questioning is imperative as a predicate for the\noffense of perjury.” Bronston v. United States, 409 U.S. 352,\n362 (1973).\n\n Precision, however, is assessed in context. An\nexaminer’s line of questioning should, at a minimum,\nestablish the factual basis grounding an accusation that an\nanswer to a particular question is false. Miller, 527 F.3d at\n78. So a perjury conviction is supported by the record “when\nthe defendant’s testimony ‘can reasonably be inferred to be\nknowingly untruthful and intentionally misleading, even\nthough the specific question to which the response is given\nmay itself be imprecise.’” United States v. Serafini, 167 F.3d\n812, 823 (3d Cir. 1999) (quoting United States v. DeZarn,\n157 F.3d 1042, 1043 (6th Cir. 1998)).\n\n Challenges to the clarity of a question are typically left\nto the jury, which has the responsibility of determining\nwhether the defendant understood the question to be\nconfusing or subject to many interpretations. United States v.\nSlawik, 548 F.2d 75, 86 (3d Cir. 1977). Moreover, consistent\nwith our standard of review, we will not disturb a jury’s\ndetermination that a response under oath constitutes perjury\nunless “it is ‘entirely unreasonable to expect that the\ndefendant understood the question posed to him.’” Serafini,\n167 F.3d at 820 (quoting United States v. Ryan, 828 F.2d\n1010, 1015 (3d Cir. 1987), abrogated on other grounds by\n\n\n\n\n 26\n\fUnited States v. Wells, 519 U.S. 482 (1997)). 22 On appeal,\nwe review every aspect of the record pertinent to both the\nquestion and answer to reach a conclusion about whether, in\ncontext, the witness understood the question well enough to\ngive an answer that he or she knew to be false. See Miller,\n527 F.3d at 78. Our review, however, is focused on glaring\ninstances of vagueness or double-speak by the examiner at the\ntime of questioning (rather than artful post-hoc interpretations\nof the questions) that—by the lights of any reasonable fact-\nfinder—would mislead or confuse a witness into making a\nresponse that later becomes the basis of a perjury conviction.\nQuestions that breach this threshold are “fundamentally\nambiguous” and cannot legitimately ground a perjury\nconviction. Id. at 77. 23\n\n\n22\n The Court of Appeals for the Second Circuit underscored\nthe high bar this establishes for appellants by noting that a\nfundamentally ambiguous question is “not a phrase with a\nmeaning about which men of ordinary intellect could agree,\nnor one which could be used with mutual understanding by a\nquestioner and answerer unless it were defined at the time it\nwere sought and offered as testimony.” United States v.\nLighte, 782 F.2d 367, 375 (2d Cir. 1986) (quoting United\nStates v. Lattimore, 127 F. Supp. 405, 410 (D. D.C.), aff’d,\n232 F.2d. 334 (D.C. Cir. 1955)).\n23\n The rule of fundamental ambiguity is intended to\n“preclude convictions that are grounded on little more than\nsurmise or conjecture, and . . . prevent witnesses . . . from\nunfairly bearing the risks associated with the inadequacies of\ntheir examiners.” Ryan, 828 F.2d at 1015.\n\n\n\n\n 27\n\f That is the law applicable to the claims raised by\nTynes, Lowry and Mulgrew. But, because our review is fact-\ndependent, and because each raises some unique issues, we\nwill address each of their claims individually. 24\n B.\n\n\n\n\n24\n Adopting the arguments made by Alfano and Hird,\nAppellants Lowry, Mulgrew and Tynes assert that the\nGovernment improperly charged them with conspiracy, wire\nfraud, and mail fraud. Therefore, they assert, their joint trial\non these counts of the indictment prejudiced the jury’s\ndeliberation on the charges of perjury. They claim such\nevidence would have been excluded under Federal Rule of\nEvidence. 403. They also contend that, without a charge of\nconspiracy, the joinder of their cases would have been\nimpermissible under Federal Rule of Criminal Evidence 8(b)\nor, at the very least, severance of their cases would have been\nwarranted under Federal Rule of Criminal Procedure 14(a).\nCertainly, where there is evidence of prejudice resulting from\n“spillover” evidence from counts that should have been\ndismissed, reversal is warranted. See United States v. Wright,\n665 F.3d 560, 575-577 (3d Cir. 2012). But we have\nconcluded that the District Court did not err by denying the\nmotion, under Federal Rule of Civil Procedure 12(b)(3), to\ndismiss the conspiracy, wire fraud and mail fraud counts of\nthe indictment. Thus, Appellants’ spillover argument has\nbeen nullified. Likewise, Appellants have no basis to claim\nthat the Court unfairly prejudiced them by not granting\nseparate trials.\n\n\n\n\n 28\n\f Appellant Tynes 25\n\n Appellant Tynes claims her convictions for perjury at\nCount 71 and Count 72 lack sufficient evidence because she\nwas responding to questions that were fundamentally\nambiguous. The perjury charged at Count 71 arises from the\nfollowing exchange.\n\n Q. In all the years\n you’ve been [at Traffic\n Court] have you\n ever been asked to give\n\n\n25\n Tynes filed a separate motion to dismiss. App. 291-99.\nThe record also contains Tynes’ proposed order to join\nSullivan’s motion to dismiss. App. 290. However, Tynes’\nmotion contains no such request. Moreover, the\nGovernment’s response to the motions notes that Lowry and\nMulgrew moved to join (without argument), and makes no\nmention of Tynes. The District Court’s ruling on Tynes’\nmotion to dismiss relates only to the arguments she made\nseparately in her brief. As a result, we cannot consider\nTynes’ arguments on appeal that relate to those raised in\nSullivan’s motion. Moreover, since she failed to raise any of\nthe arguments she made in her separate motion to dismiss,\nthese arguments are waived. With that said, we will affirm\nthe District Court’s ruling on the Motion raised by Sullivan\nand joined by the five Appellants. Therefore, we need not\naddress Tynes’ assertion that the District Court’s mishandled\nher joinder motion because it does not prejudice the outcome\nof her appeal.\n\n\n\n\n 29\n\f favorable treatment on\n a case to anybody?\n\n A. No, not favorable\n treatment. People basically\n know me. The lawyers\n know me. The court\n officers know me. I have\n been called a nononsense\n person because I’m just not\n that way. I take my\n position seriously, and the\n cards fall where they may.\n\nApp. 255, 5720. 26 Tynes contends that the Government\npursued a novel theory here (applying federal fraud statutes to\nallegations of ticket fixing) and used the vague term\n“favorable treatment” to gloss over its uncertainty about what,\nultimately, would constitute an illegal act. She points out that\nthe term had not been used before in reference to this case\nand that the Government offered no explanation or definition\nof the term to alert Tynes to the intent of the question.\n\n Also, from Tynes’ perspective, every litigant\nappearing before a court seeks an outcome that is favorable,\nthus making “favorable treatment” a term that essentially\nreferred to “how litigation works.” She claims that its use\namounted to a fishing expedition designed to capture unfairly\n\n26\n We cite to the testimony quoted in the indictment and the\nGrand Jury that was used at trial. We note that there are some\ntypographical inconsistencies between these sources and in\nthose instances we have quoted the Grand Jury testimony.\n\n\n\n\n 30\n\fthe entirety of her conduct in the courtroom. She warns that\nthis is precisely the type of “open-ended construction” in\nquestioning that we found unacceptable in Serafini. 167 F.3d\nat 822.\n\n Tynes makes a related argument against her perjury\nconviction for Count 72. That conviction is based on this\nexchange.\n Q. You’ve never taken\n action on a request?\n\n A. No.\n\nApp. 257, 5722. She maintains that the word “request” was\npresented to the jury as a follow-on to the question grounding\nCount 71, requiring a person to link the term “favorable\ntreatment” and the word “request” to make sense of it. She\nargues that the Government took advantage of the ambiguity\nof “favorable treatment,” forcing the jury to speculate that\nTynes interpreted “request” as “favorable treatment.” This\nreliance on “sequential referents” is, from her perspective,\nexactly what we criticized in Serafini. 167 F.3d at 821. But\nshe misconstrues our holding.\n\n In Serafini, the surrounding questions focused on a\ndifferent topic. This bolstered appellant’s argument in that\ncase that the question on which the perjury conviction rested\nwas fundamentally ambiguous. Id. The appellant said the\nmultiplicity of topics in surrounding questions caused the jury\nto speculate improperly on how he understood the question at\nissue. We said: “The meaning of individual questions and\nanswers is not determined by ‘lifting a statement . . . out of its\nimmediate context,’ when it is that very context which fixes\n\n\n\n\n 31\n\fthe meaning of the question.” Serafini, 167 F.3d at 821\n(quoting United States v. Tonelli, 577 F.3d 194, 198 (3d Cir.\n1978)). In the case of Serafini, the context made the\nconfusing nature of the question apparent. The various topics\nin surrounding questions created sufficient ambiguity to\nundermine the conviction. Id.\n\n Here, however, even though the terms used by the\nexaminer changed, we conclude that the line of questioning—\nincluding both questions that ground Count 71 and 72—have\nan obvious, consistent focus.\n\n Q. In all the years\n you’ve been [at Traffic\n Court] have you\n ever been asked to give\n favorable treatment on\n a case to anybody?\n\n A. No, not favorable\n treatment. People basically\n know me. The lawyers\n know me. The court\n officers know me. I have\n been called a nononsense\n person because I’m just not\n that way. I take my\n position seriously and the\n cards fall where they\n may. Most of the time . . .\n the people in my Court\n plea bargain. They know\n that most of the time,\n\n\n\n\n 32\n\fninety percent of the time,\nsay 90 percent, I go with\nthe police officer’s\nrecommendation. . . .\n\nQ. So, in all those years\nno one has ever asked you\nto find somebody not\nguilty--\n\nA. No.\n\nQ. --or to find a lesser\nviolation; find a lesser fine;\nanything along those lines?\n\nA. No. I will say to\npeople go to court, go to\ntrial and see what\nhappens. . . .\n\nQ. Ward leaders,\npoliticians has anyone\ncalled you and said I\nhave Johnny Jones coming\nup next week and I\nwould appreciate it if -- if\nyou would look\nfavorably on him when he\ncomes through? Has\nanything like that ever\nhappened?\n\n\n\n\n 33\n\f A. Throughout the\n years ward leaders and\n people have called all the\n time and asked me\n questions. The only thing I\n will say to them is they\n need to go to court. If you\n think it’s a problem, they\n need to hire a lawyer, or\n make sure you bring all\n your evidence to court. If\n it’s something like\n inspection, make sure you\n bring your -- papers and\n things like that. That’s\n what I would tell them to\n do. I give advice that\n way. I don’t know if that’s\n wrong or not, but I do.\n\n Q. You’ve never taken\n action on a request?\n\n A. No.\n\nApp. 528-29, 530; 5720-22. This broader context would give\nany reasonable fact-finder more than enough basis to\nconclude that the witness knew the point of reference for both\nthe term “favorable treatment” and “request” was ticket\nfixing. In fact, Tynes is asking us to do precisely the thing we\ncriticized in Serafini, to lift a phrase or statement out of its\ncontext. Serafini, 167 F.3d at 821. Tynes has not persuaded\nus that the question harbors any fatal ambiguity.\n\n\n\n\n 34\n\f Tynes next contends that her responses to questions\ngrounding Count 71 and Count 72 cannot support convictions\nfor perjury because they were literally true. Of course,\nperjury arises only from making knowingly false material\ndeclarations. 18 U.S.C. § 1623. Therefore, a witness who\nanswers an ambiguous question with a non-responsive answer\nthat the witness believes is true—even if the answer is\nmisleading—does not commit perjury. See Bronston, 409\nU.S. at 361-62; see also United States v. Reilly, 33 F.3d 1396,\n1416 (3d Cir. 1994).\n Tynes argues that, because she regarded the question\nabout favorable treatment as vague, she interpreted it as\nasking whether she accepted any bribes in exchange for a\njudgment of not guilty or a reduced punishment. Her\nresponse of “no” (grounding Count 71) is literally true—she\nsays—because there is no evidence that she accepted any\nbribes in return for giving preferential outcomes in the\nadjudication of some individuals who were cited for breaking\nthe law. Under this theory, the same argument can also\nnegate the charges at Count 72 since she says she did not\naccept any “requests” (bribes) in exchange for preferential\ntreatment.\n\n Although the jury is permitted reasonable inferences\ndrawn from the record about the witness’ understanding of\nthe truth or falsity of the answer, it is not (as we noted above)\npermitted to reach conclusions based merely on speculation\nor conjecture. See Bronston, 409 U.S. at 359. Tynes’\nassertion of literal truth is undermined because the trial record\nsupports no reasonable inference that the Government was\nasking her about matters outside of the alleged bribes, nor\n\n\n\n\n 35\n\fdoes it provide any reason why Tynes would interpret the\nquestion in this way.\n\n Finally, Tynes contends that the evidence was not\nsufficient to support her conviction. However, the jury heard\nTynes’ personal assistant, Medaglia “Dolly” Warren, testify\nthat she received from personal assistants of other judges\nthree to four cards per week requesting consideration. Each\ncard had the name of a person who was appearing before\nTynes on that day. She passed these to Tynes’ court officer,\nwho was present during the proceedings. App. 4593-95.\nTynes also instructed Warren to give similar cards to the staff\nof other judges. App. 4598. Warren knew to act discreetly\nwhen she was transferring the cards. App. 4599. The jury\nalso heard testimony from those who actually received\nconsideration from Tynes. For example, Timothy Blong was\ncited for reckless driving and driving without a license. He\nadmitted in testimony that he did not have a license when he\nwas cited. App. 3150. He also testified that he requested\nconsideration through a Traffic Court employee (Danielle\nCzerniakowski, who worked as a personal assistant to a\nTraffic Court judge) with whom he was acquainted. When he\nappeared in court, he was simply told that his case was\ndismissed. He did not have to say anything, App. 3159-60.\nBlong testified he was told his case was dismissed because\nthe police officer did not appear (App. 3160-61), but the\ngovernment produced evidence that an officer was present.\nApp. 3193-96. The Government also showed that Tynes was\nthe presiding judge in Blong’s case. App. 3193. Richard\nCarrigan—who admitted in testimony that he drove through a\nred light—described a similar experience in which, after\nrequesting favorable treatment through Judge Lowry’s\npersonal assistant, Kevin O’Donnell, his case was dismissed\n\n\n\n\n 36\n\fby Judge Tynes without ever having to say a word. App.\n3178-82.\n\n Tynes does not challenge any of this in her appeal.\nInstead she focuses on the weight of other evidence and\nperceived gaps in testimony. We conclude that all of this\nprovides more than a sufficient basis to support a reasonable\njury’s conclusion that Tynes did “give favorable treatment on\na case,” and did “take[] action on a request.” App. 528-30.\n\n For all of these reasons, we will affirm the judgment of\nconviction on perjury as to Appellant Tynes.\n C.\n\n Appellant Lowry 27\n\n Like Tynes, Appellant Lowry advances arguments of\nfundamental ambiguity and literal truth. His perjury\nconviction centered on one question and answer.\n\n\n Q. So if I understand\n your testimony, you’re\n saying you don’t give out\n special favors; is that right?\n\n A. No, I treat\n everybody in that\n courtroom the same.\n\n\n27\n Lowry was charged with perjury in Count 69 of the\nindictment.\n\n\n\n\n 37\n\fApp. 489. Lowry attacks the Government’s use of the term\n“special favors” as one with many potential meanings.\nHowever, as we noted above in our reference to Serafini, we\nreject arguments that lift individual questions or answers—or\nindividual phrases embedded in either—from the context of\nsurrounding questions that help fix their meaning. Serafini,\n167 F.3d at 821. The larger context for the question asked of\nLowry is as follows.\n\n Q. So if I understand\n your testimony, you’re\n saying you don’t give out\n special favors; is that right?\n\n A. Well, I know it\n appears that way; and it’s\n hard for me to prove to\n you . . .\n\n Q. I’m just asking,\n your testimony is you don’t\n give out special favors, is\n that right?\n\n A. No, I treat\n everybody in that\n courtroom the same.\n\n Q. You treat everybody\n fairly?\n\n A. I’m a lenient judge.\n I will admit to that.\n\n\n\n\n 38\n\f Q. You treat everybody\n fairly?\n\n A. Yes, I do.\n\n Q. And these notices\n that you get from your\n personal or from other\n people, they don’t affect\n you in any way; is that\n right?\n\n A. Virtually no effect\n at all.\n\n\nApp. 489-90.\n\n Lowry’s assertion that the phrase “special favors” is\nsubject to many interpretations is unconvincing. We note two\nthings. First, the line of questioning reasonably supports a\nconclusion that this inquiry referenced conduct associated\nwith allegations of ticket fixing. Second, Lowry answered as\nif his understanding of the question was consistent with this\ninterpretation. He said that he was aware it may “appear” that\nhe gave special favors. He also defended himself by saying\nthat such requests did not affect his conduct in the courtroom\nat all. If—as he says—he understood “special favors” to\nmean fair treatment, his answer makes no sense.\n\n Lowry next claims that, since the question was\nstructured to elicit a negative response, his answer cannot be\n\n\n\n\n 39\n\fused as the basis of a perjury charge. Relatedly, he contends\nthat the question was merely a summation of an answer that\nhe gave just before this question. In essence he argues that\nthis was a leading question. We have concluded, in the\ncontext of a trial, that the propriety of leading questions in\ndirect examinations is a matter left to the sound discretion of\nthe trial judge. See United States v. Montgomery, 126 F.2d\n151, 153 (3d Cir. 1942). We extend the same deference here\nto the District Court’s decision to admit this portion of the\nGrand Jury transcript. We do not regard the question as\nfundamentally unfair or unclear, or something outside the\nnorm of questions typically employed on direct examination.\nFor these reasons, we conclude that the District Court did not\nabuse its discretion here.\n\n Alternatively, Lowry argues that—if the term is\nunderstood to reference fixing tickets—there is no evidence\nto contradict his response that requests for special favors did\nnot impact any of his adjudications. We do not agree. The\nrecord contains the following testimony.\n\n Kevin O’Donnell, who was Lowry’s personal\nassistant, testified about Lowry’s involvement with requesting\nand giving consideration. He said that Lowry made four to\nfive requests each month for consideration and that\nO’Donnell transmitted them to the personal assistants of other\nTraffic Court judges. App. 1854. Likewise, he said other\njudges transmitted requests for consideration to Lowry\nthrough their personal assistants. App. 1812-13. Appellant\nHird and various politicians also made requests of Lowry for\nconsideration. App. 1827-28, 1832-33. O’Donnell said he\nwould give the requests to Lowry on the day scheduled for\nhearing on the citation. App. 1818-19. The requests were for\n\n\n\n\n 40\n\fpreferential treatment in the adjudication of particular\ncitations: typically the requests were for “removing points”\nand obtaining a “not guilty” judgment. App. 1819.\nO’Donnell said he sometimes had to signal Lowry in the\ncourtroom to remind him that a particular case was supposed\nto receive consideration. App. 1822-23. He testified from\nhis own observation that Lowry typically honored requests\nfor consideration. App. 1829. He also declared if Lowry\nclaimed he never gave consideration or asked it of others, this\nwould not be truthful. App. 1813. The same assistant\ntestified that if Lowry testified that he ignored requests for\nconsideration, or that he never honored requests for\nconsideration, that testimony would not be true. App. 1855.\nThe Government also asked: “If [Lowry] claimed that . . .\nconsideration requests had no impact when he disposed of\ncases, would that be true?” The assistant responded,\n“probably not.” Id.\n\n Another witness, Walt Smaczylo, employed as a court\nofficer in the Traffic Court, provided an example of how\n“consideration” worked in the courtroom.\n\n When someone comes in,\n for example, for a reckless\n driving ticket and that\n judge normally comes\n down pretty hard and finds\n that defendant guilty and\n then the same type cases\n come in and you see a\n defendant walk out either\n not guilty or a significantly\n reduced charge.\n\n\n\n\n 41\n\fApp. 1912. The Government asked Smaczylo if he saw\nLowry preside over such instances, and he answered: “That’s\ncorrect, yes.” Id. Smaczylo testified that requests for\nconsideration were written on small note cards or “sticky”\nnotes and that he saw Lowry in possession of these cards and\nnotes. App. 1914. He also provided a generalized example\nof consideration, based on his observation and understanding,\nin which a reckless driving citation would be reduced to\ncareless driving. In such instances, he indicated that a $300\nto $400 fine would be cut in half. He said: “So, that money\nwas not collected, obviously, by the state. If that ticket was\nfixed then I saw it as stealing.” App. 1919. Smaczylo was\nasked: “[I]f Judge Lowry testified at the [G]rand [J]ury he\ndidn’t give consideration would that be a truth or would that\nbe a lie?” He responded: “That would not be the truth.”\nApp. 1921.\n\n All of this testimony provides more than a sufficient\nbasis to support a reasonable jury’s conclusion that Lowry\nwas not truthful when he responded to the Government’s\nquestion about special favors. 28\n\n28\n Lowry points to the cross-examination of both witnesses in\nwhich they seem to equivocate on some of their observations\nand responses to the Government. For instance O’Donnell\nstated his view that giving consideration was no different\nfrom the leniency that Lowry extended to every other person\nwho pleaded not guilty and appeared at the hearing.\nHowever, we do not weigh the credibility of evidence in the\nrecord. We only judge whether there is sufficient evidence in\nthe record to support a reasonable fact-finder’s determination\nthat the record supported conviction of Lowry on a charge of\n\n\n\n\n 42\n\f Finally, Lowry argues that the Government’s question\nsought a dispositive response from him on the charges of\nconspiracy and fraud. He says an affirmative answer to\nwhether he gave “special favors” to certain individuals would\nhave been enough to convict him of conspiracy and fraud.\nThus, he maintains that his acquittal on charges of mail fraud,\nwire fraud, and conspiracy is res judicata as to the perjury\ncharges that are based on his answer. He said he did not\ncommit fraud and the jury agreed with him. Therefore, he\nsays, he did not perjure himself. However, even if we\naccepted Lowry’s characterization of the question, we reject\nthis argument.\n\n First, a jury’s determination that Lowry’s ticket-fixing\nconduct did not constitute wire fraud, mail fraud, and\nconspiracy does not preclude its determination that he lied\nabout this conduct before the Grand Jury. Moreover, as the\nSupreme Court has articulated, a verdict on one count that\nseems to be at odds with another “shows that either in the\nacquittal or the conviction the jury did not speak their real\nconclusions, but that does not show that they were not\nconvinced of the defendant’s guilt.” United States v. Powell,\n469 U.S. 57, 63 (1984) (quoting Dunn v. United States, 284\nU.S. 390, 393 (1932)). It is impossible to know in such cases\nwhether the verdicts were an exercise of lenity by the jury or\noutright error.\n\n Nonetheless, as the Powell Court noted, any\nassessment of the jury’s rationale for its verdicts “would be\n\n\nperjury. See United States v. Richardson, 658 F.3d 333, 337\n(3d Cir. 2011).\n\n\n\n\n 43\n\fbased either on pure speculation or would require inquiries\ninto the jury’s deliberations that courts generally will not\nundertake.” Id. at 58. So, even if Lowry was correct that the\nacquittal is relevant to his response to the question grounding\nhis perjury conviction, we are not convinced that his perjury\nconviction is unfounded. Given the substantial body of\nevidence presented to the jury, nothing here demands that we\nabandon the deference we traditionally give to the collective\njudgment of the jury. For all these reasons, we will affirm the\njury’s verdict as to Lowry.\n\n D.\n\n Appellant Mulgrew 29\n\n Mulgrew does not argue that the question asked at the\nGrand Jury was ambiguous, he simply maintains that his\nstatement was truthful. 30 The questions and answers\ngrounding his perjury conviction are as follows.\n\n Q. How about your\n personal, has your personal\n received any calls like that\n from other judges, other\n ward leaders that she’s\n conveyed to you, saying\n\n29\n Mulgrew was charged with perjury in Count 70 of the\nindictment.\n30\n Mulgrew’s claims are reviewed for plain error because he\ndid not make the same argument before the District Court.\nUnited States v. Syme, 276 F.3d 131, 148 (3d Cir. 2002).\n\n\n\n\n 44\n\f so-and-so has called about\n this case?\n\n A. If she did, she didn’t\n convey them to me.\n\n\nApp. 432-33 (emphasis added). Shortly after this, the\nfollowing exchange occurred:\n\n Q. Let me make sure as\n well that if I got your\n testimony correct [sic].\n You’re saying that if other\n people, whether they be\n political leaders, friends\n and family, anybody is\n approaching your personal\n and asking her specifically\n to look out for a case, see\n what she can do in a case,\n give preferential treatment,\n however you want to\n phrase it, that she is not\n relaying any of that\n information on to you; is\n that correct?\n\n A. No, she isn’t.\n\nApp. 438. As to the first exchange, Mulgrew claims that the\nGovernment’s use of the word “call” referred exclusively to\ntelephone calls. This mattered to him, he says, because others\n\n\n\n\n 45\n\fhad testified that personal assistants of other Traffic Court\njudges would give index cards to his personal assistant in his\nchambers or robing room containing names of some\nindividuals whose tickets were listed for hearing. Mulgrew\nclaims that there is no evidence that he ever received any\nphone calls asking that he act extrajudicially to give well-\nconnected individuals preferential treatment. The implication\nis that, had the Government asked him about receiving index\ncards with such requests, his answer would have been\ncompletely different.\n As with Tynes and Lowry, our review of claims of\nliteral truth drives us to examine the context of the question.\n\n Q. How about other\n judges, have other judges\n ever approached you or\n called to you or get a\n message to you either\n themselves or through their\n personals saying that\n someone is going to be on\n your list next week or next\n Monday and can you could\n some special way towards\n the case?\n\n A. No, they haven’t.\n\n Q. Never?\n\n A. No.\n\n\n\n\n 46\n\fQ. How about your\npersonal, has your personal\nreceived any calls like that\nfrom other judges, other\nward leaders that she’s\nconveyed to you saying so\nand so has called about this\ncase?\n\nA. If she did, she didn’t\nconvey them to me.\n\nQ. And your personal\nis who?\n\nA. Gloria McNasby.\n\nQ. Have you ever seen\non traffic court files --You\nactually get a file when\nsomeone’s case is called?\n\nA. Right.\n\nQ. So the case is called\nand you get a file presented\nto you; is that right?\n\nA. uh-huh.\n\nQ. Have you ever seen\nany index cards or\nnotations on the file\n\n\n\n\n 47\n\f indicating that a person has\n called or taken some\n special interest in this\n case?\n\n A. Nope.\n\nApp. 432-33 (emphasis added). The transcript makes it\nobvious that Mulgrew’s singular reliance on the reference to a\n“call” ignores the thrust of the Government’s line of\nquestions. The questions focus on the substance of the\ncommunications between Mulgrew’s personal assistant and\nhimself, rather than the mode of those communications.\n\n Mulgrew also claims that he responded truthfully to\nthe second question.\n\n Q. Let me make sure as\n well that if I got your\n testimony correct [sic].\n You’re saying that if other\n people whether they be\n political leaders, friends\n and family, anybody is\n approaching your personal\n and asking her specifically\n to look out for a case, see\n what she can do in a case,\n give preferential treatment,\n however you want to\n phrase it, that she is not\n relaying any of that\n\n\n\n\n 48\n\f information on to you; is\n that correct?\n\n A. No, she isn’t.\n\n Q. Wouldn’t you want\n to know it?\n\n A. No, I don’t want to\n know. Then I never have to\n worry about what I do in\n the courtroom.\n\nApp. 437-38 (emphasis added). Apparently focusing on the\nwords “see what she can do,” he says that he answered\ntruthfully by responding that his personal assistant did not tell\nhim that people were approaching her and asking her to give\nthem preferential treatment. But, as with the first question,\nMulgrew cherry-picks a small part of the question out of\ncontext, distorting it. The full text and follow up question\nshow that the thrust of the inquiry was whether Mulgrew’s\npersonal assistant was informing him of the names of those\nrequesting preferential treatment from him. And Mulgrew’s\nresponse to the follow-up question —saying that he did not\nwant to know so that he did not have to worry about what he\ndid in the courtroom—is consistent with one who understood\nthis. App. 438.\n\n We conclude that, ultimately, the evidence is sufficient\nfor a reasonable jury to conclude Mulgrew understood that\nboth of these questions were focused on whether his personal\nassistant informed him of requests for him to give preferential\ntreatment, and that he answered in the negative to both.\n\n\n\n\n 49\n\f Mulgrew alternatively asserts that the District Court\nerred by refusing to admit additional testimony from the\nGrand Jury that he claims is relevant to his perjury\nconviction. 31 After the Government introduced Mulgrew’s\nGrand Jury testimony, Mulgrew sought the admission of other\nportions of his testimony. But the District Court sustained the\nGovernment’s hearsay objection. The portion of the\ntranscript supporting the perjury conviction is as follows:\n\n Q. [W]hether you have\n ever been asked to provide,\n what I’ll call, favorable\n treatment for people in\n traffic court or however\n you define that, whether it\n would be special handling,\n keep an eye out for a\n ticket, do me a favor.\n Have you ever been asked\n to provide any type of\n treatment like that for\n people in traffic court?\n\n A. People have asked\n me for consideration, but I\n give consideration to\n everybody that comes in\n my courtroom[,] so it\n\n31\n We review the District Court’s ruling on the admissibility\nof evidence for abuse of discretion. United States v. Green,\n617 F.3d 233, 239 (3d Cir. 2010).\n\n\n\n\n 50\n\f doesn’t make a difference\n to me.\n\n\nApp. 422-23. The basis for the Government’s hearsay\nobjection to this portion of the testimony was that it raised an\nout-of-court statement not offered by a party opponent.\n\n Mulgrew first contends that the District Court erred by\nruling that this was hearsay because it was not offered for the\ntruth of the matter asserted. He says that the testimony was\ninstead offered to show his state of mind later in his\ntestimony. See United States v. Hoffecker, 530 F.3d 137,\n191-92 (3d Cir. 2008). However, we conclude that it was not\nan abuse of discretion for the District Court to sustain the\nGovernment’s hearsay objection. It was reasonable for the\nDistrict Court to conclude here that his response relied on\nout-of-court statements offered to assert his innocence since\nhis response conveys a declaration that he treated no person\ndifferent from another.\n\n Mulgrew also argues that this portion of the transcript\nis admissible under Federal Rule of Evidence 106: “[i]f a\nparty introduces all or part of a writing or recorded statement,\nan adverse party may require the introduction, at that time, of\nany other part—or any other writing or recorded statement—\nthat in fairness ought to be considered at the same time.”\nMulgrew maintains that this question and answer provides\ncontext showing that he did not commit perjury. He also\nmaintains that the “doctrine of completeness” applies here:\nfairness demanded the admission of the statements. See\n\n\n\n\n 51\n\fUnited States v. Soures, 736 F.2d 87, 91 (3d Cir. 1984). 32 We\nare not convinced.\n\n The excerpt at issue occurs many pages before the\ntestimony regarded as perjurious. It is unrelated in the overall\nsequence of questions and to the answers grounding his\nconviction. Moreover, as the intervening pages suggest, it\nwas separated by the passage of time during questioning. We\nalso fail to see how Mulgrew’s equivocation over the term\n“consideration” gives helpful context to his later denial of\nreceiving requests for consideration. For these reasons, we\nconclude the District Court did not abuse its discretion by\nsustaining the Government’s hearsay objection.\n\n IV.\n\n Appellant Singletary 33\n\n\n32\n “Under this doctrine of completeness, a second writing may\nbe required to be read if it is necessary to (1) explain the\nadmitted portion, (2) place the admitted portion in context, (3)\navoid misleading the trier of fact, or (4) insure a fair and\nimpartial understanding.” Soures, 736 F.2d at 91.\n33\n Appellant Singletary was charged with making false\nstatements in Counts 73 and 74 of the indictment. He states\nin his brief that he ‘joins all arguments on behalf of co-\nappellants pursuant to Federal Rules of Appellate Procedure\n28(i).” Singletary Br. 19. To the extent that he joins the\nargument of prejudice resulting from the trial on the fraud and\nconspiracy charges, we already have determined that the\nindictment was proper and no prejudice resulted from\n\n\n\n\n 52\n\f During the investigation of the Traffic Court by the\nFederal Bureau of Investigation, Appellant Singletary was\namong those interviewed. The jury acquitted Singletary of all\ncounts of wire fraud, mail fraud, and conspiracy. It found\nhim guilty of false statements made to the Federal Bureau of\nInvestigation. At sentencing, over Singletary’s objection, the\nDistrict Court sentenced Singletary using the Guideline on\nobstruction.\n\n The Government agrees that the single count on which\nhe was convicted does not contain all of the elements of\nobstruction. U.S.S.G. § 2J1.2. For this reason, the\nGovernment agrees with Singletary that he is entitled to a\nremand for resentencing. Accordingly, we will vacate the\njudgment of sentence as to Singletary and remand to the\nDistrict Court for resentencing.\n\n V.\n\n For all of these reasons, we will vacate the judgment of\nsentence of the District Court with regard to Appellant\nSingletary and remand for resentencing. We will affirm the\njudgments of the District Court as to Appellants Alfano, Hird,\nLowry, Mulgrew and Tynes.\n\n\n\nbringing these charges to trial. As for the challenges to\nperjury in Counts 72 and 74, we note that Singletary was\ncharged with a different crime: false statements in a federal\ninvestigation pursuant to 18 U.S.C. § 1001. In addition, the\nchallenges to all of such charges are inherently fact-intensive.\nAs he did not provide a factual basis for such a challenge, we\nregard the issue to be waived.\n\n\n\n\n 53\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America v. William HIRD, Appellant at No. 14-4754 United States of America v. Thomasine Tynes, Appellant at No. 14-4804 United States of America v. Robert Mulgrew, Appellant at No. 14-4812 United States of America v. Michael Lowry, Appellant at No. 15-1344 United States of America v. Willie Singletary, Appellant at No. 15-1739 United States of America v. Henry P. Alfano, AKA Ed, AKA Eddie, Henry P. Alfano, Appellant at No. 15-3765\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-18\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n\\n __________\\n\\nNos. 14-4754, 14-4804, 14-4812, 15-1344, 15-1739, 15-3765\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n WILLIAM HIRD,\\n Appellant at No. 14-4754\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n THOMASINE TYNES,\\n Appellant at No. 14-4804\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n ROBERT MULGREW,\\n Appellant at No. 14-4812\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n MICHAEL LOWRY,\\n Appellant at No. 15-1344\\n\\f __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n WILLIE SINGLETARY,\\n Appellant at No. 15-1739\\n ___________\\n\\n UNITED STATES OF AMERICA\\n v.\\n HENRY P. ALFANO,\\n aka Ed, aka Eddie,\\n\\n Henry P. Alfano,\\n Appellant at No. 15-3765\\n __________\\n\\n On Appeal from the United States District Court\\n for the Eastern District of Pennsylvania\\n\\n (District Court Criminal Nos. 2-13-cr-00039-007,\\n2-13-cr-00039-005, 2-13-cr-00039-003, 2-13-cr-00039-002,\\n 2-13-cr-00039-004, 2-13-cr-00039-008)\\n District Judge: Honorable Robert F. Kelly\\n District Judge: Honorable Lawrence F. Stengel\\n\\n Argued October 23, 2017\\n\\n BEFORE: GREENAWAY, JR., NYGAARD,\\n and FISHER, Circuit Judges\\n\\n\\n (Opinion Filed: January 18, 2019)\\n\\n\\n\\n\\n 2\\n\\fAngela Halim\\nHalim Drossner\\n1528 Walnut Street, Suite 1501\\nPhiladelphia, PA 19102\\n\\nGregory J. Pagano\\n1315 Walnut Street, 12th Floor\\nPhiladelphia, PA 19107\\n Counsel for Appellant in No. 14-4754\\n\\nLisa A. Mathewson [Argued]\\n123 South Broad Street, Suite 810\\nPhiladelphia, PA 19109\\n Counsel for Appellant No. 14-4804\\n\\nPeter Goldberger [Argued]\\nPamela A. Wilk\\n50 Rittenhouse Place\\nArdmore, PA 19003\\n Counsel for Appellant in No. 14-4812\\n\\nMichael J. Engle [Argued]\\nStradley Ronon Stevens & Young\\n2005 Market Street, Suite 2600\\nPhiladelphia, PA 19103\\n\\nMeredith A. Lowry\\n1528 Walnut Street, Suite 1501\\nPhiladelphia, PA 19102\\n Counsel for Appellant in No. 15-1344\\n\\n\\n\\n\\n 3\\n\\fWilliam J. Brennan\\n1600 Locust Street\\nPhiladelphia, PA 19103\\n Counsel for Appellant in No. 15-1739\\n\\nMark E. Cedrone [Argued]\\nCedrone & Mancano\\n123 South Broad Street, Suite 810\\nPhiladelphia, PA 19109\\n Counsel for Appellant in No. 15-3765\\n\\n\\nLouis D. Lappen\\nDenise S. Wolf\\nAnthony J. Wzorek\\nRobert A. Zauzmer [Argued]\\nOffice of United States Attorney\\n615 Chestnut Street, Suite 1250\\nPhiladelphia, PA 19106\\n Counsel for Appellee\\n\\n\\n\\n\\n __________\\n\\n OPINION OF THE COURT\\n __________\\n\\nNYGAARD, Circuit Judge.\\n\\n I.\\n\\n\\n\\n\\n 4\\n\\f In the run-up to a joint trial on a 77-count indictment\\nthat charged Appellants with operating a ticket-fixing scheme\\nin the Philadelphia Traffic Court, the District Court denied a\\nmotion, under Federal Rule of Criminal Procedure\\n12(b)(3)(B)(v), to dismiss charges of conspiracy (18 U.S.C. §\\n1349), mail fraud (18 U.S.C. § 1341), and wire fraud (18\\nU.S.C. § 1343). Appellants Henry Alfano (private citizen)\\nand William Hird (Traffic Court administrator) subsequently\\npleaded guilty to all counts against them. But now they\\nappeal the District Court’s decision on this motion,\\nquestioning whether the indictment properly alleged offenses\\nof mail fraud and wire fraud. 1\\n\\n Appellants Michael Lowry, Robert Mulgrew, and\\nThomasine Tynes (Traffic Court judges) proceeded to a joint\\ntrial and were acquitted on the fraud and conspiracy counts,\\nbut they were convicted of perjury for statements they made\\nbefore the Grand Jury. Lowry, Mulgrew, and Tynes dispute\\nthe sufficiency of the evidence on which they were convicted\\nby arguing that the prosecutor’s questions were vague, and\\nthat their answers were literally true. Lowry and Mulgrew\\ncontend alternatively that the jury was prejudiced by evidence\\npresented at trial on the fraud and conspiracy counts.\\nMulgrew also complains that the District Court erred by\\nruling that certain evidence was inadmissible.\\n\\n At the same trial, the jury convicted Willie Singletary\\n(Traffic Court judge) of making false statements during the\\ninvestigation. He claims the District Court made errors when\\n\\n\\n1\\n Alfano and Hird preserved their right to appeal. See infra\\nsubsection I.C.\\n\\n\\n\\n\\n 5\\n\\fit sentenced him. 2 The Government concurs with\\nSingletary’s challenge to his sentence.\\n\\n We have consolidated these appeals for efficiency and\\nhave grouped the arguments—to the extent that it is\\npossible—by common issues. We agree with Singletary and\\nthe Government that he should be resentenced. We will\\nreverse the judgment and remand his cause to the District\\nCourt for this purpose. We are not persuaded by the rest of\\nAppellants’ arguments and will affirm their judgments of\\nconviction. 3\\n\\n II.\\n\\n Appellants Alfano 4 and Hird 5\\n\\n\\n\\n2\\n Singletary also attempted to join additional arguments raised\\nby other appellants, but for reasons we explain later, see infra\\nnote 33, we focus only on his challenge to his sentence.\\n3\\n The District Court had jurisdiction pursuant to 18 U.S.C. §\\n3231. We have jurisdiction to review these claims under 28\\nU.S.C.§ 1291 and 18 U.S.C. § 3742(a).\\n4\\n Appellant Alfano pleaded guilty to Conspiracy (Count 1),\\nWire Fraud (Counts 2, 3, 4, 5, 6, 7) and Mail Fraud (Counts\\n51, 52, 53, 54, 55, 56).\\n5\\n Appellant Hird pleaded guilty to Conspiracy (Count 1),\\nWire Fraud (Counts 3, 4, 5, 6, 16, 17, 18, 19, 20, 22, 23) and\\nMail Fraud (Counts 58, 59, 60).\\n\\n\\n\\n\\n 6\\n\\f A.\\n\\n We begin with a brief look at the indictment’s\\ndescription of the Traffic Court and its operations to\\ncontextualize the arguments made by Alfano and Hird. The\\nPhiladelphia Traffic Court was part of the First Judicial\\nDistrict of Pennsylvania. App. 186 (Indictment ¶ 2). 6 It\\nadjudicated violations of the Pennsylvania Motor Vehicle\\nCode occurring in the City of Philadelphia, no matter whether\\nthe Philadelphia Police or the Pennsylvania State Police\\nissued the tickets. App. 187 (Indictment ¶5). When a person\\nwas cited for a violation he or she was required—within ten\\ndays—to enter a plea of guilty or not guilty. If the person\\nfailed to plead, the Traffic Court issued a notice that his or her\\nlicense was being suspended. App. 189 (Indictment ¶ 12). A\\nperson who pleaded not guilty proceeded to a hearing with a\\nTraffic Court judge presiding. App. 187 (Indictment ¶ 6).\\n\\n A guilty plea, or a determination of guilt by a Traffic\\nCourt judge after a hearing, resulted in a judgment ordering\\npayment of statutory fines and court costs. App. 188\\n(Indictment ¶ 8). 7 The Traffic Court was responsible for\\ncollecting these fines (sending them to the City and\\n\\n\\n6\\n Philadelphia Traffic Court was abolished and its jurisdiction\\nwas transferred to the Municipal Court in 2013 by an Act of\\nthe Pennsylvania General Assembly. 42 Pa.Con.Stat.\\n§1121(a)(2) (2013). The court is now known as the Traffic\\nDivision of the Municipal Court.\\n7\\n Although other penalties are prescribed by the Pennsylvania\\nMotor Vehicle Code (App. 188), this appeal is limited to the\\nmonetary fines and costs. App. 355.\\n\\n\\n\\n\\n 7\\n\\fCommonwealth) and costs (which it distributed to several\\npre-designated funds). App. 188-89 (Indictment ¶ 9).\\nFinally, it reported the disposition of each adjudication to the\\nPennsylvania Department of Transportation (PennDOT).\\nApp. 189 (Indictment ¶ 11).\\n\\n B.\\n\\n The indictment charged that, at the behest of Alfano\\n(App. 193 (Indictment ¶ 25)) and others, the Traffic Court\\nadministrator and judges operated an “extra-judicial system,\\nnot sanctioned by the Pennsylvania court system” that\\nignored court procedure and gave preferential treatment\\n(“consideration”) to select individuals with connections to the\\ncourt who had been cited for motor vehicle violations. App.\\n196 (Indictment ¶ 31). The special treatment included:\\n\\n (1) dismissing tickets outright; (2)\\n finding the ticketholder not guilty\\n after a “show” hearing; (3)\\n adjudicating the ticket in a\\n manner to reduce fines and avoid\\n assignment of points to a driver’s\\n record; and (4) obtaining\\n continuances of trial dates to\\n “judge-shop,” that is find a Traffic\\n Court judge who would accede to\\n a request for preferential\\n treatment.\\n\\nApp. 195-196 (Indictment ¶ 30). All of this was “not\\navailable to the rest of the citizenry.” App. 196 (Indictment ¶\\n32). It also alleged that Appellants cooperated with each\\n\\n\\n\\n\\n 8\\n\\fother to fulfill requests they and their staffs received. App.\\n194-95 (Indictment ¶ 27). Finally, it charged that “[i]n\\nacceding to requests for ‘consideration,’ defendants were\\ndepriving the City of Philadelphia and the Commonwealth of\\nPennsylvania of money which would have been properly due\\nas fines and costs.” App. 197 (Indictment ¶ 38). 8\\n After extending consideration to favored individuals,\\nTraffic Court judges would report the final adjudication to\\n“various authorities, including PennDOT, as if there had been\\na fair and open review of the circumstances.” App. 197\\n(Indictment ¶ 34). Appellant Hird provided a printout to\\nAppellant Alfano showing citations that had been “dismissed\\nor otherwise disposed of.” App. 198-99 (Indictment ¶ 42).\\nSuch “receipts” were not routinely issued in cases.\\n\\n C.\\n\\n Hird and Alfano pleaded guilty to all the charges\\nagainst them in the indictment. But, in their plea agreement\\nthey reserved the right to appeal “whether the Indictment\\n\\n\\n8\\n An example of the many allegations involving Alfano and\\nHird is: A.S. requested assistance from Appellant Alfano and\\nAppellant Hird on Citation Number P1J0PK568L4 on or\\naround February 17, 2010. The citation charged A.S. with\\ndriving a tractor-trailer from which snow and ice fell, striking\\nvehicles on Interstate 95. The violation carried a $300 fine\\nand costs of $142. Appellant Hird promised that he would\\n“stop all action” on the citation and instructed A.S. to ignore\\nthe ticket. Although A.S. did not appear at the hearing, the\\nTraffic Court judge (who is not an appellant here) ruled A.S.\\nnot guilty. App. 210-12 (Indictment ¶¶ 25-34).\\n\\n\\n\\n\\n 9\\n\\fsufficiently alleged that the defendants engaged in a scheme\\nto defraud the Commonwealth of Pennsylvania and the City\\nof Philadelphia of money in costs and fees.” App. 355 (Plea\\nAgreement ¶ 9(b)(4)). So they now appeal the District\\nCourt’s order denying the motion to dismiss, asserting that\\nthe indictment failed to allege violations of mail fraud and\\nwire fraud.\\n\\n “To be sufficient, an indictment must allege that the\\ndefendant performed acts which, if proven, constitute a\\nviolation of the law that he is charged with violating.” United\\nStates v. Small, 793 F.3d 350, 352 (3d Cir. 2015). We\\nassume in our review that the allegations in the indictment are\\ntrue. United States v. Hedaithy, 392 F.3d 580, 583 (3d Cir.\\n2004). “The question of whether the . . . indictments alleged\\nfacts that are within the ambit of the mail fraud statute is a\\nquestion of statutory interpretation subject to plenary review.”\\nId. at 590 n.10.\\n\\n To indict on mail or wire fraud, the Government must\\nallege that defendants “devised or intend[ed] to devise any\\nscheme or artifice to defraud, or for obtaining money or\\nproperty by means of false or fraudulent pretenses,\\nrepresentations, or promises” and used mail or wire to effect\\nthe scheme. 18 U.S.C. §§ 1341, 1343. Alfano and Hird claim\\nthe Government failed to allege that the scheme to commit\\nwire and mail fraud had an objective of “obtaining money or\\nproperty.” 9\\n\\n9\\n In the context of mail fraud (§ 1341) and wire fraud (§1343)\\nthe term “money” has the same meaning. The same is true\\nfor the term “property.” Carpenter v. United States, 484 U.S.\\n19, 25 n. 6 (1987).\\n\\n\\n\\n\\n 10\\n\\f The District Court ruled that the indictment\\nsufficiently alleged that the scheme “involved defrauding the\\nCommonwealth and the City of money.” App. 20. It noted,\\namong others, allegations that:\\n\\n The conspirators used the\\n Philadelphia Traffic Court\\n (“Traffic Court”) to give\\n preferential treatment to certain\\n ticketholders, most commonly by\\n “fixing” tickets for those with\\n whom they were politically and\\n socially connected. By doing so,\\n the conspirators defrauded the\\n Commonwealth of Pennsylvania\\n and the City of Philadelphia of\\n funds to which the\\n Commonwealth and the City were\\n entitled.\\n\\nId. at 18; see also id. at 185 (Indictment ¶ 1). Similarly, it\\nreferred to the following.\\n\\n In acceding to requests for\\n “consideration,” defendants were\\n depriving the City of Philadelphia\\n and the Commonwealth of\\n Pennsylvania of money which\\n would have been properly due as\\n fines and costs.\\n\\n\\n\\n\\n 11\\n\\fId. at 9; see also id. at 197 (quoting Indictment ¶ 38).\\nHighlighting the references to “funds” and “money,” and that\\nthe monetary amounts of the fines are specifically pleaded,\\nthe District Court cited to a case from the Court of Appeals\\nfor the Eighth Circuit which concluded succinctly that\\n“[m]oney is money.” United States v. Sullivan, No. 2:13-cr-\\n00039, 2013 WL 3305217, at *7 (E.D. Pa. July 1, 2013)\\n(quoting United States v. Granberry, 908 F.2d 278, 280 (8th\\nCir. 1990)). The District Court was satisfied that the\\nindictment alleged enough.\\n\\n “Money, of course, is a form of property.” Reiter v.\\nSonotone Corp., 442 U.S. 330, 338 (1979). But Alfano and\\nHird argue that the mere mention of money in an indictment\\nis not enough. They point to a string of Supreme Court and\\nCourt of Appeals decisions analyzing Section 1341 and\\nSection 1343 which reinforce the point that crimes of mail\\nfraud and wire fraud are “limited in scope to the protection of\\nproperty rights.” McNally v. United States, 483 U.S. 350, 360\\n(1987). 10 The Supreme Court said that “[a]ny benefit which\\nthe government derives from the [mail fraud] statute must be\\nlimited to the Government’s interests as a property holder.”\\nId. at 359 n.8 (emphasis added). Appellants are convinced\\nthat money in the form of traffic fines and costs cannot be\\nregarded as the Government’s “property” for purposes of mail\\nor wire fraud, and they identify two decisions as particularly\\nsupportive of their position: Cleveland v. United States, 531\\n\\n10\\n The District Court cited to a number of cases that came\\nafter McNally: Carpenter v. United States, 484 U.S. 19\\n(1987); Cleveland v. United States, 531 U.S. 12 (2000);\\nPasquantino v. United States, 544 U.S. 349 (2005).\\n\\n\\n\\n\\n 12\\n\\fU.S. 12 (2000); and United States v. Henry¸ 29 F.3d 112 (3d\\nCir. 1994).\\n\\n The Court in Cleveland examined the mail fraud\\nconvictions of individuals who received a state video poker\\nlicense by submitting a license application that withheld\\nimportant information. Cleveland, 531 U.S. 12. 11 The Court\\nnoted that the video poker licenses were part of a state\\nprogram that was “purely regulatory.” Id. at 22 (citation\\nomitted). 12 It ruled that licenses are a “paradigmatic\\nexercise[] of the States’ traditional police powers.” Id. at 23.\\nThe Court went on to say that the state’s regulatory powers\\ninvolving “intangible rights of allocation, exclusion, and\\ncontrol” (which are embodied in a license) are not interests\\nthat traditionally have been recognized as property. Id.\\nTherefore, even though appellants may have obtained the\\nlicense through deception, this was not mail fraud because the\\nlicense—at least while still in the hands of the state—was not\\n\\n\\n\\n11\\n The licenses were part of a regulatory scheme that had as\\nits purpose to increase public confidence in the honesty of\\ngaming activities that are free of criminal involvement.\\nCleveland, 531 U.S. at 20–21 (quoting La. Rev. Stat. Ann. §\\n27:306(A)(1) (2000) (repealed 2012)).\\n12\\n The Court rebuffed the Government’s attempts to analogize\\nlicenses to other forms of property like patents and franchise\\nrights. As for likening licenses to franchise rights, the Court\\nobserved that the Government did not enter the video poker\\nbusiness, but rather decided to “permit, regulate, and tax\\nprivate operators of the games.” Id. at 24.\\n\\n\\n\\n\\n 13\\n\\fproperty. Id. at 26-27. It was a purely administrative tool\\nused to achieve regulatory objectives. Id. at 21.\\n\\n The state responded to the Court’s concerns by\\nagreeing that the licenses served a regulatory purpose, but it\\ndirected attention to the revenue it received from fees\\ncollected for license applications and renewals, as well as\\ndevice fees. Id. at 21-22. It argued that this revenue is a\\nproperty interest. Id. The Court was not convinced:\\n\\n Tellingly, as to the character of\\n Louisiana’s stake in its video\\n poker licenses, the Government\\n nowhere alleges that Cleveland\\n defrauded the State of any money\\n to which the State was entitled by\\n law. Indeed, there is no dispute\\n that TSG paid the State of\\n Louisiana its proper share of\\n revenue, which totaled more than\\n $1.2 million, between 1993 and\\n 1995. If Cleveland defrauded the\\n State of “property,” the nature of\\n that property cannot be economic.\\n\\nId. at 22 (emphasis added). It concluded that “[e]ven when\\ntied to an expected stream of revenue, the State’s right of\\ncontrol does not create a property interest any more than a\\nlaw licensing liquor sales in a State that levies a sales tax on\\n\\n\\n\\n\\n 14\\n\\fliquor.” Id. at 23. 13 The money collected from application\\nand processing fees was an integral part of the state\\nregulatory program and it did not create any property interest.\\nSee id.\\n\\n The purpose of the Pennsylvania Motor Vehicle Code\\nis to “promote the safety of persons and property within the\\nstate.” Mauer v. Boardman, 7 A.2d 466, 472 (Pa. 1939).\\nMoreover, issuing traffic tickets is a crucial element in the\\nenforcement of the Motor Vehicle Code: it is a quintessential\\nexercise of state police power. Alfano and Hird conclude,\\nmuch like Cleveland, that no property interest could arise\\nfrom revenue generated from the state’s exercise of its police\\npower in the form of a traffic-ticket fine. They see nothing\\nbut a regulatory program here. But this ignores crucial\\naspects of the case before us that make it different.\\n\\n Simply stated, fees charged to obtain a license cannot\\nbe equated with fines and costs that result from a traffic\\nticket. The license fee was imposed, adjusted, and collected\\nsolely by the state’s exercise of its regulatory authority. In\\ncontrast, here the state’s police power is exercised when a\\ncitation is issued, but this ticket merely establishes the\\nsummary violation with which the person is charged. Once a\\nperson has been charged, it is judicial power (not the state’s\\npolice power) that is exercised to determine whether the\\n\\n\\n\\n\\n13\\n Cleveland also held that Government-issued licenses have\\nno intrinsic economic worth before they are given to\\napplicants. Id. at 23.\\n\\n\\n\\n\\n 15\\n\\fperson is guilty and, if guilty, to impose the fine and costs. 14\\nThese fines and costs, although specified by the Motor\\nVehicle Code, cannot be cabined as a product of the state’s\\nregulatory authority. They are part and parcel of the\\njudgment of the court. With this in mind, it is significant that\\nthe indictment does not focus on how the citations were\\nissued (which would implicate police power), but rather\\nalleges that the judicial process was rigged to produce only\\njudgments that imposed lower fines—or most often—no fines\\nand costs at all. 15\\n\\n But this raises a further question: can a criminal\\njudgment held by the government ever be “property?” The\\nCourt in Cleveland offered a critique in its analysis of a\\n\\n14\\n The Traffic Court was not an administrative tribunal.\\nRather, it was part of the First Judicial District of\\nPennsylvania. App. 186 (Indictment ¶ 2). See also supra\\nnote 6 and accompanying text.\\n15\\n On this point, it is noteworthy that the Supreme Court also\\nsaid the following: “We resist . . . [any invitation] to approve\\na sweeping expansion of federal criminal jurisdiction in the\\nabsence of a clear statement by Congress. . . . ‘[U]nless\\nCongress conveys its purpose clearly, it will not be deemed to\\nhave significantly changed the federal-state balance’ in the\\nprosecution of crimes.” Cleveland, 531 U.S. at 24-25\\n(quoting Jones v. United States, 529 U.S. 848, 858 (2000)).\\nAs we discuss later, the legal tradition of understanding\\njudgments as property is long-established. Consequently, the\\nconcern about expanding the reach of federal fraud statutes to\\nnew classes of property that was present in the deliberation of\\nstate licenses in Cleveland is not at issue here.\\n\\n\\n\\n\\n 16\\n\\fdifferent issue (whether licenses were analogous to patents)\\nthat is apropos to answering this question.\\n\\n [W]hile a patent holder may sell\\n her patent, see 35 U.S.C. § 261 . .\\n . “patents shall have the attributes\\n of personal property” . . . the State\\n may not sell its licensing\\n authority. Instead of a patent\\n holder’s interest in an unlicensed\\n patent, the better analogy is to the\\n Federal Government’s interest in\\n an unissued patent. That interest,\\n like the State’s interest in\\n licensing video poker operations,\\n surely implicates the\\n Government’s role as sovereign,\\n not as property holder.\\n\\nCleveland, 531 U.S. at 23–24. Fines imposed by judges are\\ncriminal penalties that “implicate[] the Government’s role as\\nsovereign.” Id. at 24. Judgments ordering traffic fines and\\ncosts cannot be sold and, in the logic of Cleveland, would\\nseem then to have no intrinsic economic value. Indeed, the\\npenal (non-economic) nature of the fine is undeniable because\\nthe failure to pay a fine can result in the imposition of\\nsentences of greater consequence, including imprisonment.\\nSee Pa. R. Crim. P. 706 cmt. But Cleveland is not the last\\nword. As we will discuss below, a Supreme Court opinion\\nissued five years later, Pasquantino v. United States, 544 U.S.\\n349 (2005), forecloses the defendants’ argument.\\n\\n\\n\\n\\n 17\\n\\f Finally, we note a dissimilarity between this case and\\nCleveland, highlighted by the District Court, on the\\nsignificance of the monetary interest that the Government\\nassociates with the fraud. The Cleveland Court regarded the\\nlicensing fees as integral to the regulatory effort and collateral\\nto the matter at hand. The indictment there centered on the\\nscheme to obtain liceneses, and did not even raise the\\nlicensing fees. See Cleveland, 531 U.S. at 22. Indeed, those\\ncharged with the fraud paid all the appropriate fees; there was\\nno evidence that the government suffered any economic\\ndetriment. Id.\\n\\n In contrast, the indictment here explicitly states that\\nthe scheme deprived the City and the Commonwealth of\\nmoney, and it describes the object of the scheme as obviating\\njudgments of guilt that imposed the fines and costs. Unlike\\nCleveland, the fines and costs play a central role in the\\nscheme as alleged.\\n\\n Alfano and Hird next focus on our decision in Henry\\nto argue that the Government cannot claim to have a property\\nright because the Government never had a legal claim to the\\nfines and costs at any point in the scheme. In Henry, we\\nexamined convictions for wire fraud arising from a\\ncompetitive bidding process among banks to receive deposits\\nof a public agency’s bridge tolls. Henry v. United States, 29\\nF.3d 112 (3d Cir. 1994). Appellants—public employees—\\nwere convicted of mail fraud for giving one bank confidential\\ninformation about bids from other banks. Id. at 113. We\\nidentified several problems, 16 but Alfano and Hird highlight\\n\\n16\\n The Supreme Court had already made clear that “a\\ngovernment official’s breach of his or her obligations to the\\n\\n\\n\\n\\n 18\\n\\four observation in Henry that the object of the mail and wire\\nfraud must be something to which the victim could claim a\\nright of entitlement. Id. at 115 (“a grant of a right of\\nexclusion”) (citing Carpenter, 484 U.S. at 26-27)). 17 Indeed,\\nwe noted that a bank’s property right to the tolls would attach\\nonly after the funds were deposited. Id. at 114. So the banks\\nthat lost the bidding process never had a basis to claim any\\nlegally recognized entitlement to the toll deposits. 18 Id. at\\n115. A fraud claim cannot rest on the bidders being cheated\\nout of an opportunity to receive the deposits. For these\\nreasons, we concluded that the indictment did not allege a\\nscheme to obtain fraudulently someone’s “property.” Id. at\\n116.\\n\\n Here, the Government alleged that the defendants\\n“were depriving . . . Philadelphia and . . . Pennsylvania of\\nmoney which would have been properly due as fines and\\ncosts” by making it possible for certain well-connected\\nindividuals to avoid a judgment of guilt that imposed an\\nobligation to pay appropriate statutory fines. App. 197\\n\\n\\npublic or an employee’s breach of his or her obligations to an\\nemployer” did not fall within the scope of Section 1343.\\nHenry, 29 F.3d at 114 (citing Carpenter, 484 U.S. at 25).\\n17\\n To assess whether a particular claim is a legal entitlement,\\n“we look to whether the law traditionally has recognized and\\nenforced [the entitlement] as a property right.” Henry, 29\\nF.3d at 115.\\n18\\n They were, no doubt, robbed of a fair process, but we could\\nnot identify any legal tradition that recognized this\\ndeprivation as a property right. Id. at 115.\\n\\n\\n\\n\\n 19\\n\\f(Indictment ¶ 38). But Appellants stress that, like the\\ndeposits in Henry, the indictment here alleged an entitlement\\nthat does not yet exist because a person must be adjudicated\\n(or plead) guilty before they must pay any fines or costs.\\nNone of the cases directly associated with Alfano and Hird\\nresulted in a guilty judgment. As a result, they argue, the\\nGovernment cannot claim here that it was cheated of an\\nentitlement, because they were only fines and costs that the\\npeople might have owed if they had been found guilty.\\n\\n The District Court said it well. Accepting this\\nargument “would permit the alleged conspirators” to take\\nadvantage of their “unique position” in this case “to enter into\\na scheme to commit fraud and then hide behind the argument\\nthat the success of their fraud precludes prosecution under the\\n‘money or property interest’ requirement of the mail and wire\\nfraud statutes.” Sullivan, 2013 WL 3305217, at *7.\\nAppellants cannot rest on the very object of their scheme (to\\nwork on behalf of favored individuals to obviate judgments of\\nguilt and the imposition of fines and costs) as the basis to\\nclaim that there is no fraud. Indeed, the not-guilty judgments\\nthat Alfano and Hird worked to obtain through the\\nextrajudicial system were alleged in the indictment as\\nevidence of the scheme itself.\\n\\n Even if some of the cases in the extra-judicial system\\nwould have been judged not guilty in a real adjudication it is\\n(as the District Court correctly noted) the intent of the\\nscheme, not the successful execution of it, that is the basis for\\ncriminal liability. See Neder v. United States, 527 U.S. 1, 25\\n(1999) (In the criminal context, the court focuses on the\\nobjective of the scheme rather than its actual outcome; what\\noperatives intended to do, not whether they were successful in\\n\\n\\n\\n\\n 20\\n\\fdoing it.); United States v. Rowe, 56 F.2d 747, 749 (2d Cir.)\\n(“Civilly of course the [mail fraud statute]would fail without\\nproof of damage, but that has no application to criminal\\nliability.”), cert. denied 286 U.S. 554 (1932). The indictment\\ngenerally alleges not just that Appellants operated a system\\nthat operated outside the bounds of Traffic Court procedures,\\nbut that it did so for the purpose of obviating judgments of\\nguilt imposing fines and costs in those selected cases. See,\\ne.g., supra note 8. Moreover, we note that in one case not\\ndirectly involving either Alfano or Hird, the indictment\\nalleged that fines and costs were not just obviated, but were\\nactually erased by an alleged co-conspirator traffic court\\njudge who ignored the conviction, backdated a continuance,\\nand “adjudicated” the person not-guilty. App. 228-29\\n(Indictment ¶¶ 108-113). This episode serves to highlight\\nthat the entire scheme was centered on keeping (or taking)\\njudgments out of the hands of the Government to prevent the\\nimposition of fines and costs. As a result, Appellants’\\nreliance on our justice system’s presumption of innocence as\\na basis to argue against the existence of a governmental\\nproperty interest is a red herring that is properly disregarded\\nhere.\\n\\n Accordingly, we conclude that the indictment’s\\nallegation that the scheme had an objective of depriving\\n“Philadelphia and . . . Pennsylvania of money which would\\nhave been properly due as fines and costs” is not undermined\\nby the lack of guilty verdicts. App. 197 (Indictment ¶38\\n(emphasis added)).\\n\\n Alfano and Hird next highlight that, in Henry, our\\nproperty interest analysis centered on “whether the law\\ntraditionally has recognized and enforced [the entitlement in\\n\\n\\n\\n\\n 21\\n\\fquestion] as a property right.” 29 F.3d at 115. Appellants\\nassert that traffic fines and costs typically have not been\\nconsidered economic property and are unsupported by any\\nlegal tradition sufficient to ground charges of wire and mail\\nfraud. As we have already noted we disagree with any\\nconclusion that the fines and costs at issue have no intrinsic\\neconomic value. But we turn to another decision of the\\nSupreme Court that came after Cleveland to address squarely\\nwhether jurisprudence supports our conclusion.\\n\\n In 2005 the Supreme Court reviewed convictions\\narising from a scheme to smuggle large quantities of liquor\\nfrom the United States into Canada, evading Canadian taxes.\\nSee Pasquantino v. United States, 544 U.S. 349, 353 (2005).\\nThe Court noted that the right to be paid has been routinely\\nrecognized as property, id. at 355–56, 19 observing that there is\\nan equivalence between “money in hand and money legally\\ndue,” id. at 356. Affirming the conviction, the Court said:\\n“Had petitioners complied with this legal obligation, they\\nwould have paid money to Canada. Petitioners’ tax evasion\\ndeprived Canada of that money, inflicting an economic injury\\nno less than had they embezzled funds from the Canadian\\ntreasury.” Id. It concluded that: “[t]he object of petitioners’\\nscheme was to deprive Canada of money legally due, and\\ntheir scheme thereby had as its object the deprivation of\\nCanada’s ‘property.’” Id. Under Pasquantino, then, traffic\\ntickets (or more precisely, judgments arising from them) are\\nconsidered an “entitlement to collect money from individuals,\\n\\n\\n19\\n The Court cited 3 W. Blackstone, Commentaries on the\\nLaws of England 153–155 (1768), which classified the right\\nto sue on a debt as personal property.\\n\\n\\n\\n\\n 22\\n\\fthe possession of which is ‘something of value.’” 544 U.S. at\\n355 (quoting McNally, 483 U.S. at 358). 20 We conclude that\\na scheme to obviate judgments imposing fines, effectively\\npreventing the government from holding and collecting on\\nsuch judgments imposes an economic injury that is the\\nequivalent of unlawfully taking money from fines paid out of\\nthe Government’s accounts. See id. at 358.\\n\\n Alfano and Hird focus, finally, on the role that a\\njudge’s discretion plays in the adjudication of a case,\\nasserting that the uncertainty this creates about outcomes in\\nany given case undermines any argument that a judgment in a\\nTraffic Court case can be claimed as an entitlement to\\nproperty. To the extent that this merely rephrases the issue of\\nguilt or innocence on particular charges, we have already\\n\\n20\\n We also note that Pennsylvania law permits the government\\nto remedy the nonpayment of fines and costs as an unpaid\\ndebt through civil process, enabling the government to\\nbecome a judgment creditor. Pa. R. Crim. P. 706 cmt.\\n(“Nothing in this rule [concerning criminal fines] is intended\\nto abridge any rights the Commonwealth may have in a civil\\nproceeding to collect a fine or costs.”). Because of this, a\\nseparate legal tradition is implicated that recognizes the\\njudgment itself as property. See, e.g., Armada (Singapore)\\nPTE Ltd. v. Amcol International Corp., 885 F.3d 1090, 1094\\n(7th Cir. 2018). This long, stable legal tradition of\\nrecognizing civil judgments for money as property supports\\nthe conclusion that the fines arising from judgments in traffic\\ncourt cannot be regarded merely as implicating the act of a\\nsovereign imposing a criminal penalty. They can be collected\\nby civil process as a debt and are, thus, a property interest.\\n\\n\\n\\n\\n 23\\n\\faddressed it above. To the degree that it refers to a judge’s\\ndiscretion in sentencing, as the District Court noted, there is\\nno such discretion here. 21 The Motor Vehicle Code imposes\\nfines and costs for each violation, eliminating any judicial\\ndiscretion in this regard.\\n\\n D.\\n\\n All of this leads us to conclude that the District Court\\ndid not err by denying the motion to dismiss. We conclude\\nthat, as alleged, this scheme had the objective of preventing\\nthe City of Philadelphia and the Commonwealth of\\nPennsylvania from possessing a lawful entitlement to collect\\nmoney in the form of fines and costs—a property interest—\\nfrom individuals who Alfano and Hird assisted. We will thus\\naffirm the convictions of Appellants Alfano and Hird.\\n\\n III.\\n\\n Appellants Tynes, Lowry, and Mulgrew\\n\\n A.\\n\\n\\n\\n\\n21\\n We question, in general, the relevance of an entity’s\\nauthority to relinquish a just entitlement or to forbear an\\nobligation that an entitlement imposes upon another, as a\\nbasis to call into doubt the legitimacy of, or the very existence\\nof the entitlement. But see United States v. Mariani, 90 F.\\nSupp. 2d 574, 583 (M.D. Pa. 2000) (Discretionary civil fines\\nand penalties “may be too speculative to constitute a valid\\nproperty interest.”) (internal citation omitted).\\n\\n\\n\\n\\n 24\\n\\f In 2011, the United States Attorney presented to the\\nGrand Jury evidence arising from the Federal Bureau of\\nInvestigation’s inquiry into the Traffic Court. Appellants\\nLowry, Mulgrew, and Tynes testified and the Government\\nbrought perjury charges against them for statements they\\nmade to the Grand Jury. After Hird and Alfano pleaded\\nguilty, the rest of the Appellants went to trial. The jury\\nacquitted Lowry, Mulgrew, and Tynes of all counts against\\nthem on wire fraud, mail fraud, and conspiracy. But it found\\nthem guilty of perjury. Tynes, Lowry, and Mulgrew\\nchallenge their convictions by raising similar legal arguments\\nabout the sufficiency of the evidence.\\n As with all challenges to the sufficiency of the\\nevidence, we use a highly deferential standard of review. See\\nUnited States v. Caraballo-Rodriguez, 726 F.3d 418, 430 (3d\\nCir. 2013) (en banc). We examine the record in a light most\\nfavorable to the prosecution, and will not disturb the verdict if\\n“any rational trier of fact could have found the essential\\nelements of the crime beyond a reasonable doubt.” United\\nStates v. McGee, 763 F.3d 304, 316 (3d Cir. 2014) (emphasis\\nin original) (quoting Jackson v. Virginia, 443 U.S. 307, 319\\n(1979)). Tynes, Lowry, and Mulgrew argue that the\\nquestions asked of them at trial were fatally vague and/or that\\ntheir answers were truthful. As a result, they contend that\\nthese questions and answers are an inadequate basis for a\\nperjury conviction.\\n\\n A conviction for perjury before a grand jury requires\\nthe Government to prove that the defendant took an oath\\nbefore the grand jury and then knowingly made a “false\\nmaterial declaration.” 18 U.S.C. § 1623. But we recognized\\n(in the context of a sentencing enhancement for perjury) that\\nsometimes “confusion, mistake, or faulty memory” results in\\n\\n\\n\\n\\n 25\\n\\finaccuracies that cannot be categorized as a “willful attempt\\nto obstruct justice” under perjury statutes. United States v.\\nMiller, 527 F.3d 54, 75 (3d Cir. 2008) (quoting U.S.\\nSentencing Guidelines Manual § 3C1.1 cmt. n.2 (U.S.\\nSentencing Comm’n 2003). So we do understand that\\n“[p]recise questioning is imperative as a predicate for the\\noffense of perjury.” Bronston v. United States, 409 U.S. 352,\\n362 (1973).\\n\\n Precision, however, is assessed in context. An\\nexaminer’s line of questioning should, at a minimum,\\nestablish the factual basis grounding an accusation that an\\nanswer to a particular question is false. Miller, 527 F.3d at\\n78. So a perjury conviction is supported by the record “when\\nthe defendant’s testimony ‘can reasonably be inferred to be\\nknowingly untruthful and intentionally misleading, even\\nthough the specific question to which the response is given\\nmay itself be imprecise.’” United States v. Serafini, 167 F.3d\\n812, 823 (3d Cir. 1999) (quoting United States v. DeZarn,\\n157 F.3d 1042, 1043 (6th Cir. 1998)).\\n\\n Challenges to the clarity of a question are typically left\\nto the jury, which has the responsibility of determining\\nwhether the defendant understood the question to be\\nconfusing or subject to many interpretations. United States v.\\nSlawik, 548 F.2d 75, 86 (3d Cir. 1977). Moreover, consistent\\nwith our standard of review, we will not disturb a jury’s\\ndetermination that a response under oath constitutes perjury\\nunless “it is ‘entirely unreasonable to expect that the\\ndefendant understood the question posed to him.’” Serafini,\\n167 F.3d at 820 (quoting United States v. Ryan, 828 F.2d\\n1010, 1015 (3d Cir. 1987), abrogated on other grounds by\\n\\n\\n\\n\\n 26\\n\\fUnited States v. Wells, 519 U.S. 482 (1997)). 22 On appeal,\\nwe review every aspect of the record pertinent to both the\\nquestion and answer to reach a conclusion about whether, in\\ncontext, the witness understood the question well enough to\\ngive an answer that he or she knew to be false. See Miller,\\n527 F.3d at 78. Our review, however, is focused on glaring\\ninstances of vagueness or double-speak by the examiner at the\\ntime of questioning (rather than artful post-hoc interpretations\\nof the questions) that—by the lights of any reasonable fact-\\nfinder—would mislead or confuse a witness into making a\\nresponse that later becomes the basis of a perjury conviction.\\nQuestions that breach this threshold are “fundamentally\\nambiguous” and cannot legitimately ground a perjury\\nconviction. Id. at 77. 23\\n\\n\\n22\\n The Court of Appeals for the Second Circuit underscored\\nthe high bar this establishes for appellants by noting that a\\nfundamentally ambiguous question is “not a phrase with a\\nmeaning about which men of ordinary intellect could agree,\\nnor one which could be used with mutual understanding by a\\nquestioner and answerer unless it were defined at the time it\\nwere sought and offered as testimony.” United States v.\\nLighte, 782 F.2d 367, 375 (2d Cir. 1986) (quoting United\\nStates v. Lattimore, 127 F. Supp. 405, 410 (D. D.C.), aff’d,\\n232 F.2d. 334 (D.C. Cir. 1955)).\\n23\\n The rule of fundamental ambiguity is intended to\\n“preclude convictions that are grounded on little more than\\nsurmise or conjecture, and . . . prevent witnesses . . . from\\nunfairly bearing the risks associated with the inadequacies of\\ntheir examiners.” Ryan, 828 F.2d at 1015.\\n\\n\\n\\n\\n 27\\n\\f That is the law applicable to the claims raised by\\nTynes, Lowry and Mulgrew. But, because our review is fact-\\ndependent, and because each raises some unique issues, we\\nwill address each of their claims individually. 24\\n B.\\n\\n\\n\\n\\n24\\n Adopting the arguments made by Alfano and Hird,\\nAppellants Lowry, Mulgrew and Tynes assert that the\\nGovernment improperly charged them with conspiracy, wire\\nfraud, and mail fraud. Therefore, they assert, their joint trial\\non these counts of the indictment prejudiced the jury’s\\ndeliberation on the charges of perjury. They claim such\\nevidence would have been excluded under Federal Rule of\\nEvidence. 403. They also contend that, without a charge of\\nconspiracy, the joinder of their cases would have been\\nimpermissible under Federal Rule of Criminal Evidence 8(b)\\nor, at the very least, severance of their cases would have been\\nwarranted under Federal Rule of Criminal Procedure 14(a).\\nCertainly, where there is evidence of prejudice resulting from\\n“spillover” evidence from counts that should have been\\ndismissed, reversal is warranted. See United States v. Wright,\\n665 F.3d 560, 575-577 (3d Cir. 2012). But we have\\nconcluded that the District Court did not err by denying the\\nmotion, under Federal Rule of Civil Procedure 12(b)(3), to\\ndismiss the conspiracy, wire fraud and mail fraud counts of\\nthe indictment. Thus, Appellants’ spillover argument has\\nbeen nullified. Likewise, Appellants have no basis to claim\\nthat the Court unfairly prejudiced them by not granting\\nseparate trials.\\n\\n\\n\\n\\n 28\\n\\f Appellant Tynes 25\\n\\n Appellant Tynes claims her convictions for perjury at\\nCount 71 and Count 72 lack sufficient evidence because she\\nwas responding to questions that were fundamentally\\nambiguous. The perjury charged at Count 71 arises from the\\nfollowing exchange.\\n\\n Q. In all the years\\n you’ve been [at Traffic\\n Court] have you\\n ever been asked to give\\n\\n\\n25\\n Tynes filed a separate motion to dismiss. App. 291-99.\\nThe record also contains Tynes’ proposed order to join\\nSullivan’s motion to dismiss. App. 290. However, Tynes’\\nmotion contains no such request. Moreover, the\\nGovernment’s response to the motions notes that Lowry and\\nMulgrew moved to join (without argument), and makes no\\nmention of Tynes. The District Court’s ruling on Tynes’\\nmotion to dismiss relates only to the arguments she made\\nseparately in her brief. As a result, we cannot consider\\nTynes’ arguments on appeal that relate to those raised in\\nSullivan’s motion. Moreover, since she failed to raise any of\\nthe arguments she made in her separate motion to dismiss,\\nthese arguments are waived. With that said, we will affirm\\nthe District Court’s ruling on the Motion raised by Sullivan\\nand joined by the five Appellants. Therefore, we need not\\naddress Tynes’ assertion that the District Court’s mishandled\\nher joinder motion because it does not prejudice the outcome\\nof her appeal.\\n\\n\\n\\n\\n 29\\n\\f favorable treatment on\\n a case to anybody?\\n\\n A. No, not favorable\\n treatment. People basically\\n know me. The lawyers\\n know me. The court\\n officers know me. I have\\n been called a nononsense\\n person because I’m just not\\n that way. I take my\\n position seriously, and the\\n cards fall where they may.\\n\\nApp. 255, 5720. 26 Tynes contends that the Government\\npursued a novel theory here (applying federal fraud statutes to\\nallegations of ticket fixing) and used the vague term\\n“favorable treatment” to gloss over its uncertainty about what,\\nultimately, would constitute an illegal act. She points out that\\nthe term had not been used before in reference to this case\\nand that the Government offered no explanation or definition\\nof the term to alert Tynes to the intent of the question.\\n\\n Also, from Tynes’ perspective, every litigant\\nappearing before a court seeks an outcome that is favorable,\\nthus making “favorable treatment” a term that essentially\\nreferred to “how litigation works.” She claims that its use\\namounted to a fishing expedition designed to capture unfairly\\n\\n26\\n We cite to the testimony quoted in the indictment and the\\nGrand Jury that was used at trial. We note that there are some\\ntypographical inconsistencies between these sources and in\\nthose instances we have quoted the Grand Jury testimony.\\n\\n\\n\\n\\n 30\\n\\fthe entirety of her conduct in the courtroom. She warns that\\nthis is precisely the type of “open-ended construction” in\\nquestioning that we found unacceptable in Serafini. 167 F.3d\\nat 822.\\n\\n Tynes makes a related argument against her perjury\\nconviction for Count 72. That conviction is based on this\\nexchange.\\n Q. You’ve never taken\\n action on a request?\\n\\n A. No.\\n\\nApp. 257, 5722. She maintains that the word “request” was\\npresented to the jury as a follow-on to the question grounding\\nCount 71, requiring a person to link the term “favorable\\ntreatment” and the word “request” to make sense of it. She\\nargues that the Government took advantage of the ambiguity\\nof “favorable treatment,” forcing the jury to speculate that\\nTynes interpreted “request” as “favorable treatment.” This\\nreliance on “sequential referents” is, from her perspective,\\nexactly what we criticized in Serafini. 167 F.3d at 821. But\\nshe misconstrues our holding.\\n\\n In Serafini, the surrounding questions focused on a\\ndifferent topic. This bolstered appellant’s argument in that\\ncase that the question on which the perjury conviction rested\\nwas fundamentally ambiguous. Id. The appellant said the\\nmultiplicity of topics in surrounding questions caused the jury\\nto speculate improperly on how he understood the question at\\nissue. We said: “The meaning of individual questions and\\nanswers is not determined by ‘lifting a statement . . . out of its\\nimmediate context,’ when it is that very context which fixes\\n\\n\\n\\n\\n 31\\n\\fthe meaning of the question.” Serafini, 167 F.3d at 821\\n(quoting United States v. Tonelli, 577 F.3d 194, 198 (3d Cir.\\n1978)). In the case of Serafini, the context made the\\nconfusing nature of the question apparent. The various topics\\nin surrounding questions created sufficient ambiguity to\\nundermine the conviction. Id.\\n\\n Here, however, even though the terms used by the\\nexaminer changed, we conclude that the line of questioning—\\nincluding both questions that ground Count 71 and 72—have\\nan obvious, consistent focus.\\n\\n Q. In all the years\\n you’ve been [at Traffic\\n Court] have you\\n ever been asked to give\\n favorable treatment on\\n a case to anybody?\\n\\n A. No, not favorable\\n treatment. People basically\\n know me. The lawyers\\n know me. The court\\n officers know me. I have\\n been called a nononsense\\n person because I’m just not\\n that way. I take my\\n position seriously and the\\n cards fall where they\\n may. Most of the time . . .\\n the people in my Court\\n plea bargain. They know\\n that most of the time,\\n\\n\\n\\n\\n 32\\n\\fninety percent of the time,\\nsay 90 percent, I go with\\nthe police officer’s\\nrecommendation. . . .\\n\\nQ. So, in all those years\\nno one has ever asked you\\nto find somebody not\\nguilty--\\n\\nA. No.\\n\\nQ. --or to find a lesser\\nviolation; find a lesser fine;\\nanything along those lines?\\n\\nA. No. I will say to\\npeople go to court, go to\\ntrial and see what\\nhappens. . . .\\n\\nQ. Ward leaders,\\npoliticians has anyone\\ncalled you and said I\\nhave Johnny Jones coming\\nup next week and I\\nwould appreciate it if -- if\\nyou would look\\nfavorably on him when he\\ncomes through? Has\\nanything like that ever\\nhappened?\\n\\n\\n\\n\\n 33\\n\\f A. Throughout the\\n years ward leaders and\\n people have called all the\\n time and asked me\\n questions. The only thing I\\n will say to them is they\\n need to go to court. If you\\n think it’s a problem, they\\n need to hire a lawyer, or\\n make sure you bring all\\n your evidence to court. If\\n it’s something like\\n inspection, make sure you\\n bring your -- papers and\\n things like that. That’s\\n what I would tell them to\\n do. I give advice that\\n way. I don’t know if that’s\\n wrong or not, but I do.\\n\\n Q. You’ve never taken\\n action on a request?\\n\\n A. No.\\n\\nApp. 528-29, 530; 5720-22. This broader context would give\\nany reasonable fact-finder more than enough basis to\\nconclude that the witness knew the point of reference for both\\nthe term “favorable treatment” and “request” was ticket\\nfixing. In fact, Tynes is asking us to do precisely the thing we\\ncriticized in Serafini, to lift a phrase or statement out of its\\ncontext. Serafini, 167 F.3d at 821. Tynes has not persuaded\\nus that the question harbors any fatal ambiguity.\\n\\n\\n\\n\\n 34\\n\\f Tynes next contends that her responses to questions\\ngrounding Count 71 and Count 72 cannot support convictions\\nfor perjury because they were literally true. Of course,\\nperjury arises only from making knowingly false material\\ndeclarations. 18 U.S.C. § 1623. Therefore, a witness who\\nanswers an ambiguous question with a non-responsive answer\\nthat the witness believes is true—even if the answer is\\nmisleading—does not commit perjury. See Bronston, 409\\nU.S. at 361-62; see also United States v. Reilly, 33 F.3d 1396,\\n1416 (3d Cir. 1994).\\n Tynes argues that, because she regarded the question\\nabout favorable treatment as vague, she interpreted it as\\nasking whether she accepted any bribes in exchange for a\\njudgment of not guilty or a reduced punishment. Her\\nresponse of “no” (grounding Count 71) is literally true—she\\nsays—because there is no evidence that she accepted any\\nbribes in return for giving preferential outcomes in the\\nadjudication of some individuals who were cited for breaking\\nthe law. Under this theory, the same argument can also\\nnegate the charges at Count 72 since she says she did not\\naccept any “requests” (bribes) in exchange for preferential\\ntreatment.\\n\\n Although the jury is permitted reasonable inferences\\ndrawn from the record about the witness’ understanding of\\nthe truth or falsity of the answer, it is not (as we noted above)\\npermitted to reach conclusions based merely on speculation\\nor conjecture. See Bronston, 409 U.S. at 359. Tynes’\\nassertion of literal truth is undermined because the trial record\\nsupports no reasonable inference that the Government was\\nasking her about matters outside of the alleged bribes, nor\\n\\n\\n\\n\\n 35\\n\\fdoes it provide any reason why Tynes would interpret the\\nquestion in this way.\\n\\n Finally, Tynes contends that the evidence was not\\nsufficient to support her conviction. However, the jury heard\\nTynes’ personal assistant, Medaglia “Dolly” Warren, testify\\nthat she received from personal assistants of other judges\\nthree to four cards per week requesting consideration. Each\\ncard had the name of a person who was appearing before\\nTynes on that day. She passed these to Tynes’ court officer,\\nwho was present during the proceedings. App. 4593-95.\\nTynes also instructed Warren to give similar cards to the staff\\nof other judges. App. 4598. Warren knew to act discreetly\\nwhen she was transferring the cards. App. 4599. The jury\\nalso heard testimony from those who actually received\\nconsideration from Tynes. For example, Timothy Blong was\\ncited for reckless driving and driving without a license. He\\nadmitted in testimony that he did not have a license when he\\nwas cited. App. 3150. He also testified that he requested\\nconsideration through a Traffic Court employee (Danielle\\nCzerniakowski, who worked as a personal assistant to a\\nTraffic Court judge) with whom he was acquainted. When he\\nappeared in court, he was simply told that his case was\\ndismissed. He did not have to say anything, App. 3159-60.\\nBlong testified he was told his case was dismissed because\\nthe police officer did not appear (App. 3160-61), but the\\ngovernment produced evidence that an officer was present.\\nApp. 3193-96. The Government also showed that Tynes was\\nthe presiding judge in Blong’s case. App. 3193. Richard\\nCarrigan—who admitted in testimony that he drove through a\\nred light—described a similar experience in which, after\\nrequesting favorable treatment through Judge Lowry’s\\npersonal assistant, Kevin O’Donnell, his case was dismissed\\n\\n\\n\\n\\n 36\\n\\fby Judge Tynes without ever having to say a word. App.\\n3178-82.\\n\\n Tynes does not challenge any of this in her appeal.\\nInstead she focuses on the weight of other evidence and\\nperceived gaps in testimony. We conclude that all of this\\nprovides more than a sufficient basis to support a reasonable\\njury’s conclusion that Tynes did “give favorable treatment on\\na case,” and did “take[] action on a request.” App. 528-30.\\n\\n For all of these reasons, we will affirm the judgment of\\nconviction on perjury as to Appellant Tynes.\\n C.\\n\\n Appellant Lowry 27\\n\\n Like Tynes, Appellant Lowry advances arguments of\\nfundamental ambiguity and literal truth. His perjury\\nconviction centered on one question and answer.\\n\\n\\n Q. So if I understand\\n your testimony, you’re\\n saying you don’t give out\\n special favors; is that right?\\n\\n A. No, I treat\\n everybody in that\\n courtroom the same.\\n\\n\\n27\\n Lowry was charged with perjury in Count 69 of the\\nindictment.\\n\\n\\n\\n\\n 37\\n\\fApp. 489. Lowry attacks the Government’s use of the term\\n“special favors” as one with many potential meanings.\\nHowever, as we noted above in our reference to Serafini, we\\nreject arguments that lift individual questions or answers—or\\nindividual phrases embedded in either—from the context of\\nsurrounding questions that help fix their meaning. Serafini,\\n167 F.3d at 821. The larger context for the question asked of\\nLowry is as follows.\\n\\n Q. So if I understand\\n your testimony, you’re\\n saying you don’t give out\\n special favors; is that right?\\n\\n A. Well, I know it\\n appears that way; and it’s\\n hard for me to prove to\\n you . . .\\n\\n Q. I’m just asking,\\n your testimony is you don’t\\n give out special favors, is\\n that right?\\n\\n A. No, I treat\\n everybody in that\\n courtroom the same.\\n\\n Q. You treat everybody\\n fairly?\\n\\n A. I’m a lenient judge.\\n I will admit to that.\\n\\n\\n\\n\\n 38\\n\\f Q. You treat everybody\\n fairly?\\n\\n A. Yes, I do.\\n\\n Q. And these notices\\n that you get from your\\n personal or from other\\n people, they don’t affect\\n you in any way; is that\\n right?\\n\\n A. Virtually no effect\\n at all.\\n\\n\\nApp. 489-90.\\n\\n Lowry’s assertion that the phrase “special favors” is\\nsubject to many interpretations is unconvincing. We note two\\nthings. First, the line of questioning reasonably supports a\\nconclusion that this inquiry referenced conduct associated\\nwith allegations of ticket fixing. Second, Lowry answered as\\nif his understanding of the question was consistent with this\\ninterpretation. He said that he was aware it may “appear” that\\nhe gave special favors. He also defended himself by saying\\nthat such requests did not affect his conduct in the courtroom\\nat all. If—as he says—he understood “special favors” to\\nmean fair treatment, his answer makes no sense.\\n\\n Lowry next claims that, since the question was\\nstructured to elicit a negative response, his answer cannot be\\n\\n\\n\\n\\n 39\\n\\fused as the basis of a perjury charge. Relatedly, he contends\\nthat the question was merely a summation of an answer that\\nhe gave just before this question. In essence he argues that\\nthis was a leading question. We have concluded, in the\\ncontext of a trial, that the propriety of leading questions in\\ndirect examinations is a matter left to the sound discretion of\\nthe trial judge. See United States v. Montgomery, 126 F.2d\\n151, 153 (3d Cir. 1942). We extend the same deference here\\nto the District Court’s decision to admit this portion of the\\nGrand Jury transcript. We do not regard the question as\\nfundamentally unfair or unclear, or something outside the\\nnorm of questions typically employed on direct examination.\\nFor these reasons, we conclude that the District Court did not\\nabuse its discretion here.\\n\\n Alternatively, Lowry argues that—if the term is\\nunderstood to reference fixing tickets—there is no evidence\\nto contradict his response that requests for special favors did\\nnot impact any of his adjudications. We do not agree. The\\nrecord contains the following testimony.\\n\\n Kevin O’Donnell, who was Lowry’s personal\\nassistant, testified about Lowry’s involvement with requesting\\nand giving consideration. He said that Lowry made four to\\nfive requests each month for consideration and that\\nO’Donnell transmitted them to the personal assistants of other\\nTraffic Court judges. App. 1854. Likewise, he said other\\njudges transmitted requests for consideration to Lowry\\nthrough their personal assistants. App. 1812-13. Appellant\\nHird and various politicians also made requests of Lowry for\\nconsideration. App. 1827-28, 1832-33. O’Donnell said he\\nwould give the requests to Lowry on the day scheduled for\\nhearing on the citation. App. 1818-19. The requests were for\\n\\n\\n\\n\\n 40\\n\\fpreferential treatment in the adjudication of particular\\ncitations: typically the requests were for “removing points”\\nand obtaining a “not guilty” judgment. App. 1819.\\nO’Donnell said he sometimes had to signal Lowry in the\\ncourtroom to remind him that a particular case was supposed\\nto receive consideration. App. 1822-23. He testified from\\nhis own observation that Lowry typically honored requests\\nfor consideration. App. 1829. He also declared if Lowry\\nclaimed he never gave consideration or asked it of others, this\\nwould not be truthful. App. 1813. The same assistant\\ntestified that if Lowry testified that he ignored requests for\\nconsideration, or that he never honored requests for\\nconsideration, that testimony would not be true. App. 1855.\\nThe Government also asked: “If [Lowry] claimed that . . .\\nconsideration requests had no impact when he disposed of\\ncases, would that be true?” The assistant responded,\\n“probably not.” Id.\\n\\n Another witness, Walt Smaczylo, employed as a court\\nofficer in the Traffic Court, provided an example of how\\n“consideration” worked in the courtroom.\\n\\n When someone comes in,\\n for example, for a reckless\\n driving ticket and that\\n judge normally comes\\n down pretty hard and finds\\n that defendant guilty and\\n then the same type cases\\n come in and you see a\\n defendant walk out either\\n not guilty or a significantly\\n reduced charge.\\n\\n\\n\\n\\n 41\\n\\fApp. 1912. The Government asked Smaczylo if he saw\\nLowry preside over such instances, and he answered: “That’s\\ncorrect, yes.” Id. Smaczylo testified that requests for\\nconsideration were written on small note cards or “sticky”\\nnotes and that he saw Lowry in possession of these cards and\\nnotes. App. 1914. He also provided a generalized example\\nof consideration, based on his observation and understanding,\\nin which a reckless driving citation would be reduced to\\ncareless driving. In such instances, he indicated that a $300\\nto $400 fine would be cut in half. He said: “So, that money\\nwas not collected, obviously, by the state. If that ticket was\\nfixed then I saw it as stealing.” App. 1919. Smaczylo was\\nasked: “[I]f Judge Lowry testified at the [G]rand [J]ury he\\ndidn’t give consideration would that be a truth or would that\\nbe a lie?” He responded: “That would not be the truth.”\\nApp. 1921.\\n\\n All of this testimony provides more than a sufficient\\nbasis to support a reasonable jury’s conclusion that Lowry\\nwas not truthful when he responded to the Government’s\\nquestion about special favors. 28\\n\\n28\\n Lowry points to the cross-examination of both witnesses in\\nwhich they seem to equivocate on some of their observations\\nand responses to the Government. For instance O’Donnell\\nstated his view that giving consideration was no different\\nfrom the leniency that Lowry extended to every other person\\nwho pleaded not guilty and appeared at the hearing.\\nHowever, we do not weigh the credibility of evidence in the\\nrecord. We only judge whether there is sufficient evidence in\\nthe record to support a reasonable fact-finder’s determination\\nthat the record supported conviction of Lowry on a charge of\\n\\n\\n\\n\\n 42\\n\\f Finally, Lowry argues that the Government’s question\\nsought a dispositive response from him on the charges of\\nconspiracy and fraud. He says an affirmative answer to\\nwhether he gave “special favors” to certain individuals would\\nhave been enough to convict him of conspiracy and fraud.\\nThus, he maintains that his acquittal on charges of mail fraud,\\nwire fraud, and conspiracy is res judicata as to the perjury\\ncharges that are based on his answer. He said he did not\\ncommit fraud and the jury agreed with him. Therefore, he\\nsays, he did not perjure himself. However, even if we\\naccepted Lowry’s characterization of the question, we reject\\nthis argument.\\n\\n First, a jury’s determination that Lowry’s ticket-fixing\\nconduct did not constitute wire fraud, mail fraud, and\\nconspiracy does not preclude its determination that he lied\\nabout this conduct before the Grand Jury. Moreover, as the\\nSupreme Court has articulated, a verdict on one count that\\nseems to be at odds with another “shows that either in the\\nacquittal or the conviction the jury did not speak their real\\nconclusions, but that does not show that they were not\\nconvinced of the defendant’s guilt.” United States v. Powell,\\n469 U.S. 57, 63 (1984) (quoting Dunn v. United States, 284\\nU.S. 390, 393 (1932)). It is impossible to know in such cases\\nwhether the verdicts were an exercise of lenity by the jury or\\noutright error.\\n\\n Nonetheless, as the Powell Court noted, any\\nassessment of the jury’s rationale for its verdicts “would be\\n\\n\\nperjury. See United States v. Richardson, 658 F.3d 333, 337\\n(3d Cir. 2011).\\n\\n\\n\\n\\n 43\\n\\fbased either on pure speculation or would require inquiries\\ninto the jury’s deliberations that courts generally will not\\nundertake.” Id. at 58. So, even if Lowry was correct that the\\nacquittal is relevant to his response to the question grounding\\nhis perjury conviction, we are not convinced that his perjury\\nconviction is unfounded. Given the substantial body of\\nevidence presented to the jury, nothing here demands that we\\nabandon the deference we traditionally give to the collective\\njudgment of the jury. For all these reasons, we will affirm the\\njury’s verdict as to Lowry.\\n\\n D.\\n\\n Appellant Mulgrew 29\\n\\n Mulgrew does not argue that the question asked at the\\nGrand Jury was ambiguous, he simply maintains that his\\nstatement was truthful. 30 The questions and answers\\ngrounding his perjury conviction are as follows.\\n\\n Q. How about your\\n personal, has your personal\\n received any calls like that\\n from other judges, other\\n ward leaders that she’s\\n conveyed to you, saying\\n\\n29\\n Mulgrew was charged with perjury in Count 70 of the\\nindictment.\\n30\\n Mulgrew’s claims are reviewed for plain error because he\\ndid not make the same argument before the District Court.\\nUnited States v. Syme, 276 F.3d 131, 148 (3d Cir. 2002).\\n\\n\\n\\n\\n 44\\n\\f so-and-so has called about\\n this case?\\n\\n A. If she did, she didn’t\\n convey them to me.\\n\\n\\nApp. 432-33 (emphasis added). Shortly after this, the\\nfollowing exchange occurred:\\n\\n Q. Let me make sure as\\n well that if I got your\\n testimony correct [sic].\\n You’re saying that if other\\n people, whether they be\\n political leaders, friends\\n and family, anybody is\\n approaching your personal\\n and asking her specifically\\n to look out for a case, see\\n what she can do in a case,\\n give preferential treatment,\\n however you want to\\n phrase it, that she is not\\n relaying any of that\\n information on to you; is\\n that correct?\\n\\n A. No, she isn’t.\\n\\nApp. 438. As to the first exchange, Mulgrew claims that the\\nGovernment’s use of the word “call” referred exclusively to\\ntelephone calls. This mattered to him, he says, because others\\n\\n\\n\\n\\n 45\\n\\fhad testified that personal assistants of other Traffic Court\\njudges would give index cards to his personal assistant in his\\nchambers or robing room containing names of some\\nindividuals whose tickets were listed for hearing. Mulgrew\\nclaims that there is no evidence that he ever received any\\nphone calls asking that he act extrajudicially to give well-\\nconnected individuals preferential treatment. The implication\\nis that, had the Government asked him about receiving index\\ncards with such requests, his answer would have been\\ncompletely different.\\n As with Tynes and Lowry, our review of claims of\\nliteral truth drives us to examine the context of the question.\\n\\n Q. How about other\\n judges, have other judges\\n ever approached you or\\n called to you or get a\\n message to you either\\n themselves or through their\\n personals saying that\\n someone is going to be on\\n your list next week or next\\n Monday and can you could\\n some special way towards\\n the case?\\n\\n A. No, they haven’t.\\n\\n Q. Never?\\n\\n A. No.\\n\\n\\n\\n\\n 46\\n\\fQ. How about your\\npersonal, has your personal\\nreceived any calls like that\\nfrom other judges, other\\nward leaders that she’s\\nconveyed to you saying so\\nand so has called about this\\ncase?\\n\\nA. If she did, she didn’t\\nconvey them to me.\\n\\nQ. And your personal\\nis who?\\n\\nA. Gloria McNasby.\\n\\nQ. Have you ever seen\\non traffic court files --You\\nactually get a file when\\nsomeone’s case is called?\\n\\nA. Right.\\n\\nQ. So the case is called\\nand you get a file presented\\nto you; is that right?\\n\\nA. uh-huh.\\n\\nQ. Have you ever seen\\nany index cards or\\nnotations on the file\\n\\n\\n\\n\\n 47\\n\\f indicating that a person has\\n called or taken some\\n special interest in this\\n case?\\n\\n A. Nope.\\n\\nApp. 432-33 (emphasis added). The transcript makes it\\nobvious that Mulgrew’s singular reliance on the reference to a\\n“call” ignores the thrust of the Government’s line of\\nquestions. The questions focus on the substance of the\\ncommunications between Mulgrew’s personal assistant and\\nhimself, rather than the mode of those communications.\\n\\n Mulgrew also claims that he responded truthfully to\\nthe second question.\\n\\n Q. Let me make sure as\\n well that if I got your\\n testimony correct [sic].\\n You’re saying that if other\\n people whether they be\\n political leaders, friends\\n and family, anybody is\\n approaching your personal\\n and asking her specifically\\n to look out for a case, see\\n what she can do in a case,\\n give preferential treatment,\\n however you want to\\n phrase it, that she is not\\n relaying any of that\\n\\n\\n\\n\\n 48\\n\\f information on to you; is\\n that correct?\\n\\n A. No, she isn’t.\\n\\n Q. Wouldn’t you want\\n to know it?\\n\\n A. No, I don’t want to\\n know. Then I never have to\\n worry about what I do in\\n the courtroom.\\n\\nApp. 437-38 (emphasis added). Apparently focusing on the\\nwords “see what she can do,” he says that he answered\\ntruthfully by responding that his personal assistant did not tell\\nhim that people were approaching her and asking her to give\\nthem preferential treatment. But, as with the first question,\\nMulgrew cherry-picks a small part of the question out of\\ncontext, distorting it. The full text and follow up question\\nshow that the thrust of the inquiry was whether Mulgrew’s\\npersonal assistant was informing him of the names of those\\nrequesting preferential treatment from him. And Mulgrew’s\\nresponse to the follow-up question —saying that he did not\\nwant to know so that he did not have to worry about what he\\ndid in the courtroom—is consistent with one who understood\\nthis. App. 438.\\n\\n We conclude that, ultimately, the evidence is sufficient\\nfor a reasonable jury to conclude Mulgrew understood that\\nboth of these questions were focused on whether his personal\\nassistant informed him of requests for him to give preferential\\ntreatment, and that he answered in the negative to both.\\n\\n\\n\\n\\n 49\\n\\f Mulgrew alternatively asserts that the District Court\\nerred by refusing to admit additional testimony from the\\nGrand Jury that he claims is relevant to his perjury\\nconviction. 31 After the Government introduced Mulgrew’s\\nGrand Jury testimony, Mulgrew sought the admission of other\\nportions of his testimony. But the District Court sustained the\\nGovernment’s hearsay objection. The portion of the\\ntranscript supporting the perjury conviction is as follows:\\n\\n Q. [W]hether you have\\n ever been asked to provide,\\n what I’ll call, favorable\\n treatment for people in\\n traffic court or however\\n you define that, whether it\\n would be special handling,\\n keep an eye out for a\\n ticket, do me a favor.\\n Have you ever been asked\\n to provide any type of\\n treatment like that for\\n people in traffic court?\\n\\n A. People have asked\\n me for consideration, but I\\n give consideration to\\n everybody that comes in\\n my courtroom[,] so it\\n\\n31\\n We review the District Court’s ruling on the admissibility\\nof evidence for abuse of discretion. United States v. Green,\\n617 F.3d 233, 239 (3d Cir. 2010).\\n\\n\\n\\n\\n 50\\n\\f doesn’t make a difference\\n to me.\\n\\n\\nApp. 422-23. The basis for the Government’s hearsay\\nobjection to this portion of the testimony was that it raised an\\nout-of-court statement not offered by a party opponent.\\n\\n Mulgrew first contends that the District Court erred by\\nruling that this was hearsay because it was not offered for the\\ntruth of the matter asserted. He says that the testimony was\\ninstead offered to show his state of mind later in his\\ntestimony. See United States v. Hoffecker, 530 F.3d 137,\\n191-92 (3d Cir. 2008). However, we conclude that it was not\\nan abuse of discretion for the District Court to sustain the\\nGovernment’s hearsay objection. It was reasonable for the\\nDistrict Court to conclude here that his response relied on\\nout-of-court statements offered to assert his innocence since\\nhis response conveys a declaration that he treated no person\\ndifferent from another.\\n\\n Mulgrew also argues that this portion of the transcript\\nis admissible under Federal Rule of Evidence 106: “[i]f a\\nparty introduces all or part of a writing or recorded statement,\\nan adverse party may require the introduction, at that time, of\\nany other part—or any other writing or recorded statement—\\nthat in fairness ought to be considered at the same time.”\\nMulgrew maintains that this question and answer provides\\ncontext showing that he did not commit perjury. He also\\nmaintains that the “doctrine of completeness” applies here:\\nfairness demanded the admission of the statements. See\\n\\n\\n\\n\\n 51\\n\\fUnited States v. Soures, 736 F.2d 87, 91 (3d Cir. 1984). 32 We\\nare not convinced.\\n\\n The excerpt at issue occurs many pages before the\\ntestimony regarded as perjurious. It is unrelated in the overall\\nsequence of questions and to the answers grounding his\\nconviction. Moreover, as the intervening pages suggest, it\\nwas separated by the passage of time during questioning. We\\nalso fail to see how Mulgrew’s equivocation over the term\\n“consideration” gives helpful context to his later denial of\\nreceiving requests for consideration. For these reasons, we\\nconclude the District Court did not abuse its discretion by\\nsustaining the Government’s hearsay objection.\\n\\n IV.\\n\\n Appellant Singletary 33\\n\\n\\n32\\n “Under this doctrine of completeness, a second writing may\\nbe required to be read if it is necessary to (1) explain the\\nadmitted portion, (2) place the admitted portion in context, (3)\\navoid misleading the trier of fact, or (4) insure a fair and\\nimpartial understanding.” Soures, 736 F.2d at 91.\\n33\\n Appellant Singletary was charged with making false\\nstatements in Counts 73 and 74 of the indictment. He states\\nin his brief that he ‘joins all arguments on behalf of co-\\nappellants pursuant to Federal Rules of Appellate Procedure\\n28(i).” Singletary Br. 19. To the extent that he joins the\\nargument of prejudice resulting from the trial on the fraud and\\nconspiracy charges, we already have determined that the\\nindictment was proper and no prejudice resulted from\\n\\n\\n\\n\\n 52\\n\\f During the investigation of the Traffic Court by the\\nFederal Bureau of Investigation, Appellant Singletary was\\namong those interviewed. The jury acquitted Singletary of all\\ncounts of wire fraud, mail fraud, and conspiracy. It found\\nhim guilty of false statements made to the Federal Bureau of\\nInvestigation. At sentencing, over Singletary’s objection, the\\nDistrict Court sentenced Singletary using the Guideline on\\nobstruction.\\n\\n The Government agrees that the single count on which\\nhe was convicted does not contain all of the elements of\\nobstruction. U.S.S.G. § 2J1.2. For this reason, the\\nGovernment agrees with Singletary that he is entitled to a\\nremand for resentencing. Accordingly, we will vacate the\\njudgment of sentence as to Singletary and remand to the\\nDistrict Court for resentencing.\\n\\n V.\\n\\n For all of these reasons, we will vacate the judgment of\\nsentence of the District Court with regard to Appellant\\nSingletary and remand for resentencing. We will affirm the\\njudgments of the District Court as to Appellants Alfano, Hird,\\nLowry, Mulgrew and Tynes.\\n\\n\\n\\nbringing these charges to trial. As for the challenges to\\nperjury in Counts 72 and 74, we note that Singletary was\\ncharged with a different crime: false statements in a federal\\ninvestigation pursuant to 18 U.S.C. § 1001. In addition, the\\nchallenges to all of such charges are inherently fact-intensive.\\nAs he did not provide a factual basis for such a challenge, we\\nregard the issue to be waived.\\n\\n\\n\\n\\n 53\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":68,"cells":{"id":{"kind":"number","value":4583111,"string":"4,583,111"},"name":{"kind":"string","value":"UNITED STATES of America v. Thomasine TYNES, Appellant"},"name_abbreviation":{"kind":"string","value":"United States v. Thomasine Tynes"},"decision_date":{"kind":"string","value":"2019-01-18"},"docket_number":{"kind":"string","value":"14-4804"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN, HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE, RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges The petition for rehearing en banc\", \"parties\": \"\", \"opinions\": [{\"author\": \"Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN\", \"type\": \"010combined\", \"text\": \"UNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\\n\\n\\n\\n No. 14-4804\\n\\n\\n UNITED STATES OF AMERICA\\n\\n v.\\n\\n THOMASINE TYNES,\\n Appellant\\n\\n\\n (E. D. Pa. Criminal No. 2-13-cr-00039-005)\\n\\n\\n\\n\\n SUR PETITION FOR REHEARING\\n\\n\\n\\n\\n Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN,\\n HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE,\\n RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges\\n\\n\\n The petition for rehearing en banc filed by appellant Thomasine Tynes in\\n\\nthe above-entitled case having been submitted to the judges who participated in the\\n\\ndecision of this Court and to all the other available circuit judges of the circuit in regular\\n\\nactive service, and no judge who concurred in the decision having asked for rehearing,\\n\\n\\n\\n*\\n Pursuant to Third Circuit I.O.P. 9.5.3, Judge Richard L. Nygaard’s and Judge D.\\nMichael Fisher’s votes are limited to panel rehearing.\\n\\fand a majority of the circuit judges of the circuit in regular service not having voted for\\n\\nrehearing, the petition for rehearing en banc is DENIED.\\n\\n The petition for rehearing by the panel is GRANTED IN PART, solely as to the\\n\\nclaim that there was insufficient evidence to support Tynes’ conviction.\\n\\n After consideration of Appellant’s argument, the panel has agreed to amend the\\n\\nopinion, which will be filed simultaneously with this order in all of the consolidated\\n\\ncases. Each of the judgments entered August 21, 2018, shall remain in full force and\\n\\neffect.\\n\\n BY THE COURT,\\n\\n\\n s/ Richard L. Nygaard\\n Circuit Judge\\n\\nDated: January 18, 2019\\nPDB/CLW/cc: All Counsel of Record\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360364/\", \"author_raw\": \"Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN\"}]}"},"judge1":{"kind":"string","value":"SMITH"},"judge2":{"kind":"string","value":"MCKEE"},"judge3":{"kind":"string","value":"AMBRO"},"exactly_three_caps":{"kind":"number","value":2,"string":"2"},"extra_judges":{"kind":"string","value":"CHAGARES; JORDAN; HARDIMAN; GREENAWAY JR; SHWARTZ; KRAUSE; RESTREPO; BIBAS; PORTER; NYGAARD; FISHER"},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583111/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America v. Thomasine TYNES, Appellant\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-18\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nUNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\n\n\n\n No. 14-4804\n\n\n UNITED STATES OF AMERICA\n\n v.\n\n THOMASINE TYNES,\n Appellant\n\n\n (E. D. Pa. Criminal No. 2-13-cr-00039-005)\n\n\n\n\n SUR PETITION FOR REHEARING\n\n\n\n\n Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN,\n HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE,\n RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges\n\n\n The petition for rehearing en banc filed by appellant Thomasine Tynes in\n\nthe above-entitled case having been submitted to the judges who participated in the\n\ndecision of this Court and to all the other available circuit judges of the circuit in regular\n\nactive service, and no judge who concurred in the decision having asked for rehearing,\n\n\n\n*\n Pursuant to Third Circuit I.O.P. 9.5.3, Judge Richard L. Nygaard’s and Judge D.\nMichael Fisher’s votes are limited to panel rehearing.\n\fand a majority of the circuit judges of the circuit in regular service not having voted for\n\nrehearing, the petition for rehearing en banc is DENIED.\n\n The petition for rehearing by the panel is GRANTED IN PART, solely as to the\n\nclaim that there was insufficient evidence to support Tynes’ conviction.\n\n After consideration of Appellant’s argument, the panel has agreed to amend the\n\nopinion, which will be filed simultaneously with this order in all of the consolidated\n\ncases. Each of the judgments entered August 21, 2018, shall remain in full force and\n\neffect.\n\n BY THE COURT,\n\n\n s/ Richard L. Nygaard\n Circuit Judge\n\nDated: January 18, 2019\nPDB/CLW/cc: All Counsel of Record\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America v. Thomasine TYNES, Appellant\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-18\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nUNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\\n\\n\\n\\n No. 14-4804\\n\\n\\n UNITED STATES OF AMERICA\\n\\n v.\\n\\n THOMASINE TYNES,\\n Appellant\\n\\n\\n (E. D. Pa. Criminal No. 2-13-cr-00039-005)\\n\\n\\n\\n\\n SUR PETITION FOR REHEARING\\n\\n\\n\\n\\n Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN,\\n HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE,\\n RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges\\n\\n\\n The petition for rehearing en banc filed by appellant Thomasine Tynes in\\n\\nthe above-entitled case having been submitted to the judges who participated in the\\n\\ndecision of this Court and to all the other available circuit judges of the circuit in regular\\n\\nactive service, and no judge who concurred in the decision having asked for rehearing,\\n\\n\\n\\n*\\n Pursuant to Third Circuit I.O.P. 9.5.3, Judge Richard L. Nygaard’s and Judge D.\\nMichael Fisher’s votes are limited to panel rehearing.\\n\\fand a majority of the circuit judges of the circuit in regular service not having voted for\\n\\nrehearing, the petition for rehearing en banc is DENIED.\\n\\n The petition for rehearing by the panel is GRANTED IN PART, solely as to the\\n\\nclaim that there was insufficient evidence to support Tynes’ conviction.\\n\\n After consideration of Appellant’s argument, the panel has agreed to amend the\\n\\nopinion, which will be filed simultaneously with this order in all of the consolidated\\n\\ncases. Each of the judgments entered August 21, 2018, shall remain in full force and\\n\\neffect.\\n\\n BY THE COURT,\\n\\n\\n s/ Richard L. Nygaard\\n Circuit Judge\\n\\nDated: January 18, 2019\\nPDB/CLW/cc: All Counsel of Record\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":69,"cells":{"id":{"kind":"number","value":4583112,"string":"4,583,112"},"name":{"kind":"string","value":"UNITED STATES of America v. Robert MULGREW, Appellant"},"name_abbreviation":{"kind":"string","value":"United States v. Robert Mulgrew"},"decision_date":{"kind":"string","value":"2019-01-18"},"docket_number":{"kind":"string","value":"14-4812"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN, HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE, RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges The petition for rehearing en banc\", \"parties\": \"\", \"opinions\": [{\"author\": \"Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN\", \"type\": \"010combined\", \"text\": \"UNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\\n\\n\\n\\n No. 14-4812\\n\\n\\n UNITED STATES OF AMERICA\\n\\n v.\\n\\n ROBERT MULGREW,\\n Appellant\\n\\n\\n (E. D. Pa. Criminal No. 2-13-cr-00039-003)\\n\\n\\n\\n\\n SUR PETITION FOR REHEARING\\n\\n\\n\\n\\n Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN,\\n HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE,\\n RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges\\n\\n\\n The petition for rehearing en banc filed by appellant Robert Mulgrew in the\\n\\nabove-entitled case having been submitted to the judges who participated in the decision\\n\\nof this Court and to all the other available circuit judges of the circuit in regular active\\n\\nservice, and no judge who concurred in the decision having asked for rehearing, and a\\n\\n\\n\\n*\\n Pursuant to Third Circuit I.O.P. 9.5.3, Judge Richard L. Nygaard’s and Judge D.\\nMichael Fisher’s votes are limited to panel rehearing.\\n\\fmajority of the circuit judges of the circuit in regular service not having voted for\\n\\nrehearing, the petition for rehearing en banc is DENIED.\\n\\n The petition for rehearing by the panel is GRANTED IN PART, solely as to\\n\\nAppellant’s claim that he is entitled to a consideration of the sufficiency of the evidence\\n\\nof perjury based upon an accurate understanding of his argument relating to his response\\n\\nto a particular question.\\n\\n Q. Let me make sure as well that if I got your\\n testimony correct [sic]. You’re saying that if\\n other people whether they be political leaders,\\n friends and family, anybody is approaching\\n your personal and asking her specifically to\\n look out for a case, see what she can do in a\\n case, give preferential treatment, however you\\n want to phrase it, that she is not relaying any of\\n that information on to you; is that correct?\\n\\n A. No, she isn’t.\\n\\n\\nApp. 437-38. After consideration of Appellant’s argument, the panel has agreed to\\n\\namend the opinion, which will be filed simultaneously with this order in all of the\\n\\nconsolidated cases. Each of the judgments entered August 21, 2018, shall remain in full\\n\\nforce and effect.\\n\\n\\n BY THE COURT,\\n\\n s/ Richard L. Nygaard\\n Circuit Judge\\n\\nDated: January 18, 2019\\nPDB/CLW/cc: All Counsel of Record\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360365/\", \"author_raw\": \"Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN\"}]}"},"judge1":{"kind":"string","value":"SMITH"},"judge2":{"kind":"string","value":"MCKEE"},"judge3":{"kind":"string","value":"AMBRO"},"exactly_three_caps":{"kind":"number","value":2,"string":"2"},"extra_judges":{"kind":"string","value":"CHAGARES; JORDAN; HARDIMAN; GREENAWAY JR; SHWARTZ; KRAUSE; RESTREPO; BIBAS; PORTER; NYGAARD; FISHER"},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583112/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America v. Robert MULGREW, Appellant\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-18\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nUNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\n\n\n\n No. 14-4812\n\n\n UNITED STATES OF AMERICA\n\n v.\n\n ROBERT MULGREW,\n Appellant\n\n\n (E. D. Pa. Criminal No. 2-13-cr-00039-003)\n\n\n\n\n SUR PETITION FOR REHEARING\n\n\n\n\n Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN,\n HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE,\n RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges\n\n\n The petition for rehearing en banc filed by appellant Robert Mulgrew in the\n\nabove-entitled case having been submitted to the judges who participated in the decision\n\nof this Court and to all the other available circuit judges of the circuit in regular active\n\nservice, and no judge who concurred in the decision having asked for rehearing, and a\n\n\n\n*\n Pursuant to Third Circuit I.O.P. 9.5.3, Judge Richard L. Nygaard’s and Judge D.\nMichael Fisher’s votes are limited to panel rehearing.\n\fmajority of the circuit judges of the circuit in regular service not having voted for\n\nrehearing, the petition for rehearing en banc is DENIED.\n\n The petition for rehearing by the panel is GRANTED IN PART, solely as to\n\nAppellant’s claim that he is entitled to a consideration of the sufficiency of the evidence\n\nof perjury based upon an accurate understanding of his argument relating to his response\n\nto a particular question.\n\n Q. Let me make sure as well that if I got your\n testimony correct [sic]. You’re saying that if\n other people whether they be political leaders,\n friends and family, anybody is approaching\n your personal and asking her specifically to\n look out for a case, see what she can do in a\n case, give preferential treatment, however you\n want to phrase it, that she is not relaying any of\n that information on to you; is that correct?\n\n A. No, she isn’t.\n\n\nApp. 437-38. After consideration of Appellant’s argument, the panel has agreed to\n\namend the opinion, which will be filed simultaneously with this order in all of the\n\nconsolidated cases. Each of the judgments entered August 21, 2018, shall remain in full\n\nforce and effect.\n\n\n BY THE COURT,\n\n s/ Richard L. Nygaard\n Circuit Judge\n\nDated: January 18, 2019\nPDB/CLW/cc: All Counsel of Record\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America v. Robert MULGREW, Appellant\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-18\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nUNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\\n\\n\\n\\n No. 14-4812\\n\\n\\n UNITED STATES OF AMERICA\\n\\n v.\\n\\n ROBERT MULGREW,\\n Appellant\\n\\n\\n (E. D. Pa. Criminal No. 2-13-cr-00039-003)\\n\\n\\n\\n\\n SUR PETITION FOR REHEARING\\n\\n\\n\\n\\n Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN,\\n HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE,\\n RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges\\n\\n\\n The petition for rehearing en banc filed by appellant Robert Mulgrew in the\\n\\nabove-entitled case having been submitted to the judges who participated in the decision\\n\\nof this Court and to all the other available circuit judges of the circuit in regular active\\n\\nservice, and no judge who concurred in the decision having asked for rehearing, and a\\n\\n\\n\\n*\\n Pursuant to Third Circuit I.O.P. 9.5.3, Judge Richard L. Nygaard’s and Judge D.\\nMichael Fisher’s votes are limited to panel rehearing.\\n\\fmajority of the circuit judges of the circuit in regular service not having voted for\\n\\nrehearing, the petition for rehearing en banc is DENIED.\\n\\n The petition for rehearing by the panel is GRANTED IN PART, solely as to\\n\\nAppellant’s claim that he is entitled to a consideration of the sufficiency of the evidence\\n\\nof perjury based upon an accurate understanding of his argument relating to his response\\n\\nto a particular question.\\n\\n Q. Let me make sure as well that if I got your\\n testimony correct [sic]. You’re saying that if\\n other people whether they be political leaders,\\n friends and family, anybody is approaching\\n your personal and asking her specifically to\\n look out for a case, see what she can do in a\\n case, give preferential treatment, however you\\n want to phrase it, that she is not relaying any of\\n that information on to you; is that correct?\\n\\n A. No, she isn’t.\\n\\n\\nApp. 437-38. After consideration of Appellant’s argument, the panel has agreed to\\n\\namend the opinion, which will be filed simultaneously with this order in all of the\\n\\nconsolidated cases. Each of the judgments entered August 21, 2018, shall remain in full\\n\\nforce and effect.\\n\\n\\n BY THE COURT,\\n\\n s/ Richard L. Nygaard\\n Circuit Judge\\n\\nDated: January 18, 2019\\nPDB/CLW/cc: All Counsel of Record\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":70,"cells":{"id":{"kind":"number","value":4583113,"string":"4,583,113"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"United States v. Raymont Wright"},"decision_date":{"kind":"string","value":"2019-01-18"},"docket_number":{"kind":"string","value":"17-1972"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before: MCKEE, SHWARTZ, and NYGAARD, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-1972\\n _____________\\n\\n UNITED STATES OF AMERICA,\\n\\n Appellant\\n\\n v.\\n\\n RAYMONT WRIGHT\\n\\n ______________\\n\\n ON APPEAL FROM THE\\n UNITED STATES DISTRICT COURT\\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\\n (D.C. No. 2-14-cr-00292-001)\\n District Judge: Hon. Cathy Bissoon\\n ______________\\n\\n Argued May 24, 2018\\n ______________\\n\\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\\n Judges.\\n\\n (Opinion Filed: January 17, 2019)\\n\\n ______________\\n\\n OPINION OF THE COURT\\n ________________\\n\\nDonovan J. Cocas, Esq. [ARGUED]\\nJane M. Datttilo, Esq.\\nLaura S. Irwin, Esq.\\nOffice of the United States Attorney\\n700 Grant Street\\nSuite 4000\\nPittsburgh, PA 15219\\n\\n Attorney for Appellant\\n\\nRenee Pietropaolo, Esq. [ARGUED]\\nLisa B. Freeland, Esq.\\nAkin Adepoju, Esq.\\nOffice of the Federal Public Defender\\n1001 Liberty Avenue\\n1500 Liberty Center\\nPittsburgh, PA 15222\\n\\n Attorneys for Appellee Raymont Wright\\n\\nLawrence S. Lustberg, Esq. [ARGUED]\\nGibbons, P.C.\\nOne Gateway Center\\nNewark, NJ 07102\\n\\n Attorney for Amicus Appellee National Association of\\n Criminal Defense Lawyers\\n\\n\\n\\n\\n 2\\n\\nSHWARTZ, Circuit Judge.\\n\\n The District Court barred a retrial of and dismissed the\\nindictment against Defendant Raymont Wright with prejudice\\nafter two juries failed to reach a verdict. The Court did so\\nrelying on its inherent authority, but without finding that any\\nmisconduct had occurred or that Wright would suffer any\\nprejudice beyond the general anxiety and inconvenience of\\nfacing a retrial. Under such circumstances, the Court lacked\\nthe inherent authority to bar the retrial and dismiss the\\nindictment. Therefore, we will reverse the order dismissing the\\nindictment and remand for further proceedings.\\n\\n I\\n\\n In December 2014, Wright was charged with being a\\nfelon in possession of a firearm, in violation of 18 U.S.C.\\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\\nMay 2016. The jury was unable to reach a verdict. A second\\ntrial was held in March 2017, and that jury was also unable to\\nreach a verdict.\\n\\n During both trials, the jury heard evidence from police\\nofficers about Wright’s actions on July 24, 2014.1 That\\nevening, five Pittsburgh Police detectives were patrolling in\\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\\nwere in the lead car, and Detectives Fallert and Goob were in\\nthe second car. Around 8:30 p.m. (when it was still daylight),\\nFallert and Goob saw a man, later identified as Wright, driving\\n\\n 1\\n The following facts are drawn largely from the\\nevidence presented at the first trial.\\n\\n\\n\\n\\n 3\\n\\na car in the opposite direction well above the 25-mile-per-hour\\nspeed limit. The detectives turned around to follow Wright,\\nand Wright sped up and turned onto a loop-shaped road. The\\ndetectives pursued Wright, who fled at a high speed and ran at\\nleast four stop signs. The lead car lost sight of Wright shortly\\nthereafter and discontinued pursuit.\\n\\n Officers in the lead car then noticed skid marks\\nsuggesting that a car had intended but failed to make a left turn\\nat the end of a street. Officers thereafter came upon Wright’s\\ncar in a parking lot below. The car had gone through a fence,\\nover a hillside, and into the lot. The car hit two unoccupied\\nparked cars, its tires blew out, and its windows were down.\\n\\n Detectives Baker and Henson exited the vehicle at the\\ntop of the hill and remained where Wright’s car broke through\\nthe fence, and Detective Kennedy drove his car down to the\\nparking lot’s entrance. Baker and Henson testified that they\\nsaw Wright search around the rear passenger seat of the car,\\nback out of the vehicle with a black semi-automatic handgun\\nin his right hand, and try to “rack the slide,” which can insert\\nor remove a round from the chamber. App. 118-19. They had\\ntheir weapons drawn and told Wright to drop the gun. At first,\\nWright merely stepped back, but he eventually tossed the gun\\nto the side, backed away, and lied on the ground. Pittsburgh\\npolice officer Elliott and his partner, who heard of the crash on\\nthe radio, were the first to reach Wright, and saw him lying on\\nthe ground with a handgun next to him. Henson stated that\\nwhen he made it down to the parking lot, he heard Wright say\\nto him, “Hey, big guy. You won this time or you won this\\nround, something of that nature. He [Wright] said: You feel\\nme? You won this time,” which Henson understood to mean\\nthat he had just avoided a shootout or that he caught Wright\\n\\n\\n\\n\\n 4\\n\\nafter the pursuit. App. 125. Henson subsequently took custody\\nof the gun and noticed the slide lever was bent, and when he\\nstraightened it, saw the gun was loaded with eight rounds, and\\none in the chamber. 2\\n\\n At the close of the Government’s case, Wright moved\\nfor a directed verdict, arguing that no reasonable juror could\\nfind beyond a reasonable doubt that Wright possessed the\\nfirearm. The District Court denied the motion because “the\\nevidence does thus far demonstrate that a reasonable juror\\ncould most certainly find the Defendant guilty of the charge in\\nthis case.” App. 171. Wright did not present a case.\\n\\n The jury deliberated for approximately five hours and\\nthen reported to the Court that it was deadlocked. After polling\\nthe jurors to confirm they were deadlocked and further\\ndeliberations would not bring them closer to a unanimous\\nverdict, the District Court declared a mistrial.\\n\\n At Wright’s March 2017 retrial, the Government\\npresented substantially the same evidence. The Government\\nalso called Detective Kennedy and Lieutenant Palermo, who\\nwere at the scene after Wright was arrested, as well as experts\\nwho testified regarding the collection of DNA and fingerprint\\nevidence from firearms to respond to Wright’s argument at the\\nfirst trial that investigators chose not to test the gun for forensic\\nevidence in an effort to cover up that they had planted the gun\\nat the scene.\\n\\n\\n 2\\n The parties stipulated Wright had been convicted of a\\nqualifying felony, and an ATF Special Agent testified about\\nthe gun’s interstate nexus.\\n\\n\\n\\n\\n 5\\n\\n At the close of the Government’s case, Wright again\\nmoved for a judgment of acquittal, which the Court denied\\nbecause “there is sufficient evidence in the record to establish\\nbeyond a reasonable doubt that Mr. Wright possessed the\\nfirearm in the case,” App. 650. Wright did not put on a case.\\n\\n The second jury deliberated for approximately three\\nhours and then reported that it was hopelessly deadlocked. The\\nCourt polled the jury to confirm the deadlock and then\\ndismissed the jury. 3\\n\\n After the Government notified the Court that it intended\\nto retry the case, the Court required the parties to brief\\n“whether the Court, through an exercise of its inherent\\nauthority, should prohibit or permit a second re-trial in this\\ncase.” App. 26. After considering the parties’ arguments, the\\nDistrict Court dismissed the indictment with prejudice, holding\\nthat it “ha[d] the inherent authority, under some circumstances,\\nto dismiss an indictment following multiple mistrials.” United\\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\\nunderlying the Double Jeopardy Clause also applied to a\\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\\n(2) other courts had dismissed indictments in similar\\n\\n 3\\n Wright asserted that in the first trial, jurors voted 8-4\\nfor acquittal, and in the second trial, the jury was evenly split.\\nThe Government asserted that in the first trial, jurors voted 7-\\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\\nnot explain how he obtained these numbers, the Government\\nsaid it obtained them by speaking with the jurors.\\n\\n\\n\\n\\n 6\\n\\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\\nexpressly allows the Government to retry a case after a mistrial,\\nnothing in the rule “limits a court’s inherent supervisory\\nauthority to dismiss an indictment in the interests of\\nfundamental fairness,” id. at *4; and (4) if the Court were to\\nadopt the Government’s position that there are no limit to the\\nnumber of times the Government can retry a defendant, it\\nwould be tantamount to a “type of jury shopping” that a court\\nshould not permit, id. at *4. The District Court also considered\\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\\nconcluded that most factors supported dismissal. 4\\n\\n 4\\n The Abbati factors are\\n\\n (1) the number of prior mistrials and the\\n outcome of the juries’ deliberations, so far as is\\n known; (2) the character of prior trials in terms\\n of length, complexity, and similarity of evidence\\n presented; (3) the likelihood of any substantial\\n difference in a subsequent trial, if allowed;\\n (4) the trial court’s own evaluation of the relative\\n strength of each party’s case; and (5) the\\n professional conduct and diligence of respective\\n counsel, particularly of the prosecuting attorney.\\n The court must also give due weight to the\\n prosecutor’s decision to reprosecute, assessing\\n the reasons for that decision, such as the gravity\\n\\n\\n\\n\\n 7\\n\\n The Government appeals.\\n\\n II 5\\n\\n We review the District Court’s order dismissing the\\nindictment based on the Court’s inherent power for abuse of\\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\\n\\n of the criminal charges and the public’s concern\\n in the effective and definitive conclusion of\\n criminal prosecutions. Conversely, the court\\n should accord careful consideration to the status\\n of the individual defendant and the impact of a\\n retrial upon the defendant in terms of untoward\\n hardship and unfairness.\\n\\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\\nat 521-22). For the reasons set forth herein, we would not\\nadopt Abbati, but even if we were to consider the Abbati\\nfactors, we would conclude that they do not support dismissal\\nin this case.\\n 5\\n The District Court had jurisdiction pursuant to 18\\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\\n§ 3731.\\n 6\\n The phrases “inherent power,” “inherent authority,”\\n“supervisory power,” and “supervisory authority” are all used\\nto describe the basis for a court action seeking to maintain the\\nintegrity of the proceedings that is not directly tethered to a\\nspecific rule, statute, or constitutional provision. See, e.g.,\\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\\n43 (1991) (inherent power); Bank of Nova Scotia v. United\\n\\n\\n\\n\\n 8\\n\\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\\nindictment for abuse of discretion); cf. Chambers v. NASCO,\\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\\nsanctions under its inherent power for abuse of discretion);\\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\\n2005) (“A trial court’s remedy for a discovery violation under\\nits supervisory powers is reviewed for abuse of discretion.”).\\nA district court abuses its discretion when it makes an errant\\nconclusion of law, an improper application of law to fact, or a\\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\\n\\n A\\n\\n Federal Rule of Criminal Procedure 31 allows the\\nGovernment to retry a case if the court declares a mistrial after\\na jury announces it is unable to reach a verdict. Specifically,\\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\\non one or more counts, the court may declare a mistrial on\\nthose counts. The government may retry any defendant on any\\ncount on which the jury could not agree.” Fed. R. Crim. P.\\n31(b)(3). The word “may” means that the Government has the\\n\\n\\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(supervisory power); United States v. Payner, 447 U.S. 727,\\n733-36 (1980) (supervisory power); United States v. Nobles,\\n422 U.S. 225, 231 (1975) (inherent power).\\n Even if we accepted the distinctions our dissenting\\ncolleague has drawn between inherent judicial powers,\\nlegislatively granted judicial powers, and supervisory powers,\\neach category must operate within the constitutional\\nframework, including the separation of powers.\\n\\n\\n\\n\\n 9\\n\\ndiscretion to retry a case, and nothing in the rule or its\\ncommentary provides or even suggests a limit on the number\\nof retrials it may conduct. See United States v. Wqas Khan,\\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\\n\\n 7\\n While Rule 31 does not limit the Government’s\\nauthority to retry a case, a handful of district courts have\\ndismissed indictments following a second hung jury, but those\\ndecisions are not persuasive. In Ingram, the district court\\ndismissed the indictment sua sponte (without any initial\\nobjection by the Government) after two mistrials—in which\\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\\njailed during the pendency of the trials, and “[t]he Government\\nha[d] no new proof; it simply want[ed] another chance.” 412\\nF. Supp. at 385. The court concluded that to permit a retrial\\nwould be “to ignore the reasonable doubt standard,” and so\\n“[t]he Court’s intervention [was] required in the interest of\\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\\n(McGowan, J., dissenting)). The Ingram court, however, relied\\nin part on the dissent in De Diego. Cases since Ingram have\\napplied the De Diego majority’s view concerning a court’s\\nlimited authority to dismiss an indictment. See, e.g., United\\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\\nDe Diego and reversing the district court’s dismissal of the\\nindictment where the district court found it would be\\n“unconscionable” to retry to the defendant); United States v.\\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\\nDiego and its dissent and holding a district court does not have\\nauthority to sua sponte dismiss an indictment based on the\\n\\n\\n\\n\\n 10\\n\\ndefendant’s poor health); United States v. Mussehl, 453 F.\\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\\nto dismiss the indictment based on alleged errors at trial, and\\nciting De Diego for the proposition that “[t]he duty [to\\nadminister justice] encompasses the concept of review of the\\nquestion whether the United States Attorney, in making his\\ndecision to prosecute, complied with the law, but does not\\nallow the Court to question a United States Attorney’s\\njudgment decision to prosecute, when lawfully made”).\\n The District Court also relied on Rossoff, where the\\ncourt denied the Government’s motion to dismiss the\\nindictment under Federal Rule of Criminal Procedure 48(a),\\nbut still dismissed the indictment with prejudice. 806 F. Supp.\\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\\nbeen two trials, and the Government sought to dismiss the\\nindictment and refile the charges in a different judicial district.\\nId. The court determined it had authority to dismiss an\\nindictment with prejudice if a retrial was “against the concept\\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\\nSupp. 384), and did so because, among other reasons, the\\ndefendant was in poor health, was under significant strain, and\\na majority of jurors at both trials found him not guilty, id. at\\n203. Rossoff, however, is distinguishable from Wright’s case\\nbecause in Rossoff, the Government sought to dismiss the\\nindictment so that it could refile charges in a different judicial\\ndistrict, which caused the court to question the Government’s\\ngood faith. In Wright’s case, the District Court made no\\nfinding that the Government’s desire to retry Wright was for\\nan improper purpose.\\n In addition, and significantly, neither Ingram nor\\nRossoff addressed the doctrine of separation of powers.\\nRather, each essentially relied on a general concept of fairness\\n\\n\\n\\n\\n 11\\n\\nthe text that empowers a court to prohibit the Government from\\nretrying a case. 8\\n B\\n\\n Apparently aware that Rule 31 did not provide it with a\\nbasis to preclude a retrial in these circumstances, the District\\nCourt concluded that it had the inherent authority to forbid the\\nretrial and dismiss the indictment. The District Court erred.\\n\\n The exercise of inherent authority must satisfy two\\nrequirements: (1) it “must be a reasonable response to the\\n\\n\\nto the defendant in deciding to dismiss an indictment. See\\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\\nIn this Circuit, however, “[t]he judiciary may not impose its\\npersonal and private notions of ‘fairness’ on law enforcement\\nofficials, but does have a limited authority to affect\\nprosecutorial actions when those actions are taken in violation\\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\\n596 (3d Cir. 1992) (citations omitted).\\n 8\\n Rule 31 differs from other Federal Rules of Criminal\\nProcedure because it makes no mention of the court’s\\nauthority. For instance, Rule 48(b) states that a court has\\nauthority to dismiss an indictment “if unnecessary delay occurs\\nin: (1) presenting a charge to the grand jury; (2) filing an\\ninformation against a defendant; or (3) bringing a defendant to\\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\\ngrounds on which a district court could also dismiss an\\nindictment, but each would be triggered by a motion, such as a\\nmotion to dismiss for failure to comply with Rule 16’s\\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\\n16(d)(2)(D), or a motion asserting a defect in the indictment,\\nFed. R. Crim. P. 12(b)(3)(B).\\n\\n\\n\\n\\n 12\\n\\nproblems and needs confronting the court’s fair administration\\nof justice,” and (2) it “cannot be contrary to any express grant\\nof or limitation on the district court’s power contained in a rule\\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\\n(citations and internal quotation marks omitted). We will\\nexamine each of these requirements in turn.\\n\\n 1\\n\\n As to the first Dietz requirement, “[g]uided by\\nconsiderations of justice, and in the exercise of supervisory\\npowers, federal courts may, within limits, formulate procedural\\nrules not specifically required by the Constitution or the\\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(internal quotation marks and citation omitted). Such rules\\nmust be imposed (1) “to implement a remedy for violation of\\nrecognized rights,” (2) “to preserve judicial integrity by\\nensuring that a conviction rests on appropriate considerations\\nvalidly before the jury,” and (3) “as a remedy designed to deter\\nillegal conduct.” Id. (citations omitted). Thus, a court may\\nexercise its inherent authority only when it is necessary to\\naddress improper conduct and ensure respect for the\\nproceedings.\\n\\n Under these principles, a court may dismiss an\\nindictment based upon its inherent authority only if the\\nGovernment engaged in misconduct, the defendant was\\nprejudiced, and no less severe remedy was available to address\\nthe prejudice. See Bank of Nova Scotia v. United States, 487\\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\\n(stating that “[a] court may dismiss an indictment under its\\nsupervisory powers only when the defendant suffers\\nsubstantial prejudice and where no lesser remedial action is\\n\\n\\n\\n\\n 13\\n\\navailable” (citations and internal quotation marks omitted));\\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\\n(observing that “a district court may not, in the management of\\nits docket, exercise its discretion to dismiss an indictment with\\nprejudice, either under Rule 48(b) or under its supervisory\\npower, unless the violation caused prejudice to the defendant\\nor posed a substantial threat thereof” (emphasis omitted));\\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\\n(holding that an indictment may not be dismissed for\\nprosecutorial misconduct absent a showing that the misconduct\\nprejudiced the defendants, and stating that “virtually every\\nother circuit to consider the issue post-Hasting and Nova Scotia\\nhas also held that an indictment may not be dismissed based on\\nprosecutorial misconduct, absent a showing of prejudice to the\\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\\n(7th Cir. 1993) (“A federal judge is not authorized to punish\\nthe misconduct of a prosecutor by letting the defendant walk,\\nunless the misconduct not only violated the defendant’s rights\\nbut also prejudiced his defense . . . .”); United States v. Tucker,\\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\\nexercise its supervisory authority to reverse a conviction or\\ndismiss an indictment absent prejudice to the defendant.”);\\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\\nHasting, and Bank of Nova Scotia form a trilogy admonishing\\nfederal courts to refrain from using the supervisory power to\\nconform executive conduct to judicially preferred norms by\\ndismissing charges, absent cognizable prejudice to a particular\\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\\nCir. 1992) (“Before it may invoke this [supervisory] power [to\\ndismiss an indictment], a court must first find that the\\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\\n1480 (9th Cir. 1994).\\n\\n\\n\\n\\n 14\\n\\n In this case, there has been no misconduct. Indeed, the\\nDistrict Court noted that the Government performed diligently\\nand professionally in both trials, Wright, 2017 WL 1179006,\\nat *4, and found that the evidence was sufficient to prove\\nbeyond a reasonable doubt that Wright possessed the gun. The\\nDistrict Court nonetheless applied its own predictions about\\nwhat another jury may do when presented with the same\\nevidence, emphasized the need for finality, and opined that the\\neffect of prosecution on the defendant precluded a proper\\nprosecution from proceeding. See id. at *5-6. Invoking its own\\nnotions about the unfairness of requiring a defendant to face a\\nretrial where the Government did not obtain a majority of the\\njurors’ votes is an improper exercise of a court’s supervisory\\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\nMoreover, there is no prejudice to a defendant simply because\\nhe faces the anxiety and the normal stress of undergoing a trial.\\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975) (“[A]nxiety is present to some degree in virtually every\\ncase. Something more than the normal anxiety that\\naccompanies a trial is necessary to show a degree of\\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\\nonly real harm alleged is the general unfairness to these\\ndefendants in having to go forward yet again with a lengthy\\ntrial, in their being ‘ground down’ by the several months’ drain\\non their mental, emotional, and financial resources. A lack of\\nsuch fairness, however, does not alone violate due process.”).\\nRather, prejudice sufficient for the District Court to intervene\\nin a proper prosecution based upon its inherent authority occurs\\nonly where the Government engages in actions that place a\\ndefendant at a disadvantage in addressing the charges. That\\nsort of prejudice is absent in this case.\\n\\n\\n\\n\\n 15\\n\\n Unless there is some constitutional basis, such as a due\\nprocess violation, it makes sense to limit a court’s authority to\\nbar retrial to instances of prosecutorial misconduct and\\nprejudice. First, it ensures that a judge’s personal preferences\\nabout a case do not influence whether the case proceeds. See\\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\\n(“The judiciary may not impose its personal and private\\nnotions of ‘fairness’ on law enforcement officials, but does\\nhave a limited authority to affect prosecutorial actions when\\nthose actions are taken in violation of the Constitution.”).\\nSecond, as more fully discussed below, it guarantees that a\\ncourt limits the Executive’s decision to prosecute only where\\nthere is a constitutionally sound reason to do so. 9 This brings\\nus to the second Dietz requirement.\\n\\n\\n 9\\n For these reasons, we find unpersuasive our dissenting\\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\\nobservation that a court has the inherent power to resolve a\\ncase, as authority for allowing a court dismiss an indictment\\nafter successive hung juries. As a general matter, there is no\\ndoubt that a court has the authority to dismiss a case, but it may\\nnot simply end a case because it decides that it should not be\\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\\ntheir progeny make clear, the court must point to evidentiary\\ndeficiency, prejudicial misconduct, or a constitutional basis,\\nsuch as double jeopardy or due process, to justify precluding a\\nprosecution. If a court believed that the evidence was deficient,\\nthe prosecutor engaged in prejudicial misconduct, or a retrial\\nwould violate the constitution, then it has a basis to preclude a\\nretrial. Requiring such reasons for barring a retrial ensures that\\n\\n\\n\\n\\n 16\\n\\n 2\\n\\n The second Dietz requirement reminds a court that the\\nexercise of its powers must be in accordance with the\\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\\nwith the Constitution, a court must be mindful of its role in our\\ntripartite form of government and the doctrine of separation of\\npowers. Separation-of-powers principles limit a court’s\\ninherent authority. “Regardless of whether the supervisory\\npower stems from the federal courts’ inherent power to check\\nintrusions by other branches of government or whether it is a\\nform of specialized federal common law, the separation-of-\\npowers principle imposes significant limits on it,” and\\n“[p]roper regard for judicial integrity does not justify a\\n‘chancellor’s foot veto’ over activities of coequal branches of\\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\\nCir. 1985) (internal quotation marks omitted) (quoting United\\nStates v. Russell, 411 U.S. 423, 435 (1973)).\\n\\n In the criminal context, the Executive Branch has\\n“broad discretion as to whom to prosecute,” and this discretion\\n“rests largely on the recognition that the decision to prosecute\\nis particularly ill-suited to judicial review.” Wayte v. United\\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\\nquotation marks omitted). A court is not equipped to evaluate\\n\\n [s]uch factors as . . . the prosecution’s general\\n deterrence value, the Government’s enforcement\\n priorities, and the case’s relationship to the\\n\\n\\nthe ruling is not based on a court’s own personal sense of\\nwhether a case is worthy of prosecution.\\n\\n\\n\\n\\n 17\\n\\n Government’s overall enforcement plan . . . .\\n Judicial supervision in this area, moreover,\\n entails systemic costs of particular concern.\\n Examining the basis of a prosecution delays the\\n criminal proceeding, threatens to chill law\\n enforcement by subjecting the prosecutor’s\\n motives and decisionmaking to outside inquiry,\\n and may undermine prosecutorial effectiveness\\n by revealing the Government’s enforcement\\n policy. All of these are substantial concerns that\\n make the courts properly hesitant to examine the\\n decision whether to prosecute.\\n\\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\\n(echoing similar sentiments with respect to Rule 48(a)\\ndismissals). Thus, absent constitutional concerns, the decision\\nto try or retry a case is at the discretion of the prosecutor.\\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\\nas superprosecutors, second-guessing the legitimate exercise of\\ncore elements of prosecutorial discretion, but rather as neutral\\narbiters of the law” (citation and internal quotation marks\\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\\n1994) (“[T]he choice to forego permanently a prosecution is\\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\\n676 (“In maintaining order in our own house, we should not\\nneedlessly trample on the interest of the prosecutor and of the\\npublic in securing proper, lasting convictions.”); Isgro, 974\\nF.2d at 1097 (stating that the doctrine of separation of powers\\n“mandates judicial respect for the independence of the\\nprosecutor,” and “[d]ismissal of an indictment with prejudice\\n\\n\\n\\n\\n 18\\n\\nis the most severe sanction possible”). 10 Accordingly,\\nseparation-of-powers principles preclude a court from\\nterminating a prosecution absent misconduct and prejudice to\\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\\n974 F.2d at 1094.\\n\\n In short, a court’s power to preclude a prosecution is\\nlimited by the separation of powers and, specifically, the\\nExecutive’s law-enforcement and prosecutorial prerogative.\\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\\nhere to dismiss an indictment in the absence of misconduct and\\nprejudice and based only on the fact that two juries could not\\nreach a verdict intrudes on the Executive’s domain and thereby\\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\\nat 138; Isgro, 974 F.2d 1091.\\n\\n 10\\n Several state courts have also refused to recognize\\nany inherent authority to dismiss an indictment to prevent a\\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\\n(Fla. Dist. Ct. App. 1980). Other states, however, have\\nrecognized a court’s authority to dismiss an indictment sua\\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\\n712; Witt, 572 S.W.2d at 917. These latter cases are\\nunpersuasive because they give too little weight to the\\nseparation of powers, a crucial constitutional principle in the\\nfederal system.\\n\\n\\n\\n\\n 19\\n\\n Finally, there is no statute or procedural rule that\\npermits a court to bar a retrial in the absence of misconduct and\\nprejudice. First, a court may not dismiss an indictment as a\\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\\n505. Second, a court’s inherent power does not “include the\\npower to develop rules that circumvent or conflict with the\\nFederal Rules of Criminal Procedure.” Carlisle v. United\\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\\nexercise of inherent authority circumvents the absence of\\npower of the district court to dismiss an indictment in Rule\\n31(b). As stated above, courts have inherent authority to\\ndismiss indictments, including, for instance, for prosecutorial\\nmisconduct if the defendant was prejudiced, Bank of Nova\\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\\nnor our Court has extended a court’s inherent authority to allow\\n\\n 11\\n In Chambers, for example, the Supreme Court\\nrecognized a court’s authority to impose silence, respect, and\\ndecorum based on its authority to manage its own affairs. 501\\nU.S. at 43. This authority has been exercised by controlling\\nadmission to the bar and disciplining its members; punishing\\nfor contempt, which penalizes disruption to proceedings and\\ndisobedience to court orders; disallowing fraud on the courts;\\nensuring the proceedings move forward; and curtailing\\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\\ncivil case for failure to prosecute to prevent delays and court\\ncongestion as part of a court’s inherent power to manage its\\nown affairs). Chambers and Link address how a court may\\nmanage its own proceedings, but they do not address how the\\ncourt must also account for issues of separation of powers in\\nthe context of a criminal case.\\n\\n\\n\\n\\n 20\\n\\nthe sua sponte dismissal of an indictment solely to preclude\\nmultiple mistrials following hung juries, see Chambers, 501\\nU.S. at 47; HSBC, 863 F.3d at 136. 12\\n\\n 12\\n Most cases concerning a court’s inherent authority\\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\\n(noting a court’s inherent powers to rescind a jury discharge\\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\\n(recognizing a court’s authority to vacate a judgment upon\\nproof that a fraud was perpetrated on the court, and, in\\nparticular, to assess as a sanction the entire amount of the\\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\\n(authority to dismiss a civil case sua sponte for failure to\\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\\n(1947) (dismissing an action based on the doctrine of forum\\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\\n(citing cases involving the scope of a district court’s inherent\\npower); Eash, 757 F.2d at 561-64 (same).\\n There are other circumstances in which district courts\\nlack the inherent authority to act, and most of those situations\\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\\n433 (holding that a court does not have authority to grant a\\npost-verdict motion for judgment of acquittal, filed one day\\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\\n45-50, 55 (holding that a district court does not have inherent\\nauthority to dismiss an indictment because the Government\\nfailed to disclose to the grand jury substantial exculpatory\\nevidence; “[b]ecause the grand jury is an institution separate\\nfrom the courts, over whose functioning the courts do not\\npreside, we think it clear that, as a general matter at least, no\\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\\nat 129, 135-37 (holding that the district court violated\\nseparation-of-powers principles by sua sponte invoking its\\n\\n\\n\\n\\n 21\\n\\n Thus, the District Court abused its discretion in barring\\na retrial and dismissing the indictment. 13\\n\\n III\\n\\n For the foregoing reasons, we will reverse and remand\\nfor further proceedings.\\n\\n\\n\\n\\nsupervisory power to oversee the government’s entry into and\\nimplementation of a deferred prosecution agreement).\\n 13\", \"author\": \"SHWARTZ, Circuit Judge.\"}, {\"type\": \"dissent\", \"author\": \"Our\", \"text\": \"Our dissenting colleague says that our approach\\ndeprives the court from taking action “when warranted to\\nprotect the institutional integrity of the judiciary.” Dissent at\\n3. We disagree. This approach recognizes a court’s role in our\\ntripartite system of government and ensures that a court\\nintercedes when proceeding would violate the Constitution.\\nFurthermore, our approach does not preclude a court from\\nending a case where the evidence is insufficient or the conduct\\nof the prosecution is improper.\\n\\n\\n\\n\\n 22\"}, {\"author\": \"McKEE, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"McKEE, Circuit Judge, concurring in the judgment.\\n\\n As I shall explain, I am sympathetic to what the District\\nCourt was trying to do in this case and I think I understand why\\nthe court acted as it did. Moreover, I agree with Judge Nygaard\\ninsofar as he posits in dissent that a District Court can step in\\nat some point and bar a retrial without infringing on the\\nseparation of powers. Nevertheless, despite my belief that the\\nseparation of powers doctrine is not necessarily violated by a\\ntrial court barring a retrial after successive mistrials, and\\ndespite my belief that the District Court was trying to act in a\\nmanner that would assure a measure of justice for Wright, I\\nconcur in the judgment reversing the District Court. I simply\\ndo not believe that the current state of the law supports the\\nDistrict Court’s action in the absence of prosecutorial\\nmisconduct, bad faith, or more than two unsuccessful trials.\\nSince the record is clear that the District Court found neither\\nprosecutorial misconduct nor bad faith, I concur in the\\njudgment reversing the court’s order but feel compelled to\\nwrite separately to explain why.\\n I.\\n At the outset, it is important to note that I do not believe\\nthat a trial court lacks the power to, at some point, call a halt to\\nsuccessive prosecutions following deadlocked juries, and I do\\nnot read Judge Shwartz’s opinion as standing for that principle.\\nThe Government even conceded at oral argument that there\\ncould come a point where successive prosecutions become so\\nonerous and burdensome that additional trials rise to the level\\nof a Due Process violation which a trial court is clearly\\nempowered to prevent. Moreover, in Barkus v. Illinois, 1 the\\nSupreme Court noted that there “may” come a point where\\nmultiple prosecutions become so harassing that they violate the\\nDue Process Clause. 2\\n\\n Here the evidence in both trials consisted solely of\\npolice testimony. According to the officers’ testimony, some\\nresidents of the community witnessed crucial parts of Wright’s\\nencounter with the police, but they did not testify. Similarly,\\nWright did not testify on his own behalf, nor did the defense\\nput on a case. His theory was that he had no way of knowing\\n\\n1\\n 359 U.S. 121 (1959).\\n2\\n Id. at 127.\\n 1\\n\\nthat the men in plain clothes and unmarked cars who began\\npursuing him were police; he panicked, sped away, and\\ncrashed; and police subsequently planted the gun at the scene.\\nWright also asserted that the officers chose not to test the gun\\nfor DNA or fingerprints because they knew the results would\\ncontradict their story. In an effort to counter Wright’s\\nargument from the first trial that police decided not to test the\\ngun for fingerprints and DNA in order to hide their\\nmalfeasance, the Government called experts at the second trial\\n“who testified about the difficulty of retrieving DNA and\\nfingerprint evidence from firearms.” 3\\n\\n Nevertheless, the Government’s case depended entirely\\non the testimony of police officers who had worked together\\nfor many years and/or knew one another. Over the span of ten\\nmonths, the District Court twice listened to the police\\ntestimony during the trials. That testimony was at times\\ncontradictory and at other times strained credulity.\\n\\n At the first trial, Detective Fallert, who first noticed\\nWright speeding, testified that Wright was travelling at 90\\nmph, but he did not note that in his police paperwork nor did\\nhe note it at the pretrial hearing. His contemporaneously\\nprepared investigative report also did not claim that Wright\\nwas initially speeding. Detective Henson, who took over the\\nchase, testified that he saw Wright holding a handgun, but\\nconceded that he had no way of knowing whether Wright knew\\nhe was a police officer when the pursuit began. Lastly,\\nDetective Baker testified similarly to Henson, yet guessed that\\nWright had been going at a speed of 60 mph and accelerated.\\nThis is a very substantial discrepancy, especially for seasoned\\npolice officers who can be expected to have some expertise and\\nexperience in estimating the speed of an automobile.\\n\\n In the second trial, the Government called the same\\nwitnesses, with the exception of Detective Fallert. Notably,\\nthis time Detective Henson testified he actually did not see\\nWright speeding. Two different juries found themselves\\ndeadlocked—unable to convict or acquit.\\n II.\\n The majority opinion suggests that the District Court’s\\n\\n3\\n Appellant Br. at 11.\\n 2\\n\\ndecision to dismiss the indictment with prejudice\\nimpermissibly infringed upon the jury’s role. Judge Shwartz\\nstates: “[t]he District Court nonetheless applied its own\\npredictions about what another jury may do when presented\\nwith the same evidence,” and concluded that was “an improper\\nexercise of a court’s supervisory power.” 4 However, it is\\ndifficult to know whether the District Court ruled as it did\\nbased upon a belief that a third jury presented with the same\\nevidence would be unable to reach a verdict or whether it\\nsimply shared the doubts that some of the jurors obviously had\\nabout the veracity of police officers’ testimony.\\n\\n In any event, either scenario poses exactly the same\\nissue about a court overstepping its bounds and infringing on\\nthe role of a jury as well as prosecutorial discretion. As I stated\\nat the beginning, to the extent that a trial judge can intervene\\nand dismiss an indictment, I am skeptical that this record\\nsupports such an assertion of judicial authority. Nevertheless,\\nthere is more support for the judge’s actions here than our\\nreversal suggests.\\n\\n It is not a novel proposition that a trial judge must\\n“ensure that any and all . . . evidence is not only relevant, but\\nalso reliable.” 5 “The trial judge’s role is to preside over the\\ntrial; passively if possible but aggressively when indicated.” 6\\nThus, the law allows for trial courts to channel the jury’s\\njudgment in certain circumstances. Here, the court’s decision\\nwould prevent another jury from hearing the same evidence\\nthat has failed to convict Wright on two prior occasions.\\n\\n There are situations in which judges must act as\\n“gatekeepers” and ensure the reliability of evidence before a\\njury is able to consider it. Accordingly, in an admittedly very\\ndifferent context, the Supreme Court has described trial judges\\nas gatekeepers of evidence. 7 “[A] gatekeeping role for the\\n\\n4\\n Maj. Op. 13–14.\\n5\\n Kannankeril v. Terminix Int’l, Inc., 128 F.3d 802, 806 (3d\\nCir. 1997) (citing Daubert v. Merrill Dow Pharms., 509 U.S.\\n579, 589 (1993)).\\n6\\n Holdnrook v. Lykes Bros. Steamship Co., 80 F.3d 777, 788\\n(3d Cir. 1996).\\n7\\n Daubert, 509 U.S. at 597.\\n 3\\n\\njudge, no matter how flexible, inevitably on occasion will\\nprevent the jury from learning of authentic insights and\\ninnovations.” 8\\n\\n Despite the importance of the jury system, and the faith\\nwe place in juries, the law has thus traditionally recognized the\\ndanger that jurors may not be able to restrict their deliberations\\nto admissible evidence and that they may return a verdict based\\non factors other than the evidence presented at trial. For\\nexample, Federal Rule of Evidence 403 allows courts to\\nprevent jurors from learning of certain testimony (even\\nuncontradicted testimony) if the court concludes that the\\ntestimony could cause a jury to reach a verdict based more on\\nemotion or prejudice than on evidence. 9\\n\\n The best known example of how courts are empowered\\nto limit what a jury can consider may well be the body of law\\nthat has developed in the wake of the Supreme Court’s decision\\nin Daubert. In Daubert, the Court stated: “the trial judge must\\nensure that any and all scientific testimony or evidence\\nadmitted is not only relevant, but reliable.” 10 We certainly\\ncould, but do not, allow the jury to determine whether the\\nscientific evidence is reliable in the first instance based upon\\ntestimony at trial. Instead, that preliminary factual\\ndetermination rests solely with the trial court if the reliability\\nis challenged.\\n\\n The difficulty with relying on this body of law here is,\\nof course, the fact that the trial court’s dismissal of Wright’s\\nindictment was not limited to an intrusion into the jury-box.\\nMore fundamentally, and more importantly, it also trespassed\\non the separation of powers, and concomitantly, on the\\nprosecutorial discretion that is endemic in that concept.\\n\\n Despite Judge Nygaard’s thoughtful attempt to address\\nthat issue and the jury’s obvious concerns regarding the\\n\\n8\\n Id.\\n9\\n See, e.g., United States v. Bailey, 840 F.3d 99, 117, 121–23,\\n(3d Cir. 2016) (finding that the probative value of video\\nevidence of murder committed by coconspirators was\\nsubstantially outweighed by risk of unfair prejudice).\\n10\\n Daubert, 509 U.S. at 589.\\n 4\\n\\ntestimony of police officers in this case, I am not convinced\\nthat the United States Supreme Court would agree that the\\ninherent powers of a trial court are broad enough to justify what\\nhappened here.\\n\\n The Government clearly has the inherent authority to\\ndecide not to retry Wright given all of the circumstances in this\\ncase, including the seemingly improbable account of what\\nhappened, 11 the conflicting nature of the police testimony and\\nthe jurors’ apparent trouble with it, the fact that there is no\\nadditional evidence to offer at a third trial, and Wright’s\\napparent steps toward rehabilitation since the offense which\\ndisqualified him from lawfully owning a firearm, as well as any\\nother factors that the Government might appropriately\\nconsider. 12 However, I can find no authority that convinces me\\nthat the United States Supreme Court would agree that a trial\\ncourt’s inherent authority allows it to dismiss an indictment\\nwith prejudice on this record.\\n\\n III.\\n\\n\\n\\n11\\n According to the officers’ accounts, they watched (in the\\nopen and without cover) as Wright fumbled in the back of a\\ncar with tinted windows and came out holding a gun. They\\nthen continued to stand and watch from approximately 25\\nyards away—without cover and without taking any actions to\\nprotect themselves—as he attempted to rack the slide which\\nwould have placed a bullet in the chamber.\\n12\\n Appellee argues without contradiction that:\\n\\n [f]ollowing early involvement with the criminal\\n justice system, Mr. Wright began to turn his life\\n around, returning to school and earning his\\n Associates degree in Computer Management-\\n Networking Engineering Technology[,] . . . a\\n Bachelor of Science degree in Information\\n Technology and Management . . . graduating\\n cum laude[,] . . . and . . . a Master of Science\\n degree.\\n\\nAppellee Br. at 52.\\n 5\\n\\n As I noted at the outset, the Government agrees that\\nsuccessive prosecutions can rise to the level of a Due Process\\nviolation, which a court clearly could remedy by dismissing an\\nindictment. However, the Government strenuously argues\\nWright’s prosecution has not yet reached that point. The\\nGovernment’s position inherently argues that the court’s action\\nhere is also not justified by any concept of fundamental\\nfairness. In Ake v. Oklahoma, 13 the Supreme Court observed\\nthat the right to Due Process includes the “guarantee of\\nfundamental fairness.” 14 As has been discussed by Judge\\nShwartz, the District Court here relied on the decision of the\\nNew Jersey Supreme Court in State v. Abbati. 15 There, the\\nNew Jersey Supreme Court affirmed a trial court’s dismissal of\\nan indictment with prejudice after two juries deadlocked,\\nresulting in mistrials. 16 That situation is on “all fours” with the\\ncircumstances here and the District Court relied heavily on that\\ndecision to justify its action and fashion a rule that would\\nproperly allow a trial court to dismiss an indictment with\\nprejudice under certain circumstances. 17\\n\\n However, the New Jersey Supreme Court based its\\ndecision on the inherent authority of state courts under the New\\nJersey Constitution. 18 It did not purport to rest its decision on\\nthe U.S. Constitution and, with very limited exception, it cited\\nto state judicial decisions—not federal ones—in discussing\\nwhen consecutive hung juries justified dismissing an\\nindictment with prejudice. 19 The holding of the Court is\\n\\n13\\n 470 U.S. 68 (1985).\\n14\\n Id. at 76.\\n15\\n 493 A.2d 513 (N.J. 1985).\\n16\\n Id. at 522.\\n17\\n See United States v. Wright, Crim A No. 14-292, 2017 WL\\n1179006, at *3, *4 (W.D. Pa. Mar. 30, 2017).\\n18\\n Abbati, 493 A.3d at 517–18.\\n19\\n Abbati cited to Ake, for the general proposition that the\\n“requirement of fundamental fairness [is] grounded in [the]\\nfourteenth amendment’s due process guarantee.” 493 A.2d at\\n518. However, with the exception of a single District Court\\ncase, the Court cited numerous state court cases for the\\nproposition that a trial court had the inherent authority to\\ndismiss an indictment with prejudice after two juries\\ndeadlocked. Id. at 519–20. It concluded by finding “[t]hese\\n 6\\n\\nsummarized in its statement that the “judicial responsibility for\\nthe proper administration of criminal justice also gives rise to\\nthe inherent power to dismiss an indictment in appropriate\\ncircumstances.” 20\\n\\n The Abbati standard has not been discussed by this\\nCourt (aside from in the instant case), let alone adopted by it.\\nAlthough some of the factors used by the New Jersey Supreme\\nCourt are analogous to considerations federal courts have made\\nin similar federal cases, such as United States v. Ingram 21 and\\nUnited States v. Rossoff, 22 Abbati has no real corollary in\\nfederal case law. 23\\n\\nexamples of the courts’ exercise of their power to administer\\nthe criminal justice system assist in answering the further\\nargument of the State that recognition of an inherent judicial\\npower to dismiss an indictment with prejudice would overstep\\nthe separation of powers.” Id. at 520. Abbati dismissed that\\nargument based upon its belief that “[t]he separation of\\npowers is not an end in itself, but a general principle intended\\nto ensure that the system of checks and balances remains\\nvital.” Id. at 521 (citing State v. Leonardis, 375 A.2d 607, 612\\n(N.J. 1977)).\\n20\\n Id. at 520.\\n21\\n 412 F. Supp. 384 (D.D.C. 1976). The District Court of the\\nDistrict of Columbia dismissed an indictment after two trials\\nin which twenty-one of twenty-four jurors voted to acquit.\\nThe court found no prosecutorial misconduct. Id. at 386. It\\ninstead considered the issue a “matter of fair play,”\\nemphasizing that “[t]he Government has no new proof; it\\nsimply wants another chance” and “simply wishes to keep\\npressing so long as juries disagree in the hope that a\\nconviction eventually will result.” Id. at 385.\\n22\\n 806 F. Supp. 200 (C.D. Ill. 1992).\\n23\\n For example, the first prong of Abbati’s analysis concerns\\nthe number of mistrials and the outcome of the juries’\\ndeliberations. 493 A.2d at 521. Both Rossoff and Ingram took\\nthis into account in dismissing indictments. See Rossoff, 806\\nF. Supp. at 203 (naming, as “additional compelling\\ncircumstances: 1) the majority of jurors in both cases found\\nDr. Rossoff Not Guilty; 2) if not for the allegedly biased juror\\nin the second trial, Dr. Rossoff would have been acquitted on\\nall counts; 3) the two trials have taken over one solid month\\n 7\\n\\n Accordingly, as I noted at the outset, I am sympathetic\\nto the District Court’s efforts given the totality of the\\ncircumstances here. However, until Congress or the United\\nStates Supreme Court determines otherwise, I agree that we\\nhave no alternative but to enter judgment reversing the District\\nCourt. I therefore concur in the judgment reversing the District\\nCourt’s order.\\n\\n\\n\\n\\nof the Court’s time”); Ingram, 412 F. Supp. at 385 (“The\\nproof was legally sufficient to support a conviction in each\\ninstance but the juries simply did not credit the witnesses,\\nvoting 10–2 and 11–1 for acquittal.”).\\n The Abbati standard is also based on the likelihood of\\nany substantial difference in a subsequent trial, which the\\nIngram decision also considered. See Ingram, 412 F. Supp. at\\n385 (“If another trial takes place there is every reason to\\nbelieve the jury will again be divided or will acquit.”).\\n Finally, Rossoff and Ingram both made determinations\\nsimilar to Abbati’s seventh prong, the status of the individual\\nand the impact of a retrial upon the defendant in terms of\\nuntoward hardship and unfairness. 483 A.2d at 422; see\\nIngram, 412 F. Supp. at 385–86 (“Here is a man in jail now\\nmore than seven months primarily because of an offense\\nwhich the Government is unable to convince a jury he\\ncommitted. . . . To permit a retrial, after 21 of 24 jurors have\\nalready refused to convict, is to ignore the reasonable doubt\\nstandard.”); Rossoff, 806 F. Supp. at 203 (“Dr. Rossoff is 71\\nyears of age and in poor health. He has had heart surgery,\\nsuffers from severe anemia and at the time of the second trial\\nwas on experimental treatment. He has been under great\\nphysical and emotional strain as the result of these repeated\\ntrials and was even hospitalized immediately following the\\nsecond trial.”).\\n\\n 8\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360366/\", \"author_raw\": \"McKEE, Circuit Judge, concurring\"}, {\"author\": \"NYGAARD, Circuit Judge, dissenting\", \"type\": \"dissent\", \"text\": \"NYGAARD, Circuit Judge, dissenting\\n\\n This appeal presents us with two issues: First, does a\\ndistrict court possess the inherent power to dismiss an\\nindictment after serial hung juries, and second, did the\\nDistrict Court here abuse its discretion by dismissing this\\nindictment after two of them. I answer yes to the first and no\\nto the second. Because I view this to be a matter of\\nsubstantial importance, I must respectfully dissent.1\\n\\n As the majority notes, twice now, the Government has\\ntried Raymont Wright for a violation of federal law: being a\\nfelon in possession of a firearm.2 Twice now, the\\nGovernment has done so on the basis of essentially the same\\nevidence at trials presided over by the same District Court.\\nAnd twice now, two different juries could not reach a verdict.\\nThus, when the Government announced its intention to put\\nWright on trial for the third time, the District Court was\\nskeptical. It asked for briefing on whether it possessed the\\ninherent power to prohibit the Government from taking a\\nthird turn, and if it did, whether the court should use that\\n\\n\\n\\n\\n1\\n Whether the District Court had the inherent power to\\ndismiss the indictment is a legal question. We employ a\\nplenary standard of review to that issue. See United States v.\\nSchiff, 602 F.3d 152, 161 (3d Cir. 2010) (citing United States\\nv. Scott, 223 F.3d 208, 210 (3d Cir. 2000)). Whether the\\nDistrict Court appropriately exercised this power is reviewed\\nfor an abuse of discretion. Link v. Wabash R.R. Co., 370 U.S.\\n626, 633 (1962).\\n2\\n See 18 U.S.C. § 922(g).\\n\\n\\n\\n\\n 1\\n\\npower.3 After hearing from both sides, the District Court\\nconcluded that its inherent power applied to this\\ncircumstance. It then exercised its discretion to dismiss the\\nindictment.\\n\\n Neither the Government nor the majority disputes that\\ndistrict courts have the inherent authority to dismiss\\nindictments under at least some circumstances. Citing to\\nUnited States v. Hasting,4 however, the majority cabins that\\nauthority to those instances in which there is evidence of\\nprosecutorial misconduct. In my view, in so doing, the\\nmajority conflates and confuses the various powers of the\\ncourt. And it also hobbles the court’s discretion to probe the\\nimpact on the fair administration of justice of those\\nprosecutorial decisions that sit outside the definition of bad\\nconduct but still pose—or threaten to pose—real institutional\\nharm.\\n\\n The executive office inheres prosecutors with the\\npower to bring a case to trial. The judicial office, on the other\\nhand, inheres the court with the power to end a case.5 Both\\n\\n3\\n The District Court ordered the parties to “file cross briefs\\nstating their position regarding whether the Court, through an\\nexercise of its inherent authority, should prohibit or permit a\\nsecond re-trial in this case.” United States v. Wright, No. 14-\\ncr-292, 2017 WL 1179006, at *1 (W.D. Pa. 2017).\\n4\\n 461 U.S. 499, 505 (1983).\\n5\\n See Young v. U.S. ex rel. Vuitton et Fils S.A., 481 U.S. 787,\\n816 (1987)(Scalia, J. concurring)(“The judicial power is the\\npower to decide, in accordance with law, who should prevail\\nin a case or controversy. See Art. III, § 2. . . . [S]ince the\\nprosecution of law violators is part of the implementation of\\n\\n\\n\\n\\n 2\\n\\noffices share a responsibility to safeguard the overall integrity\\nof the judicial process. But when a prosecutor decides to\\nproceed with another trial in the aftermath of multiple\\nmistrials, who but the court is empowered to question the\\nimpact of the prosecutor’s discretion on the fair\\nadministration of justice, particularly when the court has\\nconcerns that the proceedings—and the institution—will be\\ntainted by the abuse of jury shopping? It could be argued that\\ntwo mistrials may not in some instances be enough to inflict\\nserious institutional damage. But, the majority’s combined\\nreliance on Dietz v. Bouldin6 and Fed. R. Crim. P. 31(b)(3) to\\nallow the prosecutor to bring an unlimited number of retrials,\\nso long as she or he does not stray into the realm of “illegal\\nconduct,” provides the prosecutor with an unchecked power.\\nThis poses a threat to the integrity of the judiciary and\\ncontradicts the inherent responsibility and authority vested in\\nthe judiciary by the framers of the Constitution. Thus, it is\\nthe majority’s decision—and not the District Court’s exercise\\nof its inherent authority—that violates the separation of\\npower principles on which the majority relies. We must\\naffirm that our trial court judges have the discretion,\\noriginating in the court’s inherent power, to take proper\\naction when warranted to protect the institutional integrity of\\nthe judiciary.\\n\\n Here, the District Court mindfully struck the balance\\nthat is necessary anytime the power of the court and the\\npower of the prosecutor intersect. Drawing from factors set\\n\\n\\nthe laws, it is—at least to the extent that it is publicly\\nexercised—executive power, vested by the Constitution in the\\nPresident.”) (footnote omitted)).\\n6\\n 136 S. Ct. 1885, 1892 (2016).\\n\\n\\n\\n\\n 3\\n\\nout in State v. Abbati,7 the District Court identified and\\ninvestigated a circumstance that it identified as harmful to the\\ninstitution and to the defendant: jury shopping. It also took\\nnote of the impact of serial retrials on the defendant. It then\\nproperly dismissed the indictment. Its use of the court’s\\ninherent discretion did not violate the separation of powers\\ndoctrine. To the contrary, it gave definition and substance to\\nit.\\n\\n I.\\n\\n Some review is appropriate to illuminate how and\\npossibly why I believe the majority confuses the court’s\\nvarious powers.\\n\\n A.\\n\\n Federal courts operate within a constitutional system\\nthat enumerates the powers of each branch of government, as\\nset forth in the founding document. Article I restrains\\ncongressional power to those “legislative Powers granted\\nherein.”8 By comparison, Article II vests the President with\\n“the executive Power” without further description, limitation,\\nor restriction.9 Analogous to Article II, Article III conveys\\nwithout restriction or limitation the “judicial Power” to\\nfederal courts.10 Accordingly, the Supreme Court has—since\\nat least 1812—recognized that “[c]ertain implied powers must\\nnecessarily result to our Courts of justice from the nature of\\n\\n7\\n 493 A.2d 513, 521-22 (N.J. 1985).\\n8\\n U.S. Const. art. I, § 1.\\n9\\n U.S. Const. art. II, § 1.\\n10\\n U.S. Const. art. III, § 1.\\n\\n\\n\\n\\n 4\\n\\ntheir institution.”11 “The moment the courts of the United\\nStates were called into existence and invested with\\njurisdiction over any subject, they became possessed of”\\ninherent authority.12\\n\\n Moreover, two bedrock purposes of the Constitution—\\nchecking the actions of the states and ensuring that Congress\\nand the Executive do not overstep their boundaries—require a\\nfederal judiciary that exercises its own independent judicial\\npower. That is, it would be impossible for federal courts to\\ndischarge these vital duties if they lacked some inherent\\npower beyond the reach of the Executive or the legislature. I\\nthink of it this way: the elaborate measures set out in the\\nConstitution to protect the independence of the judiciary (life\\ntenure, removal from office only through impeachment, no\\ndecrease in salary during a judge’s tenure, for example)\\nwould be meaningless if there were not some inherent,\\nunimpeachable power vested solely in the federal courts.\\n\\n In Eash v. Riggins Trucking Inc.,13 we defined inherent\\npower as vesting in federal courts upon their creation and as\\nnot deriving from any statute. In this sense, the “judicial\\npower” given to the federal courts by Article III of the\\nConstitution is the “power to decide, in accordance with law,\\nwho should prevail in a case or controversy.”14 No matter the\\ndescription, this power is intrinsic to the judicial office and\\ncannot be inhibited by any rule or act of Congress. As we\\n\\n11\\n United States v. Hudson, 11 U.S. (7 Cranch) 32, 34 (1812).\\n12\\n Ex parte Robinson, 86 U.S. 505, 510 (1873) (speaking of\\nthe inherent contempt power).\\n13\\n 757 F.2d 557, 561 (3d Cir. 1985) (en banc).\\n14\\n Young, 481 U.S. at 816 (Scalia, J., concurring).\\n\\n\\n\\n\\n 5\\n\\nhave recognized, the boundaries of this power are often\\n“nebulous” and “shadowy,”15 and “it is not always possible to\\ncategorize inherent power.”16 Yet, we have an outline.\\n\\n In Eash, we identified three main classes or categories\\nof inherent power: 1) inherent powers based in Article III,\\nthat is, the power of a lower federal court to decide a case\\nover which it has jurisdiction; 2) those powers “necessary to\\nthe exercise of all others,”17 and 3) powers that include those\\nreasonably useful to achieve justice, which are “necessary\\nonly in the practical sense of being useful.”18 Focusing on the\\nfirst category, the inherent power to decide a case is “so\\nfundamental to the essence of a court as a constitutional\\ntribunal that to divest the court of absolute command within\\nthis sphere is really to render practically meaningless the\\nterms ‘court’ and ‘judicial power.’”19 In other words, powers\\n\\n\\n15\\n Eash, 757 F.2d at 561 (citation omitted).\\n16\\n Id. at 562.\\n17\\n Id. (quoting Roadway Express, Inc., v. Piper, 447 U.S. 752,\\n764 (1980)).\\n18\\n Id. at 563; see also Am. Civil Liberties Union v. Holder,\\n673 F.3d 245, 255-56 (4th Cir. 2011) (applying Eash factors);\\nIn re Stone, 986 F.2d 898, 901-02 (5th Cir. 1993) (per\\ncuriam) (adopting Eash factors). In Chambers v. NASCO\\nInc., the Supreme Court was urged to adopt our approach to\\ninherent powers. But the Court held that it “ha[d] never so\\nclassified the inherent powers and . . . ha[d] no need to do so\\nnow.” 501 U.S. 32, 47 n.12 (1991).\\n19\\n Eash, 757 F.2d at 562. The third aspect of a court’s\\ninherent power is its authority to employ persons or\\ninstruments not connected with the court, such as experts and\\n\\n\\n\\n\\n 6\\n\\nin this category make a court a court; they are encoded into\\nthe judiciary’s DNA. Courts have referred to this power as a\\ncourt’s “irreducible inherent authority”20 and “the core Article\\nIII power.”21 It is nothing less than our ability to decide a\\ncase over which we have jurisdiction, without interference by\\nCongress or the Executive.22\\n\\n Drawing from this, when I refer to a district court’s\\ninherent power, I mean a ‘“[c]ertain implied power[] [that]\\nmust necessarily result to our Courts of justice from the\\nnature of their institution,’ [a] power[] ‘which cannot be\\ndispensed with in a Court, because they are necessary to the\\nexercise of all others.’”23 It is “grounded in the separation of\\npowers concept,” since to deny it and yet maintain an\\nindependent judiciary “is a self-contradiction.”24\\n\\n However, that is not to say that the court operates\\nsolely outside the realm of legislatively granted judicial\\n\\n\\nauditors, to assist in its decision-making function. This facet\\nof inherent power is not in play here.\\n20\\n Id.\\n21\\n Am. Civil Liberties Union v. Holder, 673 F.3d at 256.\\n22\\n United States v. Klein, 80 U.S. (13 Wall.) 128, 147 (1871),\\nEash, 757 F.2d at 562 (noting that courts may exercise this\\ntype of inherent power despite legislation to the contrary); see\\nalso Michaelson v. United States ex rel. Chicago, St. P., M. &\\nO. Ry. Co., 266 U.S. 42, 64 (1924) (acknowledging that the\\nConstitution vests courts with some powers unalterable by\\nlegislation).\\n23\\n Chambers, 501 U.S. at 43 (quoting Hudson, 11 U.S. (7\\nCranch) at 34.).\\n24\\n Eash, 757 F.2d at 562.\\n\\n\\n\\n\\n 7\\n\\npowers.25 In fact, the categorization scheme in Eash was\\nintended largely as a means of explaining the relationship\\nbetween inherent judicial powers and legislatively granted\\njudicial powers.26 It is here that I believe the majority’s\\nanalysis strays.\\n\\n B.\\n\\n The majority, the briefs, and the discussion at oral\\nargument reveal what has become a commonplace but\\nimprecise conflation of the terms “inherent power” and\\n“supervisory power.”27 The Government, while referencing\\nthe District Court’s “inherent power,” also referred to the\\ncourt’s “supervisory power,” and its “inherent supervisory\\njudicial authority.”28 The Appellee covers the entire panoply,\\nciting the District Court’s “supervisory authority,” its\\n\\n\\n25\\n See Hudson, 11 U.S. (7 Cranch) at 33.\\n26\\n See In re Tutu Wells Contamination Litig., 120 F.3d 368,\\n384 n.14 (3d Cir. 1997), overruled on other grounds by\\nCunningham v. Hamilton County, Ohio, 527 U.S. 198 (1999).\\n27\\n In Eash, we noted that “[t]he conceptual and definitional\\nproblems regarding inherent power . . . have bedeviled\\ncommentators for years,” 757 F.2d at 561, and that “those\\ncases that have employed inherent power appear to use that\\ngeneric term to describe several distinguishable court\\npowers,” id. at 562. We also noted that “this lack of\\nspecificity [has been compounded by courts] rel[ying] . . . on\\nprecedents involving one form of power to support the court’s\\nuse of another.” Id.\\n28\\n E.g., Appellant’s Br. at 13, 16; Appellant’s Reply Br. at 2,\\n14.\\n\\n\\n\\n\\n 8\\n\\n“supervisory power,” and its “inherent power.”29 At times,\\nwe too have been guilty of adding to the confusion.30 The\\nerroneous interchangeability of these terms clouds an\\nimportant distinction that is crucial to this appeal: the\\ndifference between inherent judicial powers and legislatively\\ngranted judicial powers.31 As noted supra, inherent “judicial\\npower” is given to the federal courts by Article III of the\\nConstitution.32 Through this grant, federal courts receive the\\n“power to decide, in accordance with law, who should prevail\\nin a case or controversy.”33 The merging of the terms\\n“inherent” and “supervisory” likely has its genesis in the fact\\nthat some inherent powers are supervisory in function, such\\nas a federal court’s inherent power “to supervise the\\nadministration of criminal justice.”34\\n\\n29\\n E.g., Appellee’s Br. at 22, 26.\\n30\\n See, e.g., United States v. Accetturo, 783 F.2d 382, 396 (3d\\nCir. 1986) (Sloviter, J., dissenting) (speaking of our “inherent\\nsupervisory power”); see also United States v. Watkins, 339\\nF.3d 167, 180 (3d Cir. 2003) (Nygaard, J., concurring)\\n(referring to both a court’s supervisory power and inherent\\npower to dismiss a case under Fed. R. Crim. P. 48(b)).\\n31\\n In re Tutu Wells Litig., 120 F.3d at 384 n. 14.\\n32\\n See U.S. Const. art. III, § 1.\\n33\\n Young, 481 U.S. at 816 (Scalia, J., concurring).\\n34\\n United States v. Payner, 447 U.S. 727, 735 n.7 (1980)\\n(quotation marks omitted); see also Sara Sun Beale,\\nReconsidering Supervisory Power in Criminal Cases;\\nConstitutional and Statutory Limits of the Federal Courts, 84\\nColum. L. Rev. 1433, 1433-34, 1465, 1470 (1984)\\n(identification of Article III “judicial power,” not\\ncongressional acts, as the source of the Supreme Court’s\\nsupervisory authority).\\n\\n\\n\\n\\n 9\\n\\n However, unlike inherent powers, a court’s\\nsupervisory authority may come from, and can be limited by,\\nacts of Congress or a court’s own rules.35 Supervisory power\\noften speaks to the power “to mandate ‘procedures deemed\\ndesirable from the viewpoint of sound judicial practice.’”36 A\\ncourt’s use of supervisory power can usually be classified in\\none of three ways. First, supervisory power can refer to an\\nappellate court’s supervision of a district court, through the\\nimposition of procedures in addition to those already imposed\\nby federal statute or constitutional provision.37 We have, for\\nexample, relied on our supervisory power over district courts\\nto review the application of local rules of practice and\\nprocedure.38 We have also used our supervisory power to\\n\\n\\n\\n\\n35\\n See, e.g., McNabb v. United States, 318 U.S. 332, 340-41\\n(1943); Hasting, 461 U.S. at 505.\\n36\\n United States v. Moreno, 809 F.3d 766, 780 (3d Cir. 2016)\\n(quoting Thomas v. Arn, 474 U.S. 140, 146-47 (1985)).\\n37\\n See, e.g., Castro v. United States, 540 U.S. 375, 384 (2003)\\n(instructing district courts to notify pro se litigants about\\nconsequences of re-characterizing motions as ones seeking\\nrelief under 28 U.S.C. § 2255); Thiel v. S. Pac. Co., 328 U.S.\\n217, 225 (1946) (announcing a new rule for the composition\\nof federal juries); Dunbar v. Triangle Lumber & Supply Co.,\\n816 F.2d 126, 129 (3d Cir. 1987) (prescribing procedures for\\nmotions to dismiss based on the conduct of a litigant’s\\ncounsel); United States v. Bazzano, 570 F.2d 1120, 1137-38\\n(3d Cir. 1977) (requiring district courts to state reasons for a\\ncriminal sentence).\\n38\\n See United States v. Wecht, 484 F.3d 194, 204-05 (3d Cir.\\n2007).\\n\\n\\n\\n\\n 10\\n\\nprohibit certain jury instructions in the district courts39 and to\\nreview attorney-client fee arrangements.40 Second, Courts—\\nboth trial and appellate—also refer to their “supervisory\\npower” when meaning their power to supervise pending\\nlitigation.41 They can, for example, seal and unseal records,42\\nreassign a case to a different judge on remand,43 or disqualify\\nan attorney on ethical grounds.44 Lastly, the power of a\\nfederal court to supervise law enforcement officials can also\\nbe what a court intends when it speaks of its “supervisory\\n\\n\\n\\n\\n39\\n See United States v. E. Med. Billing Inc., 230 F.3d 600,\\n607-12 (3d Cir. 2000).\\n40\\n See Ryan v. Butera, Beausang, Cohen & Brennan, 193 F.3d\\n210, 214 (3d Cir. 1999).\\n41\\n See, e.g., Carlisle v. United States, 517 U.S. 416, 425-26\\n(1996) (acknowledging “supervisory power” of district courts\\nover litigation before them).\\n42\\n See, e.g., Hagestad v. Tragesser, 49 F.3d 1430, 1434 (9th\\nCir. 1995).\\n43\\n See Gov’t of the Virgin Islands v. Walker, 261 F.3d 370,\\n376 (3d Cir. 2001) (noting that, “[a]lthough it is the standard\\npractice in the district courts and in this circuit that a case on\\nremand is assigned to the judge who originally heard it, we\\ncan, in the exercise of our supervisory power, reassign this\\ncase to a different judge upon remand.”) (quotation marks\\nomitted).\\n44\\n In re Grand Jury Investigation, 447 F. Supp. 2d 453, 456-\\n57 (E.D. Pa. 2006) (collecting cases); see also United States\\nv. Moreno, 809 F.3d at 780 (summarizing supervisory\\nauthority).\\n\\n\\n\\n\\n 11\\n\\npower.”45 These powers broadly ensure that pending cases\\nare managed uniformly and efficiently.\\n\\n I concede that the boundary between supervisory\\nauthority that is inherent to the court and that which is granted\\nby the legislature can, at times, be difficult to identify.\\nHowever, these difficulties are irrelevant to this case because\\nI conclude that the District Court here acted pursuant to its\\ninherent power and not to any authority conferred by any\\nstatute or rule. The District Court’s action was not\\nundertaken in supervision of pending litigation—two trials\\nwere already concluded and a potential third trial had not yet\\nbegun. Nor was it exercised according to a rule of procedure\\nor practice newly announced by an appellate tribunal.\\nMoreover, its action was not a response to any prosecutorial\\nmisconduct or request from Wright to dismiss the indictment.\\nThere is simply no basis to conclude that the inherent power\\nthat the District Court exercised in this case derived from any\\nlegislative grant.\\n\\n To the contrary, the specific power under review here\\nis the power to dismiss an indictment after two mistrials\\nbecause of deadlocked juries in each instance. This power\\nfalls within Eash’s first category of power because it is an\\ninherent power to resolve a case. A court, by its nature, must\\nbe able to dismiss with prejudice actions brought before it,\\njust as it must have the power to decide cases and enter\\n\\n45\\n See, e.g., United States v. Thompson, 772 F.3d 752, 763 (3d\\nCir. 2014). For a comprehensive discussion of the origins\\nand uses of supervisory power, see Amy Coney Barrett, The\\nSupervisory Power of the Supreme Court, 106 Colum. L. Rev.\\n324, 330 (2006).\\n\\n\\n\\n\\n 12\\n\\njudgments.46 Such exercises of power are fundamental to the\\nessence of a court. Were they not, the judicial system simply\\ncould not function.47\\n\\n The inherent power to dismiss is “of ancient origin,\\nhaving its roots in judgments of nonsuit and non prosequitur\\nentered at common law,” and so is a power that is part of the\\nvery nature of the judicial institution.48 It is incidental and\\nnecessary to the fair and efficient operation of the courts.49\\nIndeed, “the power to dismiss exists in many situations. For\\nexample, a district court has the inherent power to dismiss sua\\nsponte for lack of jurisdiction, or under the doctrine of forum\\nnon conveniens.”50 Because the power to resolve a case by\\ndismissing an indictment (in a criminal action) or a complaint\\n(in a civil action) is fundamental to the essence of a court of\\njustice, it cannot be interfered with. Indeed, as two\\ncommentators have explained, “McNabb, other Supreme\\n\\n46\\n We have also noted that our power to remand is a subset of\\nthe inherent power to dismiss a case. See Bradgate Assocs.,\\nInc. v. Fellows, Read & Assocs., Inc., 999 F.2d. 745, 750 n.4\\n(3d Cir. 1993).\\n47\\n See, e.g., Fitzgerald v. First E. Seventh St. Tenants Corp.,\\n221 F.3d 362, 363-364 (2d Cir. 2000) (holding a district court\\nhas the inherent power to dismiss a case, sua sponte, if it\\ndetermines that the action is frivolous or the court lacks\\njurisdiction over the matter).\\n48\\n Link, 370 U.S. at 630.\\n49\\n See, e.g., Bowers v. Nat’l Collegiate Athletic Ass’n, 564 F.\\nSupp. 2d 322, 333 (D.N.J. 2008) (citing Derzack v. County of\\nAllegheny, 173 F.R.D. 400, 411 (W.D. Pa. 1996), aff’d\\nwithout op., 118 F.3d 1575 (3d Cir. 1997)).\\n50\\n In re Prevot, 59 F.3d 556, 565-66 (6th Cir. 1995).\\n\\n\\n\\n\\n 13\\n\\nCourt cases, and an analysis of several lower court opinions\\naddressing this precise issue should sufficiently dispel any\\nnotion that the federal courts lack the power to bar repeated\\nattempts to obtain a conviction” following serial mistrials.51\\nThus, the District Court’s action here was well within the\\nboundaries of its inherent power.\\n\\n Therefore, the majority’s conclusion that “inherent\\nauthority,” “supervisory power,” and “supervisory authority”\\nall refer to the same thing (while understandable given the\\nrampant muddled references that persist) ultimately misses\\nthe point. The power at issue here is the inherent power of\\nthe court to decide a case: a power that is limited by the\\nboundaries of reason and discretion and is subject to appellate\\nreview for abuse. It is not subject to the power of Congress\\nor the Executive.\\n\\n II.\\n\\n There is no dispute that district courts have the\\ninherent power to dismiss indictments in at least some\\ncircumstance. The majority nevertheless concludes that the\\nDistrict Court lacked the power to do so in this case. The\\nmajority reaches that conclusion for three principal reasons,\\nbut none withstands scrutiny.\\n\\n A.\\n\\n51\\n Michael A. Berch & Rebecca White Berch, The Power of\\nthe Judiciary to Dismiss Criminal Charges After Several\\nHung Juries: A Proposed Rule to Control Judicial Discretion,\\n30 Loy. L.A. L. Rev. 535, 543 & nn. 42-43 (1997) (collecting\\ncases).\\n\\n\\n\\n\\n 14\\n\\n First, the majority agrees with the Government’s\\nargument that the District Court’s dismissal violated the\\nSeparation of Powers Doctrine. I agree that the District\\nCourt’s dismissal implicates the separation of powers. But its\\nactions were in furtherance—not in violation—of the\\ndoctrine. The separation of powers doctrine refers to the\\nbalance among the branches of Government which prevents\\none branch from disrupting the constitutional functions of\\nanother.52\\n\\n Here, the majority concludes that, in dismissing the\\nindictment after two hung juries, the District Court\\nencroached on the independence of the Executive because it\\nprohibited the prosecution from exercising its constitutional\\nduty to enforce the laws of the United States. Certainly, the\\nUnited States Attorney, as a member of the Executive Branch,\\nhas such a responsibility.53 And, just as certainly, the\\ndecision to prosecute “is soundly within the discretion of the\\nprosecutor, not the courts.”54 The Government’s authority\\nnot to prosecute a case is clear as well.55 But we see no sign\\nthat the District Court did anything to prevent the\\nGovernment from fulfilling its duty. To the contrary, the\\nGovernment was twice given a full and fair opportunity to\\n\\n52\\n See, e.g., Clinton v. Jones, 520 U.S. 681, 699-700 (1997);\\nMorrison v. Olson, 487 U.S. 654, 696 (1988); Nixon v. Adm’r\\nof Gen. Servs., 433 U.S. 425, 442-43 (1977); Baraka v.\\nMcGreevey, 481 F.3d 187, 201 (3d Cir. 2007).\\n53\\n See, e.g., In re Grand Jury, 286 F.3d 153, 163 (3d Cir.\\n2002).\\n54\\n United States v. Talley, 164 F.3d 989, 997 (6th Cir. 1999).\\n55\\n See, e.g., United States v. Quinn, 728 F.3d 243, 255-56 (3d\\nCir. 2013).\\n\\n\\n\\n\\n 15\\n\\npresent its case and makes no claim that the District Court\\never prevented it from doing so. Having had those\\nopportunities, the Government had no absolute right as a\\nmatter of separation of powers or otherwise to try again. As\\ntwo commentators have explained, a district court’s use of its\\ninherent power to dismiss an indictment after serial mistrials\\ndoes not raise “significant separation of powers concerns”\\nbecause the nature of that inherent power means that federal\\ncourts “need not automatically defer to a prosecutor’s\\ndecision to retry a defendant” in this situation.56\\n\\n The majority nevertheless concludes that prosecutors\\nhave the unimpeded right to try persons for violating federal\\nlaw based on an indictment as many times as they wish and\\nthat the separation of powers doctrine prohibits a federal court\\nfrom interfering. This position is untenable because it is not a\\ntrue reflection of the separation of powers. It is axiomatic\\nthat no one branch of government is completely divorced\\nfrom the other two. In reality, “our constitutional system\\nimposes on the Branches a degree of overlapping\\nresponsibility, a duty of interdependence as well as\\nindependence.”57 This overlap becomes problematic, of\\ncourse, when it results in an encroachment (when an action of\\none branch might undermine the independence of another\\nbranch) or an aggrandizement (where one branch seeks\\n“powers more appropriately diffused among separate\\nBranches”).58\\n\\n\\n56\\n Berch & Berch, supra note 51, at 544.\\n57\\n Mistretta v. United States, 488 U.S. 361, 381 (1989).\\n58\\n Id. at 381; see also In re Tribune Media Co., 799 F.3d 272,\\n285 (3d Cir. 2015) (Ambro, J., concurring).\\n\\n\\n\\n\\n 16\\n\\n But recognizing a district court’s right to prohibit a\\nretrial following serial mistrials does not implicate these\\nconcerns. To the contrary, and putting the shoe on the other\\nfoot, the Government’s position that nothing limits its\\nopportunity to try and retry a defendant as many times as it\\nchooses violates the judicial branch’s constitutional mandate\\nto exercise its judicial power. Just as the filing of an\\nindictment is an exercise of executive power, the dismissal of\\none is an exercise of judicial power. The unlimited serial\\nprosecutions that the Government advocates for, and that the\\nmajority permits, would limit a court’s authority to dismiss an\\nindictment to only those instances in which the prosecutor\\nsteps outside the bounds of professional conduct. But our\\nindependence as an institution of government must include an\\nability to adjudicate, and thus dismiss with prejudice,\\nindividual cases when a district court, in its discretion, has\\nconcerns about the impact of serial retrials on the institution\\nand the defendant. We view the prosecution of a defendant\\nafter deadlocked juries as a tipping point in balancing the\\nseparation of powers. As the repeated prosecutions increase,\\nso too does the judiciary’s power to limit them. As we stated\\nin Eash, and as we said supra, a court’s exercise of its\\ninherent power to dismiss an indictment after retrials does not\\nviolate the separation of powers but is grounded in it.59\\n\\n B.\\n\\n Second, and relatedly, the majority concludes that the\\nDistrict Court’s dismissal was in violation of Fed. R. Crim. P.\\n31(b)(3), which the majority claims confers on prosecutors\\nthe unlimited discretion to retry defendants following serial\\n\\n59\\n See Eash, 757 F.2d at 562.\\n\\n\\n\\n\\n 17\\n\\nmistrials. Rule 31 does nothing of the kind. Rule 31 provides\\nin relevant part that “if a jury cannot agree on a verdict on one\\nor more counts, the court may declare a mistrial on those\\ncounts. The government may retry any defendant on any\\ncounts on which the jury could not agree.”60 The Supreme\\nCourt adopted this rule in its original form in 1944 as a\\n“restatement of existing law.”61 The Supreme Court itself\\nappears never to have cited Rule 31(b)(3), and neither the few\\nCourts of Appeals to have done so62 nor its Advisory\\nCommittee Notes have discussed its history or purpose in any\\ndetail. Arguably, the rule’s reference to the prosecutor’s\\ngeneral ability to retry a defendant following a mistrial may\\nbe nothing more than a recognition of the longstanding\\nprinciple that retrials following mistrials are not prohibited by\\nthe Double Jeopardy Clause,63 which is not at issue here.\\n\\n In any event, this rule does not by its terms prohibit\\ndistrict courts from dismissing indictments following serial\\nmistrials. District courts have the inherent power to do so as\\nexplained above. A district court’s exercise of that power\\ncould be contrary to Rule 31(b)(3) only if the rule contained\\nan “express grant of or limitation on” that power.64 It does\\nnot. The rule does not mandate a retrial after a mistrial. Nor\\n\\n60\\n Fed. R. Crim. P. 31(b)(3).\\n61\\n Id. advisory committee’s note to 1944 adoption.\\n62\\n See United States v. Melendez, 775 F.3d 50, 57 (1st Cir.\\n2014); United States v. Warren, 593 F.3d 540, 546 (7th Cir.\\n2010); United States v. Fort, 472 F.3d 1106, 1111 n.3 (9th\\nCir. 2007); United States v. Gotti, 451 F.3d 133, 137 (2d Cir.\\n2006).\\n63\\n See United States v. Perez, 22 U.S. 579, 580 (1824).\\n64\\n Dietz, 136 S. Ct. at 1892.\\n\\n\\n\\n\\n 18\\n\\ndoes it contain any other limitation on the district court’s\\npower to prohibit one. In fact, the rule does not even mention\\nthat issue.65 Thus, as the Supreme Court has noted in\\naddressing other rules of court, “[i]t would require a much\\nclearer expression of purpose than [this rule] provides for us\\nto assume that it was intended to abrogate” the district courts’\\ninherent power.66 Put simply, when there have been multiple\\nmistrials and the prosecutor seeks to try the case again, Rule\\n31(b)(3) does not purport to reduce the role of the district\\ncourts to that of a rubber stamp.\\n\\n C.\\n\\n Finally, the majority claims that a district court can\\nexercise its inherent power to dismiss an indictment only if\\nthere is evidence of willful bad faith or prosecutorial\\nmisconduct on the part of the government and resultant\\nprejudice to the defendant. It cites to numerous decisions that\\nit says supports this position.67 But none of these cases deals\\n\\n65\\n The majority claims that Rule 31(b)(3)’s silence on this\\nissue supports the proposition that district courts lack the\\nauthority to dismiss an indictment following serial mistrials.\\nBut because district courts have the inherent power to do so\\nas explained above, the question is not whether Rule 31(b)(3)\\npermits district courts to dismiss an indictment in that\\ncircumstance. The question instead is whether Rule 31(b)(3)\\nprohibits them from doing so. It does not.\\n66\\n Link, 370 U.S. at 631-32.\\n67\\n See Bank of Nova Scotia v. United States, 487 U.S. 250,\\n254-56, 263 (1988); United States v. Chapman, 524 F.3d\\n1073, 1087 (9th Cir. 2008); United States v. Goodson, 204\\nF.3d 508, 514 (4th Cir. 2000); United States v. Derrick, 163\\n\\n\\n\\n\\n 19\\n\\nwith the particular circumstance we face here: the decision to\\nretry a defendant after serial mistrials.68 In fact, many are\\ndismissals due to prosecutorial misconduct. The majority’s\\nreliance on such decisions is misplaced because it ignores the\\nfact that the dismissal in this case was not punitive in nature;\\nit was not a sanction for misconduct.69 As two commentators\\nhave explained, “[a]lthough the inherent power principle has\\nusually involved cases of misconduct by the parties or a\\nvindication of statutory principles, the doctrine is not so\\nlimited.”70 To the contrary, courts may use their inherent\\nauthority to dismiss indictments whenever necessary to\\nvindicate “principles of fairness to the defendant and the\\ninterests of the public in the effective administration of\\njustice.”71\\n\\n That is just what the District Court did here. The\\nGovernment asked the District Court to dismiss without\\nprejudice “[e]ven if this court were inclined to dismiss the\\ncase.”72 Yet the Government proffered no additional\\n\\n\\nF.3d 799, 808 (4th Cir. 1998); United States v. Tucker, 8 F.3d\\n673, 674 (9th Cir. 1993) (en banc); United States v. Van\\nEngel, 15 F.3d 623, 631-32 (7th Cir. 1993); United States v.\\nSantana, 6 F.3d 1, 11 (1st Cir. 1993); United States v. Isgro,\\n974 F.2d 1091, 1094 (9th Cir. 1992).\\n68\\n Derrick does deal with a dismissal of the indictment after\\nan initial grant of a retrial, but the circumstance differs from\\nthis case because the mistrials were not due to deadlocked\\nverdicts. See 163 F.3d at 803\\n69\\n Cf., e.g., Isgro, 974 F.2d at 1097.\\n70\\n Berch & Berch, supra note 51, at 548.\\n71\\n Id.\\n72\\n Wright, 2017 WL 1179006, at *7.\\n\\n\\n\\n\\n 20\\n\\nevidence it would present if Wright was re-indicted. It asked\\nto try the same case again before a third jury, merely hoping\\nfor a different result. The District Court’s dismissal of the\\nindictment with prejudice was based on the merits, or lack\\nthereof, of the Government’s request, no more and no less.\\n\\n Moreover, the dismissal was not, as the majority\\ncontends, a general declaration of unfairness simply because\\nthe government failed to obtain a conviction.73 Nor was it\\nmerely an attempt to shield the defendant from the anxiety of\\na retrial.74 Reference to Miller and Shepherd misconstrues\\nnot only the circumstance of this case, but also the gravity of\\nthe District Court’s concern. As I discuss next, the District\\nCourt weighed many factors, mindful of the importance of\\neach, before making its decision. From all of this—even\\ntaking into account the separation of powers and Rule\\n31(b)(3)—it is evident to me that the District Court correctly\\nconcluded it had the inherent authority to act upon the\\nprosecutor’s decision to retry this case in the wake of two\\nmistrials.75\\n\\n73\\n See United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\n74\\n See United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975); see also Arizona v. Washington, 434 U.S. 497, 503-04\\n(1978).\\n75\\n Although we conclude that the District Court appropriately\\nexercised its inherent power as a court of law to dismiss an\\nindictment, thus placing its actions within Eash’s first\\ncategory, the District Court appeared at one point to tether its\\ndismissal to its “inherent authority to effectuate . . . the\\nspeedy and orderly administration of justice and to ensure\\nfundamental fairness.” Wright, 2017 WL 1179006, at *2.\\nThese actions are typically associated with the second\\n\\n\\n\\n\\n 21\\n\\n III.\\n\\n Before moving to the actual merits of the District\\nCourt’s decision, a word of caution is in order. Just because a\\ncourt has inherent power to dismiss an indictment after a\\nretrial does not mean it should always be exercised.76 My\\ndissenting opinion today should not be interpreted as an\\nendorsement of unchecked and ungrounded judicial power.\\nNor should it be interpreted as permitting district courts in\\nthis Circuit to dismiss indictments without a significant basis\\nfor doing so. Moreover, nothing in this opinion should be\\nread as limiting reprosecution to two trials. Cases no doubt\\nexist where a third or fourth trial on the same indictment may\\nbe appropriate where the evidence so indicates. It is simply\\nmy conclusion that, in some cases, and in the proper exercise\\nof its discretion, a district court has the inherent power to\\nprohibit continued re-prosecution by dismissing an\\nindictment.\\n\\n IV.\\n\\n This is such a case. The District Court here rightly\\nproceeded with the Government’s request for another trial\\nwith deliberate caution. Recognizing the lack of guidance\\n\\n\\nclassification of Eash’s powers. See Eash, 757 F.2d at 562-\\n563. Nonetheless, it invoked the inherent power of the court\\nand dismissed the case and it is on this basis that I conclude\\nthe District Court did not reach the boundaries of its power.\\n76\\n See Lopez v. United States 373 U.S. 427, 440 (1963); see\\nalso Chambers, 501 U.S. at 44 (“Because of their very\\npotency and discretion, inherent powers must be exercised\\nwith restraint and discretion.”).\\n\\n\\n\\n\\n 22\\n\\nfrom this Court, the District Court turned to a decision of the\\nSupreme Court of New Jersey. In State v. Abbati,77 that court\\nlisted several factors a trial court should consider before\\ndismissing an indictment after several hung juries. These\\nfactors are valid inquiries and include\\n\\n the number of previous mistrials and the\\n outcome of the juries’ deliberations, as far as\\n can be determined;\\n the character or nature of the previous trials,\\n considering their length, complexity of issues,\\n and similarities in evidence;\\n the probability that any subsequent trial will be\\n much different from the previous ones;\\n the relative strength of the party’s case, as\\n determined by the trial court;\\n the conduct of counsel during the previous\\n trials.78\\n\\nIn considering these factors, a district court must also accord\\nappropriate weight to the Government’s decision to continue\\nprosecution, giving deliberate consideration to the reasons for\\nthat choice.79\\n\\n Other considerations might include the seriousness of\\nthe crimes charged, the public’s interest in the effective\\nresolution of criminal charges, and the criminal defendant’s\\ncircumstances, including the impact that continued\\nprosecution might have on him or her and the potential for\\n\\n77\\n 493 A.2d 513.\\n78\\n Id. at 521-22.\\n79\\n See id.\\n\\n\\n\\n\\n 23\\n\\nunfairness or unnecessary hardship.80 The factors just\\noutlined are not an exhaustive list and district courts could\\nconsider other things that are reasonably useful in answering\\nwhether further prosecutions after deadlocked juries should\\nbe permitted. Moreover, all of these elements of inquiry\\nenable the court to assess the impact that a serial retrial has on\\nthe integrity of the judiciary as an institution.\\n\\n These avenues of inquiry make sense to me. Take\\ndifferences in evidence, for example. If the evidence would\\nbe different at a retrial, then there seems little chance that\\ncontinued prosecution should be curtailed. If, on the other\\nhand, there would be no substantial difference in evidence,\\nconcern about re-prosecution is appropriate. So too the\\nnumber of deadlocked juries is an important consideration.\\nContinued prosecution after two, three, or even four\\ndeadlocked juries could unbalance the scale. By inquiring\\ninto the seriousness of the charges, a district court could\\ncompare the crime being prosecuted to other cases when a\\ncourt dismissed an indictment after deadlocked juries. In\\nother words, a district court must make sufficient findings and\\nestablish a sufficient record supporting its decision, thus\\nenabling a court of appeals to accurately assess whether the\\ndistrict court abused its discretion or not. That is what the\\nDistrict Court did here.\\n\\n I see no abuse of discretion in the District Court’s\\nexercise of its inherent powers. The District Court’s ruling\\nwas not arbitrary and instead was based on a thorough,\\ncareful, and balanced consideration of the above factors. The\\nDistrict Court first acknowledged the weight of its actions\\n\\n80\\n See id.\\n\\n\\n\\n\\n 24\\n\\nwithin our constitutional scheme. It then found that the\\nevidence suggested that the deadlock was not the result of a\\nlone holdout. As to the character of the preceding trials, the\\nDistrict Court noted the Government’s position that this was a\\n“simple” case. It also stated that both previous trials were\\n“virtual duplicates” and that counsel on both sides was the\\nsame for both prosecutions. The District Court further\\nobserved the lack of any allegation of jury nullification or\\nbias. Instead, it found that “there is every indication that the\\ntwo juries engaged in deliberations in good faith, and, despite\\ntheir best efforts, were unable to reach a verdict.”\\n\\n The District Court also considered the strength of the\\nparties’ respective cases and determined that its opinion on\\nthis factor was irrelevant, given that two separate juries had\\nconcluded that the Government failed to meet its burden of\\nproof. It commended the professionalism and hence the\\neffectiveness of counsel on all sides, which it weighted as\\nfavoring disallowing any further prosecution. The District\\nCourt specifically considered the seriousness of the crime\\ncharged, and it noted that other courts had dismissed\\nindictments when the charges were far graver.81 Lastly, the\\nDistrict Court thoroughly balanced the Government’s\\nauthority to prosecute against the effect of continued\\nprosecution on Wright. Recognizing that Wright has been on\\nbond since July of 2014, and on home detention for nearly\\ntwo years, the District Court concluded that this inquiry\\ntipped in his favor.\\n\\n81\\n Wright, 2017 WL 1179006, at *6 (citing United States v.\\nIngram, 412 F. Supp. 384, 385 (D.D.C. 1976); State v.\\nMoriwake, 647 P.2d 705, 708 (Haw. 1982); Abbati, 493 A.2d\\nat 517; and State v. Witt, 572 S.W.2d 913, 914 (Tenn. 1978)).\\n\\n\\n\\n\\n 25\\n\\n V.\\n\\n In conclusion, I see no abuse of discretion in the\\nDistrict Court’s careful and thorough balancing of relevant\\nfactors, a balancing which led it to invoke its inherent power\\nand to dismiss the Government’s indictment of Wright. For\\nall of these reasons, I respectfully dissent from my esteemed\\ncolleagues in the majority. I would affirm.\\n\\n\\n\\n\\n 26\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360366/\", \"author_raw\": \"NYGAARD, Circuit Judge, dissenting\"}]}"},"judge1":{"kind":"string","value":"MCKEE"},"judge2":{"kind":"string","value":"SHWARTZ"},"judge3":{"kind":"string","value":"NYGAARD"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"MCKEE\": \", Circuit\", \"SHWARTZ\": \", Circuit\", \"NYGAARD\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":4,"string":"4"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":2,"string":"2"},"concurrence_count":{"kind":"number","value":1,"string":"1"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583113/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: United States v. Raymont Wright\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-18\nOpinion type: majority\nHas dissenting opinion: Yes\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-1972\n _____________\n\n UNITED STATES OF AMERICA,\n\n Appellant\n\n v.\n\n RAYMONT WRIGHT\n\n ______________\n\n ON APPEAL FROM THE\n UNITED STATES DISTRICT COURT\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\n (D.C. No. 2-14-cr-00292-001)\n District Judge: Hon. Cathy Bissoon\n ______________\n\n Argued May 24, 2018\n ______________\n\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\n Judges.\n\n (Opinion Filed: January 17, 2019)\n\n ______________\n\n OPINION OF THE COURT\n ________________\n\nDonovan J. Cocas, Esq. [ARGUED]\nJane M. Datttilo, Esq.\nLaura S. Irwin, Esq.\nOffice of the United States Attorney\n700 Grant Street\nSuite 4000\nPittsburgh, PA 15219\n\n Attorney for Appellant\n\nRenee Pietropaolo, Esq. [ARGUED]\nLisa B. Freeland, Esq.\nAkin Adepoju, Esq.\nOffice of the Federal Public Defender\n1001 Liberty Avenue\n1500 Liberty Center\nPittsburgh, PA 15222\n\n Attorneys for Appellee Raymont Wright\n\nLawrence S. Lustberg, Esq. [ARGUED]\nGibbons, P.C.\nOne Gateway Center\nNewark, NJ 07102\n\n Attorney for Amicus Appellee National Association of\n Criminal Defense Lawyers\n\n\n\n\n 2\n\nSHWARTZ, Circuit Judge.\n\n The District Court barred a retrial of and dismissed the\nindictment against Defendant Raymont Wright with prejudice\nafter two juries failed to reach a verdict. The Court did so\nrelying on its inherent authority, but without finding that any\nmisconduct had occurred or that Wright would suffer any\nprejudice beyond the general anxiety and inconvenience of\nfacing a retrial. Under such circumstances, the Court lacked\nthe inherent authority to bar the retrial and dismiss the\nindictment. Therefore, we will reverse the order dismissing the\nindictment and remand for further proceedings.\n\n I\n\n In December 2014, Wright was charged with being a\nfelon in possession of a firearm, in violation of 18 U.S.C.\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\nMay 2016. The jury was unable to reach a verdict. A second\ntrial was held in March 2017, and that jury was also unable to\nreach a verdict.\n\n During both trials, the jury heard evidence from police\nofficers about Wright’s actions on July 24, 2014.1 That\nevening, five Pittsburgh Police detectives were patrolling in\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\nwere in the lead car, and Detectives Fallert and Goob were in\nthe second car. Around 8:30 p.m. (when it was still daylight),\nFallert and Goob saw a man, later identified as Wright, driving\n\n 1\n The following facts are drawn largely from the\nevidence presented at the first trial.\n\n\n\n\n 3\n\na car in the opposite direction well above the 25-mile-per-hour\nspeed limit. The detectives turned around to follow Wright,\nand Wright sped up and turned onto a loop-shaped road. The\ndetectives pursued Wright, who fled at a high speed and ran at\nleast four stop signs. The lead car lost sight of Wright shortly\nthereafter and discontinued pursuit.\n\n Officers in the lead car then noticed skid marks\nsuggesting that a car had intended but failed to make a left turn\nat the end of a street. Officers thereafter came upon Wright’s\ncar in a parking lot below. The car had gone through a fence,\nover a hillside, and into the lot. The car hit two unoccupied\nparked cars, its tires blew out, and its windows were down.\n\n Detectives Baker and Henson exited the vehicle at the\ntop of the hill and remained where Wright’s car broke through\nthe fence, and Detective Kennedy drove his car down to the\nparking lot’s entrance. Baker and Henson testified that they\nsaw Wright search around the rear passenger seat of the car,\nback out of the vehicle with a black semi-automatic handgun\nin his right hand, and try to “rack the slide,” which can insert\nor remove a round from the chamber. App. 118-19. They had\ntheir weapons drawn and told Wright to drop the gun. At first,\nWright merely stepped back, but he eventually tossed the gun\nto the side, backed away, and lied on the ground. Pittsburgh\npolice officer Elliott and his partner, who heard of the crash on\nthe radio, were the first to reach Wright, and saw him lying on\nthe ground with a handgun next to him. Henson stated that\nwhen he made it down to the parking lot, he heard Wright say\nto him, “Hey, big guy. You won this time or you won this\nround, something of that nature. He [Wright] said: You feel\nme? You won this time,” which Henson understood to mean\nthat he had just avoided a shootout or that he caught Wright\n\n\n\n\n 4\n\nafter the pursuit. App. 125. Henson subsequently took custody\nof the gun and noticed the slide lever was bent, and when he\nstraightened it, saw the gun was loaded with eight rounds, and\none in the chamber. 2\n\n At the close of the Government’s case, Wright moved\nfor a directed verdict, arguing that no reasonable juror could\nfind beyond a reasonable doubt that Wright possessed the\nfirearm. The District Court denied the motion because “the\nevidence does thus far demonstrate that a reasonable juror\ncould most certainly find the Defendant guilty of the charge in\nthis case.” App. 171. Wright did not present a case.\n\n The jury deliberated for approximately five hours and\nthen reported to the Court that it was deadlocked. After polling\nthe jurors to confirm they were deadlocked and further\ndeliberations would not bring them closer to a unanimous\nverdict, the District Court declared a mistrial.\n\n At Wright’s March 2017 retrial, the Government\npresented substantially the same evidence. The Government\nalso called Detective Kennedy and Lieutenant Palermo, who\nwere at the scene after Wright was arrested, as well as experts\nwho testified regarding the collection of DNA and fingerprint\nevidence from firearms to respond to Wright’s argument at the\nfirst trial that investigators chose not to test the gun for forensic\nevidence in an effort to cover up that they had planted the gun\nat the scene.\n\n\n 2\n The parties stipulated Wright had been convicted of a\nqualifying felony, and an ATF Special Agent testified about\nthe gun’s interstate nexus.\n\n\n\n\n 5\n\n At the close of the Government’s case, Wright again\nmoved for a judgment of acquittal, which the Court denied\nbecause “there is sufficient evidence in the record to establish\nbeyond a reasonable doubt that Mr. Wright possessed the\nfirearm in the case,” App. 650. Wright did not put on a case.\n\n The second jury deliberated for approximately three\nhours and then reported that it was hopelessly deadlocked. The\nCourt polled the jury to confirm the deadlock and then\ndismissed the jury. 3\n\n After the Government notified the Court that it intended\nto retry the case, the Court required the parties to brief\n“whether the Court, through an exercise of its inherent\nauthority, should prohibit or permit a second re-trial in this\ncase.” App. 26. After considering the parties’ arguments, the\nDistrict Court dismissed the indictment with prejudice, holding\nthat it “ha[d] the inherent authority, under some circumstances,\nto dismiss an indictment following multiple mistrials.” United\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\nunderlying the Double Jeopardy Clause also applied to a\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\n(2) other courts had dismissed indictments in similar\n\n 3\n Wright asserted that in the first trial, jurors voted 8-4\nfor acquittal, and in the second trial, the jury was evenly split.\nThe Government asserted that in the first trial, jurors voted 7-\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\nnot explain how he obtained these numbers, the Government\nsaid it obtained them by speaking with the jurors.\n\n\n\n\n 6\n\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\nexpressly allows the Government to retry a case after a mistrial,\nnothing in the rule “limits a court’s inherent supervisory\nauthority to dismiss an indictment in the interests of\nfundamental fairness,” id. at *4; and (4) if the Court were to\nadopt the Government’s position that there are no limit to the\nnumber of times the Government can retry a defendant, it\nwould be tantamount to a “type of jury shopping” that a court\nshould not permit, id. at *4. The District Court also considered\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\nconcluded that most factors supported dismissal. 4\n\n 4\n The Abbati factors are\n\n (1) the number of prior mistrials and the\n outcome of the juries’ deliberations, so far as is\n known; (2) the character of prior trials in terms\n of length, complexity, and similarity of evidence\n presented; (3) the likelihood of any substantial\n difference in a subsequent trial, if allowed;\n (4) the trial court’s own evaluation of the relative\n strength of each party’s case; and (5) the\n professional conduct and diligence of respective\n counsel, particularly of the prosecuting attorney.\n The court must also give due weight to the\n prosecutor’s decision to reprosecute, assessing\n the reasons for that decision, such as the gravity\n\n\n\n\n 7\n\n The Government appeals.\n\n II 5\n\n We review the District Court’s order dismissing the\nindictment based on the Court’s inherent power for abuse of\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\n\n of the criminal charges and the public’s concern\n in the effective and definitive conclusion of\n criminal prosecutions. Conversely, the court\n should accord careful consideration to the status\n of the individual defendant and the impact of a\n retrial upon the defendant in terms of untoward\n hardship and unfairness.\n\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\nat 521-22). For the reasons set forth herein, we would not\nadopt Abbati, but even if we were to consider the Abbati\nfactors, we would conclude that they do not support dismissal\nin this case.\n 5\n The District Court had jurisdiction pursuant to 18\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\n§ 3731.\n 6\n The phrases “inherent power,” “inherent authority,”\n“supervisory power,” and “supervisory authority” are all used\nto describe the basis for a court action seeking to maintain the\nintegrity of the proceedings that is not directly tethered to a\nspecific rule, statute, or constitutional provision. See, e.g.,\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\n43 (1991) (inherent power); Bank of Nova Scotia v. United\n\n\n\n\n 8\n\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\nindictment for abuse of discretion); cf. Chambers v. NASCO,\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\nsanctions under its inherent power for abuse of discretion);\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\n2005) (“A trial court’s remedy for a discovery violation under\nits supervisory powers is reviewed for abuse of discretion.”).\nA district court abuses its discretion when it makes an errant\nconclusion of law, an improper application of law to fact, or a\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\n\n A\n\n Federal Rule of Criminal Procedure 31 allows the\nGovernment to retry a case if the court declares a mistrial after\na jury announces it is unable to reach a verdict. Specifically,\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\non one or more counts, the court may declare a mistrial on\nthose counts. The government may retry any defendant on any\ncount on which the jury could not agree.” Fed. R. Crim. P.\n31(b)(3). The word “may” means that the Government has the\n\n\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\n(supervisory power); United States v. Payner, 447 U.S. 727,\n733-36 (1980) (supervisory power); United States v. Nobles,\n422 U.S. 225, 231 (1975) (inherent power).\n Even if we accepted the distinctions our dissenting\ncolleague has drawn between inherent judicial powers,\nlegislatively granted judicial powers, and supervisory powers,\neach category must operate within the constitutional\nframework, including the separation of powers.\n\n\n\n\n 9\n\ndiscretion to retry a case, and nothing in the rule or its\ncommentary provides or even suggests a limit on the number\nof retrials it may conduct. See United States v. Wqas Khan,\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\n\n 7\n While Rule 31 does not limit the Government’s\nauthority to retry a case, a handful of district courts have\ndismissed indictments following a second hung jury, but those\ndecisions are not persuasive. In Ingram, the district court\ndismissed the indictment sua sponte (without any initial\nobjection by the Government) after two mistrials—in which\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\njailed during the pendency of the trials, and “[t]he Government\nha[d] no new proof; it simply want[ed] another chance.” 412\nF. Supp. at 385. The court concluded that to permit a retrial\nwould be “to ignore the reasonable doubt standard,” and so\n“[t]he Court’s intervention [was] required in the interest of\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\n(McGowan, J., dissenting)). The Ingram court, however, relied\nin part on the dissent in De Diego. Cases since Ingram have\napplied the De Diego majority’s view concerning a court’s\nlimited authority to dismiss an indictment. See, e.g., United\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\nDe Diego and reversing the district court’s dismissal of the\nindictment where the district court found it would be\n“unconscionable” to retry to the defendant); United States v.\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\nDiego and its dissent and holding a district court does not have\nauthority to sua sponte dismiss an indictment based on the\n\n\n\n\n 10\n\ndefendant’s poor health); United States v. Mussehl, 453 F.\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\nto dismiss the indictment based on alleged errors at trial, and\nciting De Diego for the proposition that “[t]he duty [to\nadminister justice] encompasses the concept of review of the\nquestion whether the United States Attorney, in making his\ndecision to prosecute, complied with the law, but does not\nallow the Court to question a United States Attorney’s\njudgment decision to prosecute, when lawfully made”).\n The District Court also relied on Rossoff, where the\ncourt denied the Government’s motion to dismiss the\nindictment under Federal Rule of Criminal Procedure 48(a),\nbut still dismissed the indictment with prejudice. 806 F. Supp.\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\nbeen two trials, and the Government sought to dismiss the\nindictment and refile the charges in a different judicial district.\nId. The court determined it had authority to dismiss an\nindictment with prejudice if a retrial was “against the concept\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\nSupp. 384), and did so because, among other reasons, the\ndefendant was in poor health, was under significant strain, and\na majority of jurors at both trials found him not guilty, id. at\n203. Rossoff, however, is distinguishable from Wright’s case\nbecause in Rossoff, the Government sought to dismiss the\nindictment so that it could refile charges in a different judicial\ndistrict, which caused the court to question the Government’s\ngood faith. In Wright’s case, the District Court made no\nfinding that the Government’s desire to retry Wright was for\nan improper purpose.\n In addition, and significantly, neither Ingram nor\nRossoff addressed the doctrine of separation of powers.\nRather, each essentially relied on a general concept of fairness\n\n\n\n\n 11\n\nthe text that empowers a court to prohibit the Government from\nretrying a case. 8\n B\n\n Apparently aware that Rule 31 did not provide it with a\nbasis to preclude a retrial in these circumstances, the District\nCourt concluded that it had the inherent authority to forbid the\nretrial and dismiss the indictment. The District Court erred.\n\n The exercise of inherent authority must satisfy two\nrequirements: (1) it “must be a reasonable response to the\n\n\nto the defendant in deciding to dismiss an indictment. See\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\nIn this Circuit, however, “[t]he judiciary may not impose its\npersonal and private notions of ‘fairness’ on law enforcement\nofficials, but does have a limited authority to affect\nprosecutorial actions when those actions are taken in violation\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\n596 (3d Cir. 1992) (citations omitted).\n 8\n Rule 31 differs from other Federal Rules of Criminal\nProcedure because it makes no mention of the court’s\nauthority. For instance, Rule 48(b) states that a court has\nauthority to dismiss an indictment “if unnecessary delay occurs\nin: (1) presenting a charge to the grand jury; (2) filing an\ninformation against a defendant; or (3) bringing a defendant to\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\ngrounds on which a district court could also dismiss an\nindictment, but each would be triggered by a motion, such as a\nmotion to dismiss for failure to comply with Rule 16’s\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\n16(d)(2)(D), or a motion asserting a defect in the indictment,\nFed. R. Crim. P. 12(b)(3)(B).\n\n\n\n\n 12\n\nproblems and needs confronting the court’s fair administration\nof justice,” and (2) it “cannot be contrary to any express grant\nof or limitation on the district court’s power contained in a rule\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\n(citations and internal quotation marks omitted). We will\nexamine each of these requirements in turn.\n\n 1\n\n As to the first Dietz requirement, “[g]uided by\nconsiderations of justice, and in the exercise of supervisory\npowers, federal courts may, within limits, formulate procedural\nrules not specifically required by the Constitution or the\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\n(internal quotation marks and citation omitted). Such rules\nmust be imposed (1) “to implement a remedy for violation of\nrecognized rights,” (2) “to preserve judicial integrity by\nensuring that a conviction rests on appropriate considerations\nvalidly before the jury,” and (3) “as a remedy designed to deter\nillegal conduct.” Id. (citations omitted). Thus, a court may\nexercise its inherent authority only when it is necessary to\naddress improper conduct and ensure respect for the\nproceedings.\n\n Under these principles, a court may dismiss an\nindictment based upon its inherent authority only if the\nGovernment engaged in misconduct, the defendant was\nprejudiced, and no less severe remedy was available to address\nthe prejudice. See Bank of Nova Scotia v. United States, 487\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\n(stating that “[a] court may dismiss an indictment under its\nsupervisory powers only when the defendant suffers\nsubstantial prejudice and where no lesser remedial action is\n\n\n\n\n 13\n\navailable” (citations and internal quotation marks omitted));\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\n(observing that “a district court may not, in the management of\nits docket, exercise its discretion to dismiss an indictment with\nprejudice, either under Rule 48(b) or under its supervisory\npower, unless the violation caused prejudice to the defendant\nor posed a substantial threat thereof” (emphasis omitted));\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\n(holding that an indictment may not be dismissed for\nprosecutorial misconduct absent a showing that the misconduct\nprejudiced the defendants, and stating that “virtually every\nother circuit to consider the issue post-Hasting and Nova Scotia\nhas also held that an indictment may not be dismissed based on\nprosecutorial misconduct, absent a showing of prejudice to the\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\n(7th Cir. 1993) (“A federal judge is not authorized to punish\nthe misconduct of a prosecutor by letting the defendant walk,\nunless the misconduct not only violated the defendant’s rights\nbut also prejudiced his defense . . . .”); United States v. Tucker,\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\nexercise its supervisory authority to reverse a conviction or\ndismiss an indictment absent prejudice to the defendant.”);\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\nHasting, and Bank of Nova Scotia form a trilogy admonishing\nfederal courts to refrain from using the supervisory power to\nconform executive conduct to judicially preferred norms by\ndismissing charges, absent cognizable prejudice to a particular\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\nCir. 1992) (“Before it may invoke this [supervisory] power [to\ndismiss an indictment], a court must first find that the\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\n1480 (9th Cir. 1994).\n\n\n\n\n 14\n\n In this case, there has been no misconduct. Indeed, the\nDistrict Court noted that the Government performed diligently\nand professionally in both trials, Wright, 2017 WL 1179006,\nat *4, and found that the evidence was sufficient to prove\nbeyond a reasonable doubt that Wright possessed the gun. The\nDistrict Court nonetheless applied its own predictions about\nwhat another jury may do when presented with the same\nevidence, emphasized the need for finality, and opined that the\neffect of prosecution on the defendant precluded a proper\nprosecution from proceeding. See id. at *5-6. Invoking its own\nnotions about the unfairness of requiring a defendant to face a\nretrial where the Government did not obtain a majority of the\njurors’ votes is an improper exercise of a court’s supervisory\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\nMoreover, there is no prejudice to a defendant simply because\nhe faces the anxiety and the normal stress of undergoing a trial.\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\n1975) (“[A]nxiety is present to some degree in virtually every\ncase. Something more than the normal anxiety that\naccompanies a trial is necessary to show a degree of\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\nonly real harm alleged is the general unfairness to these\ndefendants in having to go forward yet again with a lengthy\ntrial, in their being ‘ground down’ by the several months’ drain\non their mental, emotional, and financial resources. A lack of\nsuch fairness, however, does not alone violate due process.”).\nRather, prejudice sufficient for the District Court to intervene\nin a proper prosecution based upon its inherent authority occurs\nonly where the Government engages in actions that place a\ndefendant at a disadvantage in addressing the charges. That\nsort of prejudice is absent in this case.\n\n\n\n\n 15\n\n Unless there is some constitutional basis, such as a due\nprocess violation, it makes sense to limit a court’s authority to\nbar retrial to instances of prosecutorial misconduct and\nprejudice. First, it ensures that a judge’s personal preferences\nabout a case do not influence whether the case proceeds. See\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\n(“The judiciary may not impose its personal and private\nnotions of ‘fairness’ on law enforcement officials, but does\nhave a limited authority to affect prosecutorial actions when\nthose actions are taken in violation of the Constitution.”).\nSecond, as more fully discussed below, it guarantees that a\ncourt limits the Executive’s decision to prosecute only where\nthere is a constitutionally sound reason to do so. 9 This brings\nus to the second Dietz requirement.\n\n\n 9\n For these reasons, we find unpersuasive our dissenting\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\nobservation that a court has the inherent power to resolve a\ncase, as authority for allowing a court dismiss an indictment\nafter successive hung juries. As a general matter, there is no\ndoubt that a court has the authority to dismiss a case, but it may\nnot simply end a case because it decides that it should not be\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\ntheir progeny make clear, the court must point to evidentiary\ndeficiency, prejudicial misconduct, or a constitutional basis,\nsuch as double jeopardy or due process, to justify precluding a\nprosecution. If a court believed that the evidence was deficient,\nthe prosecutor engaged in prejudicial misconduct, or a retrial\nwould violate the constitution, then it has a basis to preclude a\nretrial. Requiring such reasons for barring a retrial ensures that\n\n\n\n\n 16\n\n 2\n\n The second Dietz requirement reminds a court that the\nexercise of its powers must be in accordance with the\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\nwith the Constitution, a court must be mindful of its role in our\ntripartite form of government and the doctrine of separation of\npowers. Separation-of-powers principles limit a court’s\ninherent authority. “Regardless of whether the supervisory\npower stems from the federal courts’ inherent power to check\nintrusions by other branches of government or whether it is a\nform of specialized federal common law, the separation-of-\npowers principle imposes significant limits on it,” and\n“[p]roper regard for judicial integrity does not justify a\n‘chancellor’s foot veto’ over activities of coequal branches of\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\nCir. 1985) (internal quotation marks omitted) (quoting United\nStates v. Russell, 411 U.S. 423, 435 (1973)).\n\n In the criminal context, the Executive Branch has\n“broad discretion as to whom to prosecute,” and this discretion\n“rests largely on the recognition that the decision to prosecute\nis particularly ill-suited to judicial review.” Wayte v. United\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\nquotation marks omitted). A court is not equipped to evaluate\n\n [s]uch factors as . . . the prosecution’s general\n deterrence value, the Government’s enforcement\n priorities, and the case’s relationship to the\n\n\nthe ruling is not based on a court’s own personal sense of\nwhether a case is worthy of prosecution.\n\n\n\n\n 17\n\n Government’s overall enforcement plan . . . .\n Judicial supervision in this area, moreover,\n entails systemic costs of particular concern.\n Examining the basis of a prosecution delays the\n criminal proceeding, threatens to chill law\n enforcement by subjecting the prosecutor’s\n motives and decisionmaking to outside inquiry,\n and may undermine prosecutorial effectiveness\n by revealing the Government’s enforcement\n policy. All of these are substantial concerns that\n make the courts properly hesitant to examine the\n decision whether to prosecute.\n\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\n(echoing similar sentiments with respect to Rule 48(a)\ndismissals). Thus, absent constitutional concerns, the decision\nto try or retry a case is at the discretion of the prosecutor.\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\nas superprosecutors, second-guessing the legitimate exercise of\ncore elements of prosecutorial discretion, but rather as neutral\narbiters of the law” (citation and internal quotation marks\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\n1994) (“[T]he choice to forego permanently a prosecution is\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\n676 (“In maintaining order in our own house, we should not\nneedlessly trample on the interest of the prosecutor and of the\npublic in securing proper, lasting convictions.”); Isgro, 974\nF.2d at 1097 (stating that the doctrine of separation of powers\n“mandates judicial respect for the independence of the\nprosecutor,” and “[d]ismissal of an indictment with prejudice\n\n\n\n\n 18\n\nis the most severe sanction possible”). 10 Accordingly,\nseparation-of-powers principles preclude a court from\nterminating a prosecution absent misconduct and prejudice to\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\n974 F.2d at 1094.\n\n In short, a court’s power to preclude a prosecution is\nlimited by the separation of powers and, specifically, the\nExecutive’s law-enforcement and prosecutorial prerogative.\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\nhere to dismiss an indictment in the absence of misconduct and\nprejudice and based only on the fact that two juries could not\nreach a verdict intrudes on the Executive’s domain and thereby\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\nat 138; Isgro, 974 F.2d 1091.\n\n 10\n Several state courts have also refused to recognize\nany inherent authority to dismiss an indictment to prevent a\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\n(Fla. Dist. Ct. App. 1980). Other states, however, have\nrecognized a court’s authority to dismiss an indictment sua\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\n712; Witt, 572 S.W.2d at 917. These latter cases are\nunpersuasive because they give too little weight to the\nseparation of powers, a crucial constitutional principle in the\nfederal system.\n\n\n\n\n 19\n\n Finally, there is no statute or procedural rule that\npermits a court to bar a retrial in the absence of misconduct and\nprejudice. First, a court may not dismiss an indictment as a\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\n505. Second, a court’s inherent power does not “include the\npower to develop rules that circumvent or conflict with the\nFederal Rules of Criminal Procedure.” Carlisle v. United\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\nexercise of inherent authority circumvents the absence of\npower of the district court to dismiss an indictment in Rule\n31(b). As stated above, courts have inherent authority to\ndismiss indictments, including, for instance, for prosecutorial\nmisconduct if the defendant was prejudiced, Bank of Nova\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\nnor our Court has extended a court’s inherent authority to allow\n\n 11\n In Chambers, for example, the Supreme Court\nrecognized a court’s authority to impose silence, respect, and\ndecorum based on its authority to manage its own affairs. 501\nU.S. at 43. This authority has been exercised by controlling\nadmission to the bar and disciplining its members; punishing\nfor contempt, which penalizes disruption to proceedings and\ndisobedience to court orders; disallowing fraud on the courts;\nensuring the proceedings move forward; and curtailing\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\ncivil case for failure to prosecute to prevent delays and court\ncongestion as part of a court’s inherent power to manage its\nown affairs). Chambers and Link address how a court may\nmanage its own proceedings, but they do not address how the\ncourt must also account for issues of separation of powers in\nthe context of a criminal case.\n\n\n\n\n 20\n\nthe sua sponte dismissal of an indictment solely to preclude\nmultiple mistrials following hung juries, see Chambers, 501\nU.S. at 47; HSBC, 863 F.3d at 136. 12\n\n 12\n Most cases concerning a court’s inherent authority\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\n(noting a court’s inherent powers to rescind a jury discharge\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\n(recognizing a court’s authority to vacate a judgment upon\nproof that a fraud was perpetrated on the court, and, in\nparticular, to assess as a sanction the entire amount of the\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\n(authority to dismiss a civil case sua sponte for failure to\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\n(1947) (dismissing an action based on the doctrine of forum\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\n(citing cases involving the scope of a district court’s inherent\npower); Eash, 757 F.2d at 561-64 (same).\n There are other circumstances in which district courts\nlack the inherent authority to act, and most of those situations\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\n433 (holding that a court does not have authority to grant a\npost-verdict motion for judgment of acquittal, filed one day\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\n45-50, 55 (holding that a district court does not have inherent\nauthority to dismiss an indictment because the Government\nfailed to disclose to the grand jury substantial exculpatory\nevidence; “[b]ecause the grand jury is an institution separate\nfrom the courts, over whose functioning the courts do not\npreside, we think it clear that, as a general matter at least, no\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\nat 129, 135-37 (holding that the district court violated\nseparation-of-powers principles by sua sponte invoking its\n\n\n\n\n 21\n\n Thus, the District Court abused its discretion in barring\na retrial and dismissing the indictment. 13\n\n III\n\n For the foregoing reasons, we will reverse and remand\nfor further proceedings.\n\n\n\n\nsupervisory power to oversee the government’s entry into and\nimplementation of a deferred prosecution agreement).\n 13\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: United States v. Raymont Wright\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-18\\nOpinion type: majority\\nHas dissenting opinion: Yes\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-1972\\n _____________\\n\\n UNITED STATES OF AMERICA,\\n\\n Appellant\\n\\n v.\\n\\n RAYMONT WRIGHT\\n\\n ______________\\n\\n ON APPEAL FROM THE\\n UNITED STATES DISTRICT COURT\\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\\n (D.C. No. 2-14-cr-00292-001)\\n District Judge: Hon. Cathy Bissoon\\n ______________\\n\\n Argued May 24, 2018\\n ______________\\n\\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\\n Judges.\\n\\n (Opinion Filed: January 17, 2019)\\n\\n ______________\\n\\n OPINION OF THE COURT\\n ________________\\n\\nDonovan J. Cocas, Esq. [ARGUED]\\nJane M. Datttilo, Esq.\\nLaura S. Irwin, Esq.\\nOffice of the United States Attorney\\n700 Grant Street\\nSuite 4000\\nPittsburgh, PA 15219\\n\\n Attorney for Appellant\\n\\nRenee Pietropaolo, Esq. [ARGUED]\\nLisa B. Freeland, Esq.\\nAkin Adepoju, Esq.\\nOffice of the Federal Public Defender\\n1001 Liberty Avenue\\n1500 Liberty Center\\nPittsburgh, PA 15222\\n\\n Attorneys for Appellee Raymont Wright\\n\\nLawrence S. Lustberg, Esq. [ARGUED]\\nGibbons, P.C.\\nOne Gateway Center\\nNewark, NJ 07102\\n\\n Attorney for Amicus Appellee National Association of\\n Criminal Defense Lawyers\\n\\n\\n\\n\\n 2\\n\\nSHWARTZ, Circuit Judge.\\n\\n The District Court barred a retrial of and dismissed the\\nindictment against Defendant Raymont Wright with prejudice\\nafter two juries failed to reach a verdict. The Court did so\\nrelying on its inherent authority, but without finding that any\\nmisconduct had occurred or that Wright would suffer any\\nprejudice beyond the general anxiety and inconvenience of\\nfacing a retrial. Under such circumstances, the Court lacked\\nthe inherent authority to bar the retrial and dismiss the\\nindictment. Therefore, we will reverse the order dismissing the\\nindictment and remand for further proceedings.\\n\\n I\\n\\n In December 2014, Wright was charged with being a\\nfelon in possession of a firearm, in violation of 18 U.S.C.\\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\\nMay 2016. The jury was unable to reach a verdict. A second\\ntrial was held in March 2017, and that jury was also unable to\\nreach a verdict.\\n\\n During both trials, the jury heard evidence from police\\nofficers about Wright’s actions on July 24, 2014.1 That\\nevening, five Pittsburgh Police detectives were patrolling in\\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\\nwere in the lead car, and Detectives Fallert and Goob were in\\nthe second car. Around 8:30 p.m. (when it was still daylight),\\nFallert and Goob saw a man, later identified as Wright, driving\\n\\n 1\\n The following facts are drawn largely from the\\nevidence presented at the first trial.\\n\\n\\n\\n\\n 3\\n\\na car in the opposite direction well above the 25-mile-per-hour\\nspeed limit. The detectives turned around to follow Wright,\\nand Wright sped up and turned onto a loop-shaped road. The\\ndetectives pursued Wright, who fled at a high speed and ran at\\nleast four stop signs. The lead car lost sight of Wright shortly\\nthereafter and discontinued pursuit.\\n\\n Officers in the lead car then noticed skid marks\\nsuggesting that a car had intended but failed to make a left turn\\nat the end of a street. Officers thereafter came upon Wright’s\\ncar in a parking lot below. The car had gone through a fence,\\nover a hillside, and into the lot. The car hit two unoccupied\\nparked cars, its tires blew out, and its windows were down.\\n\\n Detectives Baker and Henson exited the vehicle at the\\ntop of the hill and remained where Wright’s car broke through\\nthe fence, and Detective Kennedy drove his car down to the\\nparking lot’s entrance. Baker and Henson testified that they\\nsaw Wright search around the rear passenger seat of the car,\\nback out of the vehicle with a black semi-automatic handgun\\nin his right hand, and try to “rack the slide,” which can insert\\nor remove a round from the chamber. App. 118-19. They had\\ntheir weapons drawn and told Wright to drop the gun. At first,\\nWright merely stepped back, but he eventually tossed the gun\\nto the side, backed away, and lied on the ground. Pittsburgh\\npolice officer Elliott and his partner, who heard of the crash on\\nthe radio, were the first to reach Wright, and saw him lying on\\nthe ground with a handgun next to him. Henson stated that\\nwhen he made it down to the parking lot, he heard Wright say\\nto him, “Hey, big guy. You won this time or you won this\\nround, something of that nature. He [Wright] said: You feel\\nme? You won this time,” which Henson understood to mean\\nthat he had just avoided a shootout or that he caught Wright\\n\\n\\n\\n\\n 4\\n\\nafter the pursuit. App. 125. Henson subsequently took custody\\nof the gun and noticed the slide lever was bent, and when he\\nstraightened it, saw the gun was loaded with eight rounds, and\\none in the chamber. 2\\n\\n At the close of the Government’s case, Wright moved\\nfor a directed verdict, arguing that no reasonable juror could\\nfind beyond a reasonable doubt that Wright possessed the\\nfirearm. The District Court denied the motion because “the\\nevidence does thus far demonstrate that a reasonable juror\\ncould most certainly find the Defendant guilty of the charge in\\nthis case.” App. 171. Wright did not present a case.\\n\\n The jury deliberated for approximately five hours and\\nthen reported to the Court that it was deadlocked. After polling\\nthe jurors to confirm they were deadlocked and further\\ndeliberations would not bring them closer to a unanimous\\nverdict, the District Court declared a mistrial.\\n\\n At Wright’s March 2017 retrial, the Government\\npresented substantially the same evidence. The Government\\nalso called Detective Kennedy and Lieutenant Palermo, who\\nwere at the scene after Wright was arrested, as well as experts\\nwho testified regarding the collection of DNA and fingerprint\\nevidence from firearms to respond to Wright’s argument at the\\nfirst trial that investigators chose not to test the gun for forensic\\nevidence in an effort to cover up that they had planted the gun\\nat the scene.\\n\\n\\n 2\\n The parties stipulated Wright had been convicted of a\\nqualifying felony, and an ATF Special Agent testified about\\nthe gun’s interstate nexus.\\n\\n\\n\\n\\n 5\\n\\n At the close of the Government’s case, Wright again\\nmoved for a judgment of acquittal, which the Court denied\\nbecause “there is sufficient evidence in the record to establish\\nbeyond a reasonable doubt that Mr. Wright possessed the\\nfirearm in the case,” App. 650. Wright did not put on a case.\\n\\n The second jury deliberated for approximately three\\nhours and then reported that it was hopelessly deadlocked. The\\nCourt polled the jury to confirm the deadlock and then\\ndismissed the jury. 3\\n\\n After the Government notified the Court that it intended\\nto retry the case, the Court required the parties to brief\\n“whether the Court, through an exercise of its inherent\\nauthority, should prohibit or permit a second re-trial in this\\ncase.” App. 26. After considering the parties’ arguments, the\\nDistrict Court dismissed the indictment with prejudice, holding\\nthat it “ha[d] the inherent authority, under some circumstances,\\nto dismiss an indictment following multiple mistrials.” United\\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\\nunderlying the Double Jeopardy Clause also applied to a\\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\\n(2) other courts had dismissed indictments in similar\\n\\n 3\\n Wright asserted that in the first trial, jurors voted 8-4\\nfor acquittal, and in the second trial, the jury was evenly split.\\nThe Government asserted that in the first trial, jurors voted 7-\\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\\nnot explain how he obtained these numbers, the Government\\nsaid it obtained them by speaking with the jurors.\\n\\n\\n\\n\\n 6\\n\\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\\nexpressly allows the Government to retry a case after a mistrial,\\nnothing in the rule “limits a court’s inherent supervisory\\nauthority to dismiss an indictment in the interests of\\nfundamental fairness,” id. at *4; and (4) if the Court were to\\nadopt the Government’s position that there are no limit to the\\nnumber of times the Government can retry a defendant, it\\nwould be tantamount to a “type of jury shopping” that a court\\nshould not permit, id. at *4. The District Court also considered\\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\\nconcluded that most factors supported dismissal. 4\\n\\n 4\\n The Abbati factors are\\n\\n (1) the number of prior mistrials and the\\n outcome of the juries’ deliberations, so far as is\\n known; (2) the character of prior trials in terms\\n of length, complexity, and similarity of evidence\\n presented; (3) the likelihood of any substantial\\n difference in a subsequent trial, if allowed;\\n (4) the trial court’s own evaluation of the relative\\n strength of each party’s case; and (5) the\\n professional conduct and diligence of respective\\n counsel, particularly of the prosecuting attorney.\\n The court must also give due weight to the\\n prosecutor’s decision to reprosecute, assessing\\n the reasons for that decision, such as the gravity\\n\\n\\n\\n\\n 7\\n\\n The Government appeals.\\n\\n II 5\\n\\n We review the District Court’s order dismissing the\\nindictment based on the Court’s inherent power for abuse of\\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\\n\\n of the criminal charges and the public’s concern\\n in the effective and definitive conclusion of\\n criminal prosecutions. Conversely, the court\\n should accord careful consideration to the status\\n of the individual defendant and the impact of a\\n retrial upon the defendant in terms of untoward\\n hardship and unfairness.\\n\\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\\nat 521-22). For the reasons set forth herein, we would not\\nadopt Abbati, but even if we were to consider the Abbati\\nfactors, we would conclude that they do not support dismissal\\nin this case.\\n 5\\n The District Court had jurisdiction pursuant to 18\\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\\n§ 3731.\\n 6\\n The phrases “inherent power,” “inherent authority,”\\n“supervisory power,” and “supervisory authority” are all used\\nto describe the basis for a court action seeking to maintain the\\nintegrity of the proceedings that is not directly tethered to a\\nspecific rule, statute, or constitutional provision. See, e.g.,\\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\\n43 (1991) (inherent power); Bank of Nova Scotia v. United\\n\\n\\n\\n\\n 8\\n\\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\\nindictment for abuse of discretion); cf. Chambers v. NASCO,\\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\\nsanctions under its inherent power for abuse of discretion);\\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\\n2005) (“A trial court’s remedy for a discovery violation under\\nits supervisory powers is reviewed for abuse of discretion.”).\\nA district court abuses its discretion when it makes an errant\\nconclusion of law, an improper application of law to fact, or a\\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\\n\\n A\\n\\n Federal Rule of Criminal Procedure 31 allows the\\nGovernment to retry a case if the court declares a mistrial after\\na jury announces it is unable to reach a verdict. Specifically,\\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\\non one or more counts, the court may declare a mistrial on\\nthose counts. The government may retry any defendant on any\\ncount on which the jury could not agree.” Fed. R. Crim. P.\\n31(b)(3). The word “may” means that the Government has the\\n\\n\\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(supervisory power); United States v. Payner, 447 U.S. 727,\\n733-36 (1980) (supervisory power); United States v. Nobles,\\n422 U.S. 225, 231 (1975) (inherent power).\\n Even if we accepted the distinctions our dissenting\\ncolleague has drawn between inherent judicial powers,\\nlegislatively granted judicial powers, and supervisory powers,\\neach category must operate within the constitutional\\nframework, including the separation of powers.\\n\\n\\n\\n\\n 9\\n\\ndiscretion to retry a case, and nothing in the rule or its\\ncommentary provides or even suggests a limit on the number\\nof retrials it may conduct. See United States v. Wqas Khan,\\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\\n\\n 7\\n While Rule 31 does not limit the Government’s\\nauthority to retry a case, a handful of district courts have\\ndismissed indictments following a second hung jury, but those\\ndecisions are not persuasive. In Ingram, the district court\\ndismissed the indictment sua sponte (without any initial\\nobjection by the Government) after two mistrials—in which\\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\\njailed during the pendency of the trials, and “[t]he Government\\nha[d] no new proof; it simply want[ed] another chance.” 412\\nF. Supp. at 385. The court concluded that to permit a retrial\\nwould be “to ignore the reasonable doubt standard,” and so\\n“[t]he Court’s intervention [was] required in the interest of\\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\\n(McGowan, J., dissenting)). The Ingram court, however, relied\\nin part on the dissent in De Diego. Cases since Ingram have\\napplied the De Diego majority’s view concerning a court’s\\nlimited authority to dismiss an indictment. See, e.g., United\\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\\nDe Diego and reversing the district court’s dismissal of the\\nindictment where the district court found it would be\\n“unconscionable” to retry to the defendant); United States v.\\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\\nDiego and its dissent and holding a district court does not have\\nauthority to sua sponte dismiss an indictment based on the\\n\\n\\n\\n\\n 10\\n\\ndefendant’s poor health); United States v. Mussehl, 453 F.\\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\\nto dismiss the indictment based on alleged errors at trial, and\\nciting De Diego for the proposition that “[t]he duty [to\\nadminister justice] encompasses the concept of review of the\\nquestion whether the United States Attorney, in making his\\ndecision to prosecute, complied with the law, but does not\\nallow the Court to question a United States Attorney’s\\njudgment decision to prosecute, when lawfully made”).\\n The District Court also relied on Rossoff, where the\\ncourt denied the Government’s motion to dismiss the\\nindictment under Federal Rule of Criminal Procedure 48(a),\\nbut still dismissed the indictment with prejudice. 806 F. Supp.\\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\\nbeen two trials, and the Government sought to dismiss the\\nindictment and refile the charges in a different judicial district.\\nId. The court determined it had authority to dismiss an\\nindictment with prejudice if a retrial was “against the concept\\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\\nSupp. 384), and did so because, among other reasons, the\\ndefendant was in poor health, was under significant strain, and\\na majority of jurors at both trials found him not guilty, id. at\\n203. Rossoff, however, is distinguishable from Wright’s case\\nbecause in Rossoff, the Government sought to dismiss the\\nindictment so that it could refile charges in a different judicial\\ndistrict, which caused the court to question the Government’s\\ngood faith. In Wright’s case, the District Court made no\\nfinding that the Government’s desire to retry Wright was for\\nan improper purpose.\\n In addition, and significantly, neither Ingram nor\\nRossoff addressed the doctrine of separation of powers.\\nRather, each essentially relied on a general concept of fairness\\n\\n\\n\\n\\n 11\\n\\nthe text that empowers a court to prohibit the Government from\\nretrying a case. 8\\n B\\n\\n Apparently aware that Rule 31 did not provide it with a\\nbasis to preclude a retrial in these circumstances, the District\\nCourt concluded that it had the inherent authority to forbid the\\nretrial and dismiss the indictment. The District Court erred.\\n\\n The exercise of inherent authority must satisfy two\\nrequirements: (1) it “must be a reasonable response to the\\n\\n\\nto the defendant in deciding to dismiss an indictment. See\\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\\nIn this Circuit, however, “[t]he judiciary may not impose its\\npersonal and private notions of ‘fairness’ on law enforcement\\nofficials, but does have a limited authority to affect\\nprosecutorial actions when those actions are taken in violation\\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\\n596 (3d Cir. 1992) (citations omitted).\\n 8\\n Rule 31 differs from other Federal Rules of Criminal\\nProcedure because it makes no mention of the court’s\\nauthority. For instance, Rule 48(b) states that a court has\\nauthority to dismiss an indictment “if unnecessary delay occurs\\nin: (1) presenting a charge to the grand jury; (2) filing an\\ninformation against a defendant; or (3) bringing a defendant to\\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\\ngrounds on which a district court could also dismiss an\\nindictment, but each would be triggered by a motion, such as a\\nmotion to dismiss for failure to comply with Rule 16’s\\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\\n16(d)(2)(D), or a motion asserting a defect in the indictment,\\nFed. R. Crim. P. 12(b)(3)(B).\\n\\n\\n\\n\\n 12\\n\\nproblems and needs confronting the court’s fair administration\\nof justice,” and (2) it “cannot be contrary to any express grant\\nof or limitation on the district court’s power contained in a rule\\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\\n(citations and internal quotation marks omitted). We will\\nexamine each of these requirements in turn.\\n\\n 1\\n\\n As to the first Dietz requirement, “[g]uided by\\nconsiderations of justice, and in the exercise of supervisory\\npowers, federal courts may, within limits, formulate procedural\\nrules not specifically required by the Constitution or the\\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(internal quotation marks and citation omitted). Such rules\\nmust be imposed (1) “to implement a remedy for violation of\\nrecognized rights,” (2) “to preserve judicial integrity by\\nensuring that a conviction rests on appropriate considerations\\nvalidly before the jury,” and (3) “as a remedy designed to deter\\nillegal conduct.” Id. (citations omitted). Thus, a court may\\nexercise its inherent authority only when it is necessary to\\naddress improper conduct and ensure respect for the\\nproceedings.\\n\\n Under these principles, a court may dismiss an\\nindictment based upon its inherent authority only if the\\nGovernment engaged in misconduct, the defendant was\\nprejudiced, and no less severe remedy was available to address\\nthe prejudice. See Bank of Nova Scotia v. United States, 487\\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\\n(stating that “[a] court may dismiss an indictment under its\\nsupervisory powers only when the defendant suffers\\nsubstantial prejudice and where no lesser remedial action is\\n\\n\\n\\n\\n 13\\n\\navailable” (citations and internal quotation marks omitted));\\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\\n(observing that “a district court may not, in the management of\\nits docket, exercise its discretion to dismiss an indictment with\\nprejudice, either under Rule 48(b) or under its supervisory\\npower, unless the violation caused prejudice to the defendant\\nor posed a substantial threat thereof” (emphasis omitted));\\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\\n(holding that an indictment may not be dismissed for\\nprosecutorial misconduct absent a showing that the misconduct\\nprejudiced the defendants, and stating that “virtually every\\nother circuit to consider the issue post-Hasting and Nova Scotia\\nhas also held that an indictment may not be dismissed based on\\nprosecutorial misconduct, absent a showing of prejudice to the\\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\\n(7th Cir. 1993) (“A federal judge is not authorized to punish\\nthe misconduct of a prosecutor by letting the defendant walk,\\nunless the misconduct not only violated the defendant’s rights\\nbut also prejudiced his defense . . . .”); United States v. Tucker,\\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\\nexercise its supervisory authority to reverse a conviction or\\ndismiss an indictment absent prejudice to the defendant.”);\\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\\nHasting, and Bank of Nova Scotia form a trilogy admonishing\\nfederal courts to refrain from using the supervisory power to\\nconform executive conduct to judicially preferred norms by\\ndismissing charges, absent cognizable prejudice to a particular\\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\\nCir. 1992) (“Before it may invoke this [supervisory] power [to\\ndismiss an indictment], a court must first find that the\\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\\n1480 (9th Cir. 1994).\\n\\n\\n\\n\\n 14\\n\\n In this case, there has been no misconduct. Indeed, the\\nDistrict Court noted that the Government performed diligently\\nand professionally in both trials, Wright, 2017 WL 1179006,\\nat *4, and found that the evidence was sufficient to prove\\nbeyond a reasonable doubt that Wright possessed the gun. The\\nDistrict Court nonetheless applied its own predictions about\\nwhat another jury may do when presented with the same\\nevidence, emphasized the need for finality, and opined that the\\neffect of prosecution on the defendant precluded a proper\\nprosecution from proceeding. See id. at *5-6. Invoking its own\\nnotions about the unfairness of requiring a defendant to face a\\nretrial where the Government did not obtain a majority of the\\njurors’ votes is an improper exercise of a court’s supervisory\\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\nMoreover, there is no prejudice to a defendant simply because\\nhe faces the anxiety and the normal stress of undergoing a trial.\\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975) (“[A]nxiety is present to some degree in virtually every\\ncase. Something more than the normal anxiety that\\naccompanies a trial is necessary to show a degree of\\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\\nonly real harm alleged is the general unfairness to these\\ndefendants in having to go forward yet again with a lengthy\\ntrial, in their being ‘ground down’ by the several months’ drain\\non their mental, emotional, and financial resources. A lack of\\nsuch fairness, however, does not alone violate due process.”).\\nRather, prejudice sufficient for the District Court to intervene\\nin a proper prosecution based upon its inherent authority occurs\\nonly where the Government engages in actions that place a\\ndefendant at a disadvantage in addressing the charges. That\\nsort of prejudice is absent in this case.\\n\\n\\n\\n\\n 15\\n\\n Unless there is some constitutional basis, such as a due\\nprocess violation, it makes sense to limit a court’s authority to\\nbar retrial to instances of prosecutorial misconduct and\\nprejudice. First, it ensures that a judge’s personal preferences\\nabout a case do not influence whether the case proceeds. See\\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\\n(“The judiciary may not impose its personal and private\\nnotions of ‘fairness’ on law enforcement officials, but does\\nhave a limited authority to affect prosecutorial actions when\\nthose actions are taken in violation of the Constitution.”).\\nSecond, as more fully discussed below, it guarantees that a\\ncourt limits the Executive’s decision to prosecute only where\\nthere is a constitutionally sound reason to do so. 9 This brings\\nus to the second Dietz requirement.\\n\\n\\n 9\\n For these reasons, we find unpersuasive our dissenting\\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\\nobservation that a court has the inherent power to resolve a\\ncase, as authority for allowing a court dismiss an indictment\\nafter successive hung juries. As a general matter, there is no\\ndoubt that a court has the authority to dismiss a case, but it may\\nnot simply end a case because it decides that it should not be\\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\\ntheir progeny make clear, the court must point to evidentiary\\ndeficiency, prejudicial misconduct, or a constitutional basis,\\nsuch as double jeopardy or due process, to justify precluding a\\nprosecution. If a court believed that the evidence was deficient,\\nthe prosecutor engaged in prejudicial misconduct, or a retrial\\nwould violate the constitution, then it has a basis to preclude a\\nretrial. Requiring such reasons for barring a retrial ensures that\\n\\n\\n\\n\\n 16\\n\\n 2\\n\\n The second Dietz requirement reminds a court that the\\nexercise of its powers must be in accordance with the\\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\\nwith the Constitution, a court must be mindful of its role in our\\ntripartite form of government and the doctrine of separation of\\npowers. Separation-of-powers principles limit a court’s\\ninherent authority. “Regardless of whether the supervisory\\npower stems from the federal courts’ inherent power to check\\nintrusions by other branches of government or whether it is a\\nform of specialized federal common law, the separation-of-\\npowers principle imposes significant limits on it,” and\\n“[p]roper regard for judicial integrity does not justify a\\n‘chancellor’s foot veto’ over activities of coequal branches of\\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\\nCir. 1985) (internal quotation marks omitted) (quoting United\\nStates v. Russell, 411 U.S. 423, 435 (1973)).\\n\\n In the criminal context, the Executive Branch has\\n“broad discretion as to whom to prosecute,” and this discretion\\n“rests largely on the recognition that the decision to prosecute\\nis particularly ill-suited to judicial review.” Wayte v. United\\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\\nquotation marks omitted). A court is not equipped to evaluate\\n\\n [s]uch factors as . . . the prosecution’s general\\n deterrence value, the Government’s enforcement\\n priorities, and the case’s relationship to the\\n\\n\\nthe ruling is not based on a court’s own personal sense of\\nwhether a case is worthy of prosecution.\\n\\n\\n\\n\\n 17\\n\\n Government’s overall enforcement plan . . . .\\n Judicial supervision in this area, moreover,\\n entails systemic costs of particular concern.\\n Examining the basis of a prosecution delays the\\n criminal proceeding, threatens to chill law\\n enforcement by subjecting the prosecutor’s\\n motives and decisionmaking to outside inquiry,\\n and may undermine prosecutorial effectiveness\\n by revealing the Government’s enforcement\\n policy. All of these are substantial concerns that\\n make the courts properly hesitant to examine the\\n decision whether to prosecute.\\n\\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\\n(echoing similar sentiments with respect to Rule 48(a)\\ndismissals). Thus, absent constitutional concerns, the decision\\nto try or retry a case is at the discretion of the prosecutor.\\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\\nas superprosecutors, second-guessing the legitimate exercise of\\ncore elements of prosecutorial discretion, but rather as neutral\\narbiters of the law” (citation and internal quotation marks\\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\\n1994) (“[T]he choice to forego permanently a prosecution is\\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\\n676 (“In maintaining order in our own house, we should not\\nneedlessly trample on the interest of the prosecutor and of the\\npublic in securing proper, lasting convictions.”); Isgro, 974\\nF.2d at 1097 (stating that the doctrine of separation of powers\\n“mandates judicial respect for the independence of the\\nprosecutor,” and “[d]ismissal of an indictment with prejudice\\n\\n\\n\\n\\n 18\\n\\nis the most severe sanction possible”). 10 Accordingly,\\nseparation-of-powers principles preclude a court from\\nterminating a prosecution absent misconduct and prejudice to\\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\\n974 F.2d at 1094.\\n\\n In short, a court’s power to preclude a prosecution is\\nlimited by the separation of powers and, specifically, the\\nExecutive’s law-enforcement and prosecutorial prerogative.\\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\\nhere to dismiss an indictment in the absence of misconduct and\\nprejudice and based only on the fact that two juries could not\\nreach a verdict intrudes on the Executive’s domain and thereby\\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\\nat 138; Isgro, 974 F.2d 1091.\\n\\n 10\\n Several state courts have also refused to recognize\\nany inherent authority to dismiss an indictment to prevent a\\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\\n(Fla. Dist. Ct. App. 1980). Other states, however, have\\nrecognized a court’s authority to dismiss an indictment sua\\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\\n712; Witt, 572 S.W.2d at 917. These latter cases are\\nunpersuasive because they give too little weight to the\\nseparation of powers, a crucial constitutional principle in the\\nfederal system.\\n\\n\\n\\n\\n 19\\n\\n Finally, there is no statute or procedural rule that\\npermits a court to bar a retrial in the absence of misconduct and\\nprejudice. First, a court may not dismiss an indictment as a\\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\\n505. Second, a court’s inherent power does not “include the\\npower to develop rules that circumvent or conflict with the\\nFederal Rules of Criminal Procedure.” Carlisle v. United\\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\\nexercise of inherent authority circumvents the absence of\\npower of the district court to dismiss an indictment in Rule\\n31(b). As stated above, courts have inherent authority to\\ndismiss indictments, including, for instance, for prosecutorial\\nmisconduct if the defendant was prejudiced, Bank of Nova\\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\\nnor our Court has extended a court’s inherent authority to allow\\n\\n 11\\n In Chambers, for example, the Supreme Court\\nrecognized a court’s authority to impose silence, respect, and\\ndecorum based on its authority to manage its own affairs. 501\\nU.S. at 43. This authority has been exercised by controlling\\nadmission to the bar and disciplining its members; punishing\\nfor contempt, which penalizes disruption to proceedings and\\ndisobedience to court orders; disallowing fraud on the courts;\\nensuring the proceedings move forward; and curtailing\\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\\ncivil case for failure to prosecute to prevent delays and court\\ncongestion as part of a court’s inherent power to manage its\\nown affairs). Chambers and Link address how a court may\\nmanage its own proceedings, but they do not address how the\\ncourt must also account for issues of separation of powers in\\nthe context of a criminal case.\\n\\n\\n\\n\\n 20\\n\\nthe sua sponte dismissal of an indictment solely to preclude\\nmultiple mistrials following hung juries, see Chambers, 501\\nU.S. at 47; HSBC, 863 F.3d at 136. 12\\n\\n 12\\n Most cases concerning a court’s inherent authority\\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\\n(noting a court’s inherent powers to rescind a jury discharge\\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\\n(recognizing a court’s authority to vacate a judgment upon\\nproof that a fraud was perpetrated on the court, and, in\\nparticular, to assess as a sanction the entire amount of the\\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\\n(authority to dismiss a civil case sua sponte for failure to\\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\\n(1947) (dismissing an action based on the doctrine of forum\\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\\n(citing cases involving the scope of a district court’s inherent\\npower); Eash, 757 F.2d at 561-64 (same).\\n There are other circumstances in which district courts\\nlack the inherent authority to act, and most of those situations\\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\\n433 (holding that a court does not have authority to grant a\\npost-verdict motion for judgment of acquittal, filed one day\\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\\n45-50, 55 (holding that a district court does not have inherent\\nauthority to dismiss an indictment because the Government\\nfailed to disclose to the grand jury substantial exculpatory\\nevidence; “[b]ecause the grand jury is an institution separate\\nfrom the courts, over whose functioning the courts do not\\npreside, we think it clear that, as a general matter at least, no\\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\\nat 129, 135-37 (holding that the district court violated\\nseparation-of-powers principles by sua sponte invoking its\\n\\n\\n\\n\\n 21\\n\\n Thus, the District Court abused its discretion in barring\\na retrial and dismissing the indictment. 13\\n\\n III\\n\\n For the foregoing reasons, we will reverse and remand\\nfor further proceedings.\\n\\n\\n\\n\\nsupervisory power to oversee the government’s entry into and\\nimplementation of a deferred prosecution agreement).\\n 13\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":71,"cells":{"id":{"kind":"number","value":4583425,"string":"4,583,425"},"name":{"kind":"string","value":"UNITED STATES of America v. Jay GOLDSTEIN A/K/A Yaakov Jay Goldstein, Appellant"},"name_abbreviation":{"kind":"string","value":"United States v. Jay Goldstein"},"decision_date":{"kind":"string","value":"2019-01-22"},"docket_number":{"kind":"string","value":"15-4094"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Chagares, Restrepo, Roth\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n ________________\\n\\n No. 15-4094\\n ________________\\n\\n\\n UNITED STATES OF AMERICA\\n\\n v.\\n\\n JAY GOLDSTEIN a/k/a Yaakov\\n\\n JAY GOLDSTEIN,\\n\\nAppellant\\n ________________\\n\\n On Appeal from the United States District Court\\n for the District of New Jersey\\n (D. C. No. 3-14-cr-00287-003)\\n District Judge: Honorable Freda L. Wolfson\\n ________________\\n\\n Argued on January 25, 2017\\n Panel Rehearing Granted on August 30, 2018\\n\\n Before: CHAGARES, RESTREPO and ROTH, Circuit\\n Judges\\n\\f (Opinion filed: January 22, 2019)\\n\\n\\nAidan P. O’Connor [Argued]\\nPashman Stein Walder Hayden\\n21 Main Street\\nCourt Plaza South, Suite 200\\nHackensack, NJ 07601\\n Counsel for Appellant\\n\\nMark E. Coyne\\nOffice of United States Attorney\\n970 Broad Street, Room 700\\nNewark, NJ 07102\\n\\nNorman Gross [Argued]\\nGlenn J. Moramarco [Argued]\\nOffice of United States Attorney\\nCamden Federal Building & Courthouse\\n401 Market Street\\nCamden, NJ 08101\\n Counsel for Appellee\\n\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\n\\nROTH, Circuit Judge\\n\\n\\n\\n\\n 2\\n\\f I.\\n\\n We granted Appellant Jay Goldstein’s petition for\\nrehearing to address the effect of the Supreme Court’s recent\\ndecision in Carpenter v. United States1 on our prior panel\\ndecision, United States v. Stimler.2 In Stimler, we held that\\nthe District Court properly denied Goldstein’s motion to\\nsuppress his cell site location information (CSLI) because\\nGoldstein had no reasonable expectation of privacy in his\\nCSLI, and, therefore, the government did not need probable\\ncause to collect this data.3 Carpenter sets forth a new rule\\nthat defendants do in fact have a privacy interest in their\\nCSLI, and the government must generally obtain a search\\nwarrant supported by probable cause to obtain this\\ninformation.4 However, we still affirm the District Court’s\\ndecision under the good faith exception to the exclusionary\\nrule because the government had an objectively reasonable\\ngood faith belief that its conduct was legal when it acquired\\nGoldstein’s CSLI.\\n\\n II.\\n\\n We recited a comprehensive factual background in our\\nprevious decision.5 The facts relevant to this decision follow.\\n\\n1\\n 138 S. Ct. 2206 (2018).\\n2\\n 864 F.3d 253 (3d Cir. 2017).\\n3\\n Id. at 263. Carpenter does not affect our other holdings in\\nStimler. Those remain as written and are not addressed in or\\nchanged by this decision.\\n4\\n Carpenter, 138 S. Ct. at 2217, 2222.\\n5\\n Stimler, 864 F.3d at 259-61.\\n\\n\\n\\n\\n 3\\n\\fGoldstein was arrested for his involvement in a kidnapping\\nscheme. Hoping to find evidence placing Goldstein at the\\nscene of the kidnapping, the prosecutors obtained a court\\norder under the Stored Communications Act (SCA)—\\nspecifically 18 U.S.C. § 2703(d)—compelling Goldstein’s\\ncell phone carrier to turn over 57 days’ worth of his CSLI.\\nCSLI is a type of metadata that is generated every time a\\nuser’s cell phone connects to the nearest antenna. The user’s\\ncell phone service provider retains a time-stamped record\\nidentifying the particular antenna to which the phone\\nconnected. Because most people constantly carry and\\nfrequently use their cell phones, CSLI can provide a detailed\\nlog of an individual’s movements over a period of time.\\n\\n The legal question in this case centers on whether\\nSection 2703(d), the statutory provision under which the\\ngovernment obtained Goldstein’s CSLI, complies with the\\nFourth Amendment. The Fourth Amendment protects against\\nunreasonable searches. In order for the acquisition of CSLI to\\nbe a “search” under the Fourth Amendment, an individual\\nmust have a reasonable expectation of privacy in his CSLI.6\\nIn order for a search to be “reasonable,” it generally must be\\nconducted pursuant to a search warrant supported by probable\\ncause, unless an exception to the warrant requirement\\napplies.7 Consequently, if there is no reasonable expectation\\nof privacy as to CSLI, then its acquisition does not require a\\nsearch warrant; if there is, then a warrant is generally\\nrequired. Section 2703(d) does not require a showing of\\n\\n6\\n See United States v. Knotts, 460 U.S. 276, 281 (1983)\\n(explaining what constitutes a reasonable expectation of\\nprivacy).\\n7\\n See Riley v. California, 134 S. Ct. 2473, 2482 (2014).\\n\\n\\n\\n\\n 4\\n\\fprobable cause to obtain CSLI. Rather, it calls for a more\\nlenient standard, requiring “specific and articulable facts\\nshowing that there are reasonable grounds to believe” that the\\nCSLI is relevant and material.8\\n\\n Before trial, Goldstein moved to suppress the CSLI,\\narguing that this provision violates the Fourth Amendment\\nbecause it authorizes disclosure of CSLI without a warrant\\nsupported by probable cause. The District Court rejected this\\nargument and denied the motion. Through the testimony of\\nan FBI agent, the government introduced the CSLI at trial,\\nwhich placed him in the vicinity of the kidnapping site.\\nGoldstein was convicted and sentenced to 96 months in\\nprison.\\n\\n In our previous decision, we affirmed the District\\nCourt’s denial of Goldstein’s motion to suppress, holding that\\nSection 2703(d) complied with the Fourth Amendment\\nbecause cell phone users have no reasonable expectation of\\nprivacy in their CSLI.9 We relied on our decision in In re\\nApplication of the United States for an Order Directing a\\nProvider of Electronic Communication Service to Disclose\\nRecords to the Government (In re Application),10 which also\\nfound no reasonable expectation of privacy in CSLI,11 and we\\n\\n\\n\\n\\n8\\n 18 U.S.C. § 2703(d).\\n9\\n Stimler, 864 F.3d at 263.\\n10\\n 620 F.3d 304 (3d Cir. 2010).\\n11\\n Id. at 312-13 (holding that CSLI is obtainable without “the\\ntraditional probable cause determination” because\\nindividuals’ privacy interests do not extend to CSLI).\\n\\n\\n\\n\\n 5\\n\\freasoned that there were no intervening changes in law\\nundermining In re Application.12\\n\\n Goldstein petitioned for rehearing, and we held the\\npetition curia advisari vult pending the Supreme Court’s\\ndecision in Carpenter, which was set to address essentially\\nthe same question we answered in Stimler: whether obtaining\\nCSLI without a warrant supported by probable cause under\\nSection 2703(d) violates the Fourth Amendment’s protection\\nagainst unreasonable searches. The Supreme Court decided\\nCarpenter, and we granted Goldstein’s petition for panel\\nrehearing.13 Carpenter came to the opposite conclusion that\\nwe came to in In re Application and Stimler and held that “an\\nindividual maintains a legitimate expectation of privacy in the\\nrecord of his physical movements as captured though CSLI”\\nand that the government’s collection of CSLI requires a\\nshowing of probable cause under the Fourth Amendment.14\\nConsequently, Section 2703(d) may not be used to access\\nCSLI because it requires less than probable cause.\\n\\n Applying Carpenter to Goldstein’s case, we find that\\nthe government did violate Goldstein’s Fourth Amendment\\nrights when it acquired his CSLI under Section 2703(d) of the\\nSCA. However, we will still affirm the District Court’s\\nadmission of Goldstein’s CSLI because the government was\\nacting under an objectively reasonable good faith belief that\\n\\n\\n12\\n Stimler, 864 F.3d at 264-67.\\n13\\n Appellants Stimler and Epstein also petitioned for\\nrehearing, but we denied those petitions because the\\ngovernment did not collect their CSLI.\\n14\\n Carpenter, 138 S. Ct. at 2217, 2222.\\n\\n\\n\\n\\n 6\\n\\fobtaining CSLI under Section 2703(d) was constitutional at\\nthe time.\\n\\n\\n 15\\n III.\\n\\n It is clear that under Carpenter, acquiring Goldstein’s\\nCSLI was an unconstitutional search under the Fourth\\nAmendment because the government did not obtain a warrant\\nsupported by probable cause.16 However, evidence obtained\\nin violation of a defendant’s Fourth Amendment rights is not\\nautomatically suppressed. Evidence will be suppressed under\\nthe exclusionary rule when suppression would further the\\nexclusionary rule’s primary objective: to deter Fourth\\nAmendment violations.17 One instance where suppressing\\nevidence will not encourage deterrence is where the\\ngovernment acted “upon an objectively reasonable good faith\\nbelief in the legality of [its] conduct” when conducting a\\n\\n\\n15\\n The District Court had jurisdiction under 18 U.S.C. § 3231.\\nWe have jurisdiction pursuant to 28 U.S.C. § 1291. “In\\nreviewing a motion to suppress, ‘we review a district court’s\\nfactual findings for clear error, and we exercise de novo\\nreview over its application of the law to those factual\\nfindings.’” United States v. Katzin, 769 F.3d 163, 169 n.4 (3d\\nCir. 2014) (en banc) (quoting United States v. Pavulak, 700\\nF.3d 651, 660 (3d Cir. 2012)).\\n16\\n A warrantless search is still reasonable under the Fourth\\nAmendment if an exception to the warrant requirement\\napplies, but the parties do not argue, and we do not find, that\\nany exception applies here. Carpenter, 138 S. Ct. at 2222-23.\\n17\\n Katzin, 769 F.3d at 170-71.\\n\\n\\n\\n\\n 7\\n\\fsearch.18 Indeed, “applying the exclusionary rule would not\\n‘yield appreciable deterrence’” when government actors have\\na reasonable belief that their conduct conforms with the law.19\\nThis is known as the good faith exception, and where it\\napplies, the illegally-obtained evidence will not be suppressed\\nunder the exclusionary rule.\\n\\n The Supreme Court has applied this exception across a\\nnumber of cases where suppressing evidence would not have\\nany deterrent value—three of which are relevant here. In\\nIllinois v. Krull,20 the Court held that the good faith exception\\napplies when a search is executed pursuant to a statute that\\nwas valid at the time of the search but later declared\\nunconstitutional.21 Except in instances where a statute is\\nobviously unconstitutional, suppressing evidence obtained by\\na law enforcement officer “acting in objectively reasonable\\nreliance on a statute would have . . . little deterrent effect on\\nthe [government’s] actions.”22 Under Davis v. United\\nStates,23 this exception also applies when a search is\\nconducted based upon reasonable reliance on then-binding\\nappellate precedent because exclusion in this context would\\nnot deter improper government conduct.24 And under United\\n\\n\\n18\\n Id. at 182.\\n19\\n United States v. Vasquez-Algarin, 821 F.3d 467, 482-83 (3d\\nCir. 2016) (quoting Davis v. United States, 564 U.S. 229, 237\\n(2011)).\\n20\\n 480 U.S. 340 (1987).\\n21\\n Id. at 349-50.\\n22\\n Id.\\n23\\n 564 U.S. 229 (2011).\\n24\\n Id. at 241.\\n\\n\\n\\n\\n 8\\n\\fStates v. Leon,25 the exclusionary rule will not apply when\\nlaw enforcement conducts a search pursuant to a judicial\\norder later found invalid.26\\n\\n The good faith exception applies to the government’s\\nsearch in this case because the government acted upon an\\nobjectively reasonable, good faith belief that obtaining\\nGoldstein’s CSLI under Section 2703(d) was legal. At the\\ntime the search was executed, it was authorized under Section\\n2703(d). The government complied with all requirements of\\nSection 2703(d) and obtained a valid judicial order to collect\\nGoldstein’s CSLI. Moreover, the government had no reason\\nto question the constitutionality of obtaining CSLI through\\nSection 2703(d) because that question had been answered by\\nthis Court in In re Application—which was binding appellate\\nprecedent.27 Thus, because the government relied on a\\nproperly-obtained valid judicial order, a then-valid statute,\\nand then-binding appellate authority, it had an objectively\\nreasonable, good faith belief that its conduct was legal.\\nIndeed, the conduct was legal at the time. Excluding\\nevidence obtained through methods that complied with the\\nlaw at the time of the search cannot serve any deterrent\\npurpose. Under Krull, Davis, and Leon, the good faith\\nexception applies, and the District Court’s denial of the\\nmotion to suppress is affirmed. Our holding puts us in good\\ncompany, as many of our sister circuits have also found that\\n\\n25\\n 468 U.S. 897 (1984).\\n26\\n Id. at 922.\\n27\\n In re Application, 620 F.3d at 313 (“[W]e hold that CSLI\\nfrom cell phone calls is obtainable under a § 2703(d) order\\nand that such an order does not require the traditional\\nprobable cause determination.”).\\n\\n\\n\\n\\n 9\\n\\fthe good faith exception applies when the government\\nobtained CLSI data without a warrant prior to Carpenter.28\\n Goldstein contends that the good faith exception does\\nnot apply because the government’s reliance on Section\\n2703(d) was unreasonable for two reasons, both of which fail.\\nFirst, he argues that, at the time of the search, the Eleventh\\nCircuit had held that collecting CSLI without a warrant\\nsupported by probable cause violated the Fourth\\n\\n28\\n See, e.g., United States v. Joyner, 899 F.3d 1199, 1204-05\\n(11th Cir. 2018) (“Here, the Government complied with the\\nrequirements of the SCA in obtaining the orders to compel\\ncell site records, and when they did so in June 2015, that\\nwarrantless procedure was, under this Court’s precedent,\\nwithin the bounds of the Fourth Amendment.”);\\nUnited States v. Chavez, 894 F.3d 593, 608 (4th Cir. 2018)\\n(Carpenter does not affect cases where investigators acted\\npursuant to court orders and the SCA); United States v.\\nCurtis, 901 F.3d 846, 849 (7th Cir. 2018) (“We conclude,\\ntherefore, that even though it is now established that the\\nFourth Amendment requires a warrant for the type of cell-\\nphone data present here, exclusion of that information was\\nnot required because it was collected in good faith.”); United\\nStates v. Chambers, No. 16-163-CR, 2018 WL 4523607, at\\n*3 (2d Cir. Sept. 21, 2018) (“Thus, we conclude that even\\nafter Jones, but before Carpenter, it was objectively\\nreasonable for authorities to think that if they complied with\\nthe SCA, no warrant based on probable cause was\\nconstitutionally required to obtain cell-site information from a\\nthird party.”). Judge Restrepo’s concurrence in Stimler also\\nconcluded that the good faith exception applied here in light\\nof In re Application. See Stimler, 864 F.3d at 279-80\\n(Restrepo, J., concurring).\\n\\n\\n\\n\\n 10\\n\\fAmendment.29 But, under Davis, only binding appellate\\nprecedent is relevant to the good faith exception, and In re\\nApplication was binding in this Circuit at the time. Second,\\nhe contends the government could not have reasonably relied\\non In re Application because it had been undermined by two\\nsubsequent Supreme Court cases—United States v. Jones30\\nand Riley v. California.31 As discussed in Stimler, neither\\ncase undercuts In re Application because neither addresses\\nthe long-term collection of metadata from cell phones.32\\nJones addressed long-term collection of GPS location data\\nfrom a car—not a cell phone.33 Riley involved the contents of\\na cell phone, not the metadata transmitted from a cell phone\\nto a third party.34 Indeed, Carpenter itself recognizes that the\\ncollection of CSLI does “not fit neatly under existing\\n\\n\\n29\\n See Appellant’s Supplemental Letter at 3-4. The case that\\nGoldstein refers to was reversed on rehearing and upheld the\\nconstitutionality of CSLI obtained on less than probable\\ncause. See United States v. Davis, 785 F.3d 498, 513 (11th\\nCir. 2015).\\n30\\n 565 U.S. 400 (2012) (holding that placing a GPS tracker on\\na defendant’s car for 28 days without a warrant violated the\\nFourth Amendment).\\n31\\n 134 S. Ct. 2473 (2014) (holding that a warrantless search of\\nthe contents of a cell phone violated Fourth Amendment).\\n32\\n Stimler, 864 F.3d at 264-67.\\n33\\n Jones, 565 U.S. at 412-13. Carpenter explains that cars\\ncannot be analogized to cell phones in this context because\\ncell phones can provide law enforcement with more\\ninformation than a car about an individual’s movements.\\nCarpenter, 138 S. Ct. at 2218.\\n34\\n Riley, 134 S. Ct. at 2494-95.\\n\\n\\n\\n\\n 11\\n\\fprecedents.”35 The government could not have predicted the\\noutcome of Carpenter and the overruling of In re Application\\nfrom two Supreme Court cases that the Supreme Court itself\\nsaid are not directly applicable.\\n\\n Goldstein also argues that the good faith exception\\napplies only to police officers and other investigators, not the\\ngovernment attorneys who obtained the Section 2703(d) order\\nhere. Goldstein cites nothing in support of his proposed\\nlimitation on the good faith exception, and we see no reason\\nto limit its applicability in this case. The relevant inquiry\\nhere is not who the state actor is, but rather, whether the state\\nactor had a reasonable, good faith belief that his actions were\\nlegal. The prosecutors relied on a then-valid statute whose\\nconstitutionality had been confirmed by this Circuit. The\\ngood faith exception applies.\\n\\n IV.\\n\\n For the foregoing reasons, we affirm the District Court’s\\ndenial of Goldstein’s motion to suppress.\\n\\n\\n\\n\\n35\\n Carpenter, 138 S. Ct. at 2214-16.\\n\\n\\n\\n\\n 12\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360678/\", \"author_raw\": \"\"}]}"},"judge1":{"kind":"string","value":"CHAGARES"},"judge2":{"kind":"string","value":"RESTREPO"},"judge3":{"kind":"string","value":"ROTH"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583425/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America v. Jay GOLDSTEIN A/K/A Yaakov Jay Goldstein, Appellant\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-22\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n ________________\n\n No. 15-4094\n ________________\n\n\n UNITED STATES OF AMERICA\n\n v.\n\n JAY GOLDSTEIN a/k/a Yaakov\n\n JAY GOLDSTEIN,\n\nAppellant\n ________________\n\n On Appeal from the United States District Court\n for the District of New Jersey\n (D. C. No. 3-14-cr-00287-003)\n District Judge: Honorable Freda L. Wolfson\n ________________\n\n Argued on January 25, 2017\n Panel Rehearing Granted on August 30, 2018\n\n Before: CHAGARES, RESTREPO and ROTH, Circuit\n Judges\n\f (Opinion filed: January 22, 2019)\n\n\nAidan P. O’Connor [Argued]\nPashman Stein Walder Hayden\n21 Main Street\nCourt Plaza South, Suite 200\nHackensack, NJ 07601\n Counsel for Appellant\n\nMark E. Coyne\nOffice of United States Attorney\n970 Broad Street, Room 700\nNewark, NJ 07102\n\nNorman Gross [Argued]\nGlenn J. Moramarco [Argued]\nOffice of United States Attorney\nCamden Federal Building & Courthouse\n401 Market Street\nCamden, NJ 08101\n Counsel for Appellee\n\n\n ________________\n\n OPINION\n ________________\n\n\nROTH, Circuit Judge\n\n\n\n\n 2\n\f I.\n\n We granted Appellant Jay Goldstein’s petition for\nrehearing to address the effect of the Supreme Court’s recent\ndecision in Carpenter v. United States1 on our prior panel\ndecision, United States v. Stimler.2 In Stimler, we held that\nthe District Court properly denied Goldstein’s motion to\nsuppress his cell site location information (CSLI) because\nGoldstein had no reasonable expectation of privacy in his\nCSLI, and, therefore, the government did not need probable\ncause to collect this data.3 Carpenter sets forth a new rule\nthat defendants do in fact have a privacy interest in their\nCSLI, and the government must generally obtain a search\nwarrant supported by probable cause to obtain this\ninformation.4 However, we still affirm the District Court’s\ndecision under the good faith exception to the exclusionary\nrule because the government had an objectively reasonable\ngood faith belief that its conduct was legal when it acquired\nGoldstein’s CSLI.\n\n II.\n\n We recited a comprehensive factual background in our\nprevious decision.5 The facts relevant to this decision follow.\n\n1\n 138 S. Ct. 2206 (2018).\n2\n 864 F.3d 253 (3d Cir. 2017).\n3\n Id. at 263. Carpenter does not affect our other holdings in\nStimler. Those remain as written and are not addressed in or\nchanged by this decision.\n4\n Carpenter, 138 S. Ct. at 2217, 2222.\n5\n Stimler, 864 F.3d at 259-61.\n\n\n\n\n 3\n\fGoldstein was arrested for his involvement in a kidnapping\nscheme. Hoping to find evidence placing Goldstein at the\nscene of the kidnapping, the prosecutors obtained a court\norder under the Stored Communications Act (SCA)—\nspecifically 18 U.S.C. § 2703(d)—compelling Goldstein’s\ncell phone carrier to turn over 57 days’ worth of his CSLI.\nCSLI is a type of metadata that is generated every time a\nuser’s cell phone connects to the nearest antenna. The user’s\ncell phone service provider retains a time-stamped record\nidentifying the particular antenna to which the phone\nconnected. Because most people constantly carry and\nfrequently use their cell phones, CSLI can provide a detailed\nlog of an individual’s movements over a period of time.\n\n The legal question in this case centers on whether\nSection 2703(d), the statutory provision under which the\ngovernment obtained Goldstein’s CSLI, complies with the\nFourth Amendment. The Fourth Amendment protects against\nunreasonable searches. In order for the acquisition of CSLI to\nbe a “search” under the Fourth Amendment, an individual\nmust have a reasonable expectation of privacy in his CSLI.6\nIn order for a search to be “reasonable,” it generally must be\nconducted pursuant to a search warrant supported by probable\ncause, unless an exception to the warrant requirement\napplies.7 Consequently, if there is no reasonable expectation\nof privacy as to CSLI, then its acquisition does not require a\nsearch warrant; if there is, then a warrant is generally\nrequired. Section 2703(d) does not require a showing of\n\n6\n See United States v. Knotts, 460 U.S. 276, 281 (1983)\n(explaining what constitutes a reasonable expectation of\nprivacy).\n7\n See Riley v. California, 134 S. Ct. 2473, 2482 (2014).\n\n\n\n\n 4\n\fprobable cause to obtain CSLI. Rather, it calls for a more\nlenient standard, requiring “specific and articulable facts\nshowing that there are reasonable grounds to believe” that the\nCSLI is relevant and material.8\n\n Before trial, Goldstein moved to suppress the CSLI,\narguing that this provision violates the Fourth Amendment\nbecause it authorizes disclosure of CSLI without a warrant\nsupported by probable cause. The District Court rejected this\nargument and denied the motion. Through the testimony of\nan FBI agent, the government introduced the CSLI at trial,\nwhich placed him in the vicinity of the kidnapping site.\nGoldstein was convicted and sentenced to 96 months in\nprison.\n\n In our previous decision, we affirmed the District\nCourt’s denial of Goldstein’s motion to suppress, holding that\nSection 2703(d) complied with the Fourth Amendment\nbecause cell phone users have no reasonable expectation of\nprivacy in their CSLI.9 We relied on our decision in In re\nApplication of the United States for an Order Directing a\nProvider of Electronic Communication Service to Disclose\nRecords to the Government (In re Application),10 which also\nfound no reasonable expectation of privacy in CSLI,11 and we\n\n\n\n\n8\n 18 U.S.C. § 2703(d).\n9\n Stimler, 864 F.3d at 263.\n10\n 620 F.3d 304 (3d Cir. 2010).\n11\n Id. at 312-13 (holding that CSLI is obtainable without “the\ntraditional probable cause determination” because\nindividuals’ privacy interests do not extend to CSLI).\n\n\n\n\n 5\n\freasoned that there were no intervening changes in law\nundermining In re Application.12\n\n Goldstein petitioned for rehearing, and we held the\npetition curia advisari vult pending the Supreme Court’s\ndecision in Carpenter, which was set to address essentially\nthe same question we answered in Stimler: whether obtaining\nCSLI without a warrant supported by probable cause under\nSection 2703(d) violates the Fourth Amendment’s protection\nagainst unreasonable searches. The Supreme Court decided\nCarpenter, and we granted Goldstein’s petition for panel\nrehearing.13 Carpenter came to the opposite conclusion that\nwe came to in In re Application and Stimler and held that “an\nindividual maintains a legitimate expectation of privacy in the\nrecord of his physical movements as captured though CSLI”\nand that the government’s collection of CSLI requires a\nshowing of probable cause under the Fourth Amendment.14\nConsequently, Section 2703(d) may not be used to access\nCSLI because it requires less than probable cause.\n\n Applying Carpenter to Goldstein’s case, we find that\nthe government did violate Goldstein’s Fourth Amendment\nrights when it acquired his CSLI under Section 2703(d) of the\nSCA. However, we will still affirm the District Court’s\nadmission of Goldstein’s CSLI because the government was\nacting under an objectively reasonable good faith belief that\n\n\n12\n Stimler, 864 F.3d at 264-67.\n13\n Appellants Stimler and Epstein also petitioned for\nrehearing, but we denied those petitions because the\ngovernment did not collect their CSLI.\n14\n Carpenter, 138 S. Ct. at 2217, 2222.\n\n\n\n\n 6\n\fobtaining CSLI under Section 2703(d) was constitutional at\nthe time.\n\n\n 15\n III.\n\n It is clear that under Carpenter, acquiring Goldstein’s\nCSLI was an unconstitutional search under the Fourth\nAmendment because the government did not obtain a warrant\nsupported by probable cause.16 However, evidence obtained\nin violation of a defendant’s Fourth Amendment rights is not\nautomatically suppressed. Evidence will be suppressed under\nthe exclusionary rule when suppression would further the\nexclusionary rule’s primary objective: to deter Fourth\nAmendment violations.17 One instance where suppressing\nevidence will not encourage deterrence is where the\ngovernment acted “upon an objectively reasonable good faith\nbelief in the legality of [its] conduct” when conducting a\n\n\n15\n The District Court had jurisdiction under 18 U.S.C. § 3231.\nWe have jurisdiction pursuant to 28 U.S.C. § 1291. “In\nreviewing a motion to suppress, ‘we review a district court’s\nfactual findings for clear error, and we exercise de novo\nreview over its application of the law to those factual\nfindings.’” United States v. Katzin, 769 F.3d 163, 169 n.4 (3d\nCir. 2014) (en banc) (quoting United States v. Pavulak, 700\nF.3d 651, 660 (3d Cir. 2012)).\n16\n A warrantless search is still reasonable under the Fourth\nAmendment if an exception to the warrant requirement\napplies, but the parties do not argue, and we do not find, that\nany exception applies here. Carpenter, 138 S. Ct. at 2222-23.\n17\n Katzin, 769 F.3d at 170-71.\n\n\n\n\n 7\n\fsearch.18 Indeed, “applying the exclusionary rule would not\n‘yield appreciable deterrence’” when government actors have\na reasonable belief that their conduct conforms with the law.19\nThis is known as the good faith exception, and where it\napplies, the illegally-obtained evidence will not be suppressed\nunder the exclusionary rule.\n\n The Supreme Court has applied this exception across a\nnumber of cases where suppressing evidence would not have\nany deterrent value—three of which are relevant here. In\nIllinois v. Krull,20 the Court held that the good faith exception\napplies when a search is executed pursuant to a statute that\nwas valid at the time of the search but later declared\nunconstitutional.21 Except in instances where a statute is\nobviously unconstitutional, suppressing evidence obtained by\na law enforcement officer “acting in objectively reasonable\nreliance on a statute would have . . . little deterrent effect on\nthe [government’s] actions.”22 Under Davis v. United\nStates,23 this exception also applies when a search is\nconducted based upon reasonable reliance on then-binding\nappellate precedent because exclusion in this context would\nnot deter improper government conduct.24 And under United\n\n\n18\n Id. at 182.\n19\n United States v. Vasquez-Algarin, 821 F.3d 467, 482-83 (3d\nCir. 2016) (quoting Davis v. United States, 564 U.S. 229, 237\n(2011)).\n20\n 480 U.S. 340 (1987).\n21\n Id. at 349-50.\n22\n Id.\n23\n 564 U.S. 229 (2011).\n24\n Id. at 241.\n\n\n\n\n 8\n\fStates v. Leon,25 the exclusionary rule will not apply when\nlaw enforcement conducts a search pursuant to a judicial\norder later found invalid.26\n\n The good faith exception applies to the government’s\nsearch in this case because the government acted upon an\nobjectively reasonable, good faith belief that obtaining\nGoldstein’s CSLI under Section 2703(d) was legal. At the\ntime the search was executed, it was authorized under Section\n2703(d). The government complied with all requirements of\nSection 2703(d) and obtained a valid judicial order to collect\nGoldstein’s CSLI. Moreover, the government had no reason\nto question the constitutionality of obtaining CSLI through\nSection 2703(d) because that question had been answered by\nthis Court in In re Application—which was binding appellate\nprecedent.27 Thus, because the government relied on a\nproperly-obtained valid judicial order, a then-valid statute,\nand then-binding appellate authority, it had an objectively\nreasonable, good faith belief that its conduct was legal.\nIndeed, the conduct was legal at the time. Excluding\nevidence obtained through methods that complied with the\nlaw at the time of the search cannot serve any deterrent\npurpose. Under Krull, Davis, and Leon, the good faith\nexception applies, and the District Court’s denial of the\nmotion to suppress is affirmed. Our holding puts us in good\ncompany, as many of our sister circuits have also found that\n\n25\n 468 U.S. 897 (1984).\n26\n Id. at 922.\n27\n In re Application, 620 F.3d at 313 (“[W]e hold that CSLI\nfrom cell phone calls is obtainable under a § 2703(d) order\nand that such an order does not require the traditional\nprobable cause determination.”).\n\n\n\n\n 9\n\fthe good faith exception applies when the government\nobtained CLSI data without a warrant prior to Carpenter.28\n Goldstein contends that the good faith exception does\nnot apply because the government’s reliance on Section\n2703(d) was unreasonable for two reasons, both of which fail.\nFirst, he argues that, at the time of the search, the Eleventh\nCircuit had held that collecting CSLI without a warrant\nsupported by probable cause violated the Fourth\n\n28\n See, e.g., United States v. Joyner, 899 F.3d 1199, 1204-05\n(11th Cir. 2018) (“Here, the Government complied with the\nrequirements of the SCA in obtaining the orders to compel\ncell site records, and when they did so in June 2015, that\nwarrantless procedure was, under this Court’s precedent,\nwithin the bounds of the Fourth Amendment.”);\nUnited States v. Chavez, 894 F.3d 593, 608 (4th Cir. 2018)\n(Carpenter does not affect cases where investigators acted\npursuant to court orders and the SCA); United States v.\nCurtis, 901 F.3d 846, 849 (7th Cir. 2018) (“We conclude,\ntherefore, that even though it is now established that the\nFourth Amendment requires a warrant for the type of cell-\nphone data present here, exclusion of that information was\nnot required because it was collected in good faith.”); United\nStates v. Chambers, No. 16-163-CR, 2018 WL 4523607, at\n*3 (2d Cir. Sept. 21, 2018) (“Thus, we conclude that even\nafter Jones, but before Carpenter, it was objectively\nreasonable for authorities to think that if they complied with\nthe SCA, no warrant based on probable cause was\nconstitutionally required to obtain cell-site information from a\nthird party.”). Judge Restrepo’s concurrence in Stimler also\nconcluded that the good faith exception applied here in light\nof In re Application. See Stimler, 864 F.3d at 279-80\n(Restrepo, J., concurring).\n\n\n\n\n 10\n\fAmendment.29 But, under Davis, only binding appellate\nprecedent is relevant to the good faith exception, and In re\nApplication was binding in this Circuit at the time. Second,\nhe contends the government could not have reasonably relied\non In re Application because it had been undermined by two\nsubsequent Supreme Court cases—United States v. Jones30\nand Riley v. California.31 As discussed in Stimler, neither\ncase undercuts In re Application because neither addresses\nthe long-term collection of metadata from cell phones.32\nJones addressed long-term collection of GPS location data\nfrom a car—not a cell phone.33 Riley involved the contents of\na cell phone, not the metadata transmitted from a cell phone\nto a third party.34 Indeed, Carpenter itself recognizes that the\ncollection of CSLI does “not fit neatly under existing\n\n\n29\n See Appellant’s Supplemental Letter at 3-4. The case that\nGoldstein refers to was reversed on rehearing and upheld the\nconstitutionality of CSLI obtained on less than probable\ncause. See United States v. Davis, 785 F.3d 498, 513 (11th\nCir. 2015).\n30\n 565 U.S. 400 (2012) (holding that placing a GPS tracker on\na defendant’s car for 28 days without a warrant violated the\nFourth Amendment).\n31\n 134 S. Ct. 2473 (2014) (holding that a warrantless search of\nthe contents of a cell phone violated Fourth Amendment).\n32\n Stimler, 864 F.3d at 264-67.\n33\n Jones, 565 U.S. at 412-13. Carpenter explains that cars\ncannot be analogized to cell phones in this context because\ncell phones can provide law enforcement with more\ninformation than a car about an individual’s movements.\nCarpenter, 138 S. Ct. at 2218.\n34\n Riley, 134 S. Ct. at 2494-95.\n\n\n\n\n 11\n\fprecedents.”35 The government could not have predicted the\noutcome of Carpenter and the overruling of In re Application\nfrom two Supreme Court cases that the Supreme Court itself\nsaid are not directly applicable.\n\n Goldstein also argues that the good faith exception\napplies only to police officers and other investigators, not the\ngovernment attorneys who obtained the Section 2703(d) order\nhere. Goldstein cites nothing in support of his proposed\nlimitation on the good faith exception, and we see no reason\nto limit its applicability in this case. The relevant inquiry\nhere is not who the state actor is, but rather, whether the state\nactor had a reasonable, good faith belief that his actions were\nlegal. The prosecutors relied on a then-valid statute whose\nconstitutionality had been confirmed by this Circuit. The\ngood faith exception applies.\n\n IV.\n\n For the foregoing reasons, we affirm the District Court’s\ndenial of Goldstein’s motion to suppress.\n\n\n\n\n35\n Carpenter, 138 S. Ct. at 2214-16.\n\n\n\n\n 12\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America v. Jay GOLDSTEIN A/K/A Yaakov Jay Goldstein, Appellant\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-22\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n ________________\\n\\n No. 15-4094\\n ________________\\n\\n\\n UNITED STATES OF AMERICA\\n\\n v.\\n\\n JAY GOLDSTEIN a/k/a Yaakov\\n\\n JAY GOLDSTEIN,\\n\\nAppellant\\n ________________\\n\\n On Appeal from the United States District Court\\n for the District of New Jersey\\n (D. C. No. 3-14-cr-00287-003)\\n District Judge: Honorable Freda L. Wolfson\\n ________________\\n\\n Argued on January 25, 2017\\n Panel Rehearing Granted on August 30, 2018\\n\\n Before: CHAGARES, RESTREPO and ROTH, Circuit\\n Judges\\n\\f (Opinion filed: January 22, 2019)\\n\\n\\nAidan P. O’Connor [Argued]\\nPashman Stein Walder Hayden\\n21 Main Street\\nCourt Plaza South, Suite 200\\nHackensack, NJ 07601\\n Counsel for Appellant\\n\\nMark E. Coyne\\nOffice of United States Attorney\\n970 Broad Street, Room 700\\nNewark, NJ 07102\\n\\nNorman Gross [Argued]\\nGlenn J. Moramarco [Argued]\\nOffice of United States Attorney\\nCamden Federal Building & Courthouse\\n401 Market Street\\nCamden, NJ 08101\\n Counsel for Appellee\\n\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\n\\nROTH, Circuit Judge\\n\\n\\n\\n\\n 2\\n\\f I.\\n\\n We granted Appellant Jay Goldstein’s petition for\\nrehearing to address the effect of the Supreme Court’s recent\\ndecision in Carpenter v. United States1 on our prior panel\\ndecision, United States v. Stimler.2 In Stimler, we held that\\nthe District Court properly denied Goldstein’s motion to\\nsuppress his cell site location information (CSLI) because\\nGoldstein had no reasonable expectation of privacy in his\\nCSLI, and, therefore, the government did not need probable\\ncause to collect this data.3 Carpenter sets forth a new rule\\nthat defendants do in fact have a privacy interest in their\\nCSLI, and the government must generally obtain a search\\nwarrant supported by probable cause to obtain this\\ninformation.4 However, we still affirm the District Court’s\\ndecision under the good faith exception to the exclusionary\\nrule because the government had an objectively reasonable\\ngood faith belief that its conduct was legal when it acquired\\nGoldstein’s CSLI.\\n\\n II.\\n\\n We recited a comprehensive factual background in our\\nprevious decision.5 The facts relevant to this decision follow.\\n\\n1\\n 138 S. Ct. 2206 (2018).\\n2\\n 864 F.3d 253 (3d Cir. 2017).\\n3\\n Id. at 263. Carpenter does not affect our other holdings in\\nStimler. Those remain as written and are not addressed in or\\nchanged by this decision.\\n4\\n Carpenter, 138 S. Ct. at 2217, 2222.\\n5\\n Stimler, 864 F.3d at 259-61.\\n\\n\\n\\n\\n 3\\n\\fGoldstein was arrested for his involvement in a kidnapping\\nscheme. Hoping to find evidence placing Goldstein at the\\nscene of the kidnapping, the prosecutors obtained a court\\norder under the Stored Communications Act (SCA)—\\nspecifically 18 U.S.C. § 2703(d)—compelling Goldstein’s\\ncell phone carrier to turn over 57 days’ worth of his CSLI.\\nCSLI is a type of metadata that is generated every time a\\nuser’s cell phone connects to the nearest antenna. The user’s\\ncell phone service provider retains a time-stamped record\\nidentifying the particular antenna to which the phone\\nconnected. Because most people constantly carry and\\nfrequently use their cell phones, CSLI can provide a detailed\\nlog of an individual’s movements over a period of time.\\n\\n The legal question in this case centers on whether\\nSection 2703(d), the statutory provision under which the\\ngovernment obtained Goldstein’s CSLI, complies with the\\nFourth Amendment. The Fourth Amendment protects against\\nunreasonable searches. In order for the acquisition of CSLI to\\nbe a “search” under the Fourth Amendment, an individual\\nmust have a reasonable expectation of privacy in his CSLI.6\\nIn order for a search to be “reasonable,” it generally must be\\nconducted pursuant to a search warrant supported by probable\\ncause, unless an exception to the warrant requirement\\napplies.7 Consequently, if there is no reasonable expectation\\nof privacy as to CSLI, then its acquisition does not require a\\nsearch warrant; if there is, then a warrant is generally\\nrequired. Section 2703(d) does not require a showing of\\n\\n6\\n See United States v. Knotts, 460 U.S. 276, 281 (1983)\\n(explaining what constitutes a reasonable expectation of\\nprivacy).\\n7\\n See Riley v. California, 134 S. Ct. 2473, 2482 (2014).\\n\\n\\n\\n\\n 4\\n\\fprobable cause to obtain CSLI. Rather, it calls for a more\\nlenient standard, requiring “specific and articulable facts\\nshowing that there are reasonable grounds to believe” that the\\nCSLI is relevant and material.8\\n\\n Before trial, Goldstein moved to suppress the CSLI,\\narguing that this provision violates the Fourth Amendment\\nbecause it authorizes disclosure of CSLI without a warrant\\nsupported by probable cause. The District Court rejected this\\nargument and denied the motion. Through the testimony of\\nan FBI agent, the government introduced the CSLI at trial,\\nwhich placed him in the vicinity of the kidnapping site.\\nGoldstein was convicted and sentenced to 96 months in\\nprison.\\n\\n In our previous decision, we affirmed the District\\nCourt’s denial of Goldstein’s motion to suppress, holding that\\nSection 2703(d) complied with the Fourth Amendment\\nbecause cell phone users have no reasonable expectation of\\nprivacy in their CSLI.9 We relied on our decision in In re\\nApplication of the United States for an Order Directing a\\nProvider of Electronic Communication Service to Disclose\\nRecords to the Government (In re Application),10 which also\\nfound no reasonable expectation of privacy in CSLI,11 and we\\n\\n\\n\\n\\n8\\n 18 U.S.C. § 2703(d).\\n9\\n Stimler, 864 F.3d at 263.\\n10\\n 620 F.3d 304 (3d Cir. 2010).\\n11\\n Id. at 312-13 (holding that CSLI is obtainable without “the\\ntraditional probable cause determination” because\\nindividuals’ privacy interests do not extend to CSLI).\\n\\n\\n\\n\\n 5\\n\\freasoned that there were no intervening changes in law\\nundermining In re Application.12\\n\\n Goldstein petitioned for rehearing, and we held the\\npetition curia advisari vult pending the Supreme Court’s\\ndecision in Carpenter, which was set to address essentially\\nthe same question we answered in Stimler: whether obtaining\\nCSLI without a warrant supported by probable cause under\\nSection 2703(d) violates the Fourth Amendment’s protection\\nagainst unreasonable searches. The Supreme Court decided\\nCarpenter, and we granted Goldstein’s petition for panel\\nrehearing.13 Carpenter came to the opposite conclusion that\\nwe came to in In re Application and Stimler and held that “an\\nindividual maintains a legitimate expectation of privacy in the\\nrecord of his physical movements as captured though CSLI”\\nand that the government’s collection of CSLI requires a\\nshowing of probable cause under the Fourth Amendment.14\\nConsequently, Section 2703(d) may not be used to access\\nCSLI because it requires less than probable cause.\\n\\n Applying Carpenter to Goldstein’s case, we find that\\nthe government did violate Goldstein’s Fourth Amendment\\nrights when it acquired his CSLI under Section 2703(d) of the\\nSCA. However, we will still affirm the District Court’s\\nadmission of Goldstein’s CSLI because the government was\\nacting under an objectively reasonable good faith belief that\\n\\n\\n12\\n Stimler, 864 F.3d at 264-67.\\n13\\n Appellants Stimler and Epstein also petitioned for\\nrehearing, but we denied those petitions because the\\ngovernment did not collect their CSLI.\\n14\\n Carpenter, 138 S. Ct. at 2217, 2222.\\n\\n\\n\\n\\n 6\\n\\fobtaining CSLI under Section 2703(d) was constitutional at\\nthe time.\\n\\n\\n 15\\n III.\\n\\n It is clear that under Carpenter, acquiring Goldstein’s\\nCSLI was an unconstitutional search under the Fourth\\nAmendment because the government did not obtain a warrant\\nsupported by probable cause.16 However, evidence obtained\\nin violation of a defendant’s Fourth Amendment rights is not\\nautomatically suppressed. Evidence will be suppressed under\\nthe exclusionary rule when suppression would further the\\nexclusionary rule’s primary objective: to deter Fourth\\nAmendment violations.17 One instance where suppressing\\nevidence will not encourage deterrence is where the\\ngovernment acted “upon an objectively reasonable good faith\\nbelief in the legality of [its] conduct” when conducting a\\n\\n\\n15\\n The District Court had jurisdiction under 18 U.S.C. § 3231.\\nWe have jurisdiction pursuant to 28 U.S.C. § 1291. “In\\nreviewing a motion to suppress, ‘we review a district court’s\\nfactual findings for clear error, and we exercise de novo\\nreview over its application of the law to those factual\\nfindings.’” United States v. Katzin, 769 F.3d 163, 169 n.4 (3d\\nCir. 2014) (en banc) (quoting United States v. Pavulak, 700\\nF.3d 651, 660 (3d Cir. 2012)).\\n16\\n A warrantless search is still reasonable under the Fourth\\nAmendment if an exception to the warrant requirement\\napplies, but the parties do not argue, and we do not find, that\\nany exception applies here. Carpenter, 138 S. Ct. at 2222-23.\\n17\\n Katzin, 769 F.3d at 170-71.\\n\\n\\n\\n\\n 7\\n\\fsearch.18 Indeed, “applying the exclusionary rule would not\\n‘yield appreciable deterrence’” when government actors have\\na reasonable belief that their conduct conforms with the law.19\\nThis is known as the good faith exception, and where it\\napplies, the illegally-obtained evidence will not be suppressed\\nunder the exclusionary rule.\\n\\n The Supreme Court has applied this exception across a\\nnumber of cases where suppressing evidence would not have\\nany deterrent value—three of which are relevant here. In\\nIllinois v. Krull,20 the Court held that the good faith exception\\napplies when a search is executed pursuant to a statute that\\nwas valid at the time of the search but later declared\\nunconstitutional.21 Except in instances where a statute is\\nobviously unconstitutional, suppressing evidence obtained by\\na law enforcement officer “acting in objectively reasonable\\nreliance on a statute would have . . . little deterrent effect on\\nthe [government’s] actions.”22 Under Davis v. United\\nStates,23 this exception also applies when a search is\\nconducted based upon reasonable reliance on then-binding\\nappellate precedent because exclusion in this context would\\nnot deter improper government conduct.24 And under United\\n\\n\\n18\\n Id. at 182.\\n19\\n United States v. Vasquez-Algarin, 821 F.3d 467, 482-83 (3d\\nCir. 2016) (quoting Davis v. United States, 564 U.S. 229, 237\\n(2011)).\\n20\\n 480 U.S. 340 (1987).\\n21\\n Id. at 349-50.\\n22\\n Id.\\n23\\n 564 U.S. 229 (2011).\\n24\\n Id. at 241.\\n\\n\\n\\n\\n 8\\n\\fStates v. Leon,25 the exclusionary rule will not apply when\\nlaw enforcement conducts a search pursuant to a judicial\\norder later found invalid.26\\n\\n The good faith exception applies to the government’s\\nsearch in this case because the government acted upon an\\nobjectively reasonable, good faith belief that obtaining\\nGoldstein’s CSLI under Section 2703(d) was legal. At the\\ntime the search was executed, it was authorized under Section\\n2703(d). The government complied with all requirements of\\nSection 2703(d) and obtained a valid judicial order to collect\\nGoldstein’s CSLI. Moreover, the government had no reason\\nto question the constitutionality of obtaining CSLI through\\nSection 2703(d) because that question had been answered by\\nthis Court in In re Application—which was binding appellate\\nprecedent.27 Thus, because the government relied on a\\nproperly-obtained valid judicial order, a then-valid statute,\\nand then-binding appellate authority, it had an objectively\\nreasonable, good faith belief that its conduct was legal.\\nIndeed, the conduct was legal at the time. Excluding\\nevidence obtained through methods that complied with the\\nlaw at the time of the search cannot serve any deterrent\\npurpose. Under Krull, Davis, and Leon, the good faith\\nexception applies, and the District Court’s denial of the\\nmotion to suppress is affirmed. Our holding puts us in good\\ncompany, as many of our sister circuits have also found that\\n\\n25\\n 468 U.S. 897 (1984).\\n26\\n Id. at 922.\\n27\\n In re Application, 620 F.3d at 313 (“[W]e hold that CSLI\\nfrom cell phone calls is obtainable under a § 2703(d) order\\nand that such an order does not require the traditional\\nprobable cause determination.”).\\n\\n\\n\\n\\n 9\\n\\fthe good faith exception applies when the government\\nobtained CLSI data without a warrant prior to Carpenter.28\\n Goldstein contends that the good faith exception does\\nnot apply because the government’s reliance on Section\\n2703(d) was unreasonable for two reasons, both of which fail.\\nFirst, he argues that, at the time of the search, the Eleventh\\nCircuit had held that collecting CSLI without a warrant\\nsupported by probable cause violated the Fourth\\n\\n28\\n See, e.g., United States v. Joyner, 899 F.3d 1199, 1204-05\\n(11th Cir. 2018) (“Here, the Government complied with the\\nrequirements of the SCA in obtaining the orders to compel\\ncell site records, and when they did so in June 2015, that\\nwarrantless procedure was, under this Court’s precedent,\\nwithin the bounds of the Fourth Amendment.”);\\nUnited States v. Chavez, 894 F.3d 593, 608 (4th Cir. 2018)\\n(Carpenter does not affect cases where investigators acted\\npursuant to court orders and the SCA); United States v.\\nCurtis, 901 F.3d 846, 849 (7th Cir. 2018) (“We conclude,\\ntherefore, that even though it is now established that the\\nFourth Amendment requires a warrant for the type of cell-\\nphone data present here, exclusion of that information was\\nnot required because it was collected in good faith.”); United\\nStates v. Chambers, No. 16-163-CR, 2018 WL 4523607, at\\n*3 (2d Cir. Sept. 21, 2018) (“Thus, we conclude that even\\nafter Jones, but before Carpenter, it was objectively\\nreasonable for authorities to think that if they complied with\\nthe SCA, no warrant based on probable cause was\\nconstitutionally required to obtain cell-site information from a\\nthird party.”). Judge Restrepo’s concurrence in Stimler also\\nconcluded that the good faith exception applied here in light\\nof In re Application. See Stimler, 864 F.3d at 279-80\\n(Restrepo, J., concurring).\\n\\n\\n\\n\\n 10\\n\\fAmendment.29 But, under Davis, only binding appellate\\nprecedent is relevant to the good faith exception, and In re\\nApplication was binding in this Circuit at the time. Second,\\nhe contends the government could not have reasonably relied\\non In re Application because it had been undermined by two\\nsubsequent Supreme Court cases—United States v. Jones30\\nand Riley v. California.31 As discussed in Stimler, neither\\ncase undercuts In re Application because neither addresses\\nthe long-term collection of metadata from cell phones.32\\nJones addressed long-term collection of GPS location data\\nfrom a car—not a cell phone.33 Riley involved the contents of\\na cell phone, not the metadata transmitted from a cell phone\\nto a third party.34 Indeed, Carpenter itself recognizes that the\\ncollection of CSLI does “not fit neatly under existing\\n\\n\\n29\\n See Appellant’s Supplemental Letter at 3-4. The case that\\nGoldstein refers to was reversed on rehearing and upheld the\\nconstitutionality of CSLI obtained on less than probable\\ncause. See United States v. Davis, 785 F.3d 498, 513 (11th\\nCir. 2015).\\n30\\n 565 U.S. 400 (2012) (holding that placing a GPS tracker on\\na defendant’s car for 28 days without a warrant violated the\\nFourth Amendment).\\n31\\n 134 S. Ct. 2473 (2014) (holding that a warrantless search of\\nthe contents of a cell phone violated Fourth Amendment).\\n32\\n Stimler, 864 F.3d at 264-67.\\n33\\n Jones, 565 U.S. at 412-13. Carpenter explains that cars\\ncannot be analogized to cell phones in this context because\\ncell phones can provide law enforcement with more\\ninformation than a car about an individual’s movements.\\nCarpenter, 138 S. Ct. at 2218.\\n34\\n Riley, 134 S. Ct. at 2494-95.\\n\\n\\n\\n\\n 11\\n\\fprecedents.”35 The government could not have predicted the\\noutcome of Carpenter and the overruling of In re Application\\nfrom two Supreme Court cases that the Supreme Court itself\\nsaid are not directly applicable.\\n\\n Goldstein also argues that the good faith exception\\napplies only to police officers and other investigators, not the\\ngovernment attorneys who obtained the Section 2703(d) order\\nhere. Goldstein cites nothing in support of his proposed\\nlimitation on the good faith exception, and we see no reason\\nto limit its applicability in this case. The relevant inquiry\\nhere is not who the state actor is, but rather, whether the state\\nactor had a reasonable, good faith belief that his actions were\\nlegal. The prosecutors relied on a then-valid statute whose\\nconstitutionality had been confirmed by this Circuit. The\\ngood faith exception applies.\\n\\n IV.\\n\\n For the foregoing reasons, we affirm the District Court’s\\ndenial of Goldstein’s motion to suppress.\\n\\n\\n\\n\\n35\\n Carpenter, 138 S. Ct. at 2214-16.\\n\\n\\n\\n\\n 12\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":72,"cells":{"id":{"kind":"number","value":4583426,"string":"4,583,426"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"G.S. v. Rose Tree Media School Distric"},"decision_date":{"kind":"string","value":"2019-01-22"},"docket_number":{"kind":"string","value":"17-2886"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Present: AMBRO and JORDAN, Circuit Judges Motion by Amici to Convert a Not Precedential Opinion to Precedential.\", \"parties\": \"\", \"opinions\": [{\"author\": \"s/Thomas L. Ambro, Circuit Judge\", \"type\": \"010combined\", \"text\": \"UNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\\n\\n No. 17-2886\\n\\n G.S., a minor, by his parents, J.S. and E.S.\\n\\n v.\\n\\n ROSE TREE MEDIA SCHOOL DISTRICT\\n (E.D. Pa. No. 2-16-cv-04782)\\n\\n ROSE TREE MEDIA SCHOOL DISTRICT\\n\\n v.\\n\\n E.S. and J.S., Parents and Natural Guardians of G.S., a Minor\\n (E.D. Pa. No. 2-16-cv-04849)\\n\\n Rose Tree Media School District,\\n Appellant\\n\\nPresent: AMBRO and JORDAN, Circuit Judges\\n\\n Motion by Amici to Convert a Not Precedential Opinion to Precedential.\\n\\n Respectfully,\\n Clerk/nmr\\n_______________________________O R D E R ____________________________\\nThe foregoing Motion by Amici to convert a Not Precedential Opinion to a Precedential\\nOpinion is granted.\\n\\n By the Court,\\n\\n s/Thomas L. Ambro, Circuit Judge\\n\\nDated: January 22, 2019\\n\\n\\n\\n\\n The Honorable Thomas I. Vanaskie, who authored the Court’s opinion in this matter,\\nretired from the Court on January 1, 2019 and did not participate in the consideration of\\nthe motion.\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360679/\", \"author_raw\": \"s/Thomas L. Ambro, Circuit Judge\"}]}"},"judge1":{"kind":"string","value":"AMBRO"},"judge2":{"kind":"string","value":"JORDAN"},"judge3":{"kind":"string","value":""},"exactly_three_caps":{"kind":"number","value":0,"string":"0"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583426/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: G.S. v. Rose Tree Media School Distric\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-22\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nUNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\n\n No. 17-2886\n\n G.S., a minor, by his parents, J.S. and E.S.\n\n v.\n\n ROSE TREE MEDIA SCHOOL DISTRICT\n (E.D. Pa. No. 2-16-cv-04782)\n\n ROSE TREE MEDIA SCHOOL DISTRICT\n\n v.\n\n E.S. and J.S., Parents and Natural Guardians of G.S., a Minor\n (E.D. Pa. No. 2-16-cv-04849)\n\n Rose Tree Media School District,\n Appellant\n\nPresent: AMBRO and JORDAN, Circuit Judges\n\n Motion by Amici to Convert a Not Precedential Opinion to Precedential.\n\n Respectfully,\n Clerk/nmr\n_______________________________O R D E R ____________________________\nThe foregoing Motion by Amici to convert a Not Precedential Opinion to a Precedential\nOpinion is granted.\n\n By the Court,\n\n s/Thomas L. Ambro, Circuit Judge\n\nDated: January 22, 2019\n\n\n\n\n The Honorable Thomas I. Vanaskie, who authored the Court’s opinion in this matter,\nretired from the Court on January 1, 2019 and did not participate in the consideration of\nthe motion.\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: G.S. v. Rose Tree Media School Distric\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-22\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nUNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\\n\\n No. 17-2886\\n\\n G.S., a minor, by his parents, J.S. and E.S.\\n\\n v.\\n\\n ROSE TREE MEDIA SCHOOL DISTRICT\\n (E.D. Pa. No. 2-16-cv-04782)\\n\\n ROSE TREE MEDIA SCHOOL DISTRICT\\n\\n v.\\n\\n E.S. and J.S., Parents and Natural Guardians of G.S., a Minor\\n (E.D. Pa. No. 2-16-cv-04849)\\n\\n Rose Tree Media School District,\\n Appellant\\n\\nPresent: AMBRO and JORDAN, Circuit Judges\\n\\n Motion by Amici to Convert a Not Precedential Opinion to Precedential.\\n\\n Respectfully,\\n Clerk/nmr\\n_______________________________O R D E R ____________________________\\nThe foregoing Motion by Amici to convert a Not Precedential Opinion to a Precedential\\nOpinion is granted.\\n\\n By the Court,\\n\\n s/Thomas L. Ambro, Circuit Judge\\n\\nDated: January 22, 2019\\n\\n\\n\\n\\n The Honorable Thomas I. Vanaskie, who authored the Court’s opinion in this matter,\\nretired from the Court on January 1, 2019 and did not participate in the consideration of\\nthe motion.\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":73,"cells":{"id":{"kind":"number","value":4583427,"string":"4,583,427"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"G.S. v. Rose Tree Media School Distric"},"decision_date":{"kind":"string","value":"2019-01-22"},"docket_number":{"kind":"string","value":"17-2886"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before: AMBRO, JORDAN, and VANASKIE,* Circuit Judges (Opinion\", \"parties\": \"\", \"opinions\": [{\"author\": \"Vanaskie. Judge Vanaskie retired from the Court on January\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-2886\\n _____________\\n\\n G.S., a minor, by his parents, J.S. and E.S.\\n\\n v.\\n\\n ROSE TREE MEDIA SCHOOL DISTRICT\\n (E.D. Pa. No. 2-16-cv-04782)\\n\\n ROSE TREE MEDIA SCHOOL DISTRICT\\n\\n v.\\n\\nE.S. and J.S., Parents and Natural Guardians of G.S., a Minor\\n (E.D. Pa. No. 2-16-cv-04849)\\n\\n Rose Tree Media School District,\\n Appellant\\n _____________\\n On Appeal from the United States District Court\\n for the Eastern District of Pennsylvania\\n (D.C. Civil Nos. 2-16-cv-04782 & 2-16-cv-04849)\\n District Judge: Honorable Eduardo C. Robreno\\n ______________\\n\\n Argued June 4, 2018\\n\\f ______________\\n\\n Before: AMBRO, JORDAN,\\n and VANASKIE,* Circuit Judges\\n\\n (Opinion Filed: November 6, 2018)\\n\\nGabrielle C. Goham, Esq.\\nKatherine H. Meehan, Esq. [Argued]\\nRaffaele Puppio\\n19 West Third Street\\nMedia, PA 19063\\n Counsel for Appellant\\n\\nMichael D. Raffaele, Esq. [Argued]\\nKershenbaum and Raffaele\\n1230 County Line Road\\nBryn Mawr, PA 19010\\n Counsel for Appellees\\n\\n\\n\\n\\n*\\n On November 6, 2018, the panel issued a not precedential\\nopinion in this matter authored by the Honorable Thomas I.\\nVanaskie. Judge Vanaskie retired from the Court on January\\n1, 2019. After Judge Vanaskie's retirement, amici curiae filed\\na motion to issue the opinion as a precedential opinion which\\nwas considered by the remaining members of the merits\\npanel. Today, the Court has issued the opinion as a\\nprecedential per curiam opinion. See 3rd Cir. I.O.P. 12.1 (d).\\n\\n\\n\\n\\n 2\\n\\fShannon L.C. Ammon, Esq.\\nJeffrey A. Sturgeon, Esq.\\nMorgan Lewis & Bockius\\n1701 Market Street\\nPhiladelphia, PA 19103\\n\\nMaura McInerney\\nEducation Law Center\\n1315 Walnut Street, Suite 400\\nPhiladelphia, PA 19107\\n Counsel for Amicus Appellees\\n\\n\\n ______________\\n\\n OPINION OF THE COURT\\n ______________\\n\\nPER CURIAM\\n\\n Appellant Rose Tree Media School District (“Rose\\nTree”) appeals the District Court’s grant of summary judgment\\nconcluding that Rose Tree was obligated to enroll Appellee\\nG.S. under Subtitle VII-B of the McKinney-Vento Homeless\\nAssistance Act (“McKinney-Vento” or the “Act”), 42 U.S.C.\\n§ 11434a(2) and § 11432(g)(3)(A)(i). We agree with the\\nDistrict Court that G.S. satisfies the Act’s definition of youth\\nhomelessness because he has been living in his maternal\\ngrandmother’s home, along with his parents, ever since his\\nparents lost their home in November 2014. Accordingly, we\\nwill affirm.\\n\\n I.\\n\\n\\n\\n\\n 3\\n\\f In 2010, G.S., along with his parents, his two sisters,\\nand his paternal grandparents, moved into a rental home within\\nRose Tree. At the time, G.S. and his sister, S.S., attended\\nschools within Rose Tree. In November 2014, G.S.’s parents\\nwere unable to make payments and lost the home. As a result,\\nG.S. moved in with Ba.S., his maternal grandmother. The\\ngrandmother’s single-family, 1500-square-foot row house was\\nlocated outside of Rose Tree.\\n\\n With the addition of G.S., a total of ten people—five\\nadults and five children—resided in the grandmother’s home.\\nInitially, G.S. slept in the living room with his parents and two\\nsisters. At times, G.S. moved his cot to the kitchen or basement\\nto obtain some privacy. The parties agree that, to date, G.S.’s\\nliving conditions remain unchanged.\\n\\n Rose Tree immediately learned of the change in G.S.’s\\nliving conditions. At that time, Rose Tree deemed G.S. and\\nS.S. homeless and thus continued to enroll them in a manner\\nconsistent with its obligations under McKinney-Vento,\\n42 U.S.C. § 11432(g)(3)(A)(i).\\n\\n In January 2015—less than two months after G.S.\\nmoved in with his maternal grandmother—he was involved in\\na disciplinary incident at school. Rose Tree suspended G.S. for\\nthree days, extended the suspension to ten days, and threatened\\nhim with expulsion. G.S.’s parents challenged Rose Tree’s\\nactions. The parties resolved the matter pursuant to a written\\nSettlement Agreement. Rose Tree, for its part, agreed to pay\\nfor G.S. to attend a school outside of its jurisdiction for the\\n2015–16 school year. In exchange, G.S.’s parents agreed to\\nwaive all claims through August 31, 2016. The Settlement\\nAgreement also included a provision purporting to waive\\nG.S.’s right to claim homelessness after the 2015–16 academic\\nyear.\\n\\n\\n\\n\\n 4\\n\\f Pursuant to the Agreement, G.S. attended a school\\noutside Rose Tree for the 2015–16 school year. Following the\\nconclusion of that academic year, in July 2016, G.S.’s parents\\nnotified Rose Tree of the family’s intent to re-enroll G.S. in\\none of its schools for the 2016–17 academic year. Rose Tree\\nrefused to enroll G.S., reasoning that his parents had waived\\nhis right to claim homelessness and thereby enroll under\\nMcKinney-Vento.\\n\\n G.S.’s parents initiated state grievance proceedings.\\nAfter conducting an inquiry, the Pennsylvania Department of\\nEducation issued a determination letter, stating:\\n\\n the outcome of our investigation is\\n that [G.S.] . . . ha[s] the right under\\n the federal McKinney-Vento\\n Homelessness Act to continue\\n being educated in the Rose Tree\\n Media School District since it is\\n [his] school district of origin and\\n [he] is temporarily residing in a\\n doubled up living situation that is\\n not fixed, regular nor adequate.\\n\\n(App. 365.) G.S.’s parents again attempted to enroll G.S. in\\nRose Tree, but the School District again refused.\\n Throughout the pendency of this matter, Rose Tree\\ncontinued to enroll G.S.’s sister, S.S, in one of its schools. The\\nparties do not dispute that S.S.’s living conditions are identical\\nto those of G.S.\\n\\n G.S. and his parents filed suit in federal court, Case No.\\n16-4782, against Rose Tree, seeking enrollment. Rose Tree\\nfiled a separate lawsuit in federal court, Case No. 16-4849,\\nagainst G.S.’s parents, seeking a declaration that it was not\\n\\n\\n\\n\\n 5\\n\\fobligated to enroll G.S. The District Court consolidated the\\ntwo cases in February 2017. Both parties moved for summary\\njudgment. The District Court resolved both motions in a single\\norder, finding in favor of G.S. Rose Tree timely appealed. On\\nappeal, the Education Law Center, the Homeless Children’s\\nEducation Fund, the National Law Center of Homelessness and\\nPoverty, and the People’s Emergency Center appear as amici\\nin support of G.S.\\n\\n II.\\n\\n The District Court had jurisdiction under 28 U.S.C.\\n§ 1331. We have appellate jurisdiction under 28 U.S.C.\\n§ 1291. We exercise plenary review over a district court’s\\ngrant of summary judgment. Blunt v. Lower Merion Sch. Dist.,\\n767 F.3d 247, 265 (3d Cir. 2014).\\n\\n III.\\n\\n Rose Tree argues that the grant of summary judgment\\nin favor of Appellees was erroneous because: (1) G.S.’s\\nparents waived his McKinney-Vento rights for the 2016–17\\nacademic year in the Settlement Agreement; (2) G.S. is no\\nlonger “homeless” within the meaning of the Act; and (3)\\nenrollment in Rose Tree is not in G.S.’s “best interest.”\\n\\n\\n\\n\\n 6\\n\\f A.\\n As a threshold matter, we must determine whether\\nG.S.’s parents waived his McKinney-Vento rights in the\\nSettlement Agreement. The parties agree that Pennsylvania\\nlaw governs our interpretation of the Agreement. Under\\nPennsylvania law, “[t]he fundamental rule in contract\\ninterpretation is to ascertain the intent of the contracting\\nparties.” Ins. Adjustment Bureau, Inc. v. Allstate Ins. Co., 905\\nA.2d 462, 468 (Pa. 2006) (internal citation omitted). “In cases\\nof a written contract, the intent of the parties is the writing itself\\n. . . When the terms of a contract are clear and unambiguous,\\nthe intent of the parties is to be ascertained from the document\\nitself.” Id. (internal citations omitted).\\n\\n In relevant part, the Settlement Agreement includes a\\nprovision purporting to waive G.S.’s McKinney-Vento rights\\nfor the 2016–17 academic year. This provision states:\\n\\n Parents agree that they will make\\n no claim of homeless status after\\n the 2015-16 school year and that\\n the District will have no further\\n obligations to Student after the\\n 2015-16 school year.\\n\\n(App. 140.) The District Court concluded that the waiver was\\nunenforceable for lack of consideration. We agree.\\n\\n Under Pennsylvania law, consideration is an essential\\nelement of a valid contract. See Taylor v. Stanley Co. of Am.,\\n158 A. 157, 158 (Pa. 1932); see also Johnston the Florist, Inc.\\nv. TEDCO Constr. Corp., 657 A.2d 511, 516 (Pa. Super. Ct.\\n1995). In addition to the waiver provision excerpted above, the\\nSettlement Agreement includes a provision titled “Adequate\\nConsideration.” This provision states:\\n\\n\\n\\n\\n 7\\n\\f Adequate Consideration. The Parents\\n specifically acknowledge and agree that the\\n District’s agreement to make the above\\n payments is intended to and does provide the\\n Parents with sufficient consideration for a\\n settlement and compromise of any and all\\n outstanding education and discrimination claims\\n that they may now have or have had, whether\\n known or unknown, from the beginning of time\\n through August 31, 2016. The Parents also\\n expressly acknowledge and confirm that: (1) the\\n only consideration for their signing of this\\n Agreement consists of the terms and provisions\\n stated herein; and (2) no other promise or\\n agreement of any kind, save those set forth in this\\n Agreement, has been made by any person or\\n entity whatsoever to cause them to sign the\\n document.\\n\\n(App. 141) (emphasis in original).\\n\\n Rose Tree argues, in conclusory fashion, that the family\\nreceived “adequate” and “substantial consideration for all of\\nthe promises made . . . .” (Appellant’s Br. 6.) G.S. and his\\nparents counter that the “Adequate Consideration” provision of\\nthe Agreement expressly limits consideration to claims arising\\nbefore August 31, 2016, and thus any waiver of claims\\nconcerning the 2016–17 academic year lacks consideration.\\n(Appellees’ Br. 11–12, 15–16.) As the District Court\\nconcluded, the clear and unambiguous language of this\\nprovision states that consideration was only provided for\\nclaims through August 31, 2016, which pre-dates claims\\narising out of the 2016–17 academic year. Accordingly, we\\nagree that any purported waiver of claims arising after August\\n31, 2016 lacks consideration and is unenforceable.\\n\\n\\n\\n\\n 8\\n\\f B.\\n Next, Rose Tree contends it need not enroll G.S.\\nbecause he is no longer “homeless” within the meaning of the\\nAct. Subtitle VII-B of the Act, “Education for Homeless\\nChildren and Youths” (“EHCY”), addresses the educational\\nbarriers faced by homeless children. EHCY preserves the right\\nof equal access to a “free, appropriate public education”\\nindependent of a child’s housing status. 42 U.S.C. § 11431(1).\\nSpecifically, under this subtitle, local education agencies are\\nrequired to continue a homeless child’s education in his or her\\n“school of origin” for the “duration” of his or her homelessness\\nif doing so is in the child’s “best interest.” Id.\\n§ 11432(g)(3)(A)(i). Notably, there is no statutory limit on the\\nduration of homelessness.\\n\\n Whether a child is eligible under EHCY is determined\\nby the Act’s definition of youth homelessness, 42 U.S.C.\\n§ 11434a(2). In relevant part, this definition provides:\\n\\n The term “homeless children and youths”—\\n\\n (A) means individuals who lack a\\n fixed, regular, and adequate\\n nighttime residence (within the\\n meaning of section 11302(a)(1) of\\n this title); and\\n (B) includes—\\n\\n (i) children and youths who\\n are sharing the housing of\\n other persons due to loss of\\n housing, economic\\n hardship, or a similar\\n reason; . . .\\n\\n\\n\\n\\n 9\\n\\fId. § 11434a(2). Children who satisfy § 11434a(2)(B)(i) are\\noften described as living “doubled up.” See U.S. Dep’t of\\nEduc., Education for Homeless Children and Youths Program\\nNon-Regulatory Guidance, 5 (2016),\\nhttps://www2.ed.gov/policy/elsec/leg/essa/160240ehcyguidan\\nce072716.pdf.\\n\\n There is no dispute that G.S. satisfied § 11434a(2) when\\nhe first moved in with his maternal grandmother. Rather, the\\nquestion is whether G.S. continues to satisfy this definition\\nalmost four years later. Rose Tree argues that G.S. no longer\\nlacks a fixed, regular, and adequate nighttime residence due to\\nthe fact that his doubled-up living arrangement has persisted\\nfor several years. We are not convinced.\\n\\n First, Rose Tree’s interpretation is inconsistent with the\\nplain meaning of the statute. There is no dispute that G.S.\\ncontinues to satisfy § 11434a(2)(B)(i), which is listed as a\\nspecific example of youth homelessness. Second, the Act does\\nnot impose a limit on the duration of homelessness. This\\nundermines Rose Tree’s argument that a doubled-up\\narrangement can transform into a fixed, adequate, and regular\\nnighttime residence if it persists long enough. Third, Rose\\nTree fails to cite any authority other than general provisions of\\nthe Act and the dictionary for its interpretation. This is\\nunsurprising—to date, no court has adopted Rose Tree’s\\ninterpretation. Fourth, several circumstances particular to this\\ncase persuade us that G.S. is eligible for coverage. Rose Tree\\ninitially treated G.S. as homeless, and the parties agree his\\nliving arrangements have not changed. It is also compelling\\nthat Rose Tree has continued to enroll G.S.’s similarly situated\\nsister, S.S., throughout the duration of this matter.1 And\\n 1\\n Although S.S. is enrolled, the record is unclear as to\\nwhether Rose Tree still considers her to be homeless within the\\nmeaning of the McKinney-Vento Act. (App. 292–93.) At oral\\n\\n\\n\\n\\n 10\\n\\ffinally, the Pennsylvania Department of Education determined\\nthat G.S. remains homeless. Although we are not bound by the\\nAgency’s determination, we think it is well-reasoned and,\\ntherefore, instructive. To remove G.S. from the protections of\\nthe Act under these circumstances strikes us as nothing short\\nof arbitrary. Accordingly, we agree that G.S. continues to\\nqualify as homeless for purposes of enrollment in a Rose Tree\\nschool.\\n\\n C.\\n\\n Finally, assuming G.S. qualifies as homeless, Rose Tree\\nargues it need not enroll G.S. because enrollment is not in his\\nbest interest. It raises this argument for the first time on appeal\\nand thus we need not consider it. See Caisson Corp. v.\\nIngersoll-Rand Co., 622 F.2d 672, 680 (3d Cir. 1980).\\nNonetheless, we take a moment to reject this argument on its\\nmerits.\\n\\n A school district is required to enroll a homeless student\\nso long as doing so accords with the child’s “best interest.” 42\\nU.S.C. § 11432(g)(3)(A). It is presumed that the best interest\\nof the student is to remain in his or her school of origin unless\\ndoing so is contrary to the request of the parent or youth. Id.\\n§ 11432(g)(3)(B). School of origin “means [either] the school\\nthat a child or youth attended when permanently housed or the\\nschool in which the child or youth was last enrolled, including\\na preschool.” Id. § 11432(g)(3)(I)(i).\\n\\n Here, all of the statutory considerations align to suggest\\nenrollment in Rose Tree is in G.S.’s best interest. Rose Tree\\nhosts the school where G.S. was enrolled when he became\\n\\nargument, the School District took the position that while S.S.\\nwas homeless at the start of the 2016–17 academic year, she\\nmay not be homeless currently.\\n\\n\\n\\n\\n 11\\n\\fhomeless; the school where G.S. was last enrolled; the school\\nwhere his sister attends; and the school where he and his\\nparents seek enrollment. Under these circumstances, we\\nconclude that continued enrollment in Rose Tree is in G.S.’s\\nbest interest.\\n IV.\\n\\n For these reasons, we will affirm the order of the\\nDistrict Court dated July 31, 2017.\\n\\n\\n\\n\\n 12\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360680/\", \"author_raw\": \"Vanaskie. Judge Vanaskie retired from the Court on January\"}]}"},"judge1":{"kind":"string","value":"AMBRO"},"judge2":{"kind":"string","value":"JORDAN"},"judge3":{"kind":"string","value":"VANASKIE"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"AMBRO\": \", Circuit\", \"JORDAN\": \", Circuit\", \"VANASKIE\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583427/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: G.S. v. Rose Tree Media School Distric\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-22\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-2886\n _____________\n\n G.S., a minor, by his parents, J.S. and E.S.\n\n v.\n\n ROSE TREE MEDIA SCHOOL DISTRICT\n (E.D. Pa. No. 2-16-cv-04782)\n\n ROSE TREE MEDIA SCHOOL DISTRICT\n\n v.\n\nE.S. and J.S., Parents and Natural Guardians of G.S., a Minor\n (E.D. Pa. No. 2-16-cv-04849)\n\n Rose Tree Media School District,\n Appellant\n _____________\n On Appeal from the United States District Court\n for the Eastern District of Pennsylvania\n (D.C. Civil Nos. 2-16-cv-04782 & 2-16-cv-04849)\n District Judge: Honorable Eduardo C. Robreno\n ______________\n\n Argued June 4, 2018\n\f ______________\n\n Before: AMBRO, JORDAN,\n and VANASKIE,* Circuit Judges\n\n (Opinion Filed: November 6, 2018)\n\nGabrielle C. Goham, Esq.\nKatherine H. Meehan, Esq. [Argued]\nRaffaele Puppio\n19 West Third Street\nMedia, PA 19063\n Counsel for Appellant\n\nMichael D. Raffaele, Esq. [Argued]\nKershenbaum and Raffaele\n1230 County Line Road\nBryn Mawr, PA 19010\n Counsel for Appellees\n\n\n\n\n*\n On November 6, 2018, the panel issued a not precedential\nopinion in this matter authored by the Honorable Thomas I.\nVanaskie. Judge Vanaskie retired from the Court on January\n1, 2019. After Judge Vanaskie's retirement, amici curiae filed\na motion to issue the opinion as a precedential opinion which\nwas considered by the remaining members of the merits\npanel. Today, the Court has issued the opinion as a\nprecedential per curiam opinion. See 3rd Cir. I.O.P. 12.1 (d).\n\n\n\n\n 2\n\fShannon L.C. Ammon, Esq.\nJeffrey A. Sturgeon, Esq.\nMorgan Lewis & Bockius\n1701 Market Street\nPhiladelphia, PA 19103\n\nMaura McInerney\nEducation Law Center\n1315 Walnut Street, Suite 400\nPhiladelphia, PA 19107\n Counsel for Amicus Appellees\n\n\n ______________\n\n OPINION OF THE COURT\n ______________\n\nPER CURIAM\n\n Appellant Rose Tree Media School District (“Rose\nTree”) appeals the District Court’s grant of summary judgment\nconcluding that Rose Tree was obligated to enroll Appellee\nG.S. under Subtitle VII-B of the McKinney-Vento Homeless\nAssistance Act (“McKinney-Vento” or the “Act”), 42 U.S.C.\n§ 11434a(2) and § 11432(g)(3)(A)(i). We agree with the\nDistrict Court that G.S. satisfies the Act’s definition of youth\nhomelessness because he has been living in his maternal\ngrandmother’s home, along with his parents, ever since his\nparents lost their home in November 2014. Accordingly, we\nwill affirm.\n\n I.\n\n\n\n\n 3\n\f In 2010, G.S., along with his parents, his two sisters,\nand his paternal grandparents, moved into a rental home within\nRose Tree. At the time, G.S. and his sister, S.S., attended\nschools within Rose Tree. In November 2014, G.S.’s parents\nwere unable to make payments and lost the home. As a result,\nG.S. moved in with Ba.S., his maternal grandmother. The\ngrandmother’s single-family, 1500-square-foot row house was\nlocated outside of Rose Tree.\n\n With the addition of G.S., a total of ten people—five\nadults and five children—resided in the grandmother’s home.\nInitially, G.S. slept in the living room with his parents and two\nsisters. At times, G.S. moved his cot to the kitchen or basement\nto obtain some privacy. The parties agree that, to date, G.S.’s\nliving conditions remain unchanged.\n\n Rose Tree immediately learned of the change in G.S.’s\nliving conditions. At that time, Rose Tree deemed G.S. and\nS.S. homeless and thus continued to enroll them in a manner\nconsistent with its obligations under McKinney-Vento,\n42 U.S.C. § 11432(g)(3)(A)(i).\n\n In January 2015—less than two months after G.S.\nmoved in with his maternal grandmother—he was involved in\na disciplinary incident at school. Rose Tree suspended G.S. for\nthree days, extended the suspension to ten days, and threatened\nhim with expulsion. G.S.’s parents challenged Rose Tree’s\nactions. The parties resolved the matter pursuant to a written\nSettlement Agreement. Rose Tree, for its part, agreed to pay\nfor G.S. to attend a school outside of its jurisdiction for the\n2015–16 school year. In exchange, G.S.’s parents agreed to\nwaive all claims through August 31, 2016. The Settlement\nAgreement also included a provision purporting to waive\nG.S.’s right to claim homelessness after the 2015–16 academic\nyear.\n\n\n\n\n 4\n\f Pursuant to the Agreement, G.S. attended a school\noutside Rose Tree for the 2015–16 school year. Following the\nconclusion of that academic year, in July 2016, G.S.’s parents\nnotified Rose Tree of the family’s intent to re-enroll G.S. in\none of its schools for the 2016–17 academic year. Rose Tree\nrefused to enroll G.S., reasoning that his parents had waived\nhis right to claim homelessness and thereby enroll under\nMcKinney-Vento.\n\n G.S.’s parents initiated state grievance proceedings.\nAfter conducting an inquiry, the Pennsylvania Department of\nEducation issued a determination letter, stating:\n\n the outcome of our investigation is\n that [G.S.] . . . ha[s] the right under\n the federal McKinney-Vento\n Homelessness Act to continue\n being educated in the Rose Tree\n Media School District since it is\n [his] school district of origin and\n [he] is temporarily residing in a\n doubled up living situation that is\n not fixed, regular nor adequate.\n\n(App. 365.) G.S.’s parents again attempted to enroll G.S. in\nRose Tree, but the School District again refused.\n Throughout the pendency of this matter, Rose Tree\ncontinued to enroll G.S.’s sister, S.S, in one of its schools. The\nparties do not dispute that S.S.’s living conditions are identical\nto those of G.S.\n\n G.S. and his parents filed suit in federal court, Case No.\n16-4782, against Rose Tree, seeking enrollment. Rose Tree\nfiled a separate lawsuit in federal court, Case No. 16-4849,\nagainst G.S.’s parents, seeking a declaration that it was not\n\n\n\n\n 5\n\fobligated to enroll G.S. The District Court consolidated the\ntwo cases in February 2017. Both parties moved for summary\njudgment. The District Court resolved both motions in a single\norder, finding in favor of G.S. Rose Tree timely appealed. On\nappeal, the Education Law Center, the Homeless Children’s\nEducation Fund, the National Law Center of Homelessness and\nPoverty, and the People’s Emergency Center appear as amici\nin support of G.S.\n\n II.\n\n The District Court had jurisdiction under 28 U.S.C.\n§ 1331. We have appellate jurisdiction under 28 U.S.C.\n§ 1291. We exercise plenary review over a district court’s\ngrant of summary judgment. Blunt v. Lower Merion Sch. Dist.,\n767 F.3d 247, 265 (3d Cir. 2014).\n\n III.\n\n Rose Tree argues that the grant of summary judgment\nin favor of Appellees was erroneous because: (1) G.S.’s\nparents waived his McKinney-Vento rights for the 2016–17\nacademic year in the Settlement Agreement; (2) G.S. is no\nlonger “homeless” within the meaning of the Act; and (3)\nenrollment in Rose Tree is not in G.S.’s “best interest.”\n\n\n\n\n 6\n\f A.\n As a threshold matter, we must determine whether\nG.S.’s parents waived his McKinney-Vento rights in the\nSettlement Agreement. The parties agree that Pennsylvania\nlaw governs our interpretation of the Agreement. Under\nPennsylvania law, “[t]he fundamental rule in contract\ninterpretation is to ascertain the intent of the contracting\nparties.” Ins. Adjustment Bureau, Inc. v. Allstate Ins. Co., 905\nA.2d 462, 468 (Pa. 2006) (internal citation omitted). “In cases\nof a written contract, the intent of the parties is the writing itself\n. . . When the terms of a contract are clear and unambiguous,\nthe intent of the parties is to be ascertained from the document\nitself.” Id. (internal citations omitted).\n\n In relevant part, the Settlement Agreement includes a\nprovision purporting to waive G.S.’s McKinney-Vento rights\nfor the 2016–17 academic year. This provision states:\n\n Parents agree that they will make\n no claim of homeless status after\n the 2015-16 school year and that\n the District will have no further\n obligations to Student after the\n 2015-16 school year.\n\n(App. 140.) The District Court concluded that the waiver was\nunenforceable for lack of consideration. We agree.\n\n Under Pennsylvania law, consideration is an essential\nelement of a valid contract. See Taylor v. Stanley Co. of Am.,\n158 A. 157, 158 (Pa. 1932); see also Johnston the Florist, Inc.\nv. TEDCO Constr. Corp., 657 A.2d 511, 516 (Pa. Super. Ct.\n1995). In addition to the waiver provision excerpted above, the\nSettlement Agreement includes a provision titled “Adequate\nConsideration.” This provision states:\n\n\n\n\n 7\n\f Adequate Consideration. The Parents\n specifically acknowledge and agree that the\n District’s agreement to make the above\n payments is intended to and does provide the\n Parents with sufficient consideration for a\n settlement and compromise of any and all\n outstanding education and discrimination claims\n that they may now have or have had, whether\n known or unknown, from the beginning of time\n through August 31, 2016. The Parents also\n expressly acknowledge and confirm that: (1) the\n only consideration for their signing of this\n Agreement consists of the terms and provisions\n stated herein; and (2) no other promise or\n agreement of any kind, save those set forth in this\n Agreement, has been made by any person or\n entity whatsoever to cause them to sign the\n document.\n\n(App. 141) (emphasis in original).\n\n Rose Tree argues, in conclusory fashion, that the family\nreceived “adequate” and “substantial consideration for all of\nthe promises made . . . .” (Appellant’s Br. 6.) G.S. and his\nparents counter that the “Adequate Consideration” provision of\nthe Agreement expressly limits consideration to claims arising\nbefore August 31, 2016, and thus any waiver of claims\nconcerning the 2016–17 academic year lacks consideration.\n(Appellees’ Br. 11–12, 15–16.) As the District Court\nconcluded, the clear and unambiguous language of this\nprovision states that consideration was only provided for\nclaims through August 31, 2016, which pre-dates claims\narising out of the 2016–17 academic year. Accordingly, we\nagree that any purported waiver of claims arising after August\n31, 2016 lacks consideration and is unenforceable.\n\n\n\n\n 8\n\f B.\n Next, Rose Tree contends it need not enroll G.S.\nbecause he is no longer “homeless” within the meaning of the\nAct. Subtitle VII-B of the Act, “Education for Homeless\nChildren and Youths” (“EHCY”), addresses the educational\nbarriers faced by homeless children. EHCY preserves the right\nof equal access to a “free, appropriate public education”\nindependent of a child’s housing status. 42 U.S.C. § 11431(1).\nSpecifically, under this subtitle, local education agencies are\nrequired to continue a homeless child’s education in his or her\n“school of origin” for the “duration” of his or her homelessness\nif doing so is in the child’s “best interest.” Id.\n§ 11432(g)(3)(A)(i). Notably, there is no statutory limit on the\nduration of homelessness.\n\n Whether a child is eligible under EHCY is determined\nby the Act’s definition of youth homelessness, 42 U.S.C.\n§ 11434a(2). In relevant part, this definition provides:\n\n The term “homeless children and youths”—\n\n (A) means individuals who lack a\n fixed, regular, and adequate\n nighttime residence (within the\n meaning of section 11302(a)(1) of\n this title); and\n (B) includes—\n\n (i) children and youths who\n are sharing the housing of\n other persons due to loss of\n housing, economic\n hardship, or a similar\n reason; . . .\n\n\n\n\n 9\n\fId. § 11434a(2). Children who satisfy § 11434a(2)(B)(i) are\noften described as living “doubled up.” See U.S. Dep’t of\nEduc., Education for Homeless Children and Youths Program\nNon-Regulatory Guidance, 5 (2016),\nhttps://www2.ed.gov/policy/elsec/leg/essa/160240ehcyguidan\nce072716.pdf.\n\n There is no dispute that G.S. satisfied § 11434a(2) when\nhe first moved in with his maternal grandmother. Rather, the\nquestion is whether G.S. continues to satisfy this definition\nalmost four years later. Rose Tree argues that G.S. no longer\nlacks a fixed, regular, and adequate nighttime residence due to\nthe fact that his doubled-up living arrangement has persisted\nfor several years. We are not convinced.\n\n First, Rose Tree’s interpretation is inconsistent with the\nplain meaning of the statute. There is no dispute that G.S.\ncontinues to satisfy § 11434a(2)(B)(i), which is listed as a\nspecific example of youth homelessness. Second, the Act does\nnot impose a limit on the duration of homelessness. This\nundermines Rose Tree’s argument that a doubled-up\narrangement can transform into a fixed, adequate, and regular\nnighttime residence if it persists long enough. Third, Rose\nTree fails to cite any authority other than general provisions of\nthe Act and the dictionary for its interpretation. This is\nunsurprising—to date, no court has adopted Rose Tree’s\ninterpretation. Fourth, several circumstances particular to this\ncase persuade us that G.S. is eligible for coverage. Rose Tree\ninitially treated G.S. as homeless, and the parties agree his\nliving arrangements have not changed. It is also compelling\nthat Rose Tree has continued to enroll G.S.’s similarly situated\nsister, S.S., throughout the duration of this matter.1 And\n 1\n Although S.S. is enrolled, the record is unclear as to\nwhether Rose Tree still considers her to be homeless within the\nmeaning of the McKinney-Vento Act. (App. 292–93.) At oral\n\n\n\n\n 10\n\ffinally, the Pennsylvania Department of Education determined\nthat G.S. remains homeless. Although we are not bound by the\nAgency’s determination, we think it is well-reasoned and,\ntherefore, instructive. To remove G.S. from the protections of\nthe Act under these circumstances strikes us as nothing short\nof arbitrary. Accordingly, we agree that G.S. continues to\nqualify as homeless for purposes of enrollment in a Rose Tree\nschool.\n\n C.\n\n Finally, assuming G.S. qualifies as homeless, Rose Tree\nargues it need not enroll G.S. because enrollment is not in his\nbest interest. It raises this argument for the first time on appeal\nand thus we need not consider it. See Caisson Corp. v.\nIngersoll-Rand Co., 622 F.2d 672, 680 (3d Cir. 1980).\nNonetheless, we take a moment to reject this argument on its\nmerits.\n\n A school district is required to enroll a homeless student\nso long as doing so accords with the child’s “best interest.” 42\nU.S.C. § 11432(g)(3)(A). It is presumed that the best interest\nof the student is to remain in his or her school of origin unless\ndoing so is contrary to the request of the parent or youth. Id.\n§ 11432(g)(3)(B). School of origin “means [either] the school\nthat a child or youth attended when permanently housed or the\nschool in which the child or youth was last enrolled, including\na preschool.” Id. § 11432(g)(3)(I)(i).\n\n Here, all of the statutory considerations align to suggest\nenrollment in Rose Tree is in G.S.’s best interest. Rose Tree\nhosts the school where G.S. was enrolled when he became\n\nargument, the School District took the position that while S.S.\nwas homeless at the start of the 2016–17 academic year, she\nmay not be homeless currently.\n\n\n\n\n 11\n\fhomeless; the school where G.S. was last enrolled; the school\nwhere his sister attends; and the school where he and his\nparents seek enrollment. Under these circumstances, we\nconclude that continued enrollment in Rose Tree is in G.S.’s\nbest interest.\n IV.\n\n For these reasons, we will affirm the order of the\nDistrict Court dated July 31, 2017.\n\n\n\n\n 12\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: G.S. v. Rose Tree Media School Distric\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-22\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-2886\\n _____________\\n\\n G.S., a minor, by his parents, J.S. and E.S.\\n\\n v.\\n\\n ROSE TREE MEDIA SCHOOL DISTRICT\\n (E.D. Pa. No. 2-16-cv-04782)\\n\\n ROSE TREE MEDIA SCHOOL DISTRICT\\n\\n v.\\n\\nE.S. and J.S., Parents and Natural Guardians of G.S., a Minor\\n (E.D. Pa. No. 2-16-cv-04849)\\n\\n Rose Tree Media School District,\\n Appellant\\n _____________\\n On Appeal from the United States District Court\\n for the Eastern District of Pennsylvania\\n (D.C. Civil Nos. 2-16-cv-04782 & 2-16-cv-04849)\\n District Judge: Honorable Eduardo C. Robreno\\n ______________\\n\\n Argued June 4, 2018\\n\\f ______________\\n\\n Before: AMBRO, JORDAN,\\n and VANASKIE,* Circuit Judges\\n\\n (Opinion Filed: November 6, 2018)\\n\\nGabrielle C. Goham, Esq.\\nKatherine H. Meehan, Esq. [Argued]\\nRaffaele Puppio\\n19 West Third Street\\nMedia, PA 19063\\n Counsel for Appellant\\n\\nMichael D. Raffaele, Esq. [Argued]\\nKershenbaum and Raffaele\\n1230 County Line Road\\nBryn Mawr, PA 19010\\n Counsel for Appellees\\n\\n\\n\\n\\n*\\n On November 6, 2018, the panel issued a not precedential\\nopinion in this matter authored by the Honorable Thomas I.\\nVanaskie. Judge Vanaskie retired from the Court on January\\n1, 2019. After Judge Vanaskie's retirement, amici curiae filed\\na motion to issue the opinion as a precedential opinion which\\nwas considered by the remaining members of the merits\\npanel. Today, the Court has issued the opinion as a\\nprecedential per curiam opinion. See 3rd Cir. I.O.P. 12.1 (d).\\n\\n\\n\\n\\n 2\\n\\fShannon L.C. Ammon, Esq.\\nJeffrey A. Sturgeon, Esq.\\nMorgan Lewis & Bockius\\n1701 Market Street\\nPhiladelphia, PA 19103\\n\\nMaura McInerney\\nEducation Law Center\\n1315 Walnut Street, Suite 400\\nPhiladelphia, PA 19107\\n Counsel for Amicus Appellees\\n\\n\\n ______________\\n\\n OPINION OF THE COURT\\n ______________\\n\\nPER CURIAM\\n\\n Appellant Rose Tree Media School District (“Rose\\nTree”) appeals the District Court’s grant of summary judgment\\nconcluding that Rose Tree was obligated to enroll Appellee\\nG.S. under Subtitle VII-B of the McKinney-Vento Homeless\\nAssistance Act (“McKinney-Vento” or the “Act”), 42 U.S.C.\\n§ 11434a(2) and § 11432(g)(3)(A)(i). We agree with the\\nDistrict Court that G.S. satisfies the Act’s definition of youth\\nhomelessness because he has been living in his maternal\\ngrandmother’s home, along with his parents, ever since his\\nparents lost their home in November 2014. Accordingly, we\\nwill affirm.\\n\\n I.\\n\\n\\n\\n\\n 3\\n\\f In 2010, G.S., along with his parents, his two sisters,\\nand his paternal grandparents, moved into a rental home within\\nRose Tree. At the time, G.S. and his sister, S.S., attended\\nschools within Rose Tree. In November 2014, G.S.’s parents\\nwere unable to make payments and lost the home. As a result,\\nG.S. moved in with Ba.S., his maternal grandmother. The\\ngrandmother’s single-family, 1500-square-foot row house was\\nlocated outside of Rose Tree.\\n\\n With the addition of G.S., a total of ten people—five\\nadults and five children—resided in the grandmother’s home.\\nInitially, G.S. slept in the living room with his parents and two\\nsisters. At times, G.S. moved his cot to the kitchen or basement\\nto obtain some privacy. The parties agree that, to date, G.S.’s\\nliving conditions remain unchanged.\\n\\n Rose Tree immediately learned of the change in G.S.’s\\nliving conditions. At that time, Rose Tree deemed G.S. and\\nS.S. homeless and thus continued to enroll them in a manner\\nconsistent with its obligations under McKinney-Vento,\\n42 U.S.C. § 11432(g)(3)(A)(i).\\n\\n In January 2015—less than two months after G.S.\\nmoved in with his maternal grandmother—he was involved in\\na disciplinary incident at school. Rose Tree suspended G.S. for\\nthree days, extended the suspension to ten days, and threatened\\nhim with expulsion. G.S.’s parents challenged Rose Tree’s\\nactions. The parties resolved the matter pursuant to a written\\nSettlement Agreement. Rose Tree, for its part, agreed to pay\\nfor G.S. to attend a school outside of its jurisdiction for the\\n2015–16 school year. In exchange, G.S.’s parents agreed to\\nwaive all claims through August 31, 2016. The Settlement\\nAgreement also included a provision purporting to waive\\nG.S.’s right to claim homelessness after the 2015–16 academic\\nyear.\\n\\n\\n\\n\\n 4\\n\\f Pursuant to the Agreement, G.S. attended a school\\noutside Rose Tree for the 2015–16 school year. Following the\\nconclusion of that academic year, in July 2016, G.S.’s parents\\nnotified Rose Tree of the family’s intent to re-enroll G.S. in\\none of its schools for the 2016–17 academic year. Rose Tree\\nrefused to enroll G.S., reasoning that his parents had waived\\nhis right to claim homelessness and thereby enroll under\\nMcKinney-Vento.\\n\\n G.S.’s parents initiated state grievance proceedings.\\nAfter conducting an inquiry, the Pennsylvania Department of\\nEducation issued a determination letter, stating:\\n\\n the outcome of our investigation is\\n that [G.S.] . . . ha[s] the right under\\n the federal McKinney-Vento\\n Homelessness Act to continue\\n being educated in the Rose Tree\\n Media School District since it is\\n [his] school district of origin and\\n [he] is temporarily residing in a\\n doubled up living situation that is\\n not fixed, regular nor adequate.\\n\\n(App. 365.) G.S.’s parents again attempted to enroll G.S. in\\nRose Tree, but the School District again refused.\\n Throughout the pendency of this matter, Rose Tree\\ncontinued to enroll G.S.’s sister, S.S, in one of its schools. The\\nparties do not dispute that S.S.’s living conditions are identical\\nto those of G.S.\\n\\n G.S. and his parents filed suit in federal court, Case No.\\n16-4782, against Rose Tree, seeking enrollment. Rose Tree\\nfiled a separate lawsuit in federal court, Case No. 16-4849,\\nagainst G.S.’s parents, seeking a declaration that it was not\\n\\n\\n\\n\\n 5\\n\\fobligated to enroll G.S. The District Court consolidated the\\ntwo cases in February 2017. Both parties moved for summary\\njudgment. The District Court resolved both motions in a single\\norder, finding in favor of G.S. Rose Tree timely appealed. On\\nappeal, the Education Law Center, the Homeless Children’s\\nEducation Fund, the National Law Center of Homelessness and\\nPoverty, and the People’s Emergency Center appear as amici\\nin support of G.S.\\n\\n II.\\n\\n The District Court had jurisdiction under 28 U.S.C.\\n§ 1331. We have appellate jurisdiction under 28 U.S.C.\\n§ 1291. We exercise plenary review over a district court’s\\ngrant of summary judgment. Blunt v. Lower Merion Sch. Dist.,\\n767 F.3d 247, 265 (3d Cir. 2014).\\n\\n III.\\n\\n Rose Tree argues that the grant of summary judgment\\nin favor of Appellees was erroneous because: (1) G.S.’s\\nparents waived his McKinney-Vento rights for the 2016–17\\nacademic year in the Settlement Agreement; (2) G.S. is no\\nlonger “homeless” within the meaning of the Act; and (3)\\nenrollment in Rose Tree is not in G.S.’s “best interest.”\\n\\n\\n\\n\\n 6\\n\\f A.\\n As a threshold matter, we must determine whether\\nG.S.’s parents waived his McKinney-Vento rights in the\\nSettlement Agreement. The parties agree that Pennsylvania\\nlaw governs our interpretation of the Agreement. Under\\nPennsylvania law, “[t]he fundamental rule in contract\\ninterpretation is to ascertain the intent of the contracting\\nparties.” Ins. Adjustment Bureau, Inc. v. Allstate Ins. Co., 905\\nA.2d 462, 468 (Pa. 2006) (internal citation omitted). “In cases\\nof a written contract, the intent of the parties is the writing itself\\n. . . When the terms of a contract are clear and unambiguous,\\nthe intent of the parties is to be ascertained from the document\\nitself.” Id. (internal citations omitted).\\n\\n In relevant part, the Settlement Agreement includes a\\nprovision purporting to waive G.S.’s McKinney-Vento rights\\nfor the 2016–17 academic year. This provision states:\\n\\n Parents agree that they will make\\n no claim of homeless status after\\n the 2015-16 school year and that\\n the District will have no further\\n obligations to Student after the\\n 2015-16 school year.\\n\\n(App. 140.) The District Court concluded that the waiver was\\nunenforceable for lack of consideration. We agree.\\n\\n Under Pennsylvania law, consideration is an essential\\nelement of a valid contract. See Taylor v. Stanley Co. of Am.,\\n158 A. 157, 158 (Pa. 1932); see also Johnston the Florist, Inc.\\nv. TEDCO Constr. Corp., 657 A.2d 511, 516 (Pa. Super. Ct.\\n1995). In addition to the waiver provision excerpted above, the\\nSettlement Agreement includes a provision titled “Adequate\\nConsideration.” This provision states:\\n\\n\\n\\n\\n 7\\n\\f Adequate Consideration. The Parents\\n specifically acknowledge and agree that the\\n District’s agreement to make the above\\n payments is intended to and does provide the\\n Parents with sufficient consideration for a\\n settlement and compromise of any and all\\n outstanding education and discrimination claims\\n that they may now have or have had, whether\\n known or unknown, from the beginning of time\\n through August 31, 2016. The Parents also\\n expressly acknowledge and confirm that: (1) the\\n only consideration for their signing of this\\n Agreement consists of the terms and provisions\\n stated herein; and (2) no other promise or\\n agreement of any kind, save those set forth in this\\n Agreement, has been made by any person or\\n entity whatsoever to cause them to sign the\\n document.\\n\\n(App. 141) (emphasis in original).\\n\\n Rose Tree argues, in conclusory fashion, that the family\\nreceived “adequate” and “substantial consideration for all of\\nthe promises made . . . .” (Appellant’s Br. 6.) G.S. and his\\nparents counter that the “Adequate Consideration” provision of\\nthe Agreement expressly limits consideration to claims arising\\nbefore August 31, 2016, and thus any waiver of claims\\nconcerning the 2016–17 academic year lacks consideration.\\n(Appellees’ Br. 11–12, 15–16.) As the District Court\\nconcluded, the clear and unambiguous language of this\\nprovision states that consideration was only provided for\\nclaims through August 31, 2016, which pre-dates claims\\narising out of the 2016–17 academic year. Accordingly, we\\nagree that any purported waiver of claims arising after August\\n31, 2016 lacks consideration and is unenforceable.\\n\\n\\n\\n\\n 8\\n\\f B.\\n Next, Rose Tree contends it need not enroll G.S.\\nbecause he is no longer “homeless” within the meaning of the\\nAct. Subtitle VII-B of the Act, “Education for Homeless\\nChildren and Youths” (“EHCY”), addresses the educational\\nbarriers faced by homeless children. EHCY preserves the right\\nof equal access to a “free, appropriate public education”\\nindependent of a child’s housing status. 42 U.S.C. § 11431(1).\\nSpecifically, under this subtitle, local education agencies are\\nrequired to continue a homeless child’s education in his or her\\n“school of origin” for the “duration” of his or her homelessness\\nif doing so is in the child’s “best interest.” Id.\\n§ 11432(g)(3)(A)(i). Notably, there is no statutory limit on the\\nduration of homelessness.\\n\\n Whether a child is eligible under EHCY is determined\\nby the Act’s definition of youth homelessness, 42 U.S.C.\\n§ 11434a(2). In relevant part, this definition provides:\\n\\n The term “homeless children and youths”—\\n\\n (A) means individuals who lack a\\n fixed, regular, and adequate\\n nighttime residence (within the\\n meaning of section 11302(a)(1) of\\n this title); and\\n (B) includes—\\n\\n (i) children and youths who\\n are sharing the housing of\\n other persons due to loss of\\n housing, economic\\n hardship, or a similar\\n reason; . . .\\n\\n\\n\\n\\n 9\\n\\fId. § 11434a(2). Children who satisfy § 11434a(2)(B)(i) are\\noften described as living “doubled up.” See U.S. Dep’t of\\nEduc., Education for Homeless Children and Youths Program\\nNon-Regulatory Guidance, 5 (2016),\\nhttps://www2.ed.gov/policy/elsec/leg/essa/160240ehcyguidan\\nce072716.pdf.\\n\\n There is no dispute that G.S. satisfied § 11434a(2) when\\nhe first moved in with his maternal grandmother. Rather, the\\nquestion is whether G.S. continues to satisfy this definition\\nalmost four years later. Rose Tree argues that G.S. no longer\\nlacks a fixed, regular, and adequate nighttime residence due to\\nthe fact that his doubled-up living arrangement has persisted\\nfor several years. We are not convinced.\\n\\n First, Rose Tree’s interpretation is inconsistent with the\\nplain meaning of the statute. There is no dispute that G.S.\\ncontinues to satisfy § 11434a(2)(B)(i), which is listed as a\\nspecific example of youth homelessness. Second, the Act does\\nnot impose a limit on the duration of homelessness. This\\nundermines Rose Tree’s argument that a doubled-up\\narrangement can transform into a fixed, adequate, and regular\\nnighttime residence if it persists long enough. Third, Rose\\nTree fails to cite any authority other than general provisions of\\nthe Act and the dictionary for its interpretation. This is\\nunsurprising—to date, no court has adopted Rose Tree’s\\ninterpretation. Fourth, several circumstances particular to this\\ncase persuade us that G.S. is eligible for coverage. Rose Tree\\ninitially treated G.S. as homeless, and the parties agree his\\nliving arrangements have not changed. It is also compelling\\nthat Rose Tree has continued to enroll G.S.’s similarly situated\\nsister, S.S., throughout the duration of this matter.1 And\\n 1\\n Although S.S. is enrolled, the record is unclear as to\\nwhether Rose Tree still considers her to be homeless within the\\nmeaning of the McKinney-Vento Act. (App. 292–93.) At oral\\n\\n\\n\\n\\n 10\\n\\ffinally, the Pennsylvania Department of Education determined\\nthat G.S. remains homeless. Although we are not bound by the\\nAgency’s determination, we think it is well-reasoned and,\\ntherefore, instructive. To remove G.S. from the protections of\\nthe Act under these circumstances strikes us as nothing short\\nof arbitrary. Accordingly, we agree that G.S. continues to\\nqualify as homeless for purposes of enrollment in a Rose Tree\\nschool.\\n\\n C.\\n\\n Finally, assuming G.S. qualifies as homeless, Rose Tree\\nargues it need not enroll G.S. because enrollment is not in his\\nbest interest. It raises this argument for the first time on appeal\\nand thus we need not consider it. See Caisson Corp. v.\\nIngersoll-Rand Co., 622 F.2d 672, 680 (3d Cir. 1980).\\nNonetheless, we take a moment to reject this argument on its\\nmerits.\\n\\n A school district is required to enroll a homeless student\\nso long as doing so accords with the child’s “best interest.” 42\\nU.S.C. § 11432(g)(3)(A). It is presumed that the best interest\\nof the student is to remain in his or her school of origin unless\\ndoing so is contrary to the request of the parent or youth. Id.\\n§ 11432(g)(3)(B). School of origin “means [either] the school\\nthat a child or youth attended when permanently housed or the\\nschool in which the child or youth was last enrolled, including\\na preschool.” Id. § 11432(g)(3)(I)(i).\\n\\n Here, all of the statutory considerations align to suggest\\nenrollment in Rose Tree is in G.S.’s best interest. Rose Tree\\nhosts the school where G.S. was enrolled when he became\\n\\nargument, the School District took the position that while S.S.\\nwas homeless at the start of the 2016–17 academic year, she\\nmay not be homeless currently.\\n\\n\\n\\n\\n 11\\n\\fhomeless; the school where G.S. was last enrolled; the school\\nwhere his sister attends; and the school where he and his\\nparents seek enrollment. Under these circumstances, we\\nconclude that continued enrollment in Rose Tree is in G.S.’s\\nbest interest.\\n IV.\\n\\n For these reasons, we will affirm the order of the\\nDistrict Court dated July 31, 2017.\\n\\n\\n\\n\\n 12\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":74,"cells":{"id":{"kind":"number","value":4583849,"string":"4,583,849"},"name":{"kind":"string","value":"FEDERAL TRADE COMMISSION; Commonwealth of Pennsylvania v. PENN STATE HERSHEY MEDICAL CENTER; Pinnacle Health System Commonwealth of Pennsylvania, Appellant"},"name_abbreviation":{"kind":"string","value":"Fed. Trade Comm'n v. Penn State Hershey Med. Ctr."},"decision_date":{"kind":"string","value":"2019-01-23"},"docket_number":{"kind":"string","value":"17-2270"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Shwartz, Nygaard, Rendell\", \"parties\": \"\", \"opinions\": [{\"author\": \"NYGAARD, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n\\n __________\\n\\n No. 17-2270\\n __________\\n\\n FEDERAL TRADE COMMISSION;\\n COMMONWEALTH OF PENNSYLVANIA\\n\\n v.\\n\\n PENN STATE HERSHEY MEDICAL CENTER;\\n PINNACLE HEALTH SYSTEM\\n\\n Commonwealth of Pennsylvania,\\n\\n Appellant\\n __________\\n\\n On Appeal from the United States District Court\\n for the Middle District of Pennsylvania\\n (District Court Civil No. 1-15-cv-02362)\\n District Judge: Honorable John E. Jones III\\n\\n Argued July 10, 2018\\n\\nBEFORE: SHWARTZ, NYGAARD, and RENDELL,\\n Circuit Judges.\\n\\f (Filed: January 23, 2019)\\n\\n\\nWesley G. Carson, Esq.\\nPeggy Bayer Femenella, Esq.\\nJames W. Frost, Esq.\\nLynda Lao, Esq.\\nFederal Trade Commission\\n600 Pennsylvania Avenue, N.W.\\nWashington, DC 20580\\n\\nWilliam H. Efron, Esq.\\nRyan F. Harsch, Esq.\\nJared P. Nagley, Esq.\\nJonathan W. Platt, Esq.\\nGerald A. Stein, Esq.\\nGeralyn J. Trujillo, Esq.\\nNancy Turnblacer, Esq.\\nTheodore Zang, Esq.\\nFederal Trade Commission\\nOne Bowling Green\\nSuite 318\\nNew York, NY 10004\\n\\n Counsel for Plaintiff Federal Trade Commission\\n\\nHoward G. Hopkirk, Esq. [Argued]\\nTracy W. Wertz, Esq.\\nOffice of Attorney General of Pennsylvania\\nStrawberry Square\\nHarrisburg, PA 17120\\n\\n\\n\\n\\n 2\\n\\fKemal A. Mericli, Esq.\\nOffice of Attorney General of Pennsylvania\\n1251 Waterfront Place\\nPittsburgh, PA 15222\\n\\n Counsel for Appellant Commonwealth of Pennsylvania\\n\\n\\nWilliam D. Coglianese, Esq. [Argued]\\nChristopher N. Thatch, Esq.\\nAdrian Wager-Zito, Esq.\\nJones Day\\n51 Louisiana Avenue, N.W.\\nWashington, DC 20001\\n\\n Counsel for Appellees Penn State Hershey Medical\\n and Pinnacle Health System\\n\\nLuminita Nodit, Esq.\\nOffice of Attorney General of Washington\\n800 Fifth Avenue\\nSuite 2000\\nSeattle, WA 98104\\n\\n Counsel for Amicus Appellants\\n\\n __________\\n\\n OPINION OF THE COURT\\n __________\\n\\nNYGAARD, Circuit Judge.\\n\\n\\n\\n\\n 3\\n\\f I.\\n\\n In March 2015, the Boards of Penn State Hershey\\nMedical Center and PinnacleHealth System (“Hershey” and\\n“Pinnacle,” respectively) formally approved a plan to merge.\\nThey had announced the proposal a year earlier, so the\\nCommonwealth of Pennsylvania and the Federal Trade\\nCommission (“FTC”) were already investigating the impact\\nof the proposed merger when the Boards approved it. This\\njoint probe resulted in the FTC filing an administrative\\ncomplaint alleging that the merger violated Section 7 of the\\nClayton Act. 1 The FTC scheduled an administrative hearing\\non the merits for May 2016. At the same time, the\\nCommonwealth and the FTC jointly sued Hershey and\\nPinnacle under Section 16 of the Clayton Act, 2 and Section\\n13(b) of the Federal Trade Commission Act (“FTC Act”), 3 to\\n“prevent and restrain Hershey and Pinnacle from violating\\nSection 7 of the Clayton Act . . . pending the Commission’s\\nadministrative proceeding.” 4 They sought a preliminary\\ninjunction and a temporary restraining order.\\n\\n The District Court denied relief. 5 But, on September\\n27, 2016, we reversed the District Court’s order and directed\\nit to preliminarily enjoin the merger “pending the outcome of\\n\\n1\\n 15 U.S.C. § 18.\\n2\\n 15 U.S.C. § 26.\\n3\\n 15 U.S.C. § 53(b).\\n4\\n Amended Complaint at 7 ¶ 14, FTC v. Penn State Hershey\\nMed. Ctr., 185 F. Supp. 3d 552 (M.D. Pa. 2016) (No. 1:15-\\ncv-2362) (“Hershey I”).\\n5\\n Hershey I, 185 F. Supp. 3d at 564.\\n\\n\\n\\n\\n 4\\n\\fthe FTC’s administrative adjudication.” 6 Within three weeks,\\nHershey and Pinnacle terminated their Agreement,\\nreferencing our remand ordering the temporary injunction as\\nthe impetus. The District Court ultimately issued the\\ninjunction on October 20, 2016.\\n\\n The Commonwealth then moved for attorneys’ fees\\nand costs, asserting that it “substantially prevailed” under\\nSection 16 of the Clayton Act, but the District Court denied\\nthe motion. 7 In doing so, the District Court rejected\\nHershey’s and Pinnacle’s argument that the Commonwealth\\ncould not seek attorneys’ fees and costs under Section 16 of\\nthe Clayton Act because, in ordering the injunction, we\\napplied Section 13(b) of the FTC Act instead. The District\\nCourt denied the fee request, however, because the\\nCommonwealth had not “substantially prevailed” under\\nSection 16 of the Clayton Act. The Commonwealth timely\\nappealed. We will affirm, because we credit Hershey’s and\\nPinnacle’s argument that we ordered the injunction based on\\nSection 13(b) of the FTC Act, not Section 16 of the Clayton\\nAct.\\n\\n II.\\n\\n\\n\\n\\n6\\n FTC v. Penn State Hershey Med. Ctr., 838 F.3d 327, 354\\n(3d Cir. 2016) (“Hershey II”).\\n7\\n FTC v. Penn State Hershey Med. Ctr., No. 1:15-cv-2362,\\n2017 WL 1954398, at *9 (M.D. Pa. May 11, 2017) (“Hershey\\nIII”).\\n\\n\\n\\n\\n 5\\n\\f Ordinarily, we review the District Court’s denial of\\nattorneys’ fees for abuse of discretion. 8 As explained below,\\nhowever, our decision turns on the legal question as to which\\nstatute applies. Our review of that legal question is plenary. 9\\n\\n III.\\n\\n The American Rule, grounded in longstanding\\ncommon law tradition, requires parties to pay their own legal\\ncosts “win or lose, unless a statute or contract provides\\notherwise.” 10 One such statute is Section 16 of the Clayton\\nAct. That section provides in relevant part:\\n\\n Any person, firm, corporation, or\\n association shall be entitled to sue\\n for and have injunctive relief, in\\n any court of the United States\\n having jurisdiction over the\\n parties, against threatened loss or\\n damage by a violation of the\\n antitrust laws . . . . In any action\\n under this section in which the\\n plaintiff substantially prevails, the\\n court shall award the cost of suit,\\n including a reasonable attorney’s\\n fee, to such plaintiff. 11\\n\\n8\\n Raab v. City of Ocean City, 833 F.3d 286, 292 (3d Cir.\\n2016).\\n9\\n See id.\\n10\\n Baker Botts L.L.P. v. ASARCO LLC, 135 S. Ct. 2158, 2164\\n(2015).\\n11\\n 15 U.S.C. § 26.\\n\\n\\n\\n\\n 6\\n\\f The District Court concluded that the Commonwealth\\ndid not “substantially prevail” under this section for two\\nreasons. First, the District Court ruled that the termination of\\nthe merger did not render the Commonwealth a prevailing\\nparty because the injunction itself did not terminate the\\nmerger and, even though the injunction motivated Hershey\\nand Pinnacle to do so on their own, the Supreme Court has\\nrejected the “catalyst theory” of prevailing-party status. 12\\nSecond, the District Court determined that, because our ruling\\nwas based on the holding that the Commonwealth and FTC\\nwere merely likely to succeed on the merits, our ruling was\\nnot a grant of relief “on the merits” as required for prevailing-\\nparty status by Singer Management Consultants, Inc. v.\\nMilgram. 13\\n\\n The Commonwealth contests both conclusions. But\\nHershey and Pinnacle argue that we need not address them\\nbecause Section 16 of the Clayton Act and its attorneys’ fees\\nprovision do not apply at all. Hershey and Pinnacle contend\\nthat the preliminary injunction on which the Commonwealth\\nrelies for its claim of attorneys’ fees was not entered “in an\\naction under this section” as required for application of\\nSection 16 of the Clayton Act. Instead, they argue, the\\ninjunction was issued under the authority of Section 13(b) of\\nthe FTC Act, which does not provide for attorneys’ fees. 14\\nThus, they argue, the Commonwealth does not have any legal\\nground to claim entitlement to attorneys’ fees on the basis of\\n\\n12\\n See Buckhannon Bd. & Care Home, Inc. v. W. Va. Dep’t of\\nHealth & Human Res., 532 U.S. 598, 605, 610 (2001).\\n13\\n 650 F.3d 223, 228-29 (3d Cir. 2011) (en banc).\\n14\\n 15 U.S.C. § 53(b).\\n\\n\\n\\n\\n 7\\n\\fthe injunction (or the merger termination that it prompted) in\\nthis case.\\n\\n We ultimately agree with Hershey and Pinnacle. We\\nwill therefore assume without deciding that the\\nCommonwealth is a prevailing party, leaving for another day\\nthe questions of whether the Supreme Court’s rejection of the\\ncatalyst theory controls claims for fees under Section 16 of\\nthe Clayton Act and whether a preliminary injunction entered\\npursuant to that section can constitute relief “on the merits.”\\nOur sole focus here is to examine the Commonwealth’s claim\\nthat it has a statutory basis to be awarded its fees.\\n\\n\\n IV.\\n\\n We conclude that it does not. The Commonwealth\\nclaims attorneys’ fees under Section 16 of the Clayton Act.\\nThe District Court noted that, in ordering the injunction, our\\nCourt “solely applied the standard outlined by Section 13(b)\\nof the FTC Act.” 15 And, as noted above, Section 13(b) of the\\nFTC Act makes no provision for attorneys’ fees. The District\\nCourt nevertheless determined that the Commonwealth was\\npotentially entitled to fees under Section 16 of the Clayton\\nAct because the Commonwealth referenced that section when\\nit joined with the FTC to seek a preliminary injunction\\nagainst Hershey and Pinnacle, 16 and policy and Supreme\\nCourt precedent supported the allowance of fees.\\n\\n\\n\\n\\n15\\n Hershey III, 2017 WL 1954398, at *2.\\n16\\n Id. at *3.\\n\\n\\n\\n\\n 8\\n\\f The District Court’s initial conclusion that we ordered\\nthe injunction under Section 13(b) of the FTC Act and not\\nSection 16 of the Clayton act was correct, and its inquiry\\nshould have ended there. The strongest indication that the\\ninjunction rested solely on Section 13(b) of the FTC Act was\\nthe standard that we used in ordering that injunction. When\\nconsidering requests for injunctive relief under Section 16 of\\nthe Clayton Act, courts generally apply the traditional four-\\npart preliminary injunction standard that includes a\\nconsideration of: (1) the likelihood of success on the merits;\\n(2) the threat of irreparable harm in the absence of an\\ninjunction; (3) the possibility of substantial harm to other\\ninterested parties; and (4) the public interest. 17 In ordering\\nthe injunction in Hershey II, we referenced the “traditional\\nequity standard for injunctive relief,” 18 but we did not use it.\\nInstead, we determined that the standard governing\\ninjunctions under Section 13(b) of the FTC Act is different,\\nand we went on to apply that different standard. 19\\n\\n In particular, and drawing directly from the statute, we\\nsaid that the question of preliminary injunctive relief under\\nSection 13(b) of the FTC Act is resolved by “weighing the\\nequities and considering the Commission’s likelihood of\\nultimate success” to determine whether “such action would be\\nin the public interest.” 20 In doing so, we emphasized that the\\n\\n17\\n See Holland v. Rosen, 895 F.3d 272, 285-86 (3d Cir. 2018)\\ncert. denied 139 S. Ct. 440 (2018); see also Julian O. von\\nKalinowski, Antitrust Laws and Trade Regulations §\\n172.02[3][b] & n.60 (2d ed. 2018) (collecting cases).\\n18\\n Hershey II, 838 F.3d at 337.\\n19\\n Id.\\n20\\n Id. (quoting 15 U.S.C. § 53(b)).\\n\\n\\n\\n\\n 9\\n\\fpublic interest standard in the second prong of this analysis\\ndiffers from “the traditional equity standard for injunctive\\nrelief.” 21 This assessment aligns with the judgment of other\\nCourts of Appeals, which have concluded that the Section\\n13(b) standard is not only different from, but easier to satisfy\\nthan the traditional standard for injunctive relief that courts\\napply to claims under Section 16 of the Clayton Act. 22\\n\\n In sum, in ordering the injunction on which the\\nCommonwealth relies, we expressly applied Section 13(b) of\\nthe FTC Act and its lower evidentiary bar instead of Section\\n16 of the Clayton Act. Thus, to the extent that the\\nCommonwealth can be said to have “prevailed,” it did so\\nunder Section 13(b) of the FTC Act and not Section 16 of the\\nClayton Act. For similar reasons, the only court of which we\\nare aware to have addressed the issue has concluded that an\\ninjunction issued under Section 13(b) of the FTC Act does\\nnot trigger potential entitlement to attorneys’ fees under\\n\\n\\n\\n\\n21\\n Id.\\n22\\n See, e.g., FTC v. H.J. Heinz Co., 246 F.3d 708, 714 (D.C.\\nCir. 2001) (explaining that Congress, in drafting Section\\n13(b), “intended th[e Section 13(b)] standard to depart from .\\n. . the then-traditional equity standard” so that the FTC “was\\nnot held to the high thresholds applicable where private\\nparties seek interim restraining orders”) (quotation marks\\nomitted); FTC v. Affordable Media, LLC, 179 F.3d 1228,\\n1233 (9th Cir. 1999) (recognizing that Section 13(b) “places a\\nlighter burden on the Commission than that imposed on\\nprivate litigants by the traditional equity standard”)(quotation\\nmarks omitted).\\n\\n\\n\\n\\n 10\\n\\fSection 16 of the Clayton Act. 23 We agree with that\\nconclusion.\\n\\n The District Court relied on a number of factors in\\nconcluding otherwise, but none is persuasive. The District\\nCourt first pointed to the legislative history of the Clayton\\nAct to justify its relevance here. It noted that “Congress\\nintended that an individual plaintiff should not bear ‘the very\\nhigh price of obtaining judicial enforcement of . . . the\\nantitrust laws.’” 24 However, we have examined the extensive\\nhistory of this Act and find nothing that clearly shows\\nCongress’s intent to empower us to extend the fee-shifting\\nprovision of the Clayton Act to cover an action for injunctive\\nrelief under another statute. 25 As a result, we are not\\npersuaded that the legislative history of the Clayton Act\\nsupports the District Court’s conclusion.\\n\\n The District Court also cited Supreme Court precedent,\\nMaher v. Gagne, 26 for the proposition that the fee-shifting\\nprovisions of one statute can apply to pendent claims brought\\nunder other statutes. Maher, however, does not support\\n\\n23\\n See FTC v. Staples, Inc., 239 F. Supp. 3d 1, 4-5 (D.D.C.\\n2017).\\n24\\n Hershey III, 2017 WL 1954398, at *3 (quoting H.R. Rep.\\nNo. 94-499, part 1, at 19-20 (1976)).\\n25\\n See H.R. Rep. No. 94-499, pt. 1, at 18-20 (1976); see also\\nBuckhannon Bd., 532 U.S. at 608 (holding that, “in view of\\nthe ‘American Rule’ that attorney’s fees will not be awarded\\nabsent explicit statutory authority, . . . [ambiguous] legislative\\nhistory is clearly insufficient to alter the accepted meaning of\\nthe statutory term”) (quotation marks omitted).\\n26\\n 448 U.S. 122 (1980).\\n\\n\\n\\n\\n 11\\n\\fapplication of the Clayton Act’s fee-shifting provision in this\\ncase. In Maher, the plaintiff brought claims under 42 U.S.C.\\n§ 1983, alleging that Connecticut’s Aid to Families with\\nDependent Children program violated Section 402(a)(7) of\\nthe Social Security Act, 27 as well as the Equal Protection and\\nDue Process Clauses of the Fourteenth Amendment. 28 After\\nthe District Court approved a settlement between the parties,\\nthe plaintiff sought attorneys’ fees under 42 U.S.C. § 1988,\\nwhich authorizes fees for parties who prevail under Section\\n1983 (among other statutes). Responding to objections that\\nthe Eleventh Amendment prevented a federal court from\\nordering fees against a state for statutory, non-civil rights\\nclaims like the plaintiff’s claim under the Social Security Act,\\nthe Supreme Court held that Section 1988 allows for “the\\naward of fees in a case in which the plaintiff prevails on a\\nwholly statutory, non-civil-rights claim pendent to a\\nsubstantial constitutional claim or in one in which both a\\nstatutory and a substantial constitutional claim are settled\\nfavorably to the plaintiff without adjudication.” 29 The Court\\nwent on to say: “The legislative history makes it clear that\\nCongress intended fees to be awarded where a pendent\\nconstitutional claim is involved, even if the statutory claim on\\nwhich the plaintiff prevailed is one for which fees cannot be\\nawarded under the Act.” 30\\n\\n Stretching the logic of Maher, the Commonwealth\\nargues that it is entitled to attorneys’ fees because its claim\\nunder Section 16 of the Clayton Act was pendent to the\\n\\n27\\n 42 U.S.C. § 602(a)(7).\\n28\\n Maher, 448 U.S. at 125.\\n29\\n Id. at 132.\\n30\\n Id. at 132 n.15.\\n\\n\\n\\n\\n 12\\n\\fFTC’s claim under Section 13(b) of the FTC Act. But the\\nissue in Maher was fundamentally different. The issue in\\nMaher was whether the plaintiff’s including the Social\\nSecurity Act violation in its Section 1983 complaint\\ndisqualified it from receiving fees authorized by Section\\n1988. The theory was that the fees were only to vindicate\\nviolations of the Fourteenth Amendment. But the Supreme\\nCourt held that the plaintiff could recover attorneys’ fees\\nunder Section 1988 because she had alleged violations of her\\nFourteenth Amendment Due Process and Equal Protection\\nrights. As for the fact that she had also alleged a purely\\nstatutory violation (of the Social Security Act), the Supreme\\nCourt held that this did not preclude an award of attorneys’\\nfees under Section 1988 because this was pendant to the\\nconstitutional claims. 31\\n\\n But—as we noted earlier—Section 16 of the Clayton\\nAct specifies that a party must substantially prevail “[i]n any\\naction under this section.” 32 This language limits the\\napplication of Chapter 13’s fee-shifting provision to parties\\nwho obtain relief under that section. 33 As we noted above,\\nrequests for relief under that section are assessed on a\\n\\n31\\n Id. at 132.\\n32\\n 15 U.S.C. § 26 (emphasis added).\\n33\\n See John T. ex rel. Paul T. v. Del. Cty. Intermediate Unit,\\n318 F.3d 545, 560 (3d Cir. 2003) (“When the [Individuals\\nwith Disabilities Education Act] fee-shifting provision\\nauthorizes attorneys[’] fees ‘in any action or proceeding\\nbrought under this section,’ it not only limits the universe to\\nwhich it applies but also clarifies the type of proceeding on\\nwhich a party must ‘prevail.’”) (first emphasis added)\\n(quoting 20 U.S.C. § 1415(i)(3)).\\n\\n\\n\\n\\n 13\\n\\fdifferent and more lenient standard than are requests for relief\\nunder Section 16 of the Clayton Act, and we clearly decided\\nthat the injunction should issue based on the standard of\\nSection 13(b), not Section 16. Such differences were not\\nevident in Maher. As also noted above, the legislative history\\ndoes not justify extending the Clayton Act’s fee-shifting\\nprovisions to other statutory schemes. For all of these\\nreasons, we are not persuaded that Maher gives us any basis\\nto extend the fee-shifting provisions of the Clayton Act to a\\nclaim raised and adjudicated under the FTC Act. 34\\n\\n34\\n The Commonwealth maintains that it did raise its claim\\nunder the Clayton Act and that we acknowledged this in\\nHershey II. It is true that we referenced both the Clayton Act\\nand the FTC Act as a basis for the suit brought jointly by the\\nCommonwealth and the FTC. In particular, we noted that the\\nCommonwealth and the FTC “filed suit . . . under” both\\nSection 16 of the Clayton Act and Section 13(b) of the FTC\\nAct, Hershey II, 838 F.3d at 333, and we also stated that\\n“[t]he District Court had jurisdiction” under both Section 16\\nof the Clayton Act and Section 13(b) of the FTC Act, id. at\\n335. But the Commonwealth does not have standing to\\npursue a claim under the FTC Act, and these statements\\nmerely declare that the Clayton Act gave them standing in\\nthis case. The issue of standing aside, the facts remain that\\nthe Commonwealth and the FTC litigated their request for an\\ninjunction under Section 13(b) of the FTC Act and that we\\nordered the injunction under that section and the more lenient\\nstandard that applies thereto. As one court explained in\\nrejecting the Commonwealth’s claim for attorneys’ fees in a\\nsimilar case, the Commonwealth “cannot have it both ways”\\nby “rid[ing] the FTC’s claim to a successful preliminary\\ninjunction under the more permissive Section 13(b) standard\\n\\n\\n\\n\\n 14\\n\\f Finally, the District Court raised concerns that failing\\nto allow the Commonwealth to seek attorneys’ fees in this\\nsituation would be contrary to the interests of judicial\\neconomy. Forcing the Commonwealth to pursue a separate\\ncase to bring a claim under Section 16, the District Court said,\\ncould result in “duplicative litigation, separate filings, and\\nrepetitive arguments” because this would be the only avenue\\nfor claiming attorneys’ fees. 35 We are not persuaded that\\nsuch concerns outweigh the plain language of the statutes.\\n\\n V.\\n\\n In sum, we conclude that the authority for this\\ninjunction arose from Section 13(b) of the FTC Act, which—\\nunlike Section 16 of the Clayton Act—does not provide for\\nattorneys’ fees. Hence, for all of the foregoing reasons, the\\nCommonwealth has no legal basis to claim attorneys’ fees in\\nthis case and we will affirm the order of the District Court on\\nthat ground.\\n\\n\\n\\n\\nand then cit[ing] that favorable ruling as the sole justification\\nfor fee-shifting under the more rigorous Clayton Act\\nstandard.” Staples, 239 F. Supp. 3d at 5.\\n35\\n Hershey III, 2017 WL 1954398, at *3.\\n\\n\\n\\n\\n 15\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4361102/\", \"author_raw\": \"NYGAARD, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"SHWARTZ"},"judge2":{"kind":"string","value":"NYGAARD"},"judge3":{"kind":"string","value":"RENDELL"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583849/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: FEDERAL TRADE COMMISSION; Commonwealth of Pennsylvania v. PENN STATE HERSHEY MEDICAL CENTER; Pinnacle Health System Commonwealth of Pennsylvania, Appellant\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-23\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n\n __________\n\n No. 17-2270\n __________\n\n FEDERAL TRADE COMMISSION;\n COMMONWEALTH OF PENNSYLVANIA\n\n v.\n\n PENN STATE HERSHEY MEDICAL CENTER;\n PINNACLE HEALTH SYSTEM\n\n Commonwealth of Pennsylvania,\n\n Appellant\n __________\n\n On Appeal from the United States District Court\n for the Middle District of Pennsylvania\n (District Court Civil No. 1-15-cv-02362)\n District Judge: Honorable John E. Jones III\n\n Argued July 10, 2018\n\nBEFORE: SHWARTZ, NYGAARD, and RENDELL,\n Circuit Judges.\n\f (Filed: January 23, 2019)\n\n\nWesley G. Carson, Esq.\nPeggy Bayer Femenella, Esq.\nJames W. Frost, Esq.\nLynda Lao, Esq.\nFederal Trade Commission\n600 Pennsylvania Avenue, N.W.\nWashington, DC 20580\n\nWilliam H. Efron, Esq.\nRyan F. Harsch, Esq.\nJared P. Nagley, Esq.\nJonathan W. Platt, Esq.\nGerald A. Stein, Esq.\nGeralyn J. Trujillo, Esq.\nNancy Turnblacer, Esq.\nTheodore Zang, Esq.\nFederal Trade Commission\nOne Bowling Green\nSuite 318\nNew York, NY 10004\n\n Counsel for Plaintiff Federal Trade Commission\n\nHoward G. Hopkirk, Esq. [Argued]\nTracy W. Wertz, Esq.\nOffice of Attorney General of Pennsylvania\nStrawberry Square\nHarrisburg, PA 17120\n\n\n\n\n 2\n\fKemal A. Mericli, Esq.\nOffice of Attorney General of Pennsylvania\n1251 Waterfront Place\nPittsburgh, PA 15222\n\n Counsel for Appellant Commonwealth of Pennsylvania\n\n\nWilliam D. Coglianese, Esq. [Argued]\nChristopher N. Thatch, Esq.\nAdrian Wager-Zito, Esq.\nJones Day\n51 Louisiana Avenue, N.W.\nWashington, DC 20001\n\n Counsel for Appellees Penn State Hershey Medical\n and Pinnacle Health System\n\nLuminita Nodit, Esq.\nOffice of Attorney General of Washington\n800 Fifth Avenue\nSuite 2000\nSeattle, WA 98104\n\n Counsel for Amicus Appellants\n\n __________\n\n OPINION OF THE COURT\n __________\n\nNYGAARD, Circuit Judge.\n\n\n\n\n 3\n\f I.\n\n In March 2015, the Boards of Penn State Hershey\nMedical Center and PinnacleHealth System (“Hershey” and\n“Pinnacle,” respectively) formally approved a plan to merge.\nThey had announced the proposal a year earlier, so the\nCommonwealth of Pennsylvania and the Federal Trade\nCommission (“FTC”) were already investigating the impact\nof the proposed merger when the Boards approved it. This\njoint probe resulted in the FTC filing an administrative\ncomplaint alleging that the merger violated Section 7 of the\nClayton Act. 1 The FTC scheduled an administrative hearing\non the merits for May 2016. At the same time, the\nCommonwealth and the FTC jointly sued Hershey and\nPinnacle under Section 16 of the Clayton Act, 2 and Section\n13(b) of the Federal Trade Commission Act (“FTC Act”), 3 to\n“prevent and restrain Hershey and Pinnacle from violating\nSection 7 of the Clayton Act . . . pending the Commission’s\nadministrative proceeding.” 4 They sought a preliminary\ninjunction and a temporary restraining order.\n\n The District Court denied relief. 5 But, on September\n27, 2016, we reversed the District Court’s order and directed\nit to preliminarily enjoin the merger “pending the outcome of\n\n1\n 15 U.S.C. § 18.\n2\n 15 U.S.C. § 26.\n3\n 15 U.S.C. § 53(b).\n4\n Amended Complaint at 7 ¶ 14, FTC v. Penn State Hershey\nMed. Ctr., 185 F. Supp. 3d 552 (M.D. Pa. 2016) (No. 1:15-\ncv-2362) (“Hershey I”).\n5\n Hershey I, 185 F. Supp. 3d at 564.\n\n\n\n\n 4\n\fthe FTC’s administrative adjudication.” 6 Within three weeks,\nHershey and Pinnacle terminated their Agreement,\nreferencing our remand ordering the temporary injunction as\nthe impetus. The District Court ultimately issued the\ninjunction on October 20, 2016.\n\n The Commonwealth then moved for attorneys’ fees\nand costs, asserting that it “substantially prevailed” under\nSection 16 of the Clayton Act, but the District Court denied\nthe motion. 7 In doing so, the District Court rejected\nHershey’s and Pinnacle’s argument that the Commonwealth\ncould not seek attorneys’ fees and costs under Section 16 of\nthe Clayton Act because, in ordering the injunction, we\napplied Section 13(b) of the FTC Act instead. The District\nCourt denied the fee request, however, because the\nCommonwealth had not “substantially prevailed” under\nSection 16 of the Clayton Act. The Commonwealth timely\nappealed. We will affirm, because we credit Hershey’s and\nPinnacle’s argument that we ordered the injunction based on\nSection 13(b) of the FTC Act, not Section 16 of the Clayton\nAct.\n\n II.\n\n\n\n\n6\n FTC v. Penn State Hershey Med. Ctr., 838 F.3d 327, 354\n(3d Cir. 2016) (“Hershey II”).\n7\n FTC v. Penn State Hershey Med. Ctr., No. 1:15-cv-2362,\n2017 WL 1954398, at *9 (M.D. Pa. May 11, 2017) (“Hershey\nIII”).\n\n\n\n\n 5\n\f Ordinarily, we review the District Court’s denial of\nattorneys’ fees for abuse of discretion. 8 As explained below,\nhowever, our decision turns on the legal question as to which\nstatute applies. Our review of that legal question is plenary. 9\n\n III.\n\n The American Rule, grounded in longstanding\ncommon law tradition, requires parties to pay their own legal\ncosts “win or lose, unless a statute or contract provides\notherwise.” 10 One such statute is Section 16 of the Clayton\nAct. That section provides in relevant part:\n\n Any person, firm, corporation, or\n association shall be entitled to sue\n for and have injunctive relief, in\n any court of the United States\n having jurisdiction over the\n parties, against threatened loss or\n damage by a violation of the\n antitrust laws . . . . In any action\n under this section in which the\n plaintiff substantially prevails, the\n court shall award the cost of suit,\n including a reasonable attorney’s\n fee, to such plaintiff. 11\n\n8\n Raab v. City of Ocean City, 833 F.3d 286, 292 (3d Cir.\n2016).\n9\n See id.\n10\n Baker Botts L.L.P. v. ASARCO LLC, 135 S. Ct. 2158, 2164\n(2015).\n11\n 15 U.S.C. § 26.\n\n\n\n\n 6\n\f The District Court concluded that the Commonwealth\ndid not “substantially prevail” under this section for two\nreasons. First, the District Court ruled that the termination of\nthe merger did not render the Commonwealth a prevailing\nparty because the injunction itself did not terminate the\nmerger and, even though the injunction motivated Hershey\nand Pinnacle to do so on their own, the Supreme Court has\nrejected the “catalyst theory” of prevailing-party status. 12\nSecond, the District Court determined that, because our ruling\nwas based on the holding that the Commonwealth and FTC\nwere merely likely to succeed on the merits, our ruling was\nnot a grant of relief “on the merits” as required for prevailing-\nparty status by Singer Management Consultants, Inc. v.\nMilgram. 13\n\n The Commonwealth contests both conclusions. But\nHershey and Pinnacle argue that we need not address them\nbecause Section 16 of the Clayton Act and its attorneys’ fees\nprovision do not apply at all. Hershey and Pinnacle contend\nthat the preliminary injunction on which the Commonwealth\nrelies for its claim of attorneys’ fees was not entered “in an\naction under this section” as required for application of\nSection 16 of the Clayton Act. Instead, they argue, the\ninjunction was issued under the authority of Section 13(b) of\nthe FTC Act, which does not provide for attorneys’ fees. 14\nThus, they argue, the Commonwealth does not have any legal\nground to claim entitlement to attorneys’ fees on the basis of\n\n12\n See Buckhannon Bd. & Care Home, Inc. v. W. Va. Dep’t of\nHealth & Human Res., 532 U.S. 598, 605, 610 (2001).\n13\n 650 F.3d 223, 228-29 (3d Cir. 2011) (en banc).\n14\n 15 U.S.C. § 53(b).\n\n\n\n\n 7\n\fthe injunction (or the merger termination that it prompted) in\nthis case.\n\n We ultimately agree with Hershey and Pinnacle. We\nwill therefore assume without deciding that the\nCommonwealth is a prevailing party, leaving for another day\nthe questions of whether the Supreme Court’s rejection of the\ncatalyst theory controls claims for fees under Section 16 of\nthe Clayton Act and whether a preliminary injunction entered\npursuant to that section can constitute relief “on the merits.”\nOur sole focus here is to examine the Commonwealth’s claim\nthat it has a statutory basis to be awarded its fees.\n\n\n IV.\n\n We conclude that it does not. The Commonwealth\nclaims attorneys’ fees under Section 16 of the Clayton Act.\nThe District Court noted that, in ordering the injunction, our\nCourt “solely applied the standard outlined by Section 13(b)\nof the FTC Act.” 15 And, as noted above, Section 13(b) of the\nFTC Act makes no provision for attorneys’ fees. The District\nCourt nevertheless determined that the Commonwealth was\npotentially entitled to fees under Section 16 of the Clayton\nAct because the Commonwealth referenced that section when\nit joined with the FTC to seek a preliminary injunction\nagainst Hershey and Pinnacle, 16 and policy and Supreme\nCourt precedent supported the allowance of fees.\n\n\n\n\n15\n Hershey III, 2017 WL 1954398, at *2.\n16\n Id. at *3.\n\n\n\n\n 8\n\f The District Court’s initial conclusion that we ordered\nthe injunction under Section 13(b) of the FTC Act and not\nSection 16 of the Clayton act was correct, and its inquiry\nshould have ended there. The strongest indication that the\ninjunction rested solely on Section 13(b) of the FTC Act was\nthe standard that we used in ordering that injunction. When\nconsidering requests for injunctive relief under Section 16 of\nthe Clayton Act, courts generally apply the traditional four-\npart preliminary injunction standard that includes a\nconsideration of: (1) the likelihood of success on the merits;\n(2) the threat of irreparable harm in the absence of an\ninjunction; (3) the possibility of substantial harm to other\ninterested parties; and (4) the public interest. 17 In ordering\nthe injunction in Hershey II, we referenced the “traditional\nequity standard for injunctive relief,” 18 but we did not use it.\nInstead, we determined that the standard governing\ninjunctions under Section 13(b) of the FTC Act is different,\nand we went on to apply that different standard. 19\n\n In particular, and drawing directly from the statute, we\nsaid that the question of preliminary injunctive relief under\nSection 13(b) of the FTC Act is resolved by “weighing the\nequities and considering the Commission’s likelihood of\nultimate success” to determine whether “such action would be\nin the public interest.” 20 In doing so, we emphasized that the\n\n17\n See Holland v. Rosen, 895 F.3d 272, 285-86 (3d Cir. 2018)\ncert. denied 139 S. Ct. 440 (2018); see also Julian O. von\nKalinowski, Antitrust Laws and Trade Regulations §\n172.02[3][b] & n.60 (2d ed. 2018) (collecting cases).\n18\n Hershey II, 838 F.3d at 337.\n19\n Id.\n20\n Id. (quoting 15 U.S.C. § 53(b)).\n\n\n\n\n 9\n\fpublic interest standard in the second prong of this analysis\ndiffers from “the traditional equity standard for injunctive\nrelief.” 21 This assessment aligns with the judgment of other\nCourts of Appeals, which have concluded that the Section\n13(b) standard is not only different from, but easier to satisfy\nthan the traditional standard for injunctive relief that courts\napply to claims under Section 16 of the Clayton Act. 22\n\n In sum, in ordering the injunction on which the\nCommonwealth relies, we expressly applied Section 13(b) of\nthe FTC Act and its lower evidentiary bar instead of Section\n16 of the Clayton Act. Thus, to the extent that the\nCommonwealth can be said to have “prevailed,” it did so\nunder Section 13(b) of the FTC Act and not Section 16 of the\nClayton Act. For similar reasons, the only court of which we\nare aware to have addressed the issue has concluded that an\ninjunction issued under Section 13(b) of the FTC Act does\nnot trigger potential entitlement to attorneys’ fees under\n\n\n\n\n21\n Id.\n22\n See, e.g., FTC v. H.J. Heinz Co., 246 F.3d 708, 714 (D.C.\nCir. 2001) (explaining that Congress, in drafting Section\n13(b), “intended th[e Section 13(b)] standard to depart from .\n. . the then-traditional equity standard” so that the FTC “was\nnot held to the high thresholds applicable where private\nparties seek interim restraining orders”) (quotation marks\nomitted); FTC v. Affordable Media, LLC, 179 F.3d 1228,\n1233 (9th Cir. 1999) (recognizing that Section 13(b) “places a\nlighter burden on the Commission than that imposed on\nprivate litigants by the traditional equity standard”)(quotation\nmarks omitted).\n\n\n\n\n 10\n\fSection 16 of the Clayton Act. 23 We agree with that\nconclusion.\n\n The District Court relied on a number of factors in\nconcluding otherwise, but none is persuasive. The District\nCourt first pointed to the legislative history of the Clayton\nAct to justify its relevance here. It noted that “Congress\nintended that an individual plaintiff should not bear ‘the very\nhigh price of obtaining judicial enforcement of . . . the\nantitrust laws.’” 24 However, we have examined the extensive\nhistory of this Act and find nothing that clearly shows\nCongress’s intent to empower us to extend the fee-shifting\nprovision of the Clayton Act to cover an action for injunctive\nrelief under another statute. 25 As a result, we are not\npersuaded that the legislative history of the Clayton Act\nsupports the District Court’s conclusion.\n\n The District Court also cited Supreme Court precedent,\nMaher v. Gagne, 26 for the proposition that the fee-shifting\nprovisions of one statute can apply to pendent claims brought\nunder other statutes. Maher, however, does not support\n\n23\n See FTC v. Staples, Inc., 239 F. Supp. 3d 1, 4-5 (D.D.C.\n2017).\n24\n Hershey III, 2017 WL 1954398, at *3 (quoting H.R. Rep.\nNo. 94-499, part 1, at 19-20 (1976)).\n25\n See H.R. Rep. No. 94-499, pt. 1, at 18-20 (1976); see also\nBuckhannon Bd., 532 U.S. at 608 (holding that, “in view of\nthe ‘American Rule’ that attorney’s fees will not be awarded\nabsent explicit statutory authority, . . . [ambiguous] legislative\nhistory is clearly insufficient to alter the accepted meaning of\nthe statutory term”) (quotation marks omitted).\n26\n 448 U.S. 122 (1980).\n\n\n\n\n 11\n\fapplication of the Clayton Act’s fee-shifting provision in this\ncase. In Maher, the plaintiff brought claims under 42 U.S.C.\n§ 1983, alleging that Connecticut’s Aid to Families with\nDependent Children program violated Section 402(a)(7) of\nthe Social Security Act, 27 as well as the Equal Protection and\nDue Process Clauses of the Fourteenth Amendment. 28 After\nthe District Court approved a settlement between the parties,\nthe plaintiff sought attorneys’ fees under 42 U.S.C. § 1988,\nwhich authorizes fees for parties who prevail under Section\n1983 (among other statutes). Responding to objections that\nthe Eleventh Amendment prevented a federal court from\nordering fees against a state for statutory, non-civil rights\nclaims like the plaintiff’s claim under the Social Security Act,\nthe Supreme Court held that Section 1988 allows for “the\naward of fees in a case in which the plaintiff prevails on a\nwholly statutory, non-civil-rights claim pendent to a\nsubstantial constitutional claim or in one in which both a\nstatutory and a substantial constitutional claim are settled\nfavorably to the plaintiff without adjudication.” 29 The Court\nwent on to say: “The legislative history makes it clear that\nCongress intended fees to be awarded where a pendent\nconstitutional claim is involved, even if the statutory claim on\nwhich the plaintiff prevailed is one for which fees cannot be\nawarded under the Act.” 30\n\n Stretching the logic of Maher, the Commonwealth\nargues that it is entitled to attorneys’ fees because its claim\nunder Section 16 of the Clayton Act was pendent to the\n\n27\n 42 U.S.C. § 602(a)(7).\n28\n Maher, 448 U.S. at 125.\n29\n Id. at 132.\n30\n Id. at 132 n.15.\n\n\n\n\n 12\n\fFTC’s claim under Section 13(b) of the FTC Act. But the\nissue in Maher was fundamentally different. The issue in\nMaher was whether the plaintiff’s including the Social\nSecurity Act violation in its Section 1983 complaint\ndisqualified it from receiving fees authorized by Section\n1988. The theory was that the fees were only to vindicate\nviolations of the Fourteenth Amendment. But the Supreme\nCourt held that the plaintiff could recover attorneys’ fees\nunder Section 1988 because she had alleged violations of her\nFourteenth Amendment Due Process and Equal Protection\nrights. As for the fact that she had also alleged a purely\nstatutory violation (of the Social Security Act), the Supreme\nCourt held that this did not preclude an award of attorneys’\nfees under Section 1988 because this was pendant to the\nconstitutional claims. 31\n\n But—as we noted earlier—Section 16 of the Clayton\nAct specifies that a party must substantially prevail “[i]n any\naction under this section.” 32 This language limits the\napplication of Chapter 13’s fee-shifting provision to parties\nwho obtain relief under that section. 33 As we noted above,\nrequests for relief under that section are assessed on a\n\n31\n Id. at 132.\n32\n 15 U.S.C. § 26 (emphasis added).\n33\n See John T. ex rel. Paul T. v. Del. Cty. Intermediate Unit,\n318 F.3d 545, 560 (3d Cir. 2003) (“When the [Individuals\nwith Disabilities Education Act] fee-shifting provision\nauthorizes attorneys[’] fees ‘in any action or proceeding\nbrought under this section,’ it not only limits the universe to\nwhich it applies but also clarifies the type of proceeding on\nwhich a party must ‘prevail.’”) (first emphasis added)\n(quoting 20 U.S.C. § 1415(i)(3)).\n\n\n\n\n 13\n\fdifferent and more lenient standard than are requests for relief\nunder Section 16 of the Clayton Act, and we clearly decided\nthat the injunction should issue based on the standard of\nSection 13(b), not Section 16. Such differences were not\nevident in Maher. As also noted above, the legislative history\ndoes not justify extending the Clayton Act’s fee-shifting\nprovisions to other statutory schemes. For all of these\nreasons, we are not persuaded that Maher gives us any basis\nto extend the fee-shifting provisions of the Clayton Act to a\nclaim raised and adjudicated under the FTC Act. 34\n\n34\n The Commonwealth maintains that it did raise its claim\nunder the Clayton Act and that we acknowledged this in\nHershey II. It is true that we referenced both the Clayton Act\nand the FTC Act as a basis for the suit brought jointly by the\nCommonwealth and the FTC. In particular, we noted that the\nCommonwealth and the FTC “filed suit . . . under” both\nSection 16 of the Clayton Act and Section 13(b) of the FTC\nAct, Hershey II, 838 F.3d at 333, and we also stated that\n“[t]he District Court had jurisdiction” under both Section 16\nof the Clayton Act and Section 13(b) of the FTC Act, id. at\n335. But the Commonwealth does not have standing to\npursue a claim under the FTC Act, and these statements\nmerely declare that the Clayton Act gave them standing in\nthis case. The issue of standing aside, the facts remain that\nthe Commonwealth and the FTC litigated their request for an\ninjunction under Section 13(b) of the FTC Act and that we\nordered the injunction under that section and the more lenient\nstandard that applies thereto. As one court explained in\nrejecting the Commonwealth’s claim for attorneys’ fees in a\nsimilar case, the Commonwealth “cannot have it both ways”\nby “rid[ing] the FTC’s claim to a successful preliminary\ninjunction under the more permissive Section 13(b) standard\n\n\n\n\n 14\n\f Finally, the District Court raised concerns that failing\nto allow the Commonwealth to seek attorneys’ fees in this\nsituation would be contrary to the interests of judicial\neconomy. Forcing the Commonwealth to pursue a separate\ncase to bring a claim under Section 16, the District Court said,\ncould result in “duplicative litigation, separate filings, and\nrepetitive arguments” because this would be the only avenue\nfor claiming attorneys’ fees. 35 We are not persuaded that\nsuch concerns outweigh the plain language of the statutes.\n\n V.\n\n In sum, we conclude that the authority for this\ninjunction arose from Section 13(b) of the FTC Act, which—\nunlike Section 16 of the Clayton Act—does not provide for\nattorneys’ fees. Hence, for all of the foregoing reasons, the\nCommonwealth has no legal basis to claim attorneys’ fees in\nthis case and we will affirm the order of the District Court on\nthat ground.\n\n\n\n\nand then cit[ing] that favorable ruling as the sole justification\nfor fee-shifting under the more rigorous Clayton Act\nstandard.” Staples, 239 F. Supp. 3d at 5.\n35\n Hershey III, 2017 WL 1954398, at *3.\n\n\n\n\n 15\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: FEDERAL TRADE COMMISSION; Commonwealth of Pennsylvania v. PENN STATE HERSHEY MEDICAL CENTER; Pinnacle Health System Commonwealth of Pennsylvania, Appellant\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-23\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n\\n __________\\n\\n No. 17-2270\\n __________\\n\\n FEDERAL TRADE COMMISSION;\\n COMMONWEALTH OF PENNSYLVANIA\\n\\n v.\\n\\n PENN STATE HERSHEY MEDICAL CENTER;\\n PINNACLE HEALTH SYSTEM\\n\\n Commonwealth of Pennsylvania,\\n\\n Appellant\\n __________\\n\\n On Appeal from the United States District Court\\n for the Middle District of Pennsylvania\\n (District Court Civil No. 1-15-cv-02362)\\n District Judge: Honorable John E. Jones III\\n\\n Argued July 10, 2018\\n\\nBEFORE: SHWARTZ, NYGAARD, and RENDELL,\\n Circuit Judges.\\n\\f (Filed: January 23, 2019)\\n\\n\\nWesley G. Carson, Esq.\\nPeggy Bayer Femenella, Esq.\\nJames W. Frost, Esq.\\nLynda Lao, Esq.\\nFederal Trade Commission\\n600 Pennsylvania Avenue, N.W.\\nWashington, DC 20580\\n\\nWilliam H. Efron, Esq.\\nRyan F. Harsch, Esq.\\nJared P. Nagley, Esq.\\nJonathan W. Platt, Esq.\\nGerald A. Stein, Esq.\\nGeralyn J. Trujillo, Esq.\\nNancy Turnblacer, Esq.\\nTheodore Zang, Esq.\\nFederal Trade Commission\\nOne Bowling Green\\nSuite 318\\nNew York, NY 10004\\n\\n Counsel for Plaintiff Federal Trade Commission\\n\\nHoward G. Hopkirk, Esq. [Argued]\\nTracy W. Wertz, Esq.\\nOffice of Attorney General of Pennsylvania\\nStrawberry Square\\nHarrisburg, PA 17120\\n\\n\\n\\n\\n 2\\n\\fKemal A. Mericli, Esq.\\nOffice of Attorney General of Pennsylvania\\n1251 Waterfront Place\\nPittsburgh, PA 15222\\n\\n Counsel for Appellant Commonwealth of Pennsylvania\\n\\n\\nWilliam D. Coglianese, Esq. [Argued]\\nChristopher N. Thatch, Esq.\\nAdrian Wager-Zito, Esq.\\nJones Day\\n51 Louisiana Avenue, N.W.\\nWashington, DC 20001\\n\\n Counsel for Appellees Penn State Hershey Medical\\n and Pinnacle Health System\\n\\nLuminita Nodit, Esq.\\nOffice of Attorney General of Washington\\n800 Fifth Avenue\\nSuite 2000\\nSeattle, WA 98104\\n\\n Counsel for Amicus Appellants\\n\\n __________\\n\\n OPINION OF THE COURT\\n __________\\n\\nNYGAARD, Circuit Judge.\\n\\n\\n\\n\\n 3\\n\\f I.\\n\\n In March 2015, the Boards of Penn State Hershey\\nMedical Center and PinnacleHealth System (“Hershey” and\\n“Pinnacle,” respectively) formally approved a plan to merge.\\nThey had announced the proposal a year earlier, so the\\nCommonwealth of Pennsylvania and the Federal Trade\\nCommission (“FTC”) were already investigating the impact\\nof the proposed merger when the Boards approved it. This\\njoint probe resulted in the FTC filing an administrative\\ncomplaint alleging that the merger violated Section 7 of the\\nClayton Act. 1 The FTC scheduled an administrative hearing\\non the merits for May 2016. At the same time, the\\nCommonwealth and the FTC jointly sued Hershey and\\nPinnacle under Section 16 of the Clayton Act, 2 and Section\\n13(b) of the Federal Trade Commission Act (“FTC Act”), 3 to\\n“prevent and restrain Hershey and Pinnacle from violating\\nSection 7 of the Clayton Act . . . pending the Commission’s\\nadministrative proceeding.” 4 They sought a preliminary\\ninjunction and a temporary restraining order.\\n\\n The District Court denied relief. 5 But, on September\\n27, 2016, we reversed the District Court’s order and directed\\nit to preliminarily enjoin the merger “pending the outcome of\\n\\n1\\n 15 U.S.C. § 18.\\n2\\n 15 U.S.C. § 26.\\n3\\n 15 U.S.C. § 53(b).\\n4\\n Amended Complaint at 7 ¶ 14, FTC v. Penn State Hershey\\nMed. Ctr., 185 F. Supp. 3d 552 (M.D. Pa. 2016) (No. 1:15-\\ncv-2362) (“Hershey I”).\\n5\\n Hershey I, 185 F. Supp. 3d at 564.\\n\\n\\n\\n\\n 4\\n\\fthe FTC’s administrative adjudication.” 6 Within three weeks,\\nHershey and Pinnacle terminated their Agreement,\\nreferencing our remand ordering the temporary injunction as\\nthe impetus. The District Court ultimately issued the\\ninjunction on October 20, 2016.\\n\\n The Commonwealth then moved for attorneys’ fees\\nand costs, asserting that it “substantially prevailed” under\\nSection 16 of the Clayton Act, but the District Court denied\\nthe motion. 7 In doing so, the District Court rejected\\nHershey’s and Pinnacle’s argument that the Commonwealth\\ncould not seek attorneys’ fees and costs under Section 16 of\\nthe Clayton Act because, in ordering the injunction, we\\napplied Section 13(b) of the FTC Act instead. The District\\nCourt denied the fee request, however, because the\\nCommonwealth had not “substantially prevailed” under\\nSection 16 of the Clayton Act. The Commonwealth timely\\nappealed. We will affirm, because we credit Hershey’s and\\nPinnacle’s argument that we ordered the injunction based on\\nSection 13(b) of the FTC Act, not Section 16 of the Clayton\\nAct.\\n\\n II.\\n\\n\\n\\n\\n6\\n FTC v. Penn State Hershey Med. Ctr., 838 F.3d 327, 354\\n(3d Cir. 2016) (“Hershey II”).\\n7\\n FTC v. Penn State Hershey Med. Ctr., No. 1:15-cv-2362,\\n2017 WL 1954398, at *9 (M.D. Pa. May 11, 2017) (“Hershey\\nIII”).\\n\\n\\n\\n\\n 5\\n\\f Ordinarily, we review the District Court’s denial of\\nattorneys’ fees for abuse of discretion. 8 As explained below,\\nhowever, our decision turns on the legal question as to which\\nstatute applies. Our review of that legal question is plenary. 9\\n\\n III.\\n\\n The American Rule, grounded in longstanding\\ncommon law tradition, requires parties to pay their own legal\\ncosts “win or lose, unless a statute or contract provides\\notherwise.” 10 One such statute is Section 16 of the Clayton\\nAct. That section provides in relevant part:\\n\\n Any person, firm, corporation, or\\n association shall be entitled to sue\\n for and have injunctive relief, in\\n any court of the United States\\n having jurisdiction over the\\n parties, against threatened loss or\\n damage by a violation of the\\n antitrust laws . . . . In any action\\n under this section in which the\\n plaintiff substantially prevails, the\\n court shall award the cost of suit,\\n including a reasonable attorney’s\\n fee, to such plaintiff. 11\\n\\n8\\n Raab v. City of Ocean City, 833 F.3d 286, 292 (3d Cir.\\n2016).\\n9\\n See id.\\n10\\n Baker Botts L.L.P. v. ASARCO LLC, 135 S. Ct. 2158, 2164\\n(2015).\\n11\\n 15 U.S.C. § 26.\\n\\n\\n\\n\\n 6\\n\\f The District Court concluded that the Commonwealth\\ndid not “substantially prevail” under this section for two\\nreasons. First, the District Court ruled that the termination of\\nthe merger did not render the Commonwealth a prevailing\\nparty because the injunction itself did not terminate the\\nmerger and, even though the injunction motivated Hershey\\nand Pinnacle to do so on their own, the Supreme Court has\\nrejected the “catalyst theory” of prevailing-party status. 12\\nSecond, the District Court determined that, because our ruling\\nwas based on the holding that the Commonwealth and FTC\\nwere merely likely to succeed on the merits, our ruling was\\nnot a grant of relief “on the merits” as required for prevailing-\\nparty status by Singer Management Consultants, Inc. v.\\nMilgram. 13\\n\\n The Commonwealth contests both conclusions. But\\nHershey and Pinnacle argue that we need not address them\\nbecause Section 16 of the Clayton Act and its attorneys’ fees\\nprovision do not apply at all. Hershey and Pinnacle contend\\nthat the preliminary injunction on which the Commonwealth\\nrelies for its claim of attorneys’ fees was not entered “in an\\naction under this section” as required for application of\\nSection 16 of the Clayton Act. Instead, they argue, the\\ninjunction was issued under the authority of Section 13(b) of\\nthe FTC Act, which does not provide for attorneys’ fees. 14\\nThus, they argue, the Commonwealth does not have any legal\\nground to claim entitlement to attorneys’ fees on the basis of\\n\\n12\\n See Buckhannon Bd. & Care Home, Inc. v. W. Va. Dep’t of\\nHealth & Human Res., 532 U.S. 598, 605, 610 (2001).\\n13\\n 650 F.3d 223, 228-29 (3d Cir. 2011) (en banc).\\n14\\n 15 U.S.C. § 53(b).\\n\\n\\n\\n\\n 7\\n\\fthe injunction (or the merger termination that it prompted) in\\nthis case.\\n\\n We ultimately agree with Hershey and Pinnacle. We\\nwill therefore assume without deciding that the\\nCommonwealth is a prevailing party, leaving for another day\\nthe questions of whether the Supreme Court’s rejection of the\\ncatalyst theory controls claims for fees under Section 16 of\\nthe Clayton Act and whether a preliminary injunction entered\\npursuant to that section can constitute relief “on the merits.”\\nOur sole focus here is to examine the Commonwealth’s claim\\nthat it has a statutory basis to be awarded its fees.\\n\\n\\n IV.\\n\\n We conclude that it does not. The Commonwealth\\nclaims attorneys’ fees under Section 16 of the Clayton Act.\\nThe District Court noted that, in ordering the injunction, our\\nCourt “solely applied the standard outlined by Section 13(b)\\nof the FTC Act.” 15 And, as noted above, Section 13(b) of the\\nFTC Act makes no provision for attorneys’ fees. The District\\nCourt nevertheless determined that the Commonwealth was\\npotentially entitled to fees under Section 16 of the Clayton\\nAct because the Commonwealth referenced that section when\\nit joined with the FTC to seek a preliminary injunction\\nagainst Hershey and Pinnacle, 16 and policy and Supreme\\nCourt precedent supported the allowance of fees.\\n\\n\\n\\n\\n15\\n Hershey III, 2017 WL 1954398, at *2.\\n16\\n Id. at *3.\\n\\n\\n\\n\\n 8\\n\\f The District Court’s initial conclusion that we ordered\\nthe injunction under Section 13(b) of the FTC Act and not\\nSection 16 of the Clayton act was correct, and its inquiry\\nshould have ended there. The strongest indication that the\\ninjunction rested solely on Section 13(b) of the FTC Act was\\nthe standard that we used in ordering that injunction. When\\nconsidering requests for injunctive relief under Section 16 of\\nthe Clayton Act, courts generally apply the traditional four-\\npart preliminary injunction standard that includes a\\nconsideration of: (1) the likelihood of success on the merits;\\n(2) the threat of irreparable harm in the absence of an\\ninjunction; (3) the possibility of substantial harm to other\\ninterested parties; and (4) the public interest. 17 In ordering\\nthe injunction in Hershey II, we referenced the “traditional\\nequity standard for injunctive relief,” 18 but we did not use it.\\nInstead, we determined that the standard governing\\ninjunctions under Section 13(b) of the FTC Act is different,\\nand we went on to apply that different standard. 19\\n\\n In particular, and drawing directly from the statute, we\\nsaid that the question of preliminary injunctive relief under\\nSection 13(b) of the FTC Act is resolved by “weighing the\\nequities and considering the Commission’s likelihood of\\nultimate success” to determine whether “such action would be\\nin the public interest.” 20 In doing so, we emphasized that the\\n\\n17\\n See Holland v. Rosen, 895 F.3d 272, 285-86 (3d Cir. 2018)\\ncert. denied 139 S. Ct. 440 (2018); see also Julian O. von\\nKalinowski, Antitrust Laws and Trade Regulations §\\n172.02[3][b] & n.60 (2d ed. 2018) (collecting cases).\\n18\\n Hershey II, 838 F.3d at 337.\\n19\\n Id.\\n20\\n Id. (quoting 15 U.S.C. § 53(b)).\\n\\n\\n\\n\\n 9\\n\\fpublic interest standard in the second prong of this analysis\\ndiffers from “the traditional equity standard for injunctive\\nrelief.” 21 This assessment aligns with the judgment of other\\nCourts of Appeals, which have concluded that the Section\\n13(b) standard is not only different from, but easier to satisfy\\nthan the traditional standard for injunctive relief that courts\\napply to claims under Section 16 of the Clayton Act. 22\\n\\n In sum, in ordering the injunction on which the\\nCommonwealth relies, we expressly applied Section 13(b) of\\nthe FTC Act and its lower evidentiary bar instead of Section\\n16 of the Clayton Act. Thus, to the extent that the\\nCommonwealth can be said to have “prevailed,” it did so\\nunder Section 13(b) of the FTC Act and not Section 16 of the\\nClayton Act. For similar reasons, the only court of which we\\nare aware to have addressed the issue has concluded that an\\ninjunction issued under Section 13(b) of the FTC Act does\\nnot trigger potential entitlement to attorneys’ fees under\\n\\n\\n\\n\\n21\\n Id.\\n22\\n See, e.g., FTC v. H.J. Heinz Co., 246 F.3d 708, 714 (D.C.\\nCir. 2001) (explaining that Congress, in drafting Section\\n13(b), “intended th[e Section 13(b)] standard to depart from .\\n. . the then-traditional equity standard” so that the FTC “was\\nnot held to the high thresholds applicable where private\\nparties seek interim restraining orders”) (quotation marks\\nomitted); FTC v. Affordable Media, LLC, 179 F.3d 1228,\\n1233 (9th Cir. 1999) (recognizing that Section 13(b) “places a\\nlighter burden on the Commission than that imposed on\\nprivate litigants by the traditional equity standard”)(quotation\\nmarks omitted).\\n\\n\\n\\n\\n 10\\n\\fSection 16 of the Clayton Act. 23 We agree with that\\nconclusion.\\n\\n The District Court relied on a number of factors in\\nconcluding otherwise, but none is persuasive. The District\\nCourt first pointed to the legislative history of the Clayton\\nAct to justify its relevance here. It noted that “Congress\\nintended that an individual plaintiff should not bear ‘the very\\nhigh price of obtaining judicial enforcement of . . . the\\nantitrust laws.’” 24 However, we have examined the extensive\\nhistory of this Act and find nothing that clearly shows\\nCongress’s intent to empower us to extend the fee-shifting\\nprovision of the Clayton Act to cover an action for injunctive\\nrelief under another statute. 25 As a result, we are not\\npersuaded that the legislative history of the Clayton Act\\nsupports the District Court’s conclusion.\\n\\n The District Court also cited Supreme Court precedent,\\nMaher v. Gagne, 26 for the proposition that the fee-shifting\\nprovisions of one statute can apply to pendent claims brought\\nunder other statutes. Maher, however, does not support\\n\\n23\\n See FTC v. Staples, Inc., 239 F. Supp. 3d 1, 4-5 (D.D.C.\\n2017).\\n24\\n Hershey III, 2017 WL 1954398, at *3 (quoting H.R. Rep.\\nNo. 94-499, part 1, at 19-20 (1976)).\\n25\\n See H.R. Rep. No. 94-499, pt. 1, at 18-20 (1976); see also\\nBuckhannon Bd., 532 U.S. at 608 (holding that, “in view of\\nthe ‘American Rule’ that attorney’s fees will not be awarded\\nabsent explicit statutory authority, . . . [ambiguous] legislative\\nhistory is clearly insufficient to alter the accepted meaning of\\nthe statutory term”) (quotation marks omitted).\\n26\\n 448 U.S. 122 (1980).\\n\\n\\n\\n\\n 11\\n\\fapplication of the Clayton Act’s fee-shifting provision in this\\ncase. In Maher, the plaintiff brought claims under 42 U.S.C.\\n§ 1983, alleging that Connecticut’s Aid to Families with\\nDependent Children program violated Section 402(a)(7) of\\nthe Social Security Act, 27 as well as the Equal Protection and\\nDue Process Clauses of the Fourteenth Amendment. 28 After\\nthe District Court approved a settlement between the parties,\\nthe plaintiff sought attorneys’ fees under 42 U.S.C. § 1988,\\nwhich authorizes fees for parties who prevail under Section\\n1983 (among other statutes). Responding to objections that\\nthe Eleventh Amendment prevented a federal court from\\nordering fees against a state for statutory, non-civil rights\\nclaims like the plaintiff’s claim under the Social Security Act,\\nthe Supreme Court held that Section 1988 allows for “the\\naward of fees in a case in which the plaintiff prevails on a\\nwholly statutory, non-civil-rights claim pendent to a\\nsubstantial constitutional claim or in one in which both a\\nstatutory and a substantial constitutional claim are settled\\nfavorably to the plaintiff without adjudication.” 29 The Court\\nwent on to say: “The legislative history makes it clear that\\nCongress intended fees to be awarded where a pendent\\nconstitutional claim is involved, even if the statutory claim on\\nwhich the plaintiff prevailed is one for which fees cannot be\\nawarded under the Act.” 30\\n\\n Stretching the logic of Maher, the Commonwealth\\nargues that it is entitled to attorneys’ fees because its claim\\nunder Section 16 of the Clayton Act was pendent to the\\n\\n27\\n 42 U.S.C. § 602(a)(7).\\n28\\n Maher, 448 U.S. at 125.\\n29\\n Id. at 132.\\n30\\n Id. at 132 n.15.\\n\\n\\n\\n\\n 12\\n\\fFTC’s claim under Section 13(b) of the FTC Act. But the\\nissue in Maher was fundamentally different. The issue in\\nMaher was whether the plaintiff’s including the Social\\nSecurity Act violation in its Section 1983 complaint\\ndisqualified it from receiving fees authorized by Section\\n1988. The theory was that the fees were only to vindicate\\nviolations of the Fourteenth Amendment. But the Supreme\\nCourt held that the plaintiff could recover attorneys’ fees\\nunder Section 1988 because she had alleged violations of her\\nFourteenth Amendment Due Process and Equal Protection\\nrights. As for the fact that she had also alleged a purely\\nstatutory violation (of the Social Security Act), the Supreme\\nCourt held that this did not preclude an award of attorneys’\\nfees under Section 1988 because this was pendant to the\\nconstitutional claims. 31\\n\\n But—as we noted earlier—Section 16 of the Clayton\\nAct specifies that a party must substantially prevail “[i]n any\\naction under this section.” 32 This language limits the\\napplication of Chapter 13’s fee-shifting provision to parties\\nwho obtain relief under that section. 33 As we noted above,\\nrequests for relief under that section are assessed on a\\n\\n31\\n Id. at 132.\\n32\\n 15 U.S.C. § 26 (emphasis added).\\n33\\n See John T. ex rel. Paul T. v. Del. Cty. Intermediate Unit,\\n318 F.3d 545, 560 (3d Cir. 2003) (“When the [Individuals\\nwith Disabilities Education Act] fee-shifting provision\\nauthorizes attorneys[’] fees ‘in any action or proceeding\\nbrought under this section,’ it not only limits the universe to\\nwhich it applies but also clarifies the type of proceeding on\\nwhich a party must ‘prevail.’”) (first emphasis added)\\n(quoting 20 U.S.C. § 1415(i)(3)).\\n\\n\\n\\n\\n 13\\n\\fdifferent and more lenient standard than are requests for relief\\nunder Section 16 of the Clayton Act, and we clearly decided\\nthat the injunction should issue based on the standard of\\nSection 13(b), not Section 16. Such differences were not\\nevident in Maher. As also noted above, the legislative history\\ndoes not justify extending the Clayton Act’s fee-shifting\\nprovisions to other statutory schemes. For all of these\\nreasons, we are not persuaded that Maher gives us any basis\\nto extend the fee-shifting provisions of the Clayton Act to a\\nclaim raised and adjudicated under the FTC Act. 34\\n\\n34\\n The Commonwealth maintains that it did raise its claim\\nunder the Clayton Act and that we acknowledged this in\\nHershey II. It is true that we referenced both the Clayton Act\\nand the FTC Act as a basis for the suit brought jointly by the\\nCommonwealth and the FTC. In particular, we noted that the\\nCommonwealth and the FTC “filed suit . . . under” both\\nSection 16 of the Clayton Act and Section 13(b) of the FTC\\nAct, Hershey II, 838 F.3d at 333, and we also stated that\\n“[t]he District Court had jurisdiction” under both Section 16\\nof the Clayton Act and Section 13(b) of the FTC Act, id. at\\n335. But the Commonwealth does not have standing to\\npursue a claim under the FTC Act, and these statements\\nmerely declare that the Clayton Act gave them standing in\\nthis case. The issue of standing aside, the facts remain that\\nthe Commonwealth and the FTC litigated their request for an\\ninjunction under Section 13(b) of the FTC Act and that we\\nordered the injunction under that section and the more lenient\\nstandard that applies thereto. As one court explained in\\nrejecting the Commonwealth’s claim for attorneys’ fees in a\\nsimilar case, the Commonwealth “cannot have it both ways”\\nby “rid[ing] the FTC’s claim to a successful preliminary\\ninjunction under the more permissive Section 13(b) standard\\n\\n\\n\\n\\n 14\\n\\f Finally, the District Court raised concerns that failing\\nto allow the Commonwealth to seek attorneys’ fees in this\\nsituation would be contrary to the interests of judicial\\neconomy. Forcing the Commonwealth to pursue a separate\\ncase to bring a claim under Section 16, the District Court said,\\ncould result in “duplicative litigation, separate filings, and\\nrepetitive arguments” because this would be the only avenue\\nfor claiming attorneys’ fees. 35 We are not persuaded that\\nsuch concerns outweigh the plain language of the statutes.\\n\\n V.\\n\\n In sum, we conclude that the authority for this\\ninjunction arose from Section 13(b) of the FTC Act, which—\\nunlike Section 16 of the Clayton Act—does not provide for\\nattorneys’ fees. Hence, for all of the foregoing reasons, the\\nCommonwealth has no legal basis to claim attorneys’ fees in\\nthis case and we will affirm the order of the District Court on\\nthat ground.\\n\\n\\n\\n\\nand then cit[ing] that favorable ruling as the sole justification\\nfor fee-shifting under the more rigorous Clayton Act\\nstandard.” Staples, 239 F. Supp. 3d at 5.\\n35\\n Hershey III, 2017 WL 1954398, at *3.\\n\\n\\n\\n\\n 15\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":75,"cells":{"id":{"kind":"number","value":4583850,"string":"4,583,850"},"name":{"kind":"string","value":"Dieuland JEAN LOUIS, Petitioner v. ATTORNEY GENERAL UNITED STATES of America, Respondent"},"name_abbreviation":{"kind":"string","value":"Dieuland Jean Louis v. Attorney General United States"},"decision_date":{"kind":"string","value":"2019-01-23"},"docket_number":{"kind":"string","value":"18-2082"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Greenaway, Shwartz, Bibas\", \"parties\": \"\", \"opinions\": [{\"author\": \"BIBAS, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _______________\\n\\n No. 18-2082\\n _______________\\n\\n DIEULAND JEAN LOUIS,\\n Petitioner\\n\\n v.\\n\\nATTORNEY GENERAL UNITED STATES OF AMERICA,\\n Respondent\\n _______________\\n\\n On Petition for Review of a Decision of the\\n United States Department of Justice\\n Board of Immigration Appeals\\n (Agency No. A206-596-150)\\n Immigration Judge: Honorable Ramin Rastegar\\n _______________\\n\\n Submitted Under Third Circuit L.A.R. 34.1(a)\\n on November 14, 2018\\n\\n Before: GREENAWAY, JR., SHWARTZ, and BIBAS,\\n Circuit Judges.\\n\\n (Filed: January 23, 2019)\\n\\f Raymond S. Vivino\\n Vivino & Vivino\\n 401 Hamburg Turnpike\\n Suite 201\\n Wayne, NJ 07474\\n Counsel for Petitioner\\n\\n Tim Ramnitz\\n Jennifer A. Singer\\n John D. Williams\\n United States Department of Justice\\n Office of Immigration Litigation\\n Room 10006\\n P.O. Box 878\\n Ben Franklin Station\\n Washington, DC 20044\\n Counsel for Respondent\\n _______________\\n\\n OPINION OF THE COURT\\n _______________\\n\\nBIBAS, Circuit Judge.\\n A non-lawyer “immigration expert” advised Dieuland Jean\\nLouis that he could miss his asylum hearing without conse-\\nquence. I App. A6-7. So he did. But the “immigration expert”\\nwas wrong—and an immigration judge relied on Jean Louis’s\\nabsence to order his removal in absentia. Id.\\n Jean Louis now contends that we should reopen that order\\nbecause the non-lawyer’s advice qualifies as an exceptional\\n\\n\\n\\n\\n 2\\n\\fcircumstance. But that is not the law. Exceptional circum-\\nstances must be grave and beyond the applicant’s control. And\\nholding the hearing without Jean Louis did not violate due pro-\\ncess because he had the opportunity to attend. He chose not to.\\nSo we will deny his petition for review.\\n I. BACKGROUND\\n Jean Louis, a native and citizen of Haiti, entered the United\\nStates illegally. He later applied for asylum. While that appli-\\ncation was pending, he married a U.S. citizen and sought citi-\\nzenship on that basis.\\n Jean Louis received a notice, dated August 2016, explain-\\ning that he had to appear for an asylum hearing in June 2017.\\nThe notice made clear that the immigration judge could hold\\nthe hearing and remove Jean Louis if he did not attend.\\n But Jean Louis, who does not speak English, wanted ad-\\nvice. So he went to Gustave Thermitus. Thermitus is associated\\nwith Caracol Financial. He is not a lawyer and does not belong\\nto a legal organization. Still, Jean Louis thought Thermitus was\\na lawyer.\\n But Thermitus did not hold himself out as a lawyer. And\\nJean Louis does not claim that Thermitus intentionally misled\\nhim. According to Jean Louis, Thermitus held himself out as\\n“an immigration expert that performed other work as well.” II\\nApp. A6.\\n Jean Louis asked Thermitus about his notice. Thermitus\\ntold him he did not have to go to the hearing because he had\\nanother path to citizenship: marriage. That advice was wrong.\\n\\n\\n\\n\\n 3\\n\\f So Jean Louis did not attend his asylum hearing. The hear-\\ning was held without him. Because he had conceded that he\\nhad entered the country illegally, the judge found him remov-\\nable and ordered him removed.\\n Jean Louis then reached out to Thermitus. Thermitus said\\nhe worked with a lawyer who could file a motion for Jean\\nLouis. This was little comfort to Jean Louis, who until that mo-\\nment had thought that Thermitus himself was a lawyer.\\n So Jean Louis hired a real lawyer and moved to reopen his\\nasylum case. The immigration judge denied the motion. The\\nBoard of Immigration Appeals affirmed because no “excep-\\ntional circumstances” had prevented Jean Louis from attending\\nhis hearing. AR 3-4.\\n The Board had jurisdiction under 8 C.F.R. § 1003.1(b)(3).\\nWe have jurisdiction under 8 U.S.C. § 1252(a)(5). We review\\nthe Board’s decision not to reopen an in absentia removal order\\nfor abuse of discretion. Ramos-Olivieri v. Att’y Gen., 624 F.3d\\n622, 625 (3d Cir. 2010). We review questions of law, including\\nwhether an alien’s due process rights were violated, de novo.\\nContreras v. Att’y Gen., 665 F.3d 578, 583 (3d Cir. 2012).\\n II. A NON-LAWYER’S BAD ADVICE IS NOT AN EXCEP-\\n TIONAL CIRCUMSTANCE\\n\\n The Board need reopen Jean Louis’s removal order only if\\n“exceptional circumstances” prevented him from attending the\\nhearing. 8 U.S.C. § 1229a(b)(5)(C) (also listing two other\\ngrounds for rescinding a removal order, neither of which ap-\\nplies here). He has not made that showing.\\n\\n\\n\\n\\n 4\\n\\f To warrant reopening an in absentia removal order, excep-\\ntional circumstances must be “beyond the control of the alien.”\\n8 U.S.C. § 1229a(e)(1). The statute lists several examples: “bat-\\ntery or extreme cruelty to the alien or any child or parent of the\\nalien, serious illness of the alien, or serious illness or death of\\nthe spouse, child, or parent of the alien.” Id. And it makes clear\\nthat other circumstances do not count if they are “less compel-\\nling” than these examples. Id. In short, exceptional circum-\\nstances must not only be extreme, but also beyond the alien’s\\ncontrol.\\n Jean Louis’s situation does not meet this high bar. He fol-\\nlowed bad advice from someone he trusted. It was his choice—\\nand his alone—to seek out and follow that advice. So his cir-\\ncumstances were not beyond his control. And his situation is a\\nfar cry from the death, serious illness, or abuse outlined in the\\nstatute. People make mistakes every day. But generally, mis-\\ntakes do not rise to the extreme level of extreme cruelty, seri-\\nous illness, or death. See id.\\n Our precedent supports this result. We have held that fraud\\ncommitted by lawyers and paralegals can qualify as an excep-\\ntional circumstance. Borges v. Gonzales, 402 F.3d 398, 408 (3d\\nCir. 2005). While some circuits have found that ineffective as-\\nsistance of counsel qualifies too, we have neither adopted nor\\nrejected that position. Id. But we have noted that the fraud al-\\nleged in Borges was more extreme than a typical ineffective-\\nassistance claim. Id.\\n Jean Louis’s case differs from Borges in two important\\nways. First, Thermitus is neither a lawyer nor a legal assistant.\\nSo accepting Jean Louis’s argument would extend Borges far\\n\\n\\n\\n\\n 5\\n\\fbeyond legal representation. Second, Jean Louis has not shown\\nthat Thermitus defrauded him. Thermitus never pretended to\\nbe a lawyer or offered to represent Jean Louis in court. But in\\nBorges, fraud was “the crucial issue.” Id. Borges carefully lim-\\nited its holding to fraud committed by lawyers and legal organ-\\nizations. We will not extend Borges’s limited holding beyond\\nthat boundary.\\n III. IN ABSENTIA REMOVAL ORDERS DO NOT CATEGORI-\\n CALLY VIOLATE DUE PROCESS\\n\\n Next, Jean Louis argues that his in absentia removal order\\nviolates his due process rights. Due process indeed guarantees\\naliens a hearing and an opportunity to be heard and present ev-\\nidence. Abdulrahman v. Ashcroft, 330 F.3d 587, 596 (3d Cir.\\n2003). But the immigration judge did not violate these rights\\nby holding the hearing without Jean Louis. Jean Louis had an\\nopportunity to attend his hearing, but chose not to.\\n Jean Louis’s argument would have troubling consequences:\\nIf we held that in absentia hearings violated due process, we\\nwould effectively invalidate 8 U.S.C. § 1229a(b)(5)(A), which\\nspecifically permits in absentia hearings. And we would per-\\nversely let aliens avoid removal by not attending their hearings.\\nSo in absentia removal orders do not categorically violate due\\nprocess.\\n Jean Louis relies on one of our precedents to make his due\\nprocess argument, but this precedent is distinguishable. In\\nCabrera-Perez v. Gonzales, an alien arrived for her hearing fif-\\nteen to twenty minutes late. 456 F.3d 109, 117 (3d Cir. 2006).\\nWe held that due process forbids treating slight lateness as a\\n\\n\\n\\n\\n 6\\n\\ffailure to appear if, when the alien arrives, the judge “is either\\nstill on the bench or recently retired.” Id. at 116. But coming\\nlate is very different from not showing up at all. Id. at 117. Jean\\nLouis did not show up at all, so Cabrera-Perez is inapt. His\\nremoval order satisfied due process.\\n *****\\n We recognize that this result may seem harsh. Jean Louis\\nrelied on someone whom he thought was an expert. But this\\nsituation, while regrettable, is not exceptional. So we will deny\\nhis petition.\\n\\n\\n\\n\\n 7\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4361103/\", \"author_raw\": \"BIBAS, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"GREENAWAY"},"judge2":{"kind":"string","value":"SHWARTZ"},"judge3":{"kind":"string","value":"BIBAS"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583850/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Dieuland JEAN LOUIS, Petitioner v. ATTORNEY GENERAL UNITED STATES of America, Respondent\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-23\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _______________\n\n No. 18-2082\n _______________\n\n DIEULAND JEAN LOUIS,\n Petitioner\n\n v.\n\nATTORNEY GENERAL UNITED STATES OF AMERICA,\n Respondent\n _______________\n\n On Petition for Review of a Decision of the\n United States Department of Justice\n Board of Immigration Appeals\n (Agency No. A206-596-150)\n Immigration Judge: Honorable Ramin Rastegar\n _______________\n\n Submitted Under Third Circuit L.A.R. 34.1(a)\n on November 14, 2018\n\n Before: GREENAWAY, JR., SHWARTZ, and BIBAS,\n Circuit Judges.\n\n (Filed: January 23, 2019)\n\f Raymond S. Vivino\n Vivino & Vivino\n 401 Hamburg Turnpike\n Suite 201\n Wayne, NJ 07474\n Counsel for Petitioner\n\n Tim Ramnitz\n Jennifer A. Singer\n John D. Williams\n United States Department of Justice\n Office of Immigration Litigation\n Room 10006\n P.O. Box 878\n Ben Franklin Station\n Washington, DC 20044\n Counsel for Respondent\n _______________\n\n OPINION OF THE COURT\n _______________\n\nBIBAS, Circuit Judge.\n A non-lawyer “immigration expert” advised Dieuland Jean\nLouis that he could miss his asylum hearing without conse-\nquence. I App. A6-7. So he did. But the “immigration expert”\nwas wrong—and an immigration judge relied on Jean Louis’s\nabsence to order his removal in absentia. Id.\n Jean Louis now contends that we should reopen that order\nbecause the non-lawyer’s advice qualifies as an exceptional\n\n\n\n\n 2\n\fcircumstance. But that is not the law. Exceptional circum-\nstances must be grave and beyond the applicant’s control. And\nholding the hearing without Jean Louis did not violate due pro-\ncess because he had the opportunity to attend. He chose not to.\nSo we will deny his petition for review.\n I. BACKGROUND\n Jean Louis, a native and citizen of Haiti, entered the United\nStates illegally. He later applied for asylum. While that appli-\ncation was pending, he married a U.S. citizen and sought citi-\nzenship on that basis.\n Jean Louis received a notice, dated August 2016, explain-\ning that he had to appear for an asylum hearing in June 2017.\nThe notice made clear that the immigration judge could hold\nthe hearing and remove Jean Louis if he did not attend.\n But Jean Louis, who does not speak English, wanted ad-\nvice. So he went to Gustave Thermitus. Thermitus is associated\nwith Caracol Financial. He is not a lawyer and does not belong\nto a legal organization. Still, Jean Louis thought Thermitus was\na lawyer.\n But Thermitus did not hold himself out as a lawyer. And\nJean Louis does not claim that Thermitus intentionally misled\nhim. According to Jean Louis, Thermitus held himself out as\n“an immigration expert that performed other work as well.” II\nApp. A6.\n Jean Louis asked Thermitus about his notice. Thermitus\ntold him he did not have to go to the hearing because he had\nanother path to citizenship: marriage. That advice was wrong.\n\n\n\n\n 3\n\f So Jean Louis did not attend his asylum hearing. The hear-\ning was held without him. Because he had conceded that he\nhad entered the country illegally, the judge found him remov-\nable and ordered him removed.\n Jean Louis then reached out to Thermitus. Thermitus said\nhe worked with a lawyer who could file a motion for Jean\nLouis. This was little comfort to Jean Louis, who until that mo-\nment had thought that Thermitus himself was a lawyer.\n So Jean Louis hired a real lawyer and moved to reopen his\nasylum case. The immigration judge denied the motion. The\nBoard of Immigration Appeals affirmed because no “excep-\ntional circumstances” had prevented Jean Louis from attending\nhis hearing. AR 3-4.\n The Board had jurisdiction under 8 C.F.R. § 1003.1(b)(3).\nWe have jurisdiction under 8 U.S.C. § 1252(a)(5). We review\nthe Board’s decision not to reopen an in absentia removal order\nfor abuse of discretion. Ramos-Olivieri v. Att’y Gen., 624 F.3d\n622, 625 (3d Cir. 2010). We review questions of law, including\nwhether an alien’s due process rights were violated, de novo.\nContreras v. Att’y Gen., 665 F.3d 578, 583 (3d Cir. 2012).\n II. A NON-LAWYER’S BAD ADVICE IS NOT AN EXCEP-\n TIONAL CIRCUMSTANCE\n\n The Board need reopen Jean Louis’s removal order only if\n“exceptional circumstances” prevented him from attending the\nhearing. 8 U.S.C. § 1229a(b)(5)(C) (also listing two other\ngrounds for rescinding a removal order, neither of which ap-\nplies here). He has not made that showing.\n\n\n\n\n 4\n\f To warrant reopening an in absentia removal order, excep-\ntional circumstances must be “beyond the control of the alien.”\n8 U.S.C. § 1229a(e)(1). The statute lists several examples: “bat-\ntery or extreme cruelty to the alien or any child or parent of the\nalien, serious illness of the alien, or serious illness or death of\nthe spouse, child, or parent of the alien.” Id. And it makes clear\nthat other circumstances do not count if they are “less compel-\nling” than these examples. Id. In short, exceptional circum-\nstances must not only be extreme, but also beyond the alien’s\ncontrol.\n Jean Louis’s situation does not meet this high bar. He fol-\nlowed bad advice from someone he trusted. It was his choice—\nand his alone—to seek out and follow that advice. So his cir-\ncumstances were not beyond his control. And his situation is a\nfar cry from the death, serious illness, or abuse outlined in the\nstatute. People make mistakes every day. But generally, mis-\ntakes do not rise to the extreme level of extreme cruelty, seri-\nous illness, or death. See id.\n Our precedent supports this result. We have held that fraud\ncommitted by lawyers and paralegals can qualify as an excep-\ntional circumstance. Borges v. Gonzales, 402 F.3d 398, 408 (3d\nCir. 2005). While some circuits have found that ineffective as-\nsistance of counsel qualifies too, we have neither adopted nor\nrejected that position. Id. But we have noted that the fraud al-\nleged in Borges was more extreme than a typical ineffective-\nassistance claim. Id.\n Jean Louis’s case differs from Borges in two important\nways. First, Thermitus is neither a lawyer nor a legal assistant.\nSo accepting Jean Louis’s argument would extend Borges far\n\n\n\n\n 5\n\fbeyond legal representation. Second, Jean Louis has not shown\nthat Thermitus defrauded him. Thermitus never pretended to\nbe a lawyer or offered to represent Jean Louis in court. But in\nBorges, fraud was “the crucial issue.” Id. Borges carefully lim-\nited its holding to fraud committed by lawyers and legal organ-\nizations. We will not extend Borges’s limited holding beyond\nthat boundary.\n III. IN ABSENTIA REMOVAL ORDERS DO NOT CATEGORI-\n CALLY VIOLATE DUE PROCESS\n\n Next, Jean Louis argues that his in absentia removal order\nviolates his due process rights. Due process indeed guarantees\naliens a hearing and an opportunity to be heard and present ev-\nidence. Abdulrahman v. Ashcroft, 330 F.3d 587, 596 (3d Cir.\n2003). But the immigration judge did not violate these rights\nby holding the hearing without Jean Louis. Jean Louis had an\nopportunity to attend his hearing, but chose not to.\n Jean Louis’s argument would have troubling consequences:\nIf we held that in absentia hearings violated due process, we\nwould effectively invalidate 8 U.S.C. § 1229a(b)(5)(A), which\nspecifically permits in absentia hearings. And we would per-\nversely let aliens avoid removal by not attending their hearings.\nSo in absentia removal orders do not categorically violate due\nprocess.\n Jean Louis relies on one of our precedents to make his due\nprocess argument, but this precedent is distinguishable. In\nCabrera-Perez v. Gonzales, an alien arrived for her hearing fif-\nteen to twenty minutes late. 456 F.3d 109, 117 (3d Cir. 2006).\nWe held that due process forbids treating slight lateness as a\n\n\n\n\n 6\n\ffailure to appear if, when the alien arrives, the judge “is either\nstill on the bench or recently retired.” Id. at 116. But coming\nlate is very different from not showing up at all. Id. at 117. Jean\nLouis did not show up at all, so Cabrera-Perez is inapt. His\nremoval order satisfied due process.\n *****\n We recognize that this result may seem harsh. Jean Louis\nrelied on someone whom he thought was an expert. But this\nsituation, while regrettable, is not exceptional. So we will deny\nhis petition.\n\n\n\n\n 7\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Dieuland JEAN LOUIS, Petitioner v. ATTORNEY GENERAL UNITED STATES of America, Respondent\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-23\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _______________\\n\\n No. 18-2082\\n _______________\\n\\n DIEULAND JEAN LOUIS,\\n Petitioner\\n\\n v.\\n\\nATTORNEY GENERAL UNITED STATES OF AMERICA,\\n Respondent\\n _______________\\n\\n On Petition for Review of a Decision of the\\n United States Department of Justice\\n Board of Immigration Appeals\\n (Agency No. A206-596-150)\\n Immigration Judge: Honorable Ramin Rastegar\\n _______________\\n\\n Submitted Under Third Circuit L.A.R. 34.1(a)\\n on November 14, 2018\\n\\n Before: GREENAWAY, JR., SHWARTZ, and BIBAS,\\n Circuit Judges.\\n\\n (Filed: January 23, 2019)\\n\\f Raymond S. Vivino\\n Vivino & Vivino\\n 401 Hamburg Turnpike\\n Suite 201\\n Wayne, NJ 07474\\n Counsel for Petitioner\\n\\n Tim Ramnitz\\n Jennifer A. Singer\\n John D. Williams\\n United States Department of Justice\\n Office of Immigration Litigation\\n Room 10006\\n P.O. Box 878\\n Ben Franklin Station\\n Washington, DC 20044\\n Counsel for Respondent\\n _______________\\n\\n OPINION OF THE COURT\\n _______________\\n\\nBIBAS, Circuit Judge.\\n A non-lawyer “immigration expert” advised Dieuland Jean\\nLouis that he could miss his asylum hearing without conse-\\nquence. I App. A6-7. So he did. But the “immigration expert”\\nwas wrong—and an immigration judge relied on Jean Louis’s\\nabsence to order his removal in absentia. Id.\\n Jean Louis now contends that we should reopen that order\\nbecause the non-lawyer’s advice qualifies as an exceptional\\n\\n\\n\\n\\n 2\\n\\fcircumstance. But that is not the law. Exceptional circum-\\nstances must be grave and beyond the applicant’s control. And\\nholding the hearing without Jean Louis did not violate due pro-\\ncess because he had the opportunity to attend. He chose not to.\\nSo we will deny his petition for review.\\n I. BACKGROUND\\n Jean Louis, a native and citizen of Haiti, entered the United\\nStates illegally. He later applied for asylum. While that appli-\\ncation was pending, he married a U.S. citizen and sought citi-\\nzenship on that basis.\\n Jean Louis received a notice, dated August 2016, explain-\\ning that he had to appear for an asylum hearing in June 2017.\\nThe notice made clear that the immigration judge could hold\\nthe hearing and remove Jean Louis if he did not attend.\\n But Jean Louis, who does not speak English, wanted ad-\\nvice. So he went to Gustave Thermitus. Thermitus is associated\\nwith Caracol Financial. He is not a lawyer and does not belong\\nto a legal organization. Still, Jean Louis thought Thermitus was\\na lawyer.\\n But Thermitus did not hold himself out as a lawyer. And\\nJean Louis does not claim that Thermitus intentionally misled\\nhim. According to Jean Louis, Thermitus held himself out as\\n“an immigration expert that performed other work as well.” II\\nApp. A6.\\n Jean Louis asked Thermitus about his notice. Thermitus\\ntold him he did not have to go to the hearing because he had\\nanother path to citizenship: marriage. That advice was wrong.\\n\\n\\n\\n\\n 3\\n\\f So Jean Louis did not attend his asylum hearing. The hear-\\ning was held without him. Because he had conceded that he\\nhad entered the country illegally, the judge found him remov-\\nable and ordered him removed.\\n Jean Louis then reached out to Thermitus. Thermitus said\\nhe worked with a lawyer who could file a motion for Jean\\nLouis. This was little comfort to Jean Louis, who until that mo-\\nment had thought that Thermitus himself was a lawyer.\\n So Jean Louis hired a real lawyer and moved to reopen his\\nasylum case. The immigration judge denied the motion. The\\nBoard of Immigration Appeals affirmed because no “excep-\\ntional circumstances” had prevented Jean Louis from attending\\nhis hearing. AR 3-4.\\n The Board had jurisdiction under 8 C.F.R. § 1003.1(b)(3).\\nWe have jurisdiction under 8 U.S.C. § 1252(a)(5). We review\\nthe Board’s decision not to reopen an in absentia removal order\\nfor abuse of discretion. Ramos-Olivieri v. Att’y Gen., 624 F.3d\\n622, 625 (3d Cir. 2010). We review questions of law, including\\nwhether an alien’s due process rights were violated, de novo.\\nContreras v. Att’y Gen., 665 F.3d 578, 583 (3d Cir. 2012).\\n II. A NON-LAWYER’S BAD ADVICE IS NOT AN EXCEP-\\n TIONAL CIRCUMSTANCE\\n\\n The Board need reopen Jean Louis’s removal order only if\\n“exceptional circumstances” prevented him from attending the\\nhearing. 8 U.S.C. § 1229a(b)(5)(C) (also listing two other\\ngrounds for rescinding a removal order, neither of which ap-\\nplies here). He has not made that showing.\\n\\n\\n\\n\\n 4\\n\\f To warrant reopening an in absentia removal order, excep-\\ntional circumstances must be “beyond the control of the alien.”\\n8 U.S.C. § 1229a(e)(1). The statute lists several examples: “bat-\\ntery or extreme cruelty to the alien or any child or parent of the\\nalien, serious illness of the alien, or serious illness or death of\\nthe spouse, child, or parent of the alien.” Id. And it makes clear\\nthat other circumstances do not count if they are “less compel-\\nling” than these examples. Id. In short, exceptional circum-\\nstances must not only be extreme, but also beyond the alien’s\\ncontrol.\\n Jean Louis’s situation does not meet this high bar. He fol-\\nlowed bad advice from someone he trusted. It was his choice—\\nand his alone—to seek out and follow that advice. So his cir-\\ncumstances were not beyond his control. And his situation is a\\nfar cry from the death, serious illness, or abuse outlined in the\\nstatute. People make mistakes every day. But generally, mis-\\ntakes do not rise to the extreme level of extreme cruelty, seri-\\nous illness, or death. See id.\\n Our precedent supports this result. We have held that fraud\\ncommitted by lawyers and paralegals can qualify as an excep-\\ntional circumstance. Borges v. Gonzales, 402 F.3d 398, 408 (3d\\nCir. 2005). While some circuits have found that ineffective as-\\nsistance of counsel qualifies too, we have neither adopted nor\\nrejected that position. Id. But we have noted that the fraud al-\\nleged in Borges was more extreme than a typical ineffective-\\nassistance claim. Id.\\n Jean Louis’s case differs from Borges in two important\\nways. First, Thermitus is neither a lawyer nor a legal assistant.\\nSo accepting Jean Louis’s argument would extend Borges far\\n\\n\\n\\n\\n 5\\n\\fbeyond legal representation. Second, Jean Louis has not shown\\nthat Thermitus defrauded him. Thermitus never pretended to\\nbe a lawyer or offered to represent Jean Louis in court. But in\\nBorges, fraud was “the crucial issue.” Id. Borges carefully lim-\\nited its holding to fraud committed by lawyers and legal organ-\\nizations. We will not extend Borges’s limited holding beyond\\nthat boundary.\\n III. IN ABSENTIA REMOVAL ORDERS DO NOT CATEGORI-\\n CALLY VIOLATE DUE PROCESS\\n\\n Next, Jean Louis argues that his in absentia removal order\\nviolates his due process rights. Due process indeed guarantees\\naliens a hearing and an opportunity to be heard and present ev-\\nidence. Abdulrahman v. Ashcroft, 330 F.3d 587, 596 (3d Cir.\\n2003). But the immigration judge did not violate these rights\\nby holding the hearing without Jean Louis. Jean Louis had an\\nopportunity to attend his hearing, but chose not to.\\n Jean Louis’s argument would have troubling consequences:\\nIf we held that in absentia hearings violated due process, we\\nwould effectively invalidate 8 U.S.C. § 1229a(b)(5)(A), which\\nspecifically permits in absentia hearings. And we would per-\\nversely let aliens avoid removal by not attending their hearings.\\nSo in absentia removal orders do not categorically violate due\\nprocess.\\n Jean Louis relies on one of our precedents to make his due\\nprocess argument, but this precedent is distinguishable. In\\nCabrera-Perez v. Gonzales, an alien arrived for her hearing fif-\\nteen to twenty minutes late. 456 F.3d 109, 117 (3d Cir. 2006).\\nWe held that due process forbids treating slight lateness as a\\n\\n\\n\\n\\n 6\\n\\ffailure to appear if, when the alien arrives, the judge “is either\\nstill on the bench or recently retired.” Id. at 116. But coming\\nlate is very different from not showing up at all. Id. at 117. Jean\\nLouis did not show up at all, so Cabrera-Perez is inapt. His\\nremoval order satisfied due process.\\n *****\\n We recognize that this result may seem harsh. Jean Louis\\nrelied on someone whom he thought was an expert. But this\\nsituation, while regrettable, is not exceptional. So we will deny\\nhis petition.\\n\\n\\n\\n\\n 7\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":76,"cells":{"id":{"kind":"number","value":4584869,"string":"4,584,869"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Frank Andrew v. Todd Buskirk"},"decision_date":{"kind":"string","value":"2019-01-25"},"docket_number":{"kind":"string","value":"17-3011"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before: GREENAWAY, JR., RESTREPO, and BIBAS, Circuit Judges The petition for rehearing\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"010combined\", \"text\": \"UNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\\n\\n ___________\\n\\n No. 17-3011\\n ___________\\n\\n FRANK E. ANDREW,\\n Appellant\\n\\n v.\\n\\n TODD BUSKIRK; FRANK LONGENBACH; ROBIN STANLEY\\n _________________________________________\\n\\n APPEAL FROM THE UNITED STATES DISTRICT COURT\\n FOR THE EASTERN DISTRICT OF PENNSYLVANIA\\n (E.D. Pa. No. 5-16-cv-03851)\\n ________________\\n\\n SUR PETITION FOR PANEL REHEARING\\n ______________\\n\\n\\nBefore: GREENAWAY, JR., RESTREPO, and BIBAS, Circuit Judges\\n\\n\\n The petition for rehearing filed by Appellant in the above-entitled case having\\n\\nbeen submitted to the judges who participated in the decision of this Court, it is hereby\\n\\nORDERED that the petition for rehearing by the panel is GRANTED. Pursuant to 3d\\n\\nCir. I.O.P. 8.3.1, the panel’s previous non-precedential opinion and judgment filed\\n\\nNovember 19, 2018 are hereby VACATED. The panel will issue an opinion and\\n\\naccompanying judgment at a later date.\\n\\n By the Court,\\n\\n s/ L. Felipe Restrepo\\n Circuit Judge\\nDated: January 25, 2019\\nJK/cc: All Counsel of Record\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4362122/\", \"author_raw\": \"\"}]}"},"judge1":{"kind":"string","value":"GREENAWAY JR"},"judge2":{"kind":"string","value":"RESTREPO"},"judge3":{"kind":"string","value":"BIBAS"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"GREENAWAY JR\": \", Circuit\", \"RESTREPO\": \", Circuit\", \"BIBAS\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4584869/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Frank Andrew v. Todd Buskirk\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-25\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nUNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\n\n ___________\n\n No. 17-3011\n ___________\n\n FRANK E. ANDREW,\n Appellant\n\n v.\n\n TODD BUSKIRK; FRANK LONGENBACH; ROBIN STANLEY\n _________________________________________\n\n APPEAL FROM THE UNITED STATES DISTRICT COURT\n FOR THE EASTERN DISTRICT OF PENNSYLVANIA\n (E.D. Pa. No. 5-16-cv-03851)\n ________________\n\n SUR PETITION FOR PANEL REHEARING\n ______________\n\n\nBefore: GREENAWAY, JR., RESTREPO, and BIBAS, Circuit Judges\n\n\n The petition for rehearing filed by Appellant in the above-entitled case having\n\nbeen submitted to the judges who participated in the decision of this Court, it is hereby\n\nORDERED that the petition for rehearing by the panel is GRANTED. Pursuant to 3d\n\nCir. I.O.P. 8.3.1, the panel’s previous non-precedential opinion and judgment filed\n\nNovember 19, 2018 are hereby VACATED. The panel will issue an opinion and\n\naccompanying judgment at a later date.\n\n By the Court,\n\n s/ L. Felipe Restrepo\n Circuit Judge\nDated: January 25, 2019\nJK/cc: All Counsel of Record\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Frank Andrew v. Todd Buskirk\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-25\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nUNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\\n\\n ___________\\n\\n No. 17-3011\\n ___________\\n\\n FRANK E. ANDREW,\\n Appellant\\n\\n v.\\n\\n TODD BUSKIRK; FRANK LONGENBACH; ROBIN STANLEY\\n _________________________________________\\n\\n APPEAL FROM THE UNITED STATES DISTRICT COURT\\n FOR THE EASTERN DISTRICT OF PENNSYLVANIA\\n (E.D. Pa. No. 5-16-cv-03851)\\n ________________\\n\\n SUR PETITION FOR PANEL REHEARING\\n ______________\\n\\n\\nBefore: GREENAWAY, JR., RESTREPO, and BIBAS, Circuit Judges\\n\\n\\n The petition for rehearing filed by Appellant in the above-entitled case having\\n\\nbeen submitted to the judges who participated in the decision of this Court, it is hereby\\n\\nORDERED that the petition for rehearing by the panel is GRANTED. Pursuant to 3d\\n\\nCir. I.O.P. 8.3.1, the panel’s previous non-precedential opinion and judgment filed\\n\\nNovember 19, 2018 are hereby VACATED. The panel will issue an opinion and\\n\\naccompanying judgment at a later date.\\n\\n By the Court,\\n\\n s/ L. Felipe Restrepo\\n Circuit Judge\\nDated: January 25, 2019\\nJK/cc: All Counsel of Record\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":77,"cells":{"id":{"kind":"number","value":8443855,"string":"8,443,855"},"name":{"kind":"string","value":"Frank E. ANDREW v. Todd BUSKIRK Frank Longenbach Robin Stanley"},"name_abbreviation":{"kind":"string","value":"Andrew v. Buskirk"},"decision_date":{"kind":"string","value":"2019-01-25"},"docket_number":{"kind":"string","value":"No. 17-3011"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/8415282/\"}]}"},"judge1":{"kind":"string","value":""},"judge2":{"kind":"string","value":""},"judge3":{"kind":"string","value":""},"exactly_three_caps":{"kind":"number","value":0,"string":"0"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/8443855/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":0,"string":"0"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Frank E. ANDREW v. Todd BUSKIRK Frank Longenbach Robin Stanley\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-25\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Frank E. ANDREW v. Todd BUSKIRK Frank Longenbach Robin Stanley\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-25\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":78,"cells":{"id":{"kind":"number","value":4585443,"string":"4,585,443"},"name":{"kind":"string","value":"Ever BEDOYA; Diego Gonzales; Manuel Decastro, on Behalf of Themselves and All Others Similarly Situated v. AMERICAN EAGLE EXPRESS INC., D/B/A AEX Group v. KV Service, LLC; M&J Express, LLC; A&D Delivery Express, LLC American Eagle Express, Inc., Appellant"},"name_abbreviation":{"kind":"string","value":"Ever Bedoya v. American Eagle Express Inc"},"decision_date":{"kind":"string","value":"2019-01-29"},"docket_number":{"kind":"string","value":"18-1641"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Greenaway, Shwartz, Bibas\", \"parties\": \"\", \"opinions\": [{\"author\": \"SHWARTZ, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 18-1641\\n _____________\\n\\n EVER BEDOYA; DIEGO GONZALES; MANUEL\\n DECASTRO,\\n on behalf of themselves and all others similarly situated\\n\\n v.\\n\\nAMERICAN EAGLE EXPRESS INC, d/b/a AEX GROUP\\n\\n v.\\n\\n KV SERVICE, LLC; M&J EXPRESS, LLC; A&D\\n DELIVERY EXPRESS, LLC\\n\\n American Eagle Express, Inc.,\\n Appellant\\n ______________\\n\\n Appeal from the United States District Court\\n for the District of New Jersey\\n (D.C. No. 2-14-cv-02811)\\n District Judge: Hon. Esther Salas\\n ______________\\n\\f Argued November 14, 2018\\n ______________\\n\\n Before: GREENAWAY, JR., SHWARTZ, and BIBAS,\\n Circuit Judges.\\n\\n (Opinion Filed: January 29, 2019)\\n\\nHarold L. Lichten [ARGUED]\\nLichten & Liss-Riordan\\n729 Boylston Street\\nSuite 2000\\nBoston, MA 02116\\n\\nR. Andrew Santillo\\nPeter D. Winebrake\\nWinebrake & Santillo\\n715 Twinning Road\\nSuite 211, Twinning Office Center\\nDresher, PA 19025\\n\\n Counsel for Plaintiff-Appellees\\n\\nJoseph C. DeBlasio [ARGUED]\\nJackson Lewis\\n220 Headquarters Plaza\\nEast Tower, 7th Floor\\nMorristown, NJ 07960\\n\\n Counsel for Defendant-Appellant\\n\\nAdina H. Rosenbaum\\nPublic Citizen Litigation Group\\n\\n\\n\\n\\n 2\\n\\f1600 20th Street, NW.\\nWashington, DC 20009\\n\\n Counsel for Amicus Public Citizen Inc.\\n\\n\\nChristopher W. Weber [ARGUED]\\nEmily M. Bisnauth\\nOffice of Attorney General of New Jersey\\nDepartment of Law & Public Safety\\nRichard J. Hughes Justice Complex\\n25 Market Street\\nP.O. Box 112\\nTrenton, NJ 08625\\n\\n Counsel for Amicus New Jersey Department of Labor\\n and Workforce Development\\n\\n\\n ___________\\n\\n OPINION\\n ___________\\n\\n\\nSHWARTZ, Circuit Judge.\\n\\n Plaintiff delivery drivers Ever Bedoya, Diego Gonzalez,\\nand Manuel Decastro (collectively, “the Drivers”) filed a\\nputative class action against Defendant American Eagle\\nExpress, Inc., (“AEX”), alleging that AEX misclassified them\\nas independent contractors when they are actually employees\\nunder the New Jersey Wage and Hour Law (“NJWHL”), N.J.\\n\\n\\n\\n\\n 3\\n\\fStat. Ann. §§ 34:11-56a to -56a3, and the New Jersey Wage\\nPayment Law (“NJWPL”), N.J. Stat. Ann. §§ 34:11-4.1 to -\\n4:14. AEX moved for judgment on the pleadings pursuant to\\nFed. R. Civ. P. 12(c), arguing that the Drivers’ claims are\\npreempted by the Federal Aviation Authorization\\nAdministration Act of 1994 (“FAAAA”), 49 U.S.C. §§ 14501-\\n06. The District Court denied AEX’s motion and certified the\\norder for interlocutory appeal. Because the FAAAA does not\\npreempt the New Jersey law for determining employment\\nstatus for the purposes of NJWHL and NJWPL, we will affirm\\nthe order and remand for further proceedings.\\n\\n I\\n\\n AEX is a logistics company that provides delivery\\nservices to various medical organizations. The Drivers are\\nNew Jersey residents who make deliveries for AEX. The\\nDrivers filed this putative class action against AEX seeking,\\namong other things, a judgment declaring that they are\\nemployees of AEX, rather than independent contractors, which\\nentitles them to compensation under the NJWHL and NJWPL.1\\nAEX moved for judgment on the pleadings, arguing that the\\nFAAAA preempts the Drivers’ claims.\\n\\n The District Court denied AEX’s motion, Bedoya v.\\nAm. Eagle Express, Civ. No. 14-2811, 2017 WL 4330351, at\\n*1 (D.N.J. Sept. 29, 2017), reasoning that “[t]here is no clear\\nindication” that Congress intended for the FAAAA to preempt\\nstate wage laws, Dkt. 109 at 6, 10, and that the connection\\nbetween regulation of AEX’s workforce and the “prices,\\n\\n 1\\n The District Court has jurisdiction pursuant to 28\\nU.S.C. § 1332(d).\\n\\n\\n\\n\\n 4\\n\\froutes, and services” provided to its consumers is too\\nattenuated to justify preempting claims under the NJWHL and\\nNJWPL, id. at 8-9. We now consider AEX’s interlocutory\\nappeal of the order denying the motion pursuant to 28 U.S.C.\\n§ 1292(b). Bedoya, 2017 WL 4330351, at *1-4.\\n\\n II2\\n\\n A\\n\\n The question before us is whether the FAAAA preempts\\nNew Jersey’s test for determining employment classification\\nfor purposes of the NJWHL and NJWPL. Under this test,\\nworkers performing services for a given company in exchange\\nfor pay are deemed employees unless the company can\\ndemonstrate each of the following:\\n\\n A. Such individual has been and will continue to\\n be free from control or direction over the\\n\\n 2\\n We review an order granting or denying a motion for\\njudgment on the pleadings de novo. Zimmerman v. Corbett,\\n873 F.3d 414, 417 (3d Cir. 2017) (citing Allah v. Al-Hafeez,\\n226 F.3d 247, 249 (3d Cir. 2007)). Judgment will not be\\ngranted unless the movant “clearly establishes there are no\\nmaterial issues of fact, and he is entitled to judgment as a\\nmatter of law.” Sikirica v. Nationwide Ins. Co., 416 F.3d 214,\\n220 (3d Cir. 2005) (citation omitted). In considering a motion\\nfor judgment on the pleadings, we must accept as true all facts\\npresented in the complaint and answer and draw all reasonable\\ninferences in favor of the non-moving party—here, the\\nDrivers. Id. at 417-18. While AEX implores us to look beyond\\nthe pleadings, we may not.\\n\\n\\n\\n\\n 5\\n\\f performance of such service, both under his\\n contract of service and in fact; and\\n\\n B. Such service is either outside the usual course\\n of the business for which such service is\\n performed, or that such service is performed\\n outside of all the places of business of the\\n enterprise for which such service is\\n performed; and\\n\\n C. Such individual is customarily engaged in an\\n independently established trade, occupation,\\n profession, or business.\\n\\nN.J. Stat. Ann. §§ 43:21-19(i)(6)(A)-(C) (“New Jersey ABC\\nclassification test”). Where a company successfully\\ndemonstrates all three elements with respect to a worker, that\\nworker qualifies as an independent contractor under the\\nNJWHL and NJWPL. Hargrove v. Sleepy’s, LLC, 106 A.3d\\n449, 458 (N.J. 2015). The company, in turn, is exempt from\\nrequirements under those statutes with respect to the worker.\\nId. For individuals classified as employees, however, the\\nemploying company is subject to each statute’s obligations,\\nincluding minimum and overtime wage requirements, N.J.\\nStat. Ann. § 34:11-56a4, conditions regarding the time and\\nmode of pay, N.J. Stat. Ann. § 34:11-4.2, 4.2a, and restrictions\\non pay deductions, N.J. Stat. Ann. § 34:11-4.4. AEX contends\\nthat the New Jersey ABC classification test is preempted by the\\nFAAAA.\\n\\n\\n\\n\\n 6\\n\\f B\\n\\n The preemption doctrine stems from the Supremacy\\nClause, which provides that “the Laws of the United States . . .\\nshall be the supreme Law of the Land . . . any Thing in the\\nConstitution or Laws of any State to the Contrary\\nnotwithstanding.” U.S. Const. art. VI, cl. 2. Thus, “Congress\\n. . . has the power to preempt state law.” In re Vehicle Carrier\\nServs. Antitrust Litig., 846 F.3d 71, 83 (3d Cir. 2017) (citing\\nArizona v. United States, 567 U.S. 387 (2012)), cert denied sub\\nnom., Alban v. Nippon Yusen Kabushiki Kaisha, 138 S. Ct.\\n114 (2017). There are three categories of preemption: field\\npreemption, conflict preemption, and express preemption.\\nHolk v. Snapple Beverage Corp., 575 F.3d 329, 334 (3d Cir.\\n2009) (citing Hillsborough County, Fla. v. Automated Med.\\nLabs., Inc., 471 U.S. 707, 713 (1985)).\\n\\n Because preemption is an affirmative defense, we\\nexamine the specific preemption defense asserted. In re\\nVehicle, 846 F.3d at 84 (citing Oneok, Inc. v. Learjet, Inc., 135\\nS. Ct. 1591 (2015)). AEX argues that New Jersey’s ABC\\nclassification test is subject to express preemption under 49\\nU.S.C. § 14501(c)(1). “Express preemption requires a[n]\\nanalysis of whether ‘[s]tate action may be foreclosed by\\nexpress language in a congressional enactment.’” Lupian v.\\nJoseph Cory Holdings, LLC, 905 F.3d 127, 131 (3d Cir. 2018)\\n(alteration in original) (quoting Lorillard Tobacco Co. v.\\nReilly, 533 U.S. 525, 541 (2001)).\\n\\n In evaluating AEX’s argument, we first decide whether\\nthe presumption against preemption applies. City of Columbus\\nv. Ours Garage & Wrecker Serv., Inc., 536 U.S. 424, 438\\n(2002) (applying the presumption against preemption in the\\n\\n\\n\\n\\n 7\\n\\fFAAAA context). Under this presumption, “the historic police\\npowers of the States” are “not to be superseded by [a] [f]ederal\\n[a]ct unless that was the clear and manifest purpose of\\nCongress.” Sikkelee v. Precision Airmotive Corp., 822 F.3d\\n680, 687 (3d Cir. 2016) (quoting Wyeth v. Levine, 555 U.S.\\n555, 565 (2009)). Thus, we “presume claims based on laws\\nembodying state police powers are not preempted.” In re\\nVehicle, 846 F.3d at 84; see also Farina v. Nokia Inc., 625 F.3d\\n97, 116 (3d Cir. 2010).\\n\\n Many employment regulations, such as the wage laws\\nat issue here, seek to ensure workers receive fair pay. Because\\nthey protect workers, they are within New Jersey’s police\\npower, and the presumption against preemption by federal law\\napplies. See, e.g., Lupian, 905 F.3d at 131 (stating wage laws\\nthat protect workers represent an exercise of “police power”);\\nsee also Fort Halifax Packing Co. v. Coyne, 482 U.S. 1, 21\\n(1987) (applying the presumption against preemption to a state\\nlabor law regarding severance pay “since the establishment of\\nlabor standards falls within the traditional police power of the\\nState”).\\n\\n The presumption is rebutted where Congress had a\\n“clear and manifest purpose” to preempt state laws. Sikkelee,\\n822 F.3d at 687 (citation omitted); see also Cipollone v. Liggett\\nGrp., Inc., 505 U.S. 504, 516 (1992) (directing courts to\\nexamine congressional intent, the “ultimate touchstone” in\\ndiscerning the preemptive scope of a statute (internal quotation\\nmarks and citation omitted)). To determine Congress’\\npurpose, we look to the plain language of the statute and, if\\nnecessary, to the statutory framework as a whole. Medtronic,\\nInc. v. Lohr, 518 U.S. 470, 486 (1996) (citation omitted).\\nThus, we next examine Congress’ purpose in enacting the\\n\\n\\n\\n\\n 8\\n\\fFAAAA and the Airline Deregulation Act of 1978 (“ADA”),\\n49 U.S.C. §§ 40101-130, an earlier statute with a similar\\npreemption provision.\\n\\n C\\n\\n In 1978, following a long period of heightened\\nregulation, Congress enacted the ADA, which sought to\\nderegulate the air-travel industry to “maxim[ize] reliance on\\ncompetitive market forces.” Morales v. Trans World Airlines,\\nInc., 504 U.S. 374, 378 (1992) (quoting 49 U.S.C. App. §\\n1302(a)(4)). To ensure that this objective would not be\\nfrustrated by state regulation, Congress included a preemption\\nprovision providing that “no State . . . shall enact or enforce\\nany law . . . relating to rates, routes, or services of any air\\ncarrier.” Id. at 420 (Stevens, J., dissenting) (quoting 49 U.S.C.\\nApp. § 1305(a)).\\n\\n Congress enacted similar laws focused on deregulating\\ninterstate trucking, culminating with the passage of the\\nFAAAA in 1994. Lupian, 905 F.3d at 132-33. Via the\\nFAAAA, Congress sought to “level the playing field” between\\nair carriers and motor carriers so that both could benefit from\\nfederal deregulation. H.R. Conf. Rep. No. 103-677, at 88\\n(1994); see also Californians for Safe & Competitive Dump\\nTruck Transp. v. Mendonca, 152 F.3d 1184, 1187-88 (9th Cir.\\n1998) (detailing FAAAA legislative history). The FAAAA\\ncontains a preemption provision modeled after the ADA’s,\\nproviding, with limited exceptions, that:\\n\\n a State . . . may not enact or enforce a law,\\n regulation, or other provision having the force\\n and effect of law related to a price, route, or\\n\\n\\n\\n\\n 9\\n\\f service of any motor carrier . . . with respect to\\n the transportation of property.\\n\\n49 U.S.C. § 14501(c)(1). Because of the parallels between the\\nADA and FAAAA, ADA cases are instructive regarding the\\nscope of FAAAA preemption. See Rowe v. N.H. Motor\\nTransp. Ass’n, 552 U.S. 364, 370 (2008) (analyzing FAAAA\\npreemption using ADA cases as guidance). As with the ADA,\\nthe FAAAA preemption provision’s central objective is to\\navoid frustrating the statute’s deregulatory purpose by\\npreventing states from imposing “a patchwork of state service-\\ndetermining laws.” Dan’s City Used Cars, Inc. v. Pelkey, 569\\nU.S. 251, 264 (2013) (quoting Rowe, 552 U.S. at 373). The\\nFAAAA, however, has a qualifier that is absent from the ADA:\\nthe preempted state law must relate to prices, routes, or services\\n“with respect to the transportation of property.” 49 U.S.C.\\n§ 14501(c)(1). The Supreme Court has recognized that this\\nlanguage “massively limits the scope of preemption ordered by\\nthe FAAAA.” Dan’s City, 569 U.S. at 261 (internal citation\\nand quotation marks omitted).\\n\\n Further insight into the limits of FAAAA preemption\\ncomes from the subjects Congress considered when enacting\\nthat statute. “Congress identified ten jurisdictions (nine states\\nand the District of Columbia . . . ) that did not regulate intrastate\\nprices, routes, and services.” Cal. Trucking Ass’n v. Su, 903\\nF.3d 953, 967 (9th Cir. 2018) (citing Mendonca, 152 F.3d at\\n1187). By implication, Congress determined that the laws then\\nin existence in those jurisdictions did not contravene its\\nderegulatory goals and thus were not preempted. Id.\\n\\n The Supreme Court has also articulated several\\nprinciples that inform us about the breadth of FAAAA\\n\\n\\n\\n\\n 10\\n\\fpreemption. First, the “related to” language from the FAAAA\\npreemption clause gives it a broad scope, encompassing any\\nstate actions that have “a connection with, or [make] reference\\nto . . . rates, routes, or services” of a motor carrier. Nw., Inc.\\nv. Ginsberg, 572 U.S. 273, 280-81 (2014) (internal quotation\\nmarks and citation omitted) (interpreting the ADA). While this\\nlanguage covers any state law that has a connection with or\\nrefers to “price[s], route[s], [or] service[s,]” id. at 280, “the\\nbreadth of the words ‘related to’ does not mean the sky is the\\nlimit,” Dan’s City, 569 U.S. at 260. Drawing from case law\\nexamining similar wording in the preemption provision of the\\nEmployee Retirement Income Security Act of 1974, 29 U.S.C.\\n§ 1144(a), see, e.g., Morales, 504 U.S. at 383-84, the Supreme\\nCourt has observed that reading the phrase “related to” with\\n“uncritical literalism” would render preemption an endless\\nexercise, Dan’s City, 569 U.S. at 260-61 (citation omitted),\\nbecause “everything [is] relat[ed] to everything else in some\\nmanner[,]” Schwann v. FedEx Ground Package Sys., Inc., 813\\nF.3d 429, 436 (1st Cir. 2016) (citing N.Y. State Conference of\\nBlue Cross & Blue Shield Plans v. Travelers Ins. Co., 514 U.S.\\n645, 655 (1955)).\\n\\n Second, FAAAA preemption reaches laws that affect\\nprices, routes, or services even if the effect “is only indirect.”\\nRowe, 552 U.S. at 370 (quoting Morales, 504 U.S. at 386).\\nHowever, where a law’s impact on carrier prices, routes, or\\nservices is so indirect that the law affects them “in only a\\ntenuous, remote, or peripheral . . . manner,” the law is not\\npreempted. Dan’s City, 569 U.S. at 261 (quoting Rowe, 552\\nU.S. at 371); Morales, 504 U.S. at 390 (quoting Shaw v. Delta\\nAir Lines, Inc., 463 U.S. 85, 100 n.21 (1983)).\\n\\n\\n\\n\\n 11\\n\\f Finally, preemption occurs where a state law has “a\\n‘significant impact’ on carrier rates, routes, or services.”3\\nRowe, 552 U.S. at 375 (emphasis omitted) (quoting Morales,\\n504 U.S. at 390).\\n\\n Mindful of these principles, we next review the case law\\nfor guidance concerning whether a law has a direct or indirect\\neffect and whether it has a significant or insignificant effect.\\nFrom our review, we identify factors courts examine and set\\nforth those factors that may shed light on a law’s directness and\\nthose that may reflect the significance of the law’s effect on the\\nregulated entities at issue.\\n\\n D\\n\\n Neither the Supreme Court nor our Court has recited\\nprecise standards for evaluating directness or significance, but\\ncases addressing the issue provide some guidance. For\\nexample, the Supreme Court has held that consumer protection\\nand fraud laws used to regulate frequent-flyer programs could\\ndirectly and significantly affect prices and services and are thus\\npreempted. See Am. Airlines, Inc. v. Wolens, 513 U.S. 219,\\n223 (1995); Morales, 504 U.S. at 388-89. Similarly, the Court\\ndetermined that a Maine law requiring a specific procedure to\\nverify the recipient of tobacco deliveries was preempted by the\\nFAAAA because it dictated a service that tobacco motor\\ncarriers were required to provide for property they transported.\\nRowe, 552 U.S. at 372. In addition, we recently observed that\\n\\n 3\\n The Supreme Court also noted that “it makes no\\ndifference whether a state law is ‘consistent’ or ‘inconsistent’\\nwith federal regulation.” Rowe, 552 U.S. at 370 (quoting\\nMorales, 504 U.S. at 386-87).\\n\\n\\n\\n\\n 12\\n\\fthe FAAAA’s “preemption clause undoubtedly applies, for\\nexample, to state laws directly restricting types of goods that\\ncan be carried by trucks, tariffs, and barriers to entry.” Lupian,\\n905 F.3d at 135; H.R. Conf. Rep. No. 103-677, at 86 (1994).\\n\\n On the other hand, the FAAAA itself, the Supreme\\nCourt, and the courts of appeals have identified laws that are\\ntoo “tenuous, remote, or peripheral” from carrier prices, routes,\\nand services to trigger preemption. See, e.g., Rowe, 552 U.S.\\nat 371; Dilts v. Penske Logistics, LLC, 769 F.3d 637, 646 (9th\\nCir. 2014). The FAAAA explicitly exempts from preemption\\nlaws governing motor vehicle safety, local route controls based\\non vehicle size and weight, and driver insurance requirements.4\\n49 U.S.C. § 14501(c)(2)(A). The Supreme Court has stated\\nthat the FAAAA does not preempt laws prohibiting\\nprostitution, gambling, and “obscene depictions,” Morales,\\n504 U.S. at 390, or those addressing zoning, Dan’s City, 569\\nU.S. at 264. We have observed that “garden variety\\nemployment claim[s]” evade ADA and FAAAA preemption\\nbecause they are “too remote and too attenuated” from carrier\\nprices, services, or routes. Lupian, 905 F.3d at 134 (quoting\\nGary v. Air Grp., Inc., 397 F.3d 183, 189 (3d Cir. 2005)). As\\nrelevant to this case, we recently held that wage claims under\\nthe Illinois Wage Payment and Collection Act (“IWPCA”),\\n820 Ill. Comp. Stat. 115/1-115/15, are not preempted under the\\nFAAAA because they are “too far removed from the statute’s\\n\\n 4\\n The House of Representatives Conference Report\\nspecifies that the list provided in 49 U.S.C. § 14501(c)(2) and\\n(3) is “not intended to be all inclusive, but merely to specify\\nsome of the matters which are not ‘prices, rates or services’ and\\nwhich are therefore not preempted.” H.R. Conf. Rep. No. 103-\\n677, at 83.\\n\\n\\n\\n\\n 13\\n\\fpurpose to warrant preemption.” Lupian, 905 F.3d at 136.\\nMany of our sister circuits have similarly held that the FAAAA\\nand ADA do not preempt state employment laws. See, e.g.,\\nAllied Concrete & Supply Co. v. Baker, 904 F.3d 1053, 1068\\n(9th Cir. 2018) (holding California prevailing wage law for\\nworkers on public projects not preempted); Su, 903 F.3d at 957\\n(holding California common law test for employee versus\\nindependent contractor status not preempted); Costello v.\\nBeavEx, Inc., 810 F.3d 1045, 1048 (7th Cir. 2016) (holding\\nIllinois wage law not preempted), cert. denied, 137 S. Ct. 2289\\n(2017); Amerijet Int’l, Inc. v. Miami-Dade County, Fla., 627\\nF. App’x 744, 751 (11th Cir. 2015) (holding Miami-Dade\\nCounty living wage ordinance as applied to air carriers not\\npreempted); Dilts, 769 F.3d at 647 (holding California meal\\nand rest-break laws not preempted); Mendonca, 152 F.3d at\\n1189 (holding California wage law not preempted).\\n\\n From the language of the FAAAA preemption provision\\nand these cases, we can distill several factors courts should\\nconsider when deciding whether a particular state law is\\nFAAAA-preempted. First, courts should examine whether the\\nstate law at issue applies to all businesses or whether it focuses\\non motor carriers. Laws that are directed at “members of the\\ngeneral public” and that are not targeted at motor carriers are\\nusually viewed as not having a direct effect on motor carriers.\\nRowe, 552 U.S. at 375.\\n\\n Even targeted laws, however, are not necessarily\\npreempted. We know from the FAAAA itself that state laws\\nthat may target motor carrier safety and insurance, or restrict\\nlocal routes based on vehicle size and weight, are not\\npreempted. 49 U.S.C. § 14501(c)(2). Conversely, laws of\\ngeneral applicability may nonetheless be preempted where\\n\\n\\n\\n\\n 14\\n\\fthey have a significant impact on the services a carrier\\nprovides. See, e.g., DiFiore v. Am. Airlines Inc., 646 F.3d 81,\\n88-89 (1st Cir. 2011) (holding generally applicable state tip\\nlaw as applied to airlines preempted under the ADA because it\\n“directly regulate[d] how an airline service is performed and\\nhow its price is displayed to customers”). Thus, whether a law\\nis applicable to every business or targets carriers is a helpful\\nbut nondispositive factor for determining whether a law has a\\ndirect effect on motor carriers’ prices, routes, or services.\\nMorales, 504 U.S. at 386.\\n\\n Second, courts should consider whether the law\\naddresses the carrier-employee relationship as opposed to the\\ncarrier-customer relationship. “[G]enerally applicable state\\nlaws that affect the carrier’s relationship with its customers\\n[differ from] those that affect the carrier’s relationship with its\\nworkforce.” Costello, 810 F.3d at 1054; see also Su, 903 F.3d\\nat 961-63 (noting same dichotomy); DiFiore, 646 F.3d at 88\\n(preempting a Massachusetts law prohibiting employer from\\ncollecting fee advertised as “service charge” because the law\\nregulates how a company performs services for its customers\\nand “not merely how the airline behaves as an employer or\\nproprietor”).\\n\\n The Court of Appeals for the Seventh Circuit provides\\na useful analysis explaining why laws governing an employer’s\\nrelationship with its employees have too remote an impact to\\nbe preempted. S.C. Johnson & Son, Inc. v. Transp. Corp. of\\nAm., Inc., 697 F.3d 544, 558 (7th Cir. 2012) (citing Mendonca,\\n152 F.3d at 1189). The court examines whether the challenged\\nstate law regulates matters needed to operate the business,\\nwhich it calls resource inputs, as opposed to laws governing\\nthe goods or services the business puts out, which it calls\\n\\n\\n\\n\\n 15\\n\\fproduct outputs. Id. The product outputs of the motor carrier\\nindustry are the services it provides—transportation of\\nproperty from origin to destination. Id. The FAAAA’s focus\\non prices, routes, and services shows that the statute is\\nconcerned with the industry’s production outputs, and seeks to\\nprotect them from state regulation.\\n\\n Resource inputs, on the other hand, are the resources\\nnecessary for a business to create product outputs, including\\n“labor, capital, and technology,” which may be regulated by\\nvarious laws. Id. “For example, labor inputs are affected by a\\nnetwork of labor laws, including minimum wage laws, worker-\\nsafety laws, anti-discrimination laws, and pension regulations.\\nCapital is regulated by banking laws, securities rules, and tax\\nlaws, among others. Technology is heavily influenced by\\nintellectual property laws.” Id. Although laws that regulate\\ninputs may impact costs and may in turn affect prices charged\\nand services provided to customers, “no one thinks that the\\nADA or the FAAAA preempts these [regulations] and the\\nmany comparable state laws[.]” Id. That is because,\\nnotwithstanding the state laws’ indirect effects, they “operate\\none or more steps away from the moment at which the firm\\noffers its customer[s] a service for a particular price” and\\ntherefore have too “remote” an effect on prices, routes, and\\nservices to be the intended target of preemption. Id. (internal\\ncitations omitted); see also Su, 903 F.3d at 966 (stating that\\ncourts should examine “where in the chain of a motor carrier’s\\nbusiness [the state law] is acting to compel a certain result (e.g.,\\nconsumer or work force), and what result it is compelling (e.g.,\\ncertain wage, non-discrimination, a specific system of\\ndelivery, a specific person to perform the delivery)”); Costello,\\n810 F.3d at 1055 (embracing S.C. Johnson, 697 F.3d at 558).\\nIn short, laws regulating labor inputs, such as wage laws, have\\n\\n\\n\\n\\n 16\\n\\ftoo remote an effect on the price the company charges, the\\nroutes it uses, and service outputs it provides and are less likely\\nto be preempted by the FAAAA.\\n\\n Third, courts should consider whether the law binds the\\ncarrier to provide a particular price, route, or service. As\\ndiscussed above, the Supreme Court held that Maine’s\\nidentification requirements for tobacco deliveries required a\\nmotor carrier transporting tobacco to provide a particular\\nservice. Rowe, 552 U.S. at 372. Similarly, the Court of\\nAppeals for the First Circuit determined that Massachusetts’\\nABC test for classifying employees in effect bound the carrier\\nto provide its services using employees rather than independent\\ncontractors. Schwann, 813 F.3d at 437. Under Massachusetts’\\nindependent contractor statute, only workers who perform a\\nservice that is outside the employer’s usual course of business\\nmay be classified as independent contractors. Id. (quoting\\nMass. Gen. Laws ch. 149, § 148B(a)(2)). Thus, application of\\nMassachusetts’ test “in substance, bar[red] [the carrier at issue]\\nfrom using any individuals as full-fledged independent\\ncontractors.” Id. In other words, the Massachusetts test\\nessentially foreclosed the independent contractor classification\\nof any of the carrier’s workers performing delivery services\\nbecause such services were within the carrier’s usual course of\\nbusiness. Id. As a result, the Massachusetts statute bound the\\ncarrier to provide its services using employees and not\\nindependent contractors.\\n\\n The same was not true with laws that do not dictate a\\nprice, route, or service. For example, the Court of Appeals for\\nthe Ninth Circuit analyzed whether the FAAAA preempted a\\nCalifornia law that requires employers to provide meal and rest\\nbreaks, reviewing, among other factors, whether the law bound\\n\\n\\n\\n\\n 17\\n\\fthe carrier to specific prices, routes, or services. Dilts, 769 F.3d\\nat 649-50. The court held that the FAAAA did not preempt\\nCalifornia’s meal and rest-break laws. Id. The court relied\\npartially on the fact that the California laws did not “set prices,\\nmandate or prohibit certain routes, or tell motor carriers what\\nservices they may or may not provide, either directly or\\nindirectly.” Id. at 647. Put simply, the law at issue did “not\\n‘bind’ motor carriers to specific prices, routes, or services.”5\\nId. (citation omitted).\\n\\n Finally, courts examining a preemption challenge to a\\nstate law should be mindful of Congress’ goal of avoiding a\\n“patchwork” of differing state “service-determining laws,”\\nwhich could undermine its “major legislative effort to leave\\n[decisions regarding the provision of services] to the\\ncompetitive marketplace.” Rowe, 552 U.S. at 373 (citing H.R.\\nConf. Rep. No. 103-677, at 87 (1994)). This goal does not\\nconstitute a categorical imperative to free motor carriers of all\\nstate regulation. Rather, the plain language of the FAAAA,\\nand its preemption of only laws “relat[ing] to” carrier “price[s],\\nroute[s], or service[s],” 49 U.S.C. § 14501(c)(1), demonstrates\\nthat Congress was concerned only with a limited set of state\\n\\n 5\\n AEX characterizes Dilts as impermissibly relying on\\nthis “binds to” test to conclude that the FAAAA did not\\npreempt California’s meal and rest break laws, arguing that\\nsuch a test construes the scope of FAAAA preemption too\\nnarrowly. While relying solely on such a “binds to” test may\\nnarrow FAAAA preemption to an unacceptable degree, Dilts\\nmerely recognized that the “binds to” test provides one of\\nseveral possible avenues to demonstrate that a state law has a\\nsignificant effect on carrier prices, routes, or services. Dilts,\\n769 F.3d at 649.\\n\\n\\n\\n\\n 18\\n\\flaws. Dilts, 769 F.3d at 646-47. Thus, “[t]he fact that laws\\nmay differ from state to state is not, on its own, cause for\\nFAAAA preemption.” Id. at 647. Laws that are “more or less\\nnationally uniform,” Chambers v. RDI Logistics, Inc., 65\\nN.E.3d 1, 11-12 (Mass. 2016), are less likely to pose the kind\\nof state law interference FAAAA preemption seeks to avoid.\\n\\n In sum, to assess the directness of a law’s effect on\\nprices, routes, or services, courts should examine whether the\\nlaw: (1) mentions a carrier’s prices, routes, or services;\\n(2) specifically targets carriers as opposed to all businesses;\\nand (3) addresses the carrier-customer relationship rather than\\nnon-customer-carrier relationships (e.g., carrier-employee). If\\na law has a direct impact on carriers’ prices, routes, or services\\nwith respect to the transportation of property, then it is\\npreempted unless it falls within one of the statutory exceptions.\\nThough we can draw no firm line between laws whose effects\\non rates, routes, or services are indirect and laws whose effects\\nare “tenuous, remote, or peripheral,” these factors, and perhaps\\nother considerations, will guide courts in the inquiry.\\n\\n To assess whether a law has a significant effect on a\\ncarrier’s prices, routes, or services, courts should consider\\nwhether: (1) the law binds a carrier to provide or not provide a\\nparticular price, route, or service; (2) the carrier has various\\navenues to comply with the law; (3) the law creates a\\npatchwork of regulation that erects barriers to entry, imposes\\ntariffs, or restricts the goods a carrier is permitted to transport;\\nand (4) the law existed in one of the jurisdictions Congress\\ndetermined lacked laws that regulate intrastate prices, routes,\\nor services and thus, by implication, is a law Congress found\\nnot to interfere with the FAAAA’s deregulatory goal. Other\\nfactors may also lead a court to decide that a state law has a\\n\\n\\n\\n\\n 19\\n\\fsignificant effect where the law undermines Congress’ goal of\\nhaving competitive market forces dictate prices, routes, or\\nservices of motor carriers.6\\n\\n E\\n\\n We have examined each of these considerations and\\nconclude that New Jersey’s ABC classification test is not\\npreempted as it has neither a direct, nor an indirect, nor a\\nsignificant effect on carrier prices, routes, or services.\\n\\n 6\\n Before the Supreme Court’s rulings in Rowe and\\nDan’s City, our Court once framed the inquiry—albeit in the\\ncontext of whether a defamation claim was preempted under\\nthe ADA (a question we answered in the negative, holding that\\nthe defamation claim was not preempted)—as whether the law\\nor claim in question would “frustrate[] deregulation by\\ninterfering with competition through public utility-style\\nregulation.” Taj Mahal Travel, Inc. v. Delta Airlines, Inc., 164\\nF.3d 186, 194 (3d Cir. 1998) (citation omitted). Elaborating\\non regulation in a “public utility sense” in the context of airline\\nservices, our Court said that regulations of “the frequency and\\nscheduling of transportation” and “the selection of markets”\\nare public-utility styled regulations (which would thus be\\npreempted under the ADA), whereas “provision of in-flight\\nbeverages, personal assistance to passengers, the handling of\\nluggage, and similar amenities” are not services in a “public\\nutility sense,” and thus could be regulated, for instance through\\nstate implementation of a duty to exercise reasonable care, the\\nviolation of which could give rise to ordinary tort claims. Id.\\nat 193 (quoting Charas v. Trans World Airlines, Inc., 160 F.3d\\n1259, 1261, 1265-66 (9th Cir. 1998) (en banc)).\\n\\n\\n\\n\\n 20\\n\\f Any effect New Jersey’s ABC classification test has on\\nprices, routes, or services is tenuous. The test does not mention\\ncarrier prices, routes, or services, nor does it single out carriers.\\nIndeed, the test applies to all businesses as part of the\\n“backdrop” they “face in conducting their affairs.” Lupian,\\n905 F.3d at 136; see also Dilts, 769 F.3d at 646 (describing a\\nstate employment law as a “background regulation[]”). The\\ntest also does not regulate carrier-customer interactions or\\nother product outputs. Rather, it only concerns employer-\\nworker relationships. Laws governing how an employer pays\\nits workers do not “directly regulate[] how [a carrier’s] service\\nis performed[;]” they merely dictate how a carrier “behaves as\\nan employer[.]” DiFiore, 646 F.3d at 88. As a result, the test\\nis “steps removed” from regulating customer-carrier\\ninteractions through prices, routes, or services. Costello, 810\\nF.3d 1054 (quoting Dilts, 769 F.3d at 646).\\n\\n The New Jersey ABC classification test does not have a\\nsignificant effect on prices, routes, or services either. The test\\ndoes not bind AEX to a particular method of providing services\\nand thus it is unlike the preempted Massachusetts law at issue\\nin Schwann, 813 F.3d 429. The Massachusetts statute does not\\ninclude New Jersey’s alternative method for reaching\\nindependent contractor status—that is, by demonstrating that\\nthe worker provides services outside of the putative employer’s\\n“places of business.” N.J. Stat. Ann. § 43:21-19(i)(6)(B).\\nThus, if the other prongs of the New Jersey classification test\\nare met, the test allows an employer to classify a worker as an\\nindependent contractor if it shows that the worker either\\nprovides a service that is “outside the [employer’s] usual\\ncourse of business . . . or [performs such service] outside of all\\n\\n\\n\\n\\n 21\\n\\fthe places of business of [the employer].” Id.7 No part of the\\nNew Jersey test categorically prevents carriers from using\\nindependent contractors. As a result, the state law at issue here\\ndoes not mandate a particular course of action—e.g., requiring\\ncarriers to use employees rather than independent\\ncontractors—and it offers carriers various options to comply\\nwith New Jersey employment law.8\\n\\n 7\\n AEX focuses its argument on the B prong of the New\\nJersey test, but also asserts that the A and C prongs of the test\\nare preempted. AEX cites no case holding that prong A or C\\nis preempted under either the FAAAA or the ADA. This is not\\nsurprising given the legion of cases holding that the A and C\\nprongs are not FAAAA-preempted. See, e.g., Vargas v. Spirit\\nDelivery & Distrib. Servs., Inc., 245 F. Supp. 3d 268, 281-84\\n(D. Mass. 2017); DaSilva v. Border Transfer of Mass., Inc.,\\n227 F. Supp. 3d 154, 159-60 (D. Mass. 2017); Portillo v. Nat’l\\nFreight, Inc., Civ. No. 15-7908, 2016 WL 5402215, at *5-6\\n(D.N.J. Sept. 26, 2016); Chambers v. RDI Logistics, Inc., 65\\nN.E.3d 1, 11-12 (Mass. 2016). AEX also provides no reason\\nwhy these prongs are preempted and in fact does not\\nindividually analyze them. Thus, AEX has failed to carry its\\nburden to demonstrate that the affirmative defense of FAAAA\\npreemption applies to these prongs.\\n 8\\n AEX makes much of the fact that the Costello and\\nLupian courts observed that certain aspects of the IWPCA\\nclassification provision could be contracted around (i.e.,\\nemployees could enter into contracts with carriers to allow\\ncertain paycheck deductions), Lupian, 905 F.3d at 135 n.12,\\nwhereas neither the New Jersey test nor the Massachusetts test\\nallows the same contractual avoidance. Contrary to AEX’s\\nargument, this does not make the current case more analogous\\n\\n\\n\\n\\n 22\\n\\f AEX argues that applying the New Jersey law may\\nrequire it to shift its model away from using independent\\ncontractors, which will increase its costs, and in turn, its prices.\\nSpecifically, AEX asserts that if it can no longer use\\nindependent contractors to perform its delivery services, then\\nit will be forced to recruit employees, bring on a human\\nresources department to manage them, acquire and maintain a\\nfleet of vehicles and pay expense reimbursements, provide\\nfringe benefits, plan and dictate delivery routes and timing, and\\npay overtime wages and employment taxes. Our Court and our\\nsister circuits have rejected similar lists of conclusory impacts.\\nLupian, 905 F.3d at 135-36; Costello, 810 F.3d at 1056;\\nMendonca, 152 F.3d at 1189. Though AEX correctly states\\nthat it need not proffer empirical evidence to support its\\nassertions of significant impact at the pleading stage, see, e.g.,\\nCostello, 810 F.3d at 1055 (citing Rowe, 552 U.S. at 373-74),\\n\\n\\nto Schwann than to Costello and Lupian. Though Costello and\\nLupian correctly took the IWPCA contractual loophole into\\naccount, neither court relied on it. See Lupian, 905 F.3d at 136\\nn.12 (observing that the Costello court “noted” the contractual\\nallowance in the IWPCA); Costello, 810 F.3d at 1057 (noting\\nin a single sentence that the IWPCA’s prohibition on\\ndeductions from wages can be contracted around, ultimately\\nholding that the IWPCA is not “related to a price, route, or\\nservice of any motor carrier”). Moreover, while a contractual\\ncircumvention option may provide another route for\\ncompliance, weighing against FAAAA preemption, it is not the\\nonly way a state statute can afford carriers some flexibility.\\nHere, the New Jersey ABC classification test gives carriers\\noptions; it does not need to provide a contractual workaround\\nto avoid preemption.\\n\\n\\n\\n\\n 23\\n\\fit does not provide even a logical connection between the\\napplication of New Jersey’s ABC classification test and the list\\nof new costs it would purportedly incur.9\\n\\n AEX’s argument that it may be subject to other legal\\nrequirements arising from reclassification, citing only the\\nAffordable Care Act,10 is equally unavailing. In the words of\\nthe Costello court, “[c]onspicuously absent from [the\\ncompany’s] parade of horrors is any citation of authority\\nshowing that it would be required to comply with [other]\\nfederal and state laws.” Id. at 1056. Instead, AEX “rel[ies] on\\nconclusory allegations that compliance with the [NJWHL and\\nNJWPL] will require [AEX] to switch its entire business model\\n. . . [but w]e see no basis for concluding that [New Jersey law]\\nwould require that change given that the federal employment\\nlaws and other state labor laws [may] have different tests” for\\ndetermining whether someone is an employee under a specific\\nstatute. Id. (citations omitted).\\n\\n Furthermore, while “[w]e have no doubt that the\\ndisruption of a labor model—especially after services have\\nbeen performed—could have negative financial and other\\nconsequences for an employer,” Lupian, 905 F.3d at 136, this\\nimpact on the employer does not equate to a significant impact\\non Congress’ goal of deregulation. Congress sought to ensure\\n\\n 9\\n For instance, we cannot see, nor has AEX explained,\\nhow reclassification of employees would necessarily require\\nAEX to acquire a new fleet of vehicles or create a human\\nresources department.\\n 10\\n Patient Protection and Affordable Care Act of 2010,\\nPub. L. No. 111-148, 124 Stat. 119 (2010).\\n\\n\\n\\n\\n 24\\n\\fmarket forces determined prices, routes, and services. Nothing\\nin that goal, however, meant to exempt workers from receiving\\nproper wages, even if the wage laws had an incidental impact\\non carrier prices, routes, or services.11\\n\\n Finally, the fact that New Jersey’s ABC classification\\ntest differs from the federal test used in the Fair Labor\\nStandards Act of 1938, 29 U.S.C. §§ 201-19, will not result in\\na “‘patchwork’ of unique state legislation, which [AEX\\ncontends] regulates differently from state to state how motor\\ncarriers are required to perform their delivery services.” Reply\\nBr. at 14. Most notably, New Jersey’s test is similar to that\\nused in many other states. See, e.g., RDI Logistics, 65 N.E.3d\\nat 11-12 (holding that prongs A and C of the Massachusetts\\ntest, which are identical to those in the New Jersey test, were\\nnot FAAAA-preempted because they did not present a\\n“patchwork problem” as they were “more or less nationally\\nuniform,” unlike the Massachusetts B prong, which was\\npreempted in Schwann because it was anomalous (quoting\\nSchwann, 813 F.3d at 440)).\\n\\n\\n\\n\\n 11\\n Indeed, Congress evinced its intent for the FAAAA\\nnot to preempt general state wage laws when it included New\\nJersey—where, at the time the FAAAA was enacted, the\\nNJWHL and NJWPL were already in effect, N.J. Stat. Ann. §§\\n34:11-56a7 & 34:11-4.1 (indicating initial enactment in 1966\\nand 1965, respectively)—in its list of jurisdictions with laws\\nthat did not run afoul of the FAAAA. H.R. Conf. Rep. No.\\n103-677, at 86 (1994); see also Mendonca, 152 F.3d at 1187-\\n88 & n.3.\\n\\n\\n\\n\\n 25\\n\\f Thus, AEX has not shown that New Jersey’s ABC\\nclassification test has a “significant impact” on Congress’\\nderegulatory efforts with respect to motor carrier businesses,\\nnor are the NJWHL and NJWPL—typical state wage and hour\\nlaws—the kinds of preexisting state regulations with which\\nCongress was concerned when it passed the FAAAA.12 See\\nLupian, 905 F.3d at 135-36; Schwann, 813 F.3d at 438;\\nCostello, 810 F.3d at 1050-51; Amerijet, 627 F. App’x at 751;\\nDilts, 769 F.3d at 647-48; Gary, 397 F.3d at 189-90;\\nMendonca, 152 F.3d at 1187-89. Notably, eight of the ten\\njurisdictions that Congress identified as not regulating\\nintrastate prices, routes, and services “had laws for\\ndifferentiating between an employee and an independent\\ncontractor,” Su, 903 F.3d at 967, and at least three codified\\nABC tests similar to that of New Jersey, see Alaska Stat. §\\n23.20.525(a)(10) (1992); Del. Code Ann. tit. 19, § 3302(9)(k)\\n(1992); Vt. Stat. Ann. tit. 21, § 1301(6)(B) (1992). Therefore,\\nAEX’s patchwork argument fails.\\n\\n Accordingly, any effect the New Jersey ABC\\nclassification test has on prices, routes, or services with respect\\nto the transportation of property is tenuous and insignificant.\\nSee Lupian, 905 F.3d at 136. As a result, the test is not\\npreempted.\\n\\n\\n\\n\\n 12\\n As the Schwann court observed, while Congress\\nsought “to avoid ‘a patchwork of state service-determining\\nlaws,’” we can assume that “Congress intended to leave\\nuntouched” “pre-existing and customary manifestation[s] of\\nthe state’s police power.” 813 F.3d at 438 (quoting Rowe, 552\\nU.S. at 373).\\n\\n\\n\\n\\n 26\\n\\f III\\n\\n For the foregoing reasons, we will affirm the District\\nCourt’s order denying AEX’s motion for judgment on the\\npleadings and remand for further proceedings.\\n\\n\\n\\n\\n 27\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4362696/\", \"author_raw\": \"SHWARTZ, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"GREENAWAY"},"judge2":{"kind":"string","value":"SHWARTZ"},"judge3":{"kind":"string","value":"BIBAS"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4585443/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Ever BEDOYA; Diego Gonzales; Manuel Decastro, on Behalf of Themselves and All Others Similarly Situated v. AMERICAN EAGLE EXPRESS INC., D/B/A AEX Group v. KV Service, LLC; M&J Express, LLC; A&D Delivery Express, LLC American Eagle Express, Inc., Appellant\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-29\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 18-1641\n _____________\n\n EVER BEDOYA; DIEGO GONZALES; MANUEL\n DECASTRO,\n on behalf of themselves and all others similarly situated\n\n v.\n\nAMERICAN EAGLE EXPRESS INC, d/b/a AEX GROUP\n\n v.\n\n KV SERVICE, LLC; M&J EXPRESS, LLC; A&D\n DELIVERY EXPRESS, LLC\n\n American Eagle Express, Inc.,\n Appellant\n ______________\n\n Appeal from the United States District Court\n for the District of New Jersey\n (D.C. No. 2-14-cv-02811)\n District Judge: Hon. Esther Salas\n ______________\n\f Argued November 14, 2018\n ______________\n\n Before: GREENAWAY, JR., SHWARTZ, and BIBAS,\n Circuit Judges.\n\n (Opinion Filed: January 29, 2019)\n\nHarold L. Lichten [ARGUED]\nLichten & Liss-Riordan\n729 Boylston Street\nSuite 2000\nBoston, MA 02116\n\nR. Andrew Santillo\nPeter D. Winebrake\nWinebrake & Santillo\n715 Twinning Road\nSuite 211, Twinning Office Center\nDresher, PA 19025\n\n Counsel for Plaintiff-Appellees\n\nJoseph C. DeBlasio [ARGUED]\nJackson Lewis\n220 Headquarters Plaza\nEast Tower, 7th Floor\nMorristown, NJ 07960\n\n Counsel for Defendant-Appellant\n\nAdina H. Rosenbaum\nPublic Citizen Litigation Group\n\n\n\n\n 2\n\f1600 20th Street, NW.\nWashington, DC 20009\n\n Counsel for Amicus Public Citizen Inc.\n\n\nChristopher W. Weber [ARGUED]\nEmily M. Bisnauth\nOffice of Attorney General of New Jersey\nDepartment of Law & Public Safety\nRichard J. Hughes Justice Complex\n25 Market Street\nP.O. Box 112\nTrenton, NJ 08625\n\n Counsel for Amicus New Jersey Department of Labor\n and Workforce Development\n\n\n ___________\n\n OPINION\n ___________\n\n\nSHWARTZ, Circuit Judge.\n\n Plaintiff delivery drivers Ever Bedoya, Diego Gonzalez,\nand Manuel Decastro (collectively, “the Drivers”) filed a\nputative class action against Defendant American Eagle\nExpress, Inc., (“AEX”), alleging that AEX misclassified them\nas independent contractors when they are actually employees\nunder the New Jersey Wage and Hour Law (“NJWHL”), N.J.\n\n\n\n\n 3\n\fStat. Ann. §§ 34:11-56a to -56a3, and the New Jersey Wage\nPayment Law (“NJWPL”), N.J. Stat. Ann. §§ 34:11-4.1 to -\n4:14. AEX moved for judgment on the pleadings pursuant to\nFed. R. Civ. P. 12(c), arguing that the Drivers’ claims are\npreempted by the Federal Aviation Authorization\nAdministration Act of 1994 (“FAAAA”), 49 U.S.C. §§ 14501-\n06. The District Court denied AEX’s motion and certified the\norder for interlocutory appeal. Because the FAAAA does not\npreempt the New Jersey law for determining employment\nstatus for the purposes of NJWHL and NJWPL, we will affirm\nthe order and remand for further proceedings.\n\n I\n\n AEX is a logistics company that provides delivery\nservices to various medical organizations. The Drivers are\nNew Jersey residents who make deliveries for AEX. The\nDrivers filed this putative class action against AEX seeking,\namong other things, a judgment declaring that they are\nemployees of AEX, rather than independent contractors, which\nentitles them to compensation under the NJWHL and NJWPL.1\nAEX moved for judgment on the pleadings, arguing that the\nFAAAA preempts the Drivers’ claims.\n\n The District Court denied AEX’s motion, Bedoya v.\nAm. Eagle Express, Civ. No. 14-2811, 2017 WL 4330351, at\n*1 (D.N.J. Sept. 29, 2017), reasoning that “[t]here is no clear\nindication” that Congress intended for the FAAAA to preempt\nstate wage laws, Dkt. 109 at 6, 10, and that the connection\nbetween regulation of AEX’s workforce and the “prices,\n\n 1\n The District Court has jurisdiction pursuant to 28\nU.S.C. § 1332(d).\n\n\n\n\n 4\n\froutes, and services” provided to its consumers is too\nattenuated to justify preempting claims under the NJWHL and\nNJWPL, id. at 8-9. We now consider AEX’s interlocutory\nappeal of the order denying the motion pursuant to 28 U.S.C.\n§ 1292(b). Bedoya, 2017 WL 4330351, at *1-4.\n\n II2\n\n A\n\n The question before us is whether the FAAAA preempts\nNew Jersey’s test for determining employment classification\nfor purposes of the NJWHL and NJWPL. Under this test,\nworkers performing services for a given company in exchange\nfor pay are deemed employees unless the company can\ndemonstrate each of the following:\n\n A. Such individual has been and will continue to\n be free from control or direction over the\n\n 2\n We review an order granting or denying a motion for\njudgment on the pleadings de novo. Zimmerman v. Corbett,\n873 F.3d 414, 417 (3d Cir. 2017) (citing Allah v. Al-Hafeez,\n226 F.3d 247, 249 (3d Cir. 2007)). Judgment will not be\ngranted unless the movant “clearly establishes there are no\nmaterial issues of fact, and he is entitled to judgment as a\nmatter of law.” Sikirica v. Nationwide Ins. Co., 416 F.3d 214,\n220 (3d Cir. 2005) (citation omitted). In considering a motion\nfor judgment on the pleadings, we must accept as true all facts\npresented in the complaint and answer and draw all reasonable\ninferences in favor of the non-moving party—here, the\nDrivers. Id. at 417-18. While AEX implores us to look beyond\nthe pleadings, we may not.\n\n\n\n\n 5\n\f performance of such service, both under his\n contract of service and in fact; and\n\n B. Such service is either outside the usual course\n of the business for which such service is\n performed, or that such service is performed\n outside of all the places of business of the\n enterprise for which such service is\n performed; and\n\n C. Such individual is customarily engaged in an\n independently established trade, occupation,\n profession, or business.\n\nN.J. Stat. Ann. §§ 43:21-19(i)(6)(A)-(C) (“New Jersey ABC\nclassification test”). Where a company successfully\ndemonstrates all three elements with respect to a worker, that\nworker qualifies as an independent contractor under the\nNJWHL and NJWPL. Hargrove v. Sleepy’s, LLC, 106 A.3d\n449, 458 (N.J. 2015). The company, in turn, is exempt from\nrequirements under those statutes with respect to the worker.\nId. For individuals classified as employees, however, the\nemploying company is subject to each statute’s obligations,\nincluding minimum and overtime wage requirements, N.J.\nStat. Ann. § 34:11-56a4, conditions regarding the time and\nmode of pay, N.J. Stat. Ann. § 34:11-4.2, 4.2a, and restrictions\non pay deductions, N.J. Stat. Ann. § 34:11-4.4. AEX contends\nthat the New Jersey ABC classification test is preempted by the\nFAAAA.\n\n\n\n\n 6\n\f B\n\n The preemption doctrine stems from the Supremacy\nClause, which provides that “the Laws of the United States . . .\nshall be the supreme Law of the Land . . . any Thing in the\nConstitution or Laws of any State to the Contrary\nnotwithstanding.” U.S. Const. art. VI, cl. 2. Thus, “Congress\n. . . has the power to preempt state law.” In re Vehicle Carrier\nServs. Antitrust Litig., 846 F.3d 71, 83 (3d Cir. 2017) (citing\nArizona v. United States, 567 U.S. 387 (2012)), cert denied sub\nnom., Alban v. Nippon Yusen Kabushiki Kaisha, 138 S. Ct.\n114 (2017). There are three categories of preemption: field\npreemption, conflict preemption, and express preemption.\nHolk v. Snapple Beverage Corp., 575 F.3d 329, 334 (3d Cir.\n2009) (citing Hillsborough County, Fla. v. Automated Med.\nLabs., Inc., 471 U.S. 707, 713 (1985)).\n\n Because preemption is an affirmative defense, we\nexamine the specific preemption defense asserted. In re\nVehicle, 846 F.3d at 84 (citing Oneok, Inc. v. Learjet, Inc., 135\nS. Ct. 1591 (2015)). AEX argues that New Jersey’s ABC\nclassification test is subject to express preemption under 49\nU.S.C. § 14501(c)(1). “Express preemption requires a[n]\nanalysis of whether ‘[s]tate action may be foreclosed by\nexpress language in a congressional enactment.’” Lupian v.\nJoseph Cory Holdings, LLC, 905 F.3d 127, 131 (3d Cir. 2018)\n(alteration in original) (quoting Lorillard Tobacco Co. v.\nReilly, 533 U.S. 525, 541 (2001)).\n\n In evaluating AEX’s argument, we first decide whether\nthe presumption against preemption applies. City of Columbus\nv. Ours Garage & Wrecker Serv., Inc., 536 U.S. 424, 438\n(2002) (applying the presumption against preemption in the\n\n\n\n\n 7\n\fFAAAA context). Under this presumption, “the historic police\npowers of the States” are “not to be superseded by [a] [f]ederal\n[a]ct unless that was the clear and manifest purpose of\nCongress.” Sikkelee v. Precision Airmotive Corp., 822 F.3d\n680, 687 (3d Cir. 2016) (quoting Wyeth v. Levine, 555 U.S.\n555, 565 (2009)). Thus, we “presume claims based on laws\nembodying state police powers are not preempted.” In re\nVehicle, 846 F.3d at 84; see also Farina v. Nokia Inc., 625 F.3d\n97, 116 (3d Cir. 2010).\n\n Many employment regulations, such as the wage laws\nat issue here, seek to ensure workers receive fair pay. Because\nthey protect workers, they are within New Jersey’s police\npower, and the presumption against preemption by federal law\napplies. See, e.g., Lupian, 905 F.3d at 131 (stating wage laws\nthat protect workers represent an exercise of “police power”);\nsee also Fort Halifax Packing Co. v. Coyne, 482 U.S. 1, 21\n(1987) (applying the presumption against preemption to a state\nlabor law regarding severance pay “since the establishment of\nlabor standards falls within the traditional police power of the\nState”).\n\n The presumption is rebutted where Congress had a\n“clear and manifest purpose” to preempt state laws. Sikkelee,\n822 F.3d at 687 (citation omitted); see also Cipollone v. Liggett\nGrp., Inc., 505 U.S. 504, 516 (1992) (directing courts to\nexamine congressional intent, the “ultimate touchstone” in\ndiscerning the preemptive scope of a statute (internal quotation\nmarks and citation omitted)). To determine Congress’\npurpose, we look to the plain language of the statute and, if\nnecessary, to the statutory framework as a whole. Medtronic,\nInc. v. Lohr, 518 U.S. 470, 486 (1996) (citation omitted).\nThus, we next examine Congress’ purpose in enacting the\n\n\n\n\n 8\n\fFAAAA and the Airline Deregulation Act of 1978 (“ADA”),\n49 U.S.C. §§ 40101-130, an earlier statute with a similar\npreemption provision.\n\n C\n\n In 1978, following a long period of heightened\nregulation, Congress enacted the ADA, which sought to\nderegulate the air-travel industry to “maxim[ize] reliance on\ncompetitive market forces.” Morales v. Trans World Airlines,\nInc., 504 U.S. 374, 378 (1992) (quoting 49 U.S.C. App. §\n1302(a)(4)). To ensure that this objective would not be\nfrustrated by state regulation, Congress included a preemption\nprovision providing that “no State . . . shall enact or enforce\nany law . . . relating to rates, routes, or services of any air\ncarrier.” Id. at 420 (Stevens, J., dissenting) (quoting 49 U.S.C.\nApp. § 1305(a)).\n\n Congress enacted similar laws focused on deregulating\ninterstate trucking, culminating with the passage of the\nFAAAA in 1994. Lupian, 905 F.3d at 132-33. Via the\nFAAAA, Congress sought to “level the playing field” between\nair carriers and motor carriers so that both could benefit from\nfederal deregulation. H.R. Conf. Rep. No. 103-677, at 88\n(1994); see also Californians for Safe & Competitive Dump\nTruck Transp. v. Mendonca, 152 F.3d 1184, 1187-88 (9th Cir.\n1998) (detailing FAAAA legislative history). The FAAAA\ncontains a preemption provision modeled after the ADA’s,\nproviding, with limited exceptions, that:\n\n a State . . . may not enact or enforce a law,\n regulation, or other provision having the force\n and effect of law related to a price, route, or\n\n\n\n\n 9\n\f service of any motor carrier . . . with respect to\n the transportation of property.\n\n49 U.S.C. § 14501(c)(1). Because of the parallels between the\nADA and FAAAA, ADA cases are instructive regarding the\nscope of FAAAA preemption. See Rowe v. N.H. Motor\nTransp. Ass’n, 552 U.S. 364, 370 (2008) (analyzing FAAAA\npreemption using ADA cases as guidance). As with the ADA,\nthe FAAAA preemption provision’s central objective is to\navoid frustrating the statute’s deregulatory purpose by\npreventing states from imposing “a patchwork of state service-\ndetermining laws.” Dan’s City Used Cars, Inc. v. Pelkey, 569\nU.S. 251, 264 (2013) (quoting Rowe, 552 U.S. at 373). The\nFAAAA, however, has a qualifier that is absent from the ADA:\nthe preempted state law must relate to prices, routes, or services\n“with respect to the transportation of property.” 49 U.S.C.\n§ 14501(c)(1). The Supreme Court has recognized that this\nlanguage “massively limits the scope of preemption ordered by\nthe FAAAA.” Dan’s City, 569 U.S. at 261 (internal citation\nand quotation marks omitted).\n\n Further insight into the limits of FAAAA preemption\ncomes from the subjects Congress considered when enacting\nthat statute. “Congress identified ten jurisdictions (nine states\nand the District of Columbia . . . ) that did not regulate intrastate\nprices, routes, and services.” Cal. Trucking Ass’n v. Su, 903\nF.3d 953, 967 (9th Cir. 2018) (citing Mendonca, 152 F.3d at\n1187). By implication, Congress determined that the laws then\nin existence in those jurisdictions did not contravene its\nderegulatory goals and thus were not preempted. Id.\n\n The Supreme Court has also articulated several\nprinciples that inform us about the breadth of FAAAA\n\n\n\n\n 10\n\fpreemption. First, the “related to” language from the FAAAA\npreemption clause gives it a broad scope, encompassing any\nstate actions that have “a connection with, or [make] reference\nto . . . rates, routes, or services” of a motor carrier. Nw., Inc.\nv. Ginsberg, 572 U.S. 273, 280-81 (2014) (internal quotation\nmarks and citation omitted) (interpreting the ADA). While this\nlanguage covers any state law that has a connection with or\nrefers to “price[s], route[s], [or] service[s,]” id. at 280, “the\nbreadth of the words ‘related to’ does not mean the sky is the\nlimit,” Dan’s City, 569 U.S. at 260. Drawing from case law\nexamining similar wording in the preemption provision of the\nEmployee Retirement Income Security Act of 1974, 29 U.S.C.\n§ 1144(a), see, e.g., Morales, 504 U.S. at 383-84, the Supreme\nCourt has observed that reading the phrase “related to” with\n“uncritical literalism” would render preemption an endless\nexercise, Dan’s City, 569 U.S. at 260-61 (citation omitted),\nbecause “everything [is] relat[ed] to everything else in some\nmanner[,]” Schwann v. FedEx Ground Package Sys., Inc., 813\nF.3d 429, 436 (1st Cir. 2016) (citing N.Y. State Conference of\nBlue Cross & Blue Shield Plans v. Travelers Ins. Co., 514 U.S.\n645, 655 (1955)).\n\n Second, FAAAA preemption reaches laws that affect\nprices, routes, or services even if the effect “is only indirect.”\nRowe, 552 U.S. at 370 (quoting Morales, 504 U.S. at 386).\nHowever, where a law’s impact on carrier prices, routes, or\nservices is so indirect that the law affects them “in only a\ntenuous, remote, or peripheral . . . manner,” the law is not\npreempted. Dan’s City, 569 U.S. at 261 (quoting Rowe, 552\nU.S. at 371); Morales, 504 U.S. at 390 (quoting Shaw v. Delta\nAir Lines, Inc., 463 U.S. 85, 100 n.21 (1983)).\n\n\n\n\n 11\n\f Finally, preemption occurs where a state law has “a\n‘significant impact’ on carrier rates, routes, or services.”3\nRowe, 552 U.S. at 375 (emphasis omitted) (quoting Morales,\n504 U.S. at 390).\n\n Mindful of these principles, we next review the case law\nfor guidance concerning whether a law has a direct or indirect\neffect and whether it has a significant or insignificant effect.\nFrom our review, we identify factors courts examine and set\nforth those factors that may shed light on a law’s directness and\nthose that may reflect the significance of the law’s effect on the\nregulated entities at issue.\n\n D\n\n Neither the Supreme Court nor our Court has recited\nprecise standards for evaluating directness or significance, but\ncases addressing the issue provide some guidance. For\nexample, the Supreme Court has held that consumer protection\nand fraud laws used to regulate frequent-flyer programs could\ndirectly and significantly affect prices and services and are thus\npreempted. See Am. Airlines, Inc. v. Wolens, 513 U.S. 219,\n223 (1995); Morales, 504 U.S. at 388-89. Similarly, the Court\ndetermined that a Maine law requiring a specific procedure to\nverify the recipient of tobacco deliveries was preempted by the\nFAAAA because it dictated a service that tobacco motor\ncarriers were required to provide for property they transported.\nRowe, 552 U.S. at 372. In addition, we recently observed that\n\n 3\n The Supreme Court also noted that “it makes no\ndifference whether a state law is ‘consistent’ or ‘inconsistent’\nwith federal regulation.” Rowe, 552 U.S. at 370 (quoting\nMorales, 504 U.S. at 386-87).\n\n\n\n\n 12\n\fthe FAAAA’s “preemption clause undoubtedly applies, for\nexample, to state laws directly restricting types of goods that\ncan be carried by trucks, tariffs, and barriers to entry.” Lupian,\n905 F.3d at 135; H.R. Conf. Rep. No. 103-677, at 86 (1994).\n\n On the other hand, the FAAAA itself, the Supreme\nCourt, and the courts of appeals have identified laws that are\ntoo “tenuous, remote, or peripheral” from carrier prices, routes,\nand services to trigger preemption. See, e.g., Rowe, 552 U.S.\nat 371; Dilts v. Penske Logistics, LLC, 769 F.3d 637, 646 (9th\nCir. 2014). The FAAAA explicitly exempts from preemption\nlaws governing motor vehicle safety, local route controls based\non vehicle size and weight, and driver insurance requirements.4\n49 U.S.C. § 14501(c)(2)(A). The Supreme Court has stated\nthat the FAAAA does not preempt laws prohibiting\nprostitution, gambling, and “obscene depictions,” Morales,\n504 U.S. at 390, or those addressing zoning, Dan’s City, 569\nU.S. at 264. We have observed that “garden variety\nemployment claim[s]” evade ADA and FAAAA preemption\nbecause they are “too remote and too attenuated” from carrier\nprices, services, or routes. Lupian, 905 F.3d at 134 (quoting\nGary v. Air Grp., Inc., 397 F.3d 183, 189 (3d Cir. 2005)). As\nrelevant to this case, we recently held that wage claims under\nthe Illinois Wage Payment and Collection Act (“IWPCA”),\n820 Ill. Comp. Stat. 115/1-115/15, are not preempted under the\nFAAAA because they are “too far removed from the statute’s\n\n 4\n The House of Representatives Conference Report\nspecifies that the list provided in 49 U.S.C. § 14501(c)(2) and\n(3) is “not intended to be all inclusive, but merely to specify\nsome of the matters which are not ‘prices, rates or services’ and\nwhich are therefore not preempted.” H.R. Conf. Rep. No. 103-\n677, at 83.\n\n\n\n\n 13\n\fpurpose to warrant preemption.” Lupian, 905 F.3d at 136.\nMany of our sister circuits have similarly held that the FAAAA\nand ADA do not preempt state employment laws. See, e.g.,\nAllied Concrete & Supply Co. v. Baker, 904 F.3d 1053, 1068\n(9th Cir. 2018) (holding California prevailing wage law for\nworkers on public projects not preempted); Su, 903 F.3d at 957\n(holding California common law test for employee versus\nindependent contractor status not preempted); Costello v.\nBeavEx, Inc., 810 F.3d 1045, 1048 (7th Cir. 2016) (holding\nIllinois wage law not preempted), cert. denied, 137 S. Ct. 2289\n(2017); Amerijet Int’l, Inc. v. Miami-Dade County, Fla., 627\nF. App’x 744, 751 (11th Cir. 2015) (holding Miami-Dade\nCounty living wage ordinance as applied to air carriers not\npreempted); Dilts, 769 F.3d at 647 (holding California meal\nand rest-break laws not preempted); Mendonca, 152 F.3d at\n1189 (holding California wage law not preempted).\n\n From the language of the FAAAA preemption provision\nand these cases, we can distill several factors courts should\nconsider when deciding whether a particular state law is\nFAAAA-preempted. First, courts should examine whether the\nstate law at issue applies to all businesses or whether it focuses\non motor carriers. Laws that are directed at “members of the\ngeneral public” and that are not targeted at motor carriers are\nusually viewed as not having a direct effect on motor carriers.\nRowe, 552 U.S. at 375.\n\n Even targeted laws, however, are not necessarily\npreempted. We know from the FAAAA itself that state laws\nthat may target motor carrier safety and insurance, or restrict\nlocal routes based on vehicle size and weight, are not\npreempted. 49 U.S.C. § 14501(c)(2). Conversely, laws of\ngeneral applicability may nonetheless be preempted where\n\n\n\n\n 14\n\fthey have a significant impact on the services a carrier\nprovides. See, e.g., DiFiore v. Am. Airlines Inc., 646 F.3d 81,\n88-89 (1st Cir. 2011) (holding generally applicable state tip\nlaw as applied to airlines preempted under the ADA because it\n“directly regulate[d] how an airline service is performed and\nhow its price is displayed to customers”). Thus, whether a law\nis applicable to every business or targets carriers is a helpful\nbut nondispositive factor for determining whether a law has a\ndirect effect on motor carriers’ prices, routes, or services.\nMorales, 504 U.S. at 386.\n\n Second, courts should consider whether the law\naddresses the carrier-employee relationship as opposed to the\ncarrier-customer relationship. “[G]enerally applicable state\nlaws that affect the carrier’s relationship with its customers\n[differ from] those that affect the carrier’s relationship with its\nworkforce.” Costello, 810 F.3d at 1054; see also Su, 903 F.3d\nat 961-63 (noting same dichotomy); DiFiore, 646 F.3d at 88\n(preempting a Massachusetts law prohibiting employer from\ncollecting fee advertised as “service charge” because the law\nregulates how a company performs services for its customers\nand “not merely how the airline behaves as an employer or\nproprietor”).\n\n The Court of Appeals for the Seventh Circuit provides\na useful analysis explaining why laws governing an employer’s\nrelationship with its employees have too remote an impact to\nbe preempted. S.C. Johnson & Son, Inc. v. Transp. Corp. of\nAm., Inc., 697 F.3d 544, 558 (7th Cir. 2012) (citing Mendonca,\n152 F.3d at 1189). The court examines whether the challenged\nstate law regulates matters needed to operate the business,\nwhich it calls resource inputs, as opposed to laws governing\nthe goods or services the business puts out, which it calls\n\n\n\n\n 15\n\fproduct outputs. Id. The product outputs of the motor carrier\nindustry are the services it provides—transportation of\nproperty from origin to destination. Id. The FAAAA’s focus\non prices, routes, and services shows that the statute is\nconcerned with the industry’s production outputs, and seeks to\nprotect them from state regulation.\n\n Resource inputs, on the other hand, are the resources\nnecessary for a business to create product outputs, including\n“labor, capital, and technology,” which may be regulated by\nvarious laws. Id. “For example, labor inputs are affected by a\nnetwork of labor laws, including minimum wage laws, worker-\nsafety laws, anti-discrimination laws, and pension regulations.\nCapital is regulated by banking laws, securities rules, and tax\nlaws, among others. Technology is heavily influenced by\nintellectual property laws.” Id. Although laws that regulate\ninputs may impact costs and may in turn affect prices charged\nand services provided to customers, “no one thinks that the\nADA or the FAAAA preempts these [regulations] and the\nmany comparable state laws[.]” Id. That is because,\nnotwithstanding the state laws’ indirect effects, they “operate\none or more steps away from the moment at which the firm\noffers its customer[s] a service for a particular price” and\ntherefore have too “remote” an effect on prices, routes, and\nservices to be the intended target of preemption. Id. (internal\ncitations omitted); see also Su, 903 F.3d at 966 (stating that\ncourts should examine “where in the chain of a motor carrier’s\nbusiness [the state law] is acting to compel a certain result (e.g.,\nconsumer or work force), and what result it is compelling (e.g.,\ncertain wage, non-discrimination, a specific system of\ndelivery, a specific person to perform the delivery)”); Costello,\n810 F.3d at 1055 (embracing S.C. Johnson, 697 F.3d at 558).\nIn short, laws regulating labor inputs, such as wage laws, have\n\n\n\n\n 16\n\ftoo remote an effect on the price the company charges, the\nroutes it uses, and service outputs it provides and are less likely\nto be preempted by the FAAAA.\n\n Third, courts should consider whether the law binds the\ncarrier to provide a particular price, route, or service. As\ndiscussed above, the Supreme Court held that Maine’s\nidentification requirements for tobacco deliveries required a\nmotor carrier transporting tobacco to provide a particular\nservice. Rowe, 552 U.S. at 372. Similarly, the Court of\nAppeals for the First Circuit determined that Massachusetts’\nABC test for classifying employees in effect bound the carrier\nto provide its services using employees rather than independent\ncontractors. Schwann, 813 F.3d at 437. Under Massachusetts’\nindependent contractor statute, only workers who perform a\nservice that is outside the employer’s usual course of business\nmay be classified as independent contractors. Id. (quoting\nMass. Gen. Laws ch. 149, § 148B(a)(2)). Thus, application of\nMassachusetts’ test “in substance, bar[red] [the carrier at issue]\nfrom using any individuals as full-fledged independent\ncontractors.” Id. In other words, the Massachusetts test\nessentially foreclosed the independent contractor classification\nof any of the carrier’s workers performing delivery services\nbecause such services were within the carrier’s usual course of\nbusiness. Id. As a result, the Massachusetts statute bound the\ncarrier to provide its services using employees and not\nindependent contractors.\n\n The same was not true with laws that do not dictate a\nprice, route, or service. For example, the Court of Appeals for\nthe Ninth Circuit analyzed whether the FAAAA preempted a\nCalifornia law that requires employers to provide meal and rest\nbreaks, reviewing, among other factors, whether the law bound\n\n\n\n\n 17\n\fthe carrier to specific prices, routes, or services. Dilts, 769 F.3d\nat 649-50. The court held that the FAAAA did not preempt\nCalifornia’s meal and rest-break laws. Id. The court relied\npartially on the fact that the California laws did not “set prices,\nmandate or prohibit certain routes, or tell motor carriers what\nservices they may or may not provide, either directly or\nindirectly.” Id. at 647. Put simply, the law at issue did “not\n‘bind’ motor carriers to specific prices, routes, or services.”5\nId. (citation omitted).\n\n Finally, courts examining a preemption challenge to a\nstate law should be mindful of Congress’ goal of avoiding a\n“patchwork” of differing state “service-determining laws,”\nwhich could undermine its “major legislative effort to leave\n[decisions regarding the provision of services] to the\ncompetitive marketplace.” Rowe, 552 U.S. at 373 (citing H.R.\nConf. Rep. No. 103-677, at 87 (1994)). This goal does not\nconstitute a categorical imperative to free motor carriers of all\nstate regulation. Rather, the plain language of the FAAAA,\nand its preemption of only laws “relat[ing] to” carrier “price[s],\nroute[s], or service[s],” 49 U.S.C. § 14501(c)(1), demonstrates\nthat Congress was concerned only with a limited set of state\n\n 5\n AEX characterizes Dilts as impermissibly relying on\nthis “binds to” test to conclude that the FAAAA did not\npreempt California’s meal and rest break laws, arguing that\nsuch a test construes the scope of FAAAA preemption too\nnarrowly. While relying solely on such a “binds to” test may\nnarrow FAAAA preemption to an unacceptable degree, Dilts\nmerely recognized that the “binds to” test provides one of\nseveral possible avenues to demonstrate that a state law has a\nsignificant effect on carrier prices, routes, or services. Dilts,\n769 F.3d at 649.\n\n\n\n\n 18\n\flaws. Dilts, 769 F.3d at 646-47. Thus, “[t]he fact that laws\nmay differ from state to state is not, on its own, cause for\nFAAAA preemption.” Id. at 647. Laws that are “more or less\nnationally uniform,” Chambers v. RDI Logistics, Inc., 65\nN.E.3d 1, 11-12 (Mass. 2016), are less likely to pose the kind\nof state law interference FAAAA preemption seeks to avoid.\n\n In sum, to assess the directness of a law’s effect on\nprices, routes, or services, courts should examine whether the\nlaw: (1) mentions a carrier’s prices, routes, or services;\n(2) specifically targets carriers as opposed to all businesses;\nand (3) addresses the carrier-customer relationship rather than\nnon-customer-carrier relationships (e.g., carrier-employee). If\na law has a direct impact on carriers’ prices, routes, or services\nwith respect to the transportation of property, then it is\npreempted unless it falls within one of the statutory exceptions.\nThough we can draw no firm line between laws whose effects\non rates, routes, or services are indirect and laws whose effects\nare “tenuous, remote, or peripheral,” these factors, and perhaps\nother considerations, will guide courts in the inquiry.\n\n To assess whether a law has a significant effect on a\ncarrier’s prices, routes, or services, courts should consider\nwhether: (1) the law binds a carrier to provide or not provide a\nparticular price, route, or service; (2) the carrier has various\navenues to comply with the law; (3) the law creates a\npatchwork of regulation that erects barriers to entry, imposes\ntariffs, or restricts the goods a carrier is permitted to transport;\nand (4) the law existed in one of the jurisdictions Congress\ndetermined lacked laws that regulate intrastate prices, routes,\nor services and thus, by implication, is a law Congress found\nnot to interfere with the FAAAA’s deregulatory goal. Other\nfactors may also lead a court to decide that a state law has a\n\n\n\n\n 19\n\fsignificant effect where the law undermines Congress’ goal of\nhaving competitive market forces dictate prices, routes, or\nservices of motor carriers.6\n\n E\n\n We have examined each of these considerations and\nconclude that New Jersey’s ABC classification test is not\npreempted as it has neither a direct, nor an indirect, nor a\nsignificant effect on carrier prices, routes, or services.\n\n 6\n Before the Supreme Court’s rulings in Rowe and\nDan’s City, our Court once framed the inquiry—albeit in the\ncontext of whether a defamation claim was preempted under\nthe ADA (a question we answered in the negative, holding that\nthe defamation claim was not preempted)—as whether the law\nor claim in question would “frustrate[] deregulation by\ninterfering with competition through public utility-style\nregulation.” Taj Mahal Travel, Inc. v. Delta Airlines, Inc., 164\nF.3d 186, 194 (3d Cir. 1998) (citation omitted). Elaborating\non regulation in a “public utility sense” in the context of airline\nservices, our Court said that regulations of “the frequency and\nscheduling of transportation” and “the selection of markets”\nare public-utility styled regulations (which would thus be\npreempted under the ADA), whereas “provision of in-flight\nbeverages, personal assistance to passengers, the handling of\nluggage, and similar amenities” are not services in a “public\nutility sense,” and thus could be regulated, for instance through\nstate implementation of a duty to exercise reasonable care, the\nviolation of which could give rise to ordinary tort claims. Id.\nat 193 (quoting Charas v. Trans World Airlines, Inc., 160 F.3d\n1259, 1261, 1265-66 (9th Cir. 1998) (en banc)).\n\n\n\n\n 20\n\f Any effect New Jersey’s ABC classification test has on\nprices, routes, or services is tenuous. The test does not mention\ncarrier prices, routes, or services, nor does it single out carriers.\nIndeed, the test applies to all businesses as part of the\n“backdrop” they “face in conducting their affairs.” Lupian,\n905 F.3d at 136; see also Dilts, 769 F.3d at 646 (describing a\nstate employment law as a “background regulation[]”). The\ntest also does not regulate carrier-customer interactions or\nother product outputs. Rather, it only concerns employer-\nworker relationships. Laws governing how an employer pays\nits workers do not “directly regulate[] how [a carrier’s] service\nis performed[;]” they merely dictate how a carrier “behaves as\nan employer[.]” DiFiore, 646 F.3d at 88. As a result, the test\nis “steps removed” from regulating customer-carrier\ninteractions through prices, routes, or services. Costello, 810\nF.3d 1054 (quoting Dilts, 769 F.3d at 646).\n\n The New Jersey ABC classification test does not have a\nsignificant effect on prices, routes, or services either. The test\ndoes not bind AEX to a particular method of providing services\nand thus it is unlike the preempted Massachusetts law at issue\nin Schwann, 813 F.3d 429. The Massachusetts statute does not\ninclude New Jersey’s alternative method for reaching\nindependent contractor status—that is, by demonstrating that\nthe worker provides services outside of the putative employer’s\n“places of business.” N.J. Stat. Ann. § 43:21-19(i)(6)(B).\nThus, if the other prongs of the New Jersey classification test\nare met, the test allows an employer to classify a worker as an\nindependent contractor if it shows that the worker either\nprovides a service that is “outside the [employer’s] usual\ncourse of business . . . or [performs such service] outside of all\n\n\n\n\n 21\n\fthe places of business of [the employer].” Id.7 No part of the\nNew Jersey test categorically prevents carriers from using\nindependent contractors. As a result, the state law at issue here\ndoes not mandate a particular course of action—e.g., requiring\ncarriers to use employees rather than independent\ncontractors—and it offers carriers various options to comply\nwith New Jersey employment law.8\n\n 7\n AEX focuses its argument on the B prong of the New\nJersey test, but also asserts that the A and C prongs of the test\nare preempted. AEX cites no case holding that prong A or C\nis preempted under either the FAAAA or the ADA. This is not\nsurprising given the legion of cases holding that the A and C\nprongs are not FAAAA-preempted. See, e.g., Vargas v. Spirit\nDelivery & Distrib. Servs., Inc., 245 F. Supp. 3d 268, 281-84\n(D. Mass. 2017); DaSilva v. Border Transfer of Mass., Inc.,\n227 F. Supp. 3d 154, 159-60 (D. Mass. 2017); Portillo v. Nat’l\nFreight, Inc., Civ. No. 15-7908, 2016 WL 5402215, at *5-6\n(D.N.J. Sept. 26, 2016); Chambers v. RDI Logistics, Inc., 65\nN.E.3d 1, 11-12 (Mass. 2016). AEX also provides no reason\nwhy these prongs are preempted and in fact does not\nindividually analyze them. Thus, AEX has failed to carry its\nburden to demonstrate that the affirmative defense of FAAAA\npreemption applies to these prongs.\n 8\n AEX makes much of the fact that the Costello and\nLupian courts observed that certain aspects of the IWPCA\nclassification provision could be contracted around (i.e.,\nemployees could enter into contracts with carriers to allow\ncertain paycheck deductions), Lupian, 905 F.3d at 135 n.12,\nwhereas neither the New Jersey test nor the Massachusetts test\nallows the same contractual avoidance. Contrary to AEX’s\nargument, this does not make the current case more analogous\n\n\n\n\n 22\n\f AEX argues that applying the New Jersey law may\nrequire it to shift its model away from using independent\ncontractors, which will increase its costs, and in turn, its prices.\nSpecifically, AEX asserts that if it can no longer use\nindependent contractors to perform its delivery services, then\nit will be forced to recruit employees, bring on a human\nresources department to manage them, acquire and maintain a\nfleet of vehicles and pay expense reimbursements, provide\nfringe benefits, plan and dictate delivery routes and timing, and\npay overtime wages and employment taxes. Our Court and our\nsister circuits have rejected similar lists of conclusory impacts.\nLupian, 905 F.3d at 135-36; Costello, 810 F.3d at 1056;\nMendonca, 152 F.3d at 1189. Though AEX correctly states\nthat it need not proffer empirical evidence to support its\nassertions of significant impact at the pleading stage, see, e.g.,\nCostello, 810 F.3d at 1055 (citing Rowe, 552 U.S. at 373-74),\n\n\nto Schwann than to Costello and Lupian. Though Costello and\nLupian correctly took the IWPCA contractual loophole into\naccount, neither court relied on it. See Lupian, 905 F.3d at 136\nn.12 (observing that the Costello court “noted” the contractual\nallowance in the IWPCA); Costello, 810 F.3d at 1057 (noting\nin a single sentence that the IWPCA’s prohibition on\ndeductions from wages can be contracted around, ultimately\nholding that the IWPCA is not “related to a price, route, or\nservice of any motor carrier”). Moreover, while a contractual\ncircumvention option may provide another route for\ncompliance, weighing against FAAAA preemption, it is not the\nonly way a state statute can afford carriers some flexibility.\nHere, the New Jersey ABC classification test gives carriers\noptions; it does not need to provide a contractual workaround\nto avoid preemption.\n\n\n\n\n 23\n\fit does not provide even a logical connection between the\napplication of New Jersey’s ABC classification test and the list\nof new costs it would purportedly incur.9\n\n AEX’s argument that it may be subject to other legal\nrequirements arising from reclassification, citing only the\nAffordable Care Act,10 is equally unavailing. In the words of\nthe Costello court, “[c]onspicuously absent from [the\ncompany’s] parade of horrors is any citation of authority\nshowing that it would be required to comply with [other]\nfederal and state laws.” Id. at 1056. Instead, AEX “rel[ies] on\nconclusory allegations that compliance with the [NJWHL and\nNJWPL] will require [AEX] to switch its entire business model\n. . . [but w]e see no basis for concluding that [New Jersey law]\nwould require that change given that the federal employment\nlaws and other state labor laws [may] have different tests” for\ndetermining whether someone is an employee under a specific\nstatute. Id. (citations omitted).\n\n Furthermore, while “[w]e have no doubt that the\ndisruption of a labor model—especially after services have\nbeen performed—could have negative financial and other\nconsequences for an employer,” Lupian, 905 F.3d at 136, this\nimpact on the employer does not equate to a significant impact\non Congress’ goal of deregulation. Congress sought to ensure\n\n 9\n For instance, we cannot see, nor has AEX explained,\nhow reclassification of employees would necessarily require\nAEX to acquire a new fleet of vehicles or create a human\nresources department.\n 10\n Patient Protection and Affordable Care Act of 2010,\nPub. L. No. 111-148, 124 Stat. 119 (2010).\n\n\n\n\n 24\n\fmarket forces determined prices, routes, and services. Nothing\nin that goal, however, meant to exempt workers from receiving\nproper wages, even if the wage laws had an incidental impact\non carrier prices, routes, or services.11\n\n Finally, the fact that New Jersey’s ABC classification\ntest differs from the federal test used in the Fair Labor\nStandards Act of 1938, 29 U.S.C. §§ 201-19, will not result in\na “‘patchwork’ of unique state legislation, which [AEX\ncontends] regulates differently from state to state how motor\ncarriers are required to perform their delivery services.” Reply\nBr. at 14. Most notably, New Jersey’s test is similar to that\nused in many other states. See, e.g., RDI Logistics, 65 N.E.3d\nat 11-12 (holding that prongs A and C of the Massachusetts\ntest, which are identical to those in the New Jersey test, were\nnot FAAAA-preempted because they did not present a\n“patchwork problem” as they were “more or less nationally\nuniform,” unlike the Massachusetts B prong, which was\npreempted in Schwann because it was anomalous (quoting\nSchwann, 813 F.3d at 440)).\n\n\n\n\n 11\n Indeed, Congress evinced its intent for the FAAAA\nnot to preempt general state wage laws when it included New\nJersey—where, at the time the FAAAA was enacted, the\nNJWHL and NJWPL were already in effect, N.J. Stat. Ann. §§\n34:11-56a7 & 34:11-4.1 (indicating initial enactment in 1966\nand 1965, respectively)—in its list of jurisdictions with laws\nthat did not run afoul of the FAAAA. H.R. Conf. Rep. No.\n103-677, at 86 (1994); see also Mendonca, 152 F.3d at 1187-\n88 & n.3.\n\n\n\n\n 25\n\f Thus, AEX has not shown that New Jersey’s ABC\nclassification test has a “significant impact” on Congress’\nderegulatory efforts with respect to motor carrier businesses,\nnor are the NJWHL and NJWPL—typical state wage and hour\nlaws—the kinds of preexisting state regulations with which\nCongress was concerned when it passed the FAAAA.12 See\nLupian, 905 F.3d at 135-36; Schwann, 813 F.3d at 438;\nCostello, 810 F.3d at 1050-51; Amerijet, 627 F. App’x at 751;\nDilts, 769 F.3d at 647-48; Gary, 397 F.3d at 189-90;\nMendonca, 152 F.3d at 1187-89. Notably, eight of the ten\njurisdictions that Congress identified as not regulating\nintrastate prices, routes, and services “had laws for\ndifferentiating between an employee and an independent\ncontractor,” Su, 903 F.3d at 967, and at least three codified\nABC tests similar to that of New Jersey, see Alaska Stat. §\n23.20.525(a)(10) (1992); Del. Code Ann. tit. 19, § 3302(9)(k)\n(1992); Vt. Stat. Ann. tit. 21, § 1301(6)(B) (1992). Therefore,\nAEX’s patchwork argument fails.\n\n Accordingly, any effect the New Jersey ABC\nclassification test has on prices, routes, or services with respect\nto the transportation of property is tenuous and insignificant.\nSee Lupian, 905 F.3d at 136. As a result, the test is not\npreempted.\n\n\n\n\n 12\n As the Schwann court observed, while Congress\nsought “to avoid ‘a patchwork of state service-determining\nlaws,’” we can assume that “Congress intended to leave\nuntouched” “pre-existing and customary manifestation[s] of\nthe state’s police power.” 813 F.3d at 438 (quoting Rowe, 552\nU.S. at 373).\n\n\n\n\n 26\n\f III\n\n For the foregoing reasons, we will affirm the District\nCourt’s order denying AEX’s motion for judgment on the\npleadings and remand for further proceedings.\n\n\n\n\n 27\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Ever BEDOYA; Diego Gonzales; Manuel Decastro, on Behalf of Themselves and All Others Similarly Situated v. AMERICAN EAGLE EXPRESS INC., D/B/A AEX Group v. KV Service, LLC; M&J Express, LLC; A&D Delivery Express, LLC American Eagle Express, Inc., Appellant\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-29\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 18-1641\\n _____________\\n\\n EVER BEDOYA; DIEGO GONZALES; MANUEL\\n DECASTRO,\\n on behalf of themselves and all others similarly situated\\n\\n v.\\n\\nAMERICAN EAGLE EXPRESS INC, d/b/a AEX GROUP\\n\\n v.\\n\\n KV SERVICE, LLC; M&J EXPRESS, LLC; A&D\\n DELIVERY EXPRESS, LLC\\n\\n American Eagle Express, Inc.,\\n Appellant\\n ______________\\n\\n Appeal from the United States District Court\\n for the District of New Jersey\\n (D.C. No. 2-14-cv-02811)\\n District Judge: Hon. Esther Salas\\n ______________\\n\\f Argued November 14, 2018\\n ______________\\n\\n Before: GREENAWAY, JR., SHWARTZ, and BIBAS,\\n Circuit Judges.\\n\\n (Opinion Filed: January 29, 2019)\\n\\nHarold L. Lichten [ARGUED]\\nLichten & Liss-Riordan\\n729 Boylston Street\\nSuite 2000\\nBoston, MA 02116\\n\\nR. Andrew Santillo\\nPeter D. Winebrake\\nWinebrake & Santillo\\n715 Twinning Road\\nSuite 211, Twinning Office Center\\nDresher, PA 19025\\n\\n Counsel for Plaintiff-Appellees\\n\\nJoseph C. DeBlasio [ARGUED]\\nJackson Lewis\\n220 Headquarters Plaza\\nEast Tower, 7th Floor\\nMorristown, NJ 07960\\n\\n Counsel for Defendant-Appellant\\n\\nAdina H. Rosenbaum\\nPublic Citizen Litigation Group\\n\\n\\n\\n\\n 2\\n\\f1600 20th Street, NW.\\nWashington, DC 20009\\n\\n Counsel for Amicus Public Citizen Inc.\\n\\n\\nChristopher W. Weber [ARGUED]\\nEmily M. Bisnauth\\nOffice of Attorney General of New Jersey\\nDepartment of Law & Public Safety\\nRichard J. Hughes Justice Complex\\n25 Market Street\\nP.O. Box 112\\nTrenton, NJ 08625\\n\\n Counsel for Amicus New Jersey Department of Labor\\n and Workforce Development\\n\\n\\n ___________\\n\\n OPINION\\n ___________\\n\\n\\nSHWARTZ, Circuit Judge.\\n\\n Plaintiff delivery drivers Ever Bedoya, Diego Gonzalez,\\nand Manuel Decastro (collectively, “the Drivers”) filed a\\nputative class action against Defendant American Eagle\\nExpress, Inc., (“AEX”), alleging that AEX misclassified them\\nas independent contractors when they are actually employees\\nunder the New Jersey Wage and Hour Law (“NJWHL”), N.J.\\n\\n\\n\\n\\n 3\\n\\fStat. Ann. §§ 34:11-56a to -56a3, and the New Jersey Wage\\nPayment Law (“NJWPL”), N.J. Stat. Ann. §§ 34:11-4.1 to -\\n4:14. AEX moved for judgment on the pleadings pursuant to\\nFed. R. Civ. P. 12(c), arguing that the Drivers’ claims are\\npreempted by the Federal Aviation Authorization\\nAdministration Act of 1994 (“FAAAA”), 49 U.S.C. §§ 14501-\\n06. The District Court denied AEX’s motion and certified the\\norder for interlocutory appeal. Because the FAAAA does not\\npreempt the New Jersey law for determining employment\\nstatus for the purposes of NJWHL and NJWPL, we will affirm\\nthe order and remand for further proceedings.\\n\\n I\\n\\n AEX is a logistics company that provides delivery\\nservices to various medical organizations. The Drivers are\\nNew Jersey residents who make deliveries for AEX. The\\nDrivers filed this putative class action against AEX seeking,\\namong other things, a judgment declaring that they are\\nemployees of AEX, rather than independent contractors, which\\nentitles them to compensation under the NJWHL and NJWPL.1\\nAEX moved for judgment on the pleadings, arguing that the\\nFAAAA preempts the Drivers’ claims.\\n\\n The District Court denied AEX’s motion, Bedoya v.\\nAm. Eagle Express, Civ. No. 14-2811, 2017 WL 4330351, at\\n*1 (D.N.J. Sept. 29, 2017), reasoning that “[t]here is no clear\\nindication” that Congress intended for the FAAAA to preempt\\nstate wage laws, Dkt. 109 at 6, 10, and that the connection\\nbetween regulation of AEX’s workforce and the “prices,\\n\\n 1\\n The District Court has jurisdiction pursuant to 28\\nU.S.C. § 1332(d).\\n\\n\\n\\n\\n 4\\n\\froutes, and services” provided to its consumers is too\\nattenuated to justify preempting claims under the NJWHL and\\nNJWPL, id. at 8-9. We now consider AEX’s interlocutory\\nappeal of the order denying the motion pursuant to 28 U.S.C.\\n§ 1292(b). Bedoya, 2017 WL 4330351, at *1-4.\\n\\n II2\\n\\n A\\n\\n The question before us is whether the FAAAA preempts\\nNew Jersey’s test for determining employment classification\\nfor purposes of the NJWHL and NJWPL. Under this test,\\nworkers performing services for a given company in exchange\\nfor pay are deemed employees unless the company can\\ndemonstrate each of the following:\\n\\n A. Such individual has been and will continue to\\n be free from control or direction over the\\n\\n 2\\n We review an order granting or denying a motion for\\njudgment on the pleadings de novo. Zimmerman v. Corbett,\\n873 F.3d 414, 417 (3d Cir. 2017) (citing Allah v. Al-Hafeez,\\n226 F.3d 247, 249 (3d Cir. 2007)). Judgment will not be\\ngranted unless the movant “clearly establishes there are no\\nmaterial issues of fact, and he is entitled to judgment as a\\nmatter of law.” Sikirica v. Nationwide Ins. Co., 416 F.3d 214,\\n220 (3d Cir. 2005) (citation omitted). In considering a motion\\nfor judgment on the pleadings, we must accept as true all facts\\npresented in the complaint and answer and draw all reasonable\\ninferences in favor of the non-moving party—here, the\\nDrivers. Id. at 417-18. While AEX implores us to look beyond\\nthe pleadings, we may not.\\n\\n\\n\\n\\n 5\\n\\f performance of such service, both under his\\n contract of service and in fact; and\\n\\n B. Such service is either outside the usual course\\n of the business for which such service is\\n performed, or that such service is performed\\n outside of all the places of business of the\\n enterprise for which such service is\\n performed; and\\n\\n C. Such individual is customarily engaged in an\\n independently established trade, occupation,\\n profession, or business.\\n\\nN.J. Stat. Ann. §§ 43:21-19(i)(6)(A)-(C) (“New Jersey ABC\\nclassification test”). Where a company successfully\\ndemonstrates all three elements with respect to a worker, that\\nworker qualifies as an independent contractor under the\\nNJWHL and NJWPL. Hargrove v. Sleepy’s, LLC, 106 A.3d\\n449, 458 (N.J. 2015). The company, in turn, is exempt from\\nrequirements under those statutes with respect to the worker.\\nId. For individuals classified as employees, however, the\\nemploying company is subject to each statute’s obligations,\\nincluding minimum and overtime wage requirements, N.J.\\nStat. Ann. § 34:11-56a4, conditions regarding the time and\\nmode of pay, N.J. Stat. Ann. § 34:11-4.2, 4.2a, and restrictions\\non pay deductions, N.J. Stat. Ann. § 34:11-4.4. AEX contends\\nthat the New Jersey ABC classification test is preempted by the\\nFAAAA.\\n\\n\\n\\n\\n 6\\n\\f B\\n\\n The preemption doctrine stems from the Supremacy\\nClause, which provides that “the Laws of the United States . . .\\nshall be the supreme Law of the Land . . . any Thing in the\\nConstitution or Laws of any State to the Contrary\\nnotwithstanding.” U.S. Const. art. VI, cl. 2. Thus, “Congress\\n. . . has the power to preempt state law.” In re Vehicle Carrier\\nServs. Antitrust Litig., 846 F.3d 71, 83 (3d Cir. 2017) (citing\\nArizona v. United States, 567 U.S. 387 (2012)), cert denied sub\\nnom., Alban v. Nippon Yusen Kabushiki Kaisha, 138 S. Ct.\\n114 (2017). There are three categories of preemption: field\\npreemption, conflict preemption, and express preemption.\\nHolk v. Snapple Beverage Corp., 575 F.3d 329, 334 (3d Cir.\\n2009) (citing Hillsborough County, Fla. v. Automated Med.\\nLabs., Inc., 471 U.S. 707, 713 (1985)).\\n\\n Because preemption is an affirmative defense, we\\nexamine the specific preemption defense asserted. In re\\nVehicle, 846 F.3d at 84 (citing Oneok, Inc. v. Learjet, Inc., 135\\nS. Ct. 1591 (2015)). AEX argues that New Jersey’s ABC\\nclassification test is subject to express preemption under 49\\nU.S.C. § 14501(c)(1). “Express preemption requires a[n]\\nanalysis of whether ‘[s]tate action may be foreclosed by\\nexpress language in a congressional enactment.’” Lupian v.\\nJoseph Cory Holdings, LLC, 905 F.3d 127, 131 (3d Cir. 2018)\\n(alteration in original) (quoting Lorillard Tobacco Co. v.\\nReilly, 533 U.S. 525, 541 (2001)).\\n\\n In evaluating AEX’s argument, we first decide whether\\nthe presumption against preemption applies. City of Columbus\\nv. Ours Garage & Wrecker Serv., Inc., 536 U.S. 424, 438\\n(2002) (applying the presumption against preemption in the\\n\\n\\n\\n\\n 7\\n\\fFAAAA context). Under this presumption, “the historic police\\npowers of the States” are “not to be superseded by [a] [f]ederal\\n[a]ct unless that was the clear and manifest purpose of\\nCongress.” Sikkelee v. Precision Airmotive Corp., 822 F.3d\\n680, 687 (3d Cir. 2016) (quoting Wyeth v. Levine, 555 U.S.\\n555, 565 (2009)). Thus, we “presume claims based on laws\\nembodying state police powers are not preempted.” In re\\nVehicle, 846 F.3d at 84; see also Farina v. Nokia Inc., 625 F.3d\\n97, 116 (3d Cir. 2010).\\n\\n Many employment regulations, such as the wage laws\\nat issue here, seek to ensure workers receive fair pay. Because\\nthey protect workers, they are within New Jersey’s police\\npower, and the presumption against preemption by federal law\\napplies. See, e.g., Lupian, 905 F.3d at 131 (stating wage laws\\nthat protect workers represent an exercise of “police power”);\\nsee also Fort Halifax Packing Co. v. Coyne, 482 U.S. 1, 21\\n(1987) (applying the presumption against preemption to a state\\nlabor law regarding severance pay “since the establishment of\\nlabor standards falls within the traditional police power of the\\nState”).\\n\\n The presumption is rebutted where Congress had a\\n“clear and manifest purpose” to preempt state laws. Sikkelee,\\n822 F.3d at 687 (citation omitted); see also Cipollone v. Liggett\\nGrp., Inc., 505 U.S. 504, 516 (1992) (directing courts to\\nexamine congressional intent, the “ultimate touchstone” in\\ndiscerning the preemptive scope of a statute (internal quotation\\nmarks and citation omitted)). To determine Congress’\\npurpose, we look to the plain language of the statute and, if\\nnecessary, to the statutory framework as a whole. Medtronic,\\nInc. v. Lohr, 518 U.S. 470, 486 (1996) (citation omitted).\\nThus, we next examine Congress’ purpose in enacting the\\n\\n\\n\\n\\n 8\\n\\fFAAAA and the Airline Deregulation Act of 1978 (“ADA”),\\n49 U.S.C. §§ 40101-130, an earlier statute with a similar\\npreemption provision.\\n\\n C\\n\\n In 1978, following a long period of heightened\\nregulation, Congress enacted the ADA, which sought to\\nderegulate the air-travel industry to “maxim[ize] reliance on\\ncompetitive market forces.” Morales v. Trans World Airlines,\\nInc., 504 U.S. 374, 378 (1992) (quoting 49 U.S.C. App. §\\n1302(a)(4)). To ensure that this objective would not be\\nfrustrated by state regulation, Congress included a preemption\\nprovision providing that “no State . . . shall enact or enforce\\nany law . . . relating to rates, routes, or services of any air\\ncarrier.” Id. at 420 (Stevens, J., dissenting) (quoting 49 U.S.C.\\nApp. § 1305(a)).\\n\\n Congress enacted similar laws focused on deregulating\\ninterstate trucking, culminating with the passage of the\\nFAAAA in 1994. Lupian, 905 F.3d at 132-33. Via the\\nFAAAA, Congress sought to “level the playing field” between\\nair carriers and motor carriers so that both could benefit from\\nfederal deregulation. H.R. Conf. Rep. No. 103-677, at 88\\n(1994); see also Californians for Safe & Competitive Dump\\nTruck Transp. v. Mendonca, 152 F.3d 1184, 1187-88 (9th Cir.\\n1998) (detailing FAAAA legislative history). The FAAAA\\ncontains a preemption provision modeled after the ADA’s,\\nproviding, with limited exceptions, that:\\n\\n a State . . . may not enact or enforce a law,\\n regulation, or other provision having the force\\n and effect of law related to a price, route, or\\n\\n\\n\\n\\n 9\\n\\f service of any motor carrier . . . with respect to\\n the transportation of property.\\n\\n49 U.S.C. § 14501(c)(1). Because of the parallels between the\\nADA and FAAAA, ADA cases are instructive regarding the\\nscope of FAAAA preemption. See Rowe v. N.H. Motor\\nTransp. Ass’n, 552 U.S. 364, 370 (2008) (analyzing FAAAA\\npreemption using ADA cases as guidance). As with the ADA,\\nthe FAAAA preemption provision’s central objective is to\\navoid frustrating the statute’s deregulatory purpose by\\npreventing states from imposing “a patchwork of state service-\\ndetermining laws.” Dan’s City Used Cars, Inc. v. Pelkey, 569\\nU.S. 251, 264 (2013) (quoting Rowe, 552 U.S. at 373). The\\nFAAAA, however, has a qualifier that is absent from the ADA:\\nthe preempted state law must relate to prices, routes, or services\\n“with respect to the transportation of property.” 49 U.S.C.\\n§ 14501(c)(1). The Supreme Court has recognized that this\\nlanguage “massively limits the scope of preemption ordered by\\nthe FAAAA.” Dan’s City, 569 U.S. at 261 (internal citation\\nand quotation marks omitted).\\n\\n Further insight into the limits of FAAAA preemption\\ncomes from the subjects Congress considered when enacting\\nthat statute. “Congress identified ten jurisdictions (nine states\\nand the District of Columbia . . . ) that did not regulate intrastate\\nprices, routes, and services.” Cal. Trucking Ass’n v. Su, 903\\nF.3d 953, 967 (9th Cir. 2018) (citing Mendonca, 152 F.3d at\\n1187). By implication, Congress determined that the laws then\\nin existence in those jurisdictions did not contravene its\\nderegulatory goals and thus were not preempted. Id.\\n\\n The Supreme Court has also articulated several\\nprinciples that inform us about the breadth of FAAAA\\n\\n\\n\\n\\n 10\\n\\fpreemption. First, the “related to” language from the FAAAA\\npreemption clause gives it a broad scope, encompassing any\\nstate actions that have “a connection with, or [make] reference\\nto . . . rates, routes, or services” of a motor carrier. Nw., Inc.\\nv. Ginsberg, 572 U.S. 273, 280-81 (2014) (internal quotation\\nmarks and citation omitted) (interpreting the ADA). While this\\nlanguage covers any state law that has a connection with or\\nrefers to “price[s], route[s], [or] service[s,]” id. at 280, “the\\nbreadth of the words ‘related to’ does not mean the sky is the\\nlimit,” Dan’s City, 569 U.S. at 260. Drawing from case law\\nexamining similar wording in the preemption provision of the\\nEmployee Retirement Income Security Act of 1974, 29 U.S.C.\\n§ 1144(a), see, e.g., Morales, 504 U.S. at 383-84, the Supreme\\nCourt has observed that reading the phrase “related to” with\\n“uncritical literalism” would render preemption an endless\\nexercise, Dan’s City, 569 U.S. at 260-61 (citation omitted),\\nbecause “everything [is] relat[ed] to everything else in some\\nmanner[,]” Schwann v. FedEx Ground Package Sys., Inc., 813\\nF.3d 429, 436 (1st Cir. 2016) (citing N.Y. State Conference of\\nBlue Cross & Blue Shield Plans v. Travelers Ins. Co., 514 U.S.\\n645, 655 (1955)).\\n\\n Second, FAAAA preemption reaches laws that affect\\nprices, routes, or services even if the effect “is only indirect.”\\nRowe, 552 U.S. at 370 (quoting Morales, 504 U.S. at 386).\\nHowever, where a law’s impact on carrier prices, routes, or\\nservices is so indirect that the law affects them “in only a\\ntenuous, remote, or peripheral . . . manner,” the law is not\\npreempted. Dan’s City, 569 U.S. at 261 (quoting Rowe, 552\\nU.S. at 371); Morales, 504 U.S. at 390 (quoting Shaw v. Delta\\nAir Lines, Inc., 463 U.S. 85, 100 n.21 (1983)).\\n\\n\\n\\n\\n 11\\n\\f Finally, preemption occurs where a state law has “a\\n‘significant impact’ on carrier rates, routes, or services.”3\\nRowe, 552 U.S. at 375 (emphasis omitted) (quoting Morales,\\n504 U.S. at 390).\\n\\n Mindful of these principles, we next review the case law\\nfor guidance concerning whether a law has a direct or indirect\\neffect and whether it has a significant or insignificant effect.\\nFrom our review, we identify factors courts examine and set\\nforth those factors that may shed light on a law’s directness and\\nthose that may reflect the significance of the law’s effect on the\\nregulated entities at issue.\\n\\n D\\n\\n Neither the Supreme Court nor our Court has recited\\nprecise standards for evaluating directness or significance, but\\ncases addressing the issue provide some guidance. For\\nexample, the Supreme Court has held that consumer protection\\nand fraud laws used to regulate frequent-flyer programs could\\ndirectly and significantly affect prices and services and are thus\\npreempted. See Am. Airlines, Inc. v. Wolens, 513 U.S. 219,\\n223 (1995); Morales, 504 U.S. at 388-89. Similarly, the Court\\ndetermined that a Maine law requiring a specific procedure to\\nverify the recipient of tobacco deliveries was preempted by the\\nFAAAA because it dictated a service that tobacco motor\\ncarriers were required to provide for property they transported.\\nRowe, 552 U.S. at 372. In addition, we recently observed that\\n\\n 3\\n The Supreme Court also noted that “it makes no\\ndifference whether a state law is ‘consistent’ or ‘inconsistent’\\nwith federal regulation.” Rowe, 552 U.S. at 370 (quoting\\nMorales, 504 U.S. at 386-87).\\n\\n\\n\\n\\n 12\\n\\fthe FAAAA’s “preemption clause undoubtedly applies, for\\nexample, to state laws directly restricting types of goods that\\ncan be carried by trucks, tariffs, and barriers to entry.” Lupian,\\n905 F.3d at 135; H.R. Conf. Rep. No. 103-677, at 86 (1994).\\n\\n On the other hand, the FAAAA itself, the Supreme\\nCourt, and the courts of appeals have identified laws that are\\ntoo “tenuous, remote, or peripheral” from carrier prices, routes,\\nand services to trigger preemption. See, e.g., Rowe, 552 U.S.\\nat 371; Dilts v. Penske Logistics, LLC, 769 F.3d 637, 646 (9th\\nCir. 2014). The FAAAA explicitly exempts from preemption\\nlaws governing motor vehicle safety, local route controls based\\non vehicle size and weight, and driver insurance requirements.4\\n49 U.S.C. § 14501(c)(2)(A). The Supreme Court has stated\\nthat the FAAAA does not preempt laws prohibiting\\nprostitution, gambling, and “obscene depictions,” Morales,\\n504 U.S. at 390, or those addressing zoning, Dan’s City, 569\\nU.S. at 264. We have observed that “garden variety\\nemployment claim[s]” evade ADA and FAAAA preemption\\nbecause they are “too remote and too attenuated” from carrier\\nprices, services, or routes. Lupian, 905 F.3d at 134 (quoting\\nGary v. Air Grp., Inc., 397 F.3d 183, 189 (3d Cir. 2005)). As\\nrelevant to this case, we recently held that wage claims under\\nthe Illinois Wage Payment and Collection Act (“IWPCA”),\\n820 Ill. Comp. Stat. 115/1-115/15, are not preempted under the\\nFAAAA because they are “too far removed from the statute’s\\n\\n 4\\n The House of Representatives Conference Report\\nspecifies that the list provided in 49 U.S.C. § 14501(c)(2) and\\n(3) is “not intended to be all inclusive, but merely to specify\\nsome of the matters which are not ‘prices, rates or services’ and\\nwhich are therefore not preempted.” H.R. Conf. Rep. No. 103-\\n677, at 83.\\n\\n\\n\\n\\n 13\\n\\fpurpose to warrant preemption.” Lupian, 905 F.3d at 136.\\nMany of our sister circuits have similarly held that the FAAAA\\nand ADA do not preempt state employment laws. See, e.g.,\\nAllied Concrete & Supply Co. v. Baker, 904 F.3d 1053, 1068\\n(9th Cir. 2018) (holding California prevailing wage law for\\nworkers on public projects not preempted); Su, 903 F.3d at 957\\n(holding California common law test for employee versus\\nindependent contractor status not preempted); Costello v.\\nBeavEx, Inc., 810 F.3d 1045, 1048 (7th Cir. 2016) (holding\\nIllinois wage law not preempted), cert. denied, 137 S. Ct. 2289\\n(2017); Amerijet Int’l, Inc. v. Miami-Dade County, Fla., 627\\nF. App’x 744, 751 (11th Cir. 2015) (holding Miami-Dade\\nCounty living wage ordinance as applied to air carriers not\\npreempted); Dilts, 769 F.3d at 647 (holding California meal\\nand rest-break laws not preempted); Mendonca, 152 F.3d at\\n1189 (holding California wage law not preempted).\\n\\n From the language of the FAAAA preemption provision\\nand these cases, we can distill several factors courts should\\nconsider when deciding whether a particular state law is\\nFAAAA-preempted. First, courts should examine whether the\\nstate law at issue applies to all businesses or whether it focuses\\non motor carriers. Laws that are directed at “members of the\\ngeneral public” and that are not targeted at motor carriers are\\nusually viewed as not having a direct effect on motor carriers.\\nRowe, 552 U.S. at 375.\\n\\n Even targeted laws, however, are not necessarily\\npreempted. We know from the FAAAA itself that state laws\\nthat may target motor carrier safety and insurance, or restrict\\nlocal routes based on vehicle size and weight, are not\\npreempted. 49 U.S.C. § 14501(c)(2). Conversely, laws of\\ngeneral applicability may nonetheless be preempted where\\n\\n\\n\\n\\n 14\\n\\fthey have a significant impact on the services a carrier\\nprovides. See, e.g., DiFiore v. Am. Airlines Inc., 646 F.3d 81,\\n88-89 (1st Cir. 2011) (holding generally applicable state tip\\nlaw as applied to airlines preempted under the ADA because it\\n“directly regulate[d] how an airline service is performed and\\nhow its price is displayed to customers”). Thus, whether a law\\nis applicable to every business or targets carriers is a helpful\\nbut nondispositive factor for determining whether a law has a\\ndirect effect on motor carriers’ prices, routes, or services.\\nMorales, 504 U.S. at 386.\\n\\n Second, courts should consider whether the law\\naddresses the carrier-employee relationship as opposed to the\\ncarrier-customer relationship. “[G]enerally applicable state\\nlaws that affect the carrier’s relationship with its customers\\n[differ from] those that affect the carrier’s relationship with its\\nworkforce.” Costello, 810 F.3d at 1054; see also Su, 903 F.3d\\nat 961-63 (noting same dichotomy); DiFiore, 646 F.3d at 88\\n(preempting a Massachusetts law prohibiting employer from\\ncollecting fee advertised as “service charge” because the law\\nregulates how a company performs services for its customers\\nand “not merely how the airline behaves as an employer or\\nproprietor”).\\n\\n The Court of Appeals for the Seventh Circuit provides\\na useful analysis explaining why laws governing an employer’s\\nrelationship with its employees have too remote an impact to\\nbe preempted. S.C. Johnson & Son, Inc. v. Transp. Corp. of\\nAm., Inc., 697 F.3d 544, 558 (7th Cir. 2012) (citing Mendonca,\\n152 F.3d at 1189). The court examines whether the challenged\\nstate law regulates matters needed to operate the business,\\nwhich it calls resource inputs, as opposed to laws governing\\nthe goods or services the business puts out, which it calls\\n\\n\\n\\n\\n 15\\n\\fproduct outputs. Id. The product outputs of the motor carrier\\nindustry are the services it provides—transportation of\\nproperty from origin to destination. Id. The FAAAA’s focus\\non prices, routes, and services shows that the statute is\\nconcerned with the industry’s production outputs, and seeks to\\nprotect them from state regulation.\\n\\n Resource inputs, on the other hand, are the resources\\nnecessary for a business to create product outputs, including\\n“labor, capital, and technology,” which may be regulated by\\nvarious laws. Id. “For example, labor inputs are affected by a\\nnetwork of labor laws, including minimum wage laws, worker-\\nsafety laws, anti-discrimination laws, and pension regulations.\\nCapital is regulated by banking laws, securities rules, and tax\\nlaws, among others. Technology is heavily influenced by\\nintellectual property laws.” Id. Although laws that regulate\\ninputs may impact costs and may in turn affect prices charged\\nand services provided to customers, “no one thinks that the\\nADA or the FAAAA preempts these [regulations] and the\\nmany comparable state laws[.]” Id. That is because,\\nnotwithstanding the state laws’ indirect effects, they “operate\\none or more steps away from the moment at which the firm\\noffers its customer[s] a service for a particular price” and\\ntherefore have too “remote” an effect on prices, routes, and\\nservices to be the intended target of preemption. Id. (internal\\ncitations omitted); see also Su, 903 F.3d at 966 (stating that\\ncourts should examine “where in the chain of a motor carrier’s\\nbusiness [the state law] is acting to compel a certain result (e.g.,\\nconsumer or work force), and what result it is compelling (e.g.,\\ncertain wage, non-discrimination, a specific system of\\ndelivery, a specific person to perform the delivery)”); Costello,\\n810 F.3d at 1055 (embracing S.C. Johnson, 697 F.3d at 558).\\nIn short, laws regulating labor inputs, such as wage laws, have\\n\\n\\n\\n\\n 16\\n\\ftoo remote an effect on the price the company charges, the\\nroutes it uses, and service outputs it provides and are less likely\\nto be preempted by the FAAAA.\\n\\n Third, courts should consider whether the law binds the\\ncarrier to provide a particular price, route, or service. As\\ndiscussed above, the Supreme Court held that Maine’s\\nidentification requirements for tobacco deliveries required a\\nmotor carrier transporting tobacco to provide a particular\\nservice. Rowe, 552 U.S. at 372. Similarly, the Court of\\nAppeals for the First Circuit determined that Massachusetts’\\nABC test for classifying employees in effect bound the carrier\\nto provide its services using employees rather than independent\\ncontractors. Schwann, 813 F.3d at 437. Under Massachusetts’\\nindependent contractor statute, only workers who perform a\\nservice that is outside the employer’s usual course of business\\nmay be classified as independent contractors. Id. (quoting\\nMass. Gen. Laws ch. 149, § 148B(a)(2)). Thus, application of\\nMassachusetts’ test “in substance, bar[red] [the carrier at issue]\\nfrom using any individuals as full-fledged independent\\ncontractors.” Id. In other words, the Massachusetts test\\nessentially foreclosed the independent contractor classification\\nof any of the carrier’s workers performing delivery services\\nbecause such services were within the carrier’s usual course of\\nbusiness. Id. As a result, the Massachusetts statute bound the\\ncarrier to provide its services using employees and not\\nindependent contractors.\\n\\n The same was not true with laws that do not dictate a\\nprice, route, or service. For example, the Court of Appeals for\\nthe Ninth Circuit analyzed whether the FAAAA preempted a\\nCalifornia law that requires employers to provide meal and rest\\nbreaks, reviewing, among other factors, whether the law bound\\n\\n\\n\\n\\n 17\\n\\fthe carrier to specific prices, routes, or services. Dilts, 769 F.3d\\nat 649-50. The court held that the FAAAA did not preempt\\nCalifornia’s meal and rest-break laws. Id. The court relied\\npartially on the fact that the California laws did not “set prices,\\nmandate or prohibit certain routes, or tell motor carriers what\\nservices they may or may not provide, either directly or\\nindirectly.” Id. at 647. Put simply, the law at issue did “not\\n‘bind’ motor carriers to specific prices, routes, or services.”5\\nId. (citation omitted).\\n\\n Finally, courts examining a preemption challenge to a\\nstate law should be mindful of Congress’ goal of avoiding a\\n“patchwork” of differing state “service-determining laws,”\\nwhich could undermine its “major legislative effort to leave\\n[decisions regarding the provision of services] to the\\ncompetitive marketplace.” Rowe, 552 U.S. at 373 (citing H.R.\\nConf. Rep. No. 103-677, at 87 (1994)). This goal does not\\nconstitute a categorical imperative to free motor carriers of all\\nstate regulation. Rather, the plain language of the FAAAA,\\nand its preemption of only laws “relat[ing] to” carrier “price[s],\\nroute[s], or service[s],” 49 U.S.C. § 14501(c)(1), demonstrates\\nthat Congress was concerned only with a limited set of state\\n\\n 5\\n AEX characterizes Dilts as impermissibly relying on\\nthis “binds to” test to conclude that the FAAAA did not\\npreempt California’s meal and rest break laws, arguing that\\nsuch a test construes the scope of FAAAA preemption too\\nnarrowly. While relying solely on such a “binds to” test may\\nnarrow FAAAA preemption to an unacceptable degree, Dilts\\nmerely recognized that the “binds to” test provides one of\\nseveral possible avenues to demonstrate that a state law has a\\nsignificant effect on carrier prices, routes, or services. Dilts,\\n769 F.3d at 649.\\n\\n\\n\\n\\n 18\\n\\flaws. Dilts, 769 F.3d at 646-47. Thus, “[t]he fact that laws\\nmay differ from state to state is not, on its own, cause for\\nFAAAA preemption.” Id. at 647. Laws that are “more or less\\nnationally uniform,” Chambers v. RDI Logistics, Inc., 65\\nN.E.3d 1, 11-12 (Mass. 2016), are less likely to pose the kind\\nof state law interference FAAAA preemption seeks to avoid.\\n\\n In sum, to assess the directness of a law’s effect on\\nprices, routes, or services, courts should examine whether the\\nlaw: (1) mentions a carrier’s prices, routes, or services;\\n(2) specifically targets carriers as opposed to all businesses;\\nand (3) addresses the carrier-customer relationship rather than\\nnon-customer-carrier relationships (e.g., carrier-employee). If\\na law has a direct impact on carriers’ prices, routes, or services\\nwith respect to the transportation of property, then it is\\npreempted unless it falls within one of the statutory exceptions.\\nThough we can draw no firm line between laws whose effects\\non rates, routes, or services are indirect and laws whose effects\\nare “tenuous, remote, or peripheral,” these factors, and perhaps\\nother considerations, will guide courts in the inquiry.\\n\\n To assess whether a law has a significant effect on a\\ncarrier’s prices, routes, or services, courts should consider\\nwhether: (1) the law binds a carrier to provide or not provide a\\nparticular price, route, or service; (2) the carrier has various\\navenues to comply with the law; (3) the law creates a\\npatchwork of regulation that erects barriers to entry, imposes\\ntariffs, or restricts the goods a carrier is permitted to transport;\\nand (4) the law existed in one of the jurisdictions Congress\\ndetermined lacked laws that regulate intrastate prices, routes,\\nor services and thus, by implication, is a law Congress found\\nnot to interfere with the FAAAA’s deregulatory goal. Other\\nfactors may also lead a court to decide that a state law has a\\n\\n\\n\\n\\n 19\\n\\fsignificant effect where the law undermines Congress’ goal of\\nhaving competitive market forces dictate prices, routes, or\\nservices of motor carriers.6\\n\\n E\\n\\n We have examined each of these considerations and\\nconclude that New Jersey’s ABC classification test is not\\npreempted as it has neither a direct, nor an indirect, nor a\\nsignificant effect on carrier prices, routes, or services.\\n\\n 6\\n Before the Supreme Court’s rulings in Rowe and\\nDan’s City, our Court once framed the inquiry—albeit in the\\ncontext of whether a defamation claim was preempted under\\nthe ADA (a question we answered in the negative, holding that\\nthe defamation claim was not preempted)—as whether the law\\nor claim in question would “frustrate[] deregulation by\\ninterfering with competition through public utility-style\\nregulation.” Taj Mahal Travel, Inc. v. Delta Airlines, Inc., 164\\nF.3d 186, 194 (3d Cir. 1998) (citation omitted). Elaborating\\non regulation in a “public utility sense” in the context of airline\\nservices, our Court said that regulations of “the frequency and\\nscheduling of transportation” and “the selection of markets”\\nare public-utility styled regulations (which would thus be\\npreempted under the ADA), whereas “provision of in-flight\\nbeverages, personal assistance to passengers, the handling of\\nluggage, and similar amenities” are not services in a “public\\nutility sense,” and thus could be regulated, for instance through\\nstate implementation of a duty to exercise reasonable care, the\\nviolation of which could give rise to ordinary tort claims. Id.\\nat 193 (quoting Charas v. Trans World Airlines, Inc., 160 F.3d\\n1259, 1261, 1265-66 (9th Cir. 1998) (en banc)).\\n\\n\\n\\n\\n 20\\n\\f Any effect New Jersey’s ABC classification test has on\\nprices, routes, or services is tenuous. The test does not mention\\ncarrier prices, routes, or services, nor does it single out carriers.\\nIndeed, the test applies to all businesses as part of the\\n“backdrop” they “face in conducting their affairs.” Lupian,\\n905 F.3d at 136; see also Dilts, 769 F.3d at 646 (describing a\\nstate employment law as a “background regulation[]”). The\\ntest also does not regulate carrier-customer interactions or\\nother product outputs. Rather, it only concerns employer-\\nworker relationships. Laws governing how an employer pays\\nits workers do not “directly regulate[] how [a carrier’s] service\\nis performed[;]” they merely dictate how a carrier “behaves as\\nan employer[.]” DiFiore, 646 F.3d at 88. As a result, the test\\nis “steps removed” from regulating customer-carrier\\ninteractions through prices, routes, or services. Costello, 810\\nF.3d 1054 (quoting Dilts, 769 F.3d at 646).\\n\\n The New Jersey ABC classification test does not have a\\nsignificant effect on prices, routes, or services either. The test\\ndoes not bind AEX to a particular method of providing services\\nand thus it is unlike the preempted Massachusetts law at issue\\nin Schwann, 813 F.3d 429. The Massachusetts statute does not\\ninclude New Jersey’s alternative method for reaching\\nindependent contractor status—that is, by demonstrating that\\nthe worker provides services outside of the putative employer’s\\n“places of business.” N.J. Stat. Ann. § 43:21-19(i)(6)(B).\\nThus, if the other prongs of the New Jersey classification test\\nare met, the test allows an employer to classify a worker as an\\nindependent contractor if it shows that the worker either\\nprovides a service that is “outside the [employer’s] usual\\ncourse of business . . . or [performs such service] outside of all\\n\\n\\n\\n\\n 21\\n\\fthe places of business of [the employer].” Id.7 No part of the\\nNew Jersey test categorically prevents carriers from using\\nindependent contractors. As a result, the state law at issue here\\ndoes not mandate a particular course of action—e.g., requiring\\ncarriers to use employees rather than independent\\ncontractors—and it offers carriers various options to comply\\nwith New Jersey employment law.8\\n\\n 7\\n AEX focuses its argument on the B prong of the New\\nJersey test, but also asserts that the A and C prongs of the test\\nare preempted. AEX cites no case holding that prong A or C\\nis preempted under either the FAAAA or the ADA. This is not\\nsurprising given the legion of cases holding that the A and C\\nprongs are not FAAAA-preempted. See, e.g., Vargas v. Spirit\\nDelivery & Distrib. Servs., Inc., 245 F. Supp. 3d 268, 281-84\\n(D. Mass. 2017); DaSilva v. Border Transfer of Mass., Inc.,\\n227 F. Supp. 3d 154, 159-60 (D. Mass. 2017); Portillo v. Nat’l\\nFreight, Inc., Civ. No. 15-7908, 2016 WL 5402215, at *5-6\\n(D.N.J. Sept. 26, 2016); Chambers v. RDI Logistics, Inc., 65\\nN.E.3d 1, 11-12 (Mass. 2016). AEX also provides no reason\\nwhy these prongs are preempted and in fact does not\\nindividually analyze them. Thus, AEX has failed to carry its\\nburden to demonstrate that the affirmative defense of FAAAA\\npreemption applies to these prongs.\\n 8\\n AEX makes much of the fact that the Costello and\\nLupian courts observed that certain aspects of the IWPCA\\nclassification provision could be contracted around (i.e.,\\nemployees could enter into contracts with carriers to allow\\ncertain paycheck deductions), Lupian, 905 F.3d at 135 n.12,\\nwhereas neither the New Jersey test nor the Massachusetts test\\nallows the same contractual avoidance. Contrary to AEX’s\\nargument, this does not make the current case more analogous\\n\\n\\n\\n\\n 22\\n\\f AEX argues that applying the New Jersey law may\\nrequire it to shift its model away from using independent\\ncontractors, which will increase its costs, and in turn, its prices.\\nSpecifically, AEX asserts that if it can no longer use\\nindependent contractors to perform its delivery services, then\\nit will be forced to recruit employees, bring on a human\\nresources department to manage them, acquire and maintain a\\nfleet of vehicles and pay expense reimbursements, provide\\nfringe benefits, plan and dictate delivery routes and timing, and\\npay overtime wages and employment taxes. Our Court and our\\nsister circuits have rejected similar lists of conclusory impacts.\\nLupian, 905 F.3d at 135-36; Costello, 810 F.3d at 1056;\\nMendonca, 152 F.3d at 1189. Though AEX correctly states\\nthat it need not proffer empirical evidence to support its\\nassertions of significant impact at the pleading stage, see, e.g.,\\nCostello, 810 F.3d at 1055 (citing Rowe, 552 U.S. at 373-74),\\n\\n\\nto Schwann than to Costello and Lupian. Though Costello and\\nLupian correctly took the IWPCA contractual loophole into\\naccount, neither court relied on it. See Lupian, 905 F.3d at 136\\nn.12 (observing that the Costello court “noted” the contractual\\nallowance in the IWPCA); Costello, 810 F.3d at 1057 (noting\\nin a single sentence that the IWPCA’s prohibition on\\ndeductions from wages can be contracted around, ultimately\\nholding that the IWPCA is not “related to a price, route, or\\nservice of any motor carrier”). Moreover, while a contractual\\ncircumvention option may provide another route for\\ncompliance, weighing against FAAAA preemption, it is not the\\nonly way a state statute can afford carriers some flexibility.\\nHere, the New Jersey ABC classification test gives carriers\\noptions; it does not need to provide a contractual workaround\\nto avoid preemption.\\n\\n\\n\\n\\n 23\\n\\fit does not provide even a logical connection between the\\napplication of New Jersey’s ABC classification test and the list\\nof new costs it would purportedly incur.9\\n\\n AEX’s argument that it may be subject to other legal\\nrequirements arising from reclassification, citing only the\\nAffordable Care Act,10 is equally unavailing. In the words of\\nthe Costello court, “[c]onspicuously absent from [the\\ncompany’s] parade of horrors is any citation of authority\\nshowing that it would be required to comply with [other]\\nfederal and state laws.” Id. at 1056. Instead, AEX “rel[ies] on\\nconclusory allegations that compliance with the [NJWHL and\\nNJWPL] will require [AEX] to switch its entire business model\\n. . . [but w]e see no basis for concluding that [New Jersey law]\\nwould require that change given that the federal employment\\nlaws and other state labor laws [may] have different tests” for\\ndetermining whether someone is an employee under a specific\\nstatute. Id. (citations omitted).\\n\\n Furthermore, while “[w]e have no doubt that the\\ndisruption of a labor model—especially after services have\\nbeen performed—could have negative financial and other\\nconsequences for an employer,” Lupian, 905 F.3d at 136, this\\nimpact on the employer does not equate to a significant impact\\non Congress’ goal of deregulation. Congress sought to ensure\\n\\n 9\\n For instance, we cannot see, nor has AEX explained,\\nhow reclassification of employees would necessarily require\\nAEX to acquire a new fleet of vehicles or create a human\\nresources department.\\n 10\\n Patient Protection and Affordable Care Act of 2010,\\nPub. L. No. 111-148, 124 Stat. 119 (2010).\\n\\n\\n\\n\\n 24\\n\\fmarket forces determined prices, routes, and services. Nothing\\nin that goal, however, meant to exempt workers from receiving\\nproper wages, even if the wage laws had an incidental impact\\non carrier prices, routes, or services.11\\n\\n Finally, the fact that New Jersey’s ABC classification\\ntest differs from the federal test used in the Fair Labor\\nStandards Act of 1938, 29 U.S.C. §§ 201-19, will not result in\\na “‘patchwork’ of unique state legislation, which [AEX\\ncontends] regulates differently from state to state how motor\\ncarriers are required to perform their delivery services.” Reply\\nBr. at 14. Most notably, New Jersey’s test is similar to that\\nused in many other states. See, e.g., RDI Logistics, 65 N.E.3d\\nat 11-12 (holding that prongs A and C of the Massachusetts\\ntest, which are identical to those in the New Jersey test, were\\nnot FAAAA-preempted because they did not present a\\n“patchwork problem” as they were “more or less nationally\\nuniform,” unlike the Massachusetts B prong, which was\\npreempted in Schwann because it was anomalous (quoting\\nSchwann, 813 F.3d at 440)).\\n\\n\\n\\n\\n 11\\n Indeed, Congress evinced its intent for the FAAAA\\nnot to preempt general state wage laws when it included New\\nJersey—where, at the time the FAAAA was enacted, the\\nNJWHL and NJWPL were already in effect, N.J. Stat. Ann. §§\\n34:11-56a7 & 34:11-4.1 (indicating initial enactment in 1966\\nand 1965, respectively)—in its list of jurisdictions with laws\\nthat did not run afoul of the FAAAA. H.R. Conf. Rep. No.\\n103-677, at 86 (1994); see also Mendonca, 152 F.3d at 1187-\\n88 & n.3.\\n\\n\\n\\n\\n 25\\n\\f Thus, AEX has not shown that New Jersey’s ABC\\nclassification test has a “significant impact” on Congress’\\nderegulatory efforts with respect to motor carrier businesses,\\nnor are the NJWHL and NJWPL—typical state wage and hour\\nlaws—the kinds of preexisting state regulations with which\\nCongress was concerned when it passed the FAAAA.12 See\\nLupian, 905 F.3d at 135-36; Schwann, 813 F.3d at 438;\\nCostello, 810 F.3d at 1050-51; Amerijet, 627 F. App’x at 751;\\nDilts, 769 F.3d at 647-48; Gary, 397 F.3d at 189-90;\\nMendonca, 152 F.3d at 1187-89. Notably, eight of the ten\\njurisdictions that Congress identified as not regulating\\nintrastate prices, routes, and services “had laws for\\ndifferentiating between an employee and an independent\\ncontractor,” Su, 903 F.3d at 967, and at least three codified\\nABC tests similar to that of New Jersey, see Alaska Stat. §\\n23.20.525(a)(10) (1992); Del. Code Ann. tit. 19, § 3302(9)(k)\\n(1992); Vt. Stat. Ann. tit. 21, § 1301(6)(B) (1992). Therefore,\\nAEX’s patchwork argument fails.\\n\\n Accordingly, any effect the New Jersey ABC\\nclassification test has on prices, routes, or services with respect\\nto the transportation of property is tenuous and insignificant.\\nSee Lupian, 905 F.3d at 136. As a result, the test is not\\npreempted.\\n\\n\\n\\n\\n 12\\n As the Schwann court observed, while Congress\\nsought “to avoid ‘a patchwork of state service-determining\\nlaws,’” we can assume that “Congress intended to leave\\nuntouched” “pre-existing and customary manifestation[s] of\\nthe state’s police power.” 813 F.3d at 438 (quoting Rowe, 552\\nU.S. at 373).\\n\\n\\n\\n\\n 26\\n\\f III\\n\\n For the foregoing reasons, we will affirm the District\\nCourt’s order denying AEX’s motion for judgment on the\\npleadings and remand for further proceedings.\\n\\n\\n\\n\\n 27\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":79,"cells":{"id":{"kind":"number","value":4585444,"string":"4,585,444"},"name":{"kind":"string","value":"*The ESTATE OF Adriano ROMAN, Jr., Appellant v. CITY OF NEWARK; City of Newark Police Department; Anthony Campos, Chief of Police; Rodger C. Mendes; Albano Ferreira ; Onofre H. Cabezas; Joseph Cueto; FNU Ressureicao; FNU Golpe; Joyce Hill, Individually and in Their Capacity as Police Officers; John Does 1-20, as Fictitious Names for Presently Unknown Agents Member Commissioners and Chiefs *(Amended Pursuant to Clerk's Order Dated 1/25/2018)"},"name_abbreviation":{"kind":"string","value":"Estate of Adriano Roman, Jr. v. City of Newark"},"decision_date":{"kind":"string","value":"2019-01-29"},"docket_number":{"kind":"string","value":"17-2302"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Jordan, Hardiman\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9887936/\", \"author_raw\": \"\"}, {\"author\": \"\", \"type\": \"030concurrence\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9887937/\", \"author_raw\": \"\"}, {\"author\": \"\", \"type\": \"035concurrenceinpart\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9887938/\", \"author_raw\": \"\"}, {\"author\": \"AMBRO, Circuit Judge\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n ________________\\n No. 17-2302\\n ________________\\n\\n *THE ESTATE OF ADRIANO ROMAN, JR.,\\n Appellant\\n\\n v.\\n\\n CITY OF NEWARK;\\n CITY OF NEWARK POLICE DEPARTMENT;\\n ANTHONY CAMPOS, Chief of Police;\\n RODGER C. MENDES;\\n ALBANO FERREIRA; ONOFRE H. CABEZAS;\\n JOSEPH CUETO;\\n FNU RESSUREICAO; FNU GOLPE; JOYCE HILL,\\n Individually and in their capacity as police officers;\\nJOHN DOES 1-20, as fictitious names for presently unknown\\n agents member commissioners and chiefs\\n\\n *(Amended pursuant to Clerk’s Order dated 1/25/18)\\n ________________\\n Appeal from the United States District Court\\n for the District of New Jersey\\n (D.C. Civil Action No. 2-16-cv-01110)\\n District Judge: Honorable Susan D. Wigenton\\n ________________\\n\\n Argued June 12, 2018\\n\\n Before: AMBRO, JORDAN, and\\n HARDIMAN, Circuit Judges\\n\\n (Opinion filed: January 29, 2019)\\n\\nJustin D. Santagata (Argued)\\nKaufman Semeraro & Leibman\\nTwo Executive Drive, Suite 530\\nFort Lee, NJ 07024\\n\\n Counsel for Appellant\\n\\nKenyatta K. Stewart, Acting Corporation Counsel\\nWilson D. Antoine (Argued)\\nCity of Newark–Department of Law\\n920 Broad Street, Room 316\\nNewark, NJ 07102\\n\\n Counsel for Appellees\\n\\n ________________\\n OPINION OF THE COURT\\n ________________\\n\\nAMBRO, Circuit Judge\\n\\n Newark police officers forcibly entered and searched\\nthe apartment of Adriano Roman’s girlfriend. App. at 386,\\n391, 459, 486. They arrested Roman, who was present in the\\napartment, after they found drugs in a common area that was\\nshared by multiple tenants. Id. at 399, 479. Though he was\\nimprisoned for over six months and indicted for various drug\\n\\n\\n\\n\\n 2\\n\\noffenses, the New Jersey Superior Court found the search to\\nbe unlawful and the charges were dropped.\\n\\n Roman now brings claims against the City of Newark\\n(which includes its Police Department) and various police\\nofficers under 42 U.S.C. § 1983 (which gives a federal\\nremedy against state officials who, acting under color of state\\nlaw, deprive “any citizen of the United States . . . of any\\nrights, privileges, or immunities secured by the [U.S.]\\nConstitution and laws”) and New Jersey tort law. He alleges\\nthe City had a pattern or practice of constitutional violations\\nand failed to train, supervise, and discipline its officers. He\\nalso pleads an unlawful search claim against the officers and\\ncontends they are liable for false imprisonment and malicious\\nprosecution. The District Court dismissed all of the claims\\nbecause they were inadequately pled. It also held the City did\\nnot have an ongoing practice of unconstitutional searches and\\narrests.\\n While most of Roman’s claims do not withstand\\ndismissal, his § 1983 claims against the City do. He has\\nadequately alleged that its Police Department had a custom of\\nwarrantless searches and false arrests. He also sufficiently\\npled that the Department failed to train, supervise, and\\ndiscipline its officers, specifically with respect to “the\\nrequirements of [the] Fourth Amendment and related law.”\\nApp. at 160. Because Roman has stated a plausible claim\\nagainst the City, we vacate and remand the District Court’s\\nholding on municipal liability. We affirm in all other\\nrespects.\\n\\n\\n\\n\\n 3\\n\\nI. Background1\\n On May 2, 2014, Roman and his girlfriend Tiffany\\nReyes were watching a movie in her apartment’s bedroom.\\nApp. at 386, 389, 395. Unbeknownst to them, four Newark\\npolice officers had set up surveillance outside of her building\\nbecause of complaints about narcotics activity. Id. at 338.\\nThe officers heard an argument between a man and a woman,\\nid. at 340-42, and decided to enter Reyes’ apartment without\\na warrant, id. at 491.\\n After they stepped inside the building, they discovered\\nthat the front door of the apartment was locked. They also\\n\\n 1\\n As noted below, we must, while reviewing a ruling\\non a motion to dismiss, view the facts in the light most\\nfavorable to the plaintiff. Accordingly, without judging the\\nfacts, we recount them as set out in the amended complaint\\nand the transcript of the suppression hearing referred to\\nbelow. Although Roman did not attach the transcript to the\\namended complaint, the Defendants included it in their\\nmotion to dismiss and told the District Court it was “capable\\nof judicial notice” and “integral to the [c]omplaint.” App. at\\n130. Thus we consider it at this stage.\\n\\n In any event, both the amended complaint and\\ntranscript note that the officers forcibly entered the apartment,\\nassaulted Roman, and falsely charged him with possession of\\na controlled substance. See Am. Compl. ¶¶ 17, 22, 28. Any\\nminor differences in the two documents do not affect our\\nanalysis of his municipal liability claim. See infra Section\\nIII.A (explaining that the events leading up to Roman’s\\nsearch and arrest are not relevant to the merits of his\\nmunicipal liability claim).\\n\\n\\n\\n\\n 4\\n\\nnoticed Melissa Isaksem, Reyes’ friend, walking inside the\\nbuilding. Id. at 417-20. They stopped and questioned her.\\nId. at 417, 419. When she told them she was visiting Reyes,\\nid. at 419, they ordered her to knock on the apartment door\\nfor them and threatened to arrest her if she did not comply, id.\\nat 419-20. Isaksem led them to the apartment and stood\\ndirectly in front of the peephole. Id. at 421. The police stood\\nto her left, presumably out of the peephole’s range. Id. An\\nofficer knocked on her behalf. Id. Reyes asked who was at\\nthe door, and Isaksem announced her presence. Id.\\n Reyes opened the door, expecting to see only Isaksem.\\nId. at 386, 400, 501. Instead, several officers rushed inside.\\nId. at 387, 400, 501. They handcuffed Roman, Reyes, and\\nIsaksem, then demanded Roman “call someone to bring drugs\\nto the [apartment].” Am. Compl. ¶ 30 (internal quotation\\nmarks omitted). If he did, they assured him they would\\n“‘make a deal’ and ‘let him go.’” Id. Roman refused the\\nofficers’ demands, id. ¶ 33, and the police searched the\\napartment. Eventually they found drugs in a common-area\\nspace that was shared by multiple tenants and located in the\\nback of the apartment. App. at 399, 479. After seizing the\\ncontraband, they yelled, “[W]e got you, motherfucker[;] . . .\\nyou’re fucked now.” Id. at 427. Officer Rodger Mendes\\nwalked back to Roman, “flipped him . . . on[]to his stomach\\n. . . , put his knee in his neck[,] and . . . said he was going to\\nget raped [in prison].” Id. at 428. Another officer informed\\nRoman’s father, who lived next door and observed parts of\\nthe search, that his son “would go away for a long time.” Id.\\nat 454.\\n Roman was arrested and imprisoned on the same night.\\nThe officers filed a criminal complaint against him for\\npossession of, as well as intent to distribute, heroin and\\ncocaine. A New Jersey grand jury returned a six-count\\nindictment against him for the same offenses.\\n\\n\\n\\n\\n 5\\n\\n In response, Roman moved to suppress the evidence\\nseized from the apartment. He argued the search was invalid\\nunder the Fourth Amendment because the contraband was not\\nin plain view and thus a warrant was needed. The New Jersey\\nSuperior Court agreed. It concluded the plain-view exception\\ndid not apply and suppressed the contraband.\\n The State of New Jersey did not appeal the ruling and\\ninstead moved to dismiss the case. The Superior Court\\ngranted its motion in December 2014 and issued a final\\njudgment of dismissal. Roman was released from prison\\nduring the same month.\\n Approximately a year later, Roman brought § 1983\\nand state-law tort claims against the City of Newark and\\nvarious police officers (for simplicity, the City and the\\nofficers are jointly referred to as the “Defendants”). Among\\nother things, he alleged the City had a custom or policy of\\nunconstitutional searches, inadequate training, and poor\\nsupervision and discipline.2 He also claimed the officers\\nunlawfully searched his apartment and were liable for the\\ntorts of unlawful imprisonment and malicious prosecution.3\\n\\n\\n 2\\n Roman’s amended complaint also included\\nallegations of discrimination of national origin in violation of\\n42 U.S.C. § 1983, civil conspiracy in violation of 42 U.S.C.\\n§ 1985, conspiracy to commit an unlawful search in violation\\nof the New Jersey Constitution and 42 U.S.C. § 1985, and\\nconspiracy to commit unlawful imprisonment in violation of\\n42 U.S.C. § 1985. We do not address these claims, as Roman\\ndoes not press them on appeal.\\n 3\\n We construe Roman’s claim for unlawful\\nimprisonment as a claim for false imprisonment. Although\\n\\n\\n\\n\\n 6\\n\\n The Defendants responded with a motion to dismiss.\\nThe District Court sided with them, dismissing the complaint\\nin its entirety. It first addressed Roman’s claim against the\\nCity and concluded the complaint “fail[ed] to plead . . . a\\ncustom or policy” of unlawful searches and a failure to train\\nor supervise officers. Roman v. City of Newark, Civil Action\\nNo. 16-1110-SDW-LDW, 2017 WL 436251, at *4 (D.N.J.\\nJan. 30, 2017). Although the complaint alleged “a pattern or\\npractice of constitutional violations in areas including stop[]\\nand arrest practices, use of force, and theft by officers,” the\\nCourt did not consider that sufficient to state a claim. Id.\\n(internal quotation marks omitted) (quoting Compl. ¶ 59).\\nInstead, it viewed those practices as predating Roman’s arrest\\nand observed that “the imposition of a [f]ederal [m]onitor\\nindicate[d] [the City’s] attempts to change any wrongful\\npolicies or practices.” Id.\\n The Court also held the unlawful search claim was\\ninadequately pled, as Roman did not “explain which\\n[Defendant(s)] committed the allegedly wrongful acts” during\\nthe search and arrest. Id. Turning to the false imprisonment\\nand malicious prosecution claims, it construed them as state-\\nlaw claims and noted that plaintiffs must comply with the\\n\\nNew Jersey lacks a cause of action for “unlawful\\nimprisonment,” it has codified the elements of a false\\nimprisonment claim. See N.J. Stat. Ann. § 2C:13-3; Mallery\\nv. Erie R. Co., 92 A. 371, 371 (N.J. 1914) (“This appeal\\nbrings up a judgment recovered by the respondent in an\\naction for false imprisonment. The declaration described\\nthe unlawful imprisonment. . . .”); see also 8 American Law\\nof Torts § 27:1 (“False imprisonment, sometimes called\\ncriminal restraint or unlawful imprisonment, is committed\\nwhen a defendant so restrains another person as to interfere\\nsubstantially with his liberty.”).\\n\\n\\n\\n\\n 7\\n\\nNew Jersey Tort Claims Act before bringing them against\\npublic entities. See N.J. Stat. Ann. § 59:8-1 et seq. Because\\nthe “[c]omplaint nowhere allege[d]” Roman complied with\\nthe Act’s procedures, the Court dismissed those claims as\\nwell. Roman, 2017 WL 436251, at *6.\\n\\n The Court’s dismissal was without prejudice, and it\\ngranted Roman leave to amend. He did so by omitting his\\ntort claims and retaining his other allegations in almost\\nidentical form. The Court dismissed his amended complaint\\nand reaffirmed its ruling on reconsideration. This appeal\\nfollowed.4\\nII. Jurisdiction and Standard of Review\\n The District Court had federal-question and\\nsupplemental jurisdiction per 28 U.S.C. §§ 1331 and 1367(a),\\nrespectively, and we have jurisdiction over its final orders\\nunder 28 U.S.C. § 1291.\\n We review de novo its dismissal of a complaint under\\nFederal Rule of Civil Procedure 12(b)(6). See Phillips v.\\nCounty of Allegheny, 515 F.3d 224, 230 (3d Cir. 2008).\\nWhen conducting our review, “we accept all factual\\nallegations as true [and] construe the complaint in the light\\nmost favorable to the plaintiff.” Warren Gen. Hosp. v.\\nAmgen Inc., 643 F.3d 77, 84 (3d Cir. 2011) (internal\\nquotation marks omitted). However, “we are not compelled\\nto accept unsupported conclusions and unwarranted\\ninferences . . . or a legal conclusion couched as a factual\\nallegation[.]” Baraka v. McGreevey, 481 F.3d 187, 195 (3d\\n\\n\\n 4\\n Roman passed away while this appeal was pending,\\nand his estate brings the claims on his behalf. We do not\\ndistinguish between Roman and his estate in this opinion.\\n\\n\\n\\n\\n 8\\n\\nCir. 2007) (internal quotation marks omitted) (internal\\ncitation omitted).\\n\\nIII. Discussion\\n A. Roman sufficiently pled a municipal liability\\n claim against Newark.\\n\\n As noted, Roman alleges the City is liable under\\n§ 1983 because it “engaged in a pattern or practice of\\nconstitutional violations,” “failed to properly train and/or\\nsupervise” its police force, and “failed to properly and\\nadequately control and discipline” its police officers.5 Am.\\nCompl. ¶¶ 68, 73-74. Before discussing the merits of his\\nclaims, Roman directs our attention to the types of documents\\nwe may consider on a motion to dismiss. He contends we\\nmay review three sources that were provided to the District\\nCourt: an article published in the Newark Star Ledger (the\\n“Star Ledger article”), a press release issued by the U.S.\\nAttorney’s Office (the “press release”), and a consent decree\\nbetween the United States and the City of Newark (the\\n“consent decree”). The Star Ledger article and press release\\nwere referenced in the amended complaint, see id. ¶¶ 68-69\\n(including hyperlinks to both), but the consent decree was\\nattached to the Defendants’ motion to dismiss, see App. at\\n129. Roman also asks us to look at one other document: the\\nDepartment of Justice’s Report on the investigation of the\\nNewark Police Department (the “DOJ Report”). Although he\\n\\n 5\\n Roman brings his municipal liability claims under\\n§ 1983 and the New Jersey Civil Rights Act, N.J. Stat. Ann.\\n§ 10:6-1 et seq. Because the latter “is interpreted analogously\\nto . . . § 1983,” we consider his New Jersey Civil Rights Act\\nclaims along with his § 1983 claim. Coles v. Carlini, 162 F.\\nSupp. 3d 380, 404 (D.N.J. 2015).\\n\\n\\n\\n\\n 9\\n\\nacknowledges the DOJ Report was never provided to the\\nDistrict Court, he now claims it is integral to the pleadings.\\n\\n Though the Defendants dispute that we may consider\\nthe DOJ Report, they add that we also cannot consider the\\nconsent decree because “no relevant provisions of [it] . . .\\nwere ever cited . . . to the District Court” and it is\\ninadmissible settlement material. Defendants’ Br. at 42.\\nThey assert as well, without any citation to the record, that\\nRoman may not rely on the decree because he asked the\\nDistrict Court to confine its analysis to the pleadings.\\n We disagree with the Defendants’ view of the consent\\ndecree. Although we examine the “complaint, exhibits\\nattached to the complaint, [and] matters of public record,”\\nMayer v. Belichick, 605 F.3d 223, 230 (3d Cir. 2010), we can\\nalso consider documents “that a defendant attaches as an\\nexhibit to a motion to dismiss,” Pension Benefits Guar. Corp.\\nv. White Consol. Indus., Inc., 998 F.2d 1192, 1196 (3d Cir.\\n1993), if they are “undisputedly authentic” and “the\\n[plaintiff’s] claims are based [on them],” Mayer, 605 F.3d at\\n230. That holding extends to settlement material because\\nplaintiffs “need not provide admissible proof at th[e] [motion-\\nto-dismiss] stage.” In re OSG Sec. Litig., 12 F. Supp. 3d 619,\\n622 (S.D.N.Y. 2014); see also In re MyFord Touch Consumer\\nLitig., 46 F. Supp. 3d 936, 961 n.5 (N.D. Cal. 2014) (same).\\nMoreover, the Supreme Court has been clear about the scope\\nof our review, stating we “must consider the complaint in its\\nentirety, as well as other sources [we] ordinarily examine\\nwhen ruling on . . . motions to dismiss, in particular,\\ndocuments incorporated into the complaint by reference, and\\nmatters of which a court may take judicial notice.” Tellabs,\\nInc. v. Makor Issues & Rights, Ltd., 551 U.S. 308, 322 (2007)\\n(emphasis added).\\n\\n\\n\\n\\n 10\\n\\n Here, although the consent decree was not attached to\\nRoman’s amended complaint, we are free to review its\\ncontents for three reasons.6 First, the Defendants attached the\\ndecree to their motion to dismiss and affirmed that it is\\n“capable of judicial notice” as an indisputably authentic\\ngovernment document. App. at 129. Second, contrary to the\\ndissent’s assertion, the Defendants themselves argued (and\\ncorrectly) before the District Court that Roman’s claims were\\nbased on the consent decree. Compare Dissenting Op. at 5\\n(“What is crucial is whether Roman’s complaint was ‘based’\\non the consent decree.”), with App. at 129 (filing from\\nDefendants characterizing the consent decree as “integral to\\nthe Complaint”). Third, the amended complaint cited, and the\\nDistrict Court discussed, the DOJ investigation and federal\\nmonitor that eventually led to the consent decree. See\\nRoman, 2017 WL 436251, at *4; see also Am. Compl. ¶¶ 68-\\n71. Thus it was especially important for the Court to have\\nconsidered the decree as well, given that it provides essential\\ncontext to Roman’s claims. That it did not was an abuse of\\ndiscretion.\\n\\n That said, we may not consider the DOJ Report at this\\nstage because it was not provided to the District Court in the\\nfirst instance by any party. Nor is it apparent that the Court\\nconsidered it sua sponte. See United States ex rel. Wilkins v.\\n\\n 6\\n Though the Defendants and our dissenting colleague\\ndo not challenge the Star Ledger article or the press release,\\nwe note that we consider them because they are referenced in\\nthe amended complaint. See Tellabs, 551 U.S. at 322. As\\nJudge Jordan explains in his concurrence, however, Roman\\ndoes not need either document or the suppression hearing\\ntranscript to state a municipal liability claim; the consent\\ndecree gives his allegations enough plausibility to survive\\ndismissal.\\n\\n\\n\\n\\n 11\\n\\nUnited Health Grp., Inc., 659 F.3d 295, 302 (3d Cir. 2011)\\n(“Though we do not doubt the authenticity of\\nthese documents, nevertheless we will not consider them\\nbecause the parties did not present them to the District Court\\nand we do not find any indication in the record that the Court\\nconsidered them on its own initiative.”). Hence it cannot\\ncarry any weight in our analysis.\\n Turning to the amended complaint, Roman claims the\\nCity is liable for his unlawful search because it “failed to train\\nits officers in the use of search and seizure techniques,\\nprobable cause, and/or methods to properly obtain a search\\nwarrant.” Am. Compl. ¶ 95. He alleges the Newark Police\\nDepartment “engaged in a pattern or practice of constitutional\\nviolations” and asserts the Department of Justice appointed a\\nfederal monitor to oversee the reforms to which the City\\nconsented. Id. ¶ 68. His allegations also touch on the City’s\\nfailure to “control and discipline” its police force, id. ¶ 74,\\nand failure to “investigate . . . instances of . . . police\\nmisconduct,” id. ¶ 81. He characterizes the City’s practices in\\nthese areas as “tantamount to a[n] [unconstitutional] custom\\nand/or policy,” id. ¶ 82, thus indicating its “deliberate\\nindifference to [its citizens’ constitutional] rights,” id. ¶ 83.\\n The Defendants respond that Roman has failed to\\nallege a municipal liability claim, as no part of the Star\\nLedger article, press release, or consent decree references the\\ntypes of constitutional violations pled in the amended\\ncomplaint. They also contend the City had no notice “of any\\npattern of constitutional violations with respect to forced\\nentry and searches of homes.” Defendants’ Br. at 50.\\n To plead a municipal liability claim, a plaintiff must\\nallege that “a [local] government’s policy or custom . . .\\ninflict[ed] the injury” in question. Monell v. Dep’t of Soc.\\nServs., 436 U.S. 658, 694 (1978). “Policy is made when a\\n\\n\\n\\n\\n 12\\n\\ndecisionmaker possess[ing] final authority to establish\\nmunicipal policy with respect to the action issues an official\\nproclamation, policy, or edict.” Andrews v. City of\\nPhiladelphia, 895 F.2d 1469, 1480 (3d Cir. 1990) (alteration\\nin original) (internal quotation marks omitted). “Custom, on\\nthe other hand, can be proven by showing that a given course\\nof conduct, although not specifically endorsed or authorized\\nby law, is so well-settled and permanent as virtually to\\nconstitute law.” Bielevicz v. Dubinon, 915 F.2d 845, 850 (3d\\nCir. 1990) (Becker, J.); see also Brown v. Muhlenberg Twp.,\\n269 F.3d 205, 215 (3d Cir. 2001) (“A custom . . . must have\\nthe force of law by virtue of the persistent practices of state\\n[or municipal] officials.” (internal quotation marks omitted)).\\n Although a policy or custom is necessary to plead a\\nmunicipal claim, it is not sufficient to survive a motion to\\ndismiss. A plaintiff must also allege that the policy or custom\\nwas the “proximate cause” of his injuries. See Kneipp v.\\nTedder, 95 F.3d 1199, 1213 (3d Cir. 1996). He may do so by\\ndemonstrating an “affirmative link” between the policy or\\ncustom and the particular constitutional violation he alleges.\\nBielevicz, 915 F.2d at 850 (internal quotation marks omitted).\\nThis is done for a custom if Roman demonstrates that Newark\\nhad knowledge of “similar unlawful conduct in the past, . . .\\nfailed to take precautions against future violations, and that\\n[its] failure, at least in part, led to [his] injury.” Id. at 851.\\nDespite these requirements, Roman does not need to identify\\na responsible decisionmaker in his pleadings. See id. at 850.\\nNor is he required to prove that the custom had the City’s\\nformal approval. See Anela v. City of Wildwood, 790 F.2d\\n1063, 1067 (3d Cir. 1986).\\n The pleading requirements are different for failure-to-\\ntrain claims because a plaintiff need not allege an\\nunconstitutional policy. See Reitz v. County of Bucks, 125\\nF.3d 139, 145 (3d Cir. 1997) (“[I]n the absence of an\\n\\n\\n\\n\\n 13\\n\\nunconstitutional policy, a municipality’s failure to properly\\ntrain its employees and officers can create an actionable\\nviolation . . . under § 1983.”). Instead, he must demonstrate\\nthat a city’s failure to train its employees “reflects a deliberate\\nor conscious choice.” Brown, 269 F.3d at 215 (internal\\nquotation marks omitted). For claims involving police\\nofficers, the Supreme Court has held that the failure to train\\n“serve[s] as [a] basis for § 1983 liability only where [it] . . .\\namounts to deliberate indifference to the rights of persons\\nwith whom the police come into contact.” City of Canton v.\\nHarris, 489 U.S. 378, 388 (1989) (footnote omitted). A\\nplaintiff sufficiently pleads deliberate indifference by\\nshowing that “(1) municipal policymakers know that\\nemployees will confront a particular situation[,] (2) the\\nsituation involves a difficult choice or a history of employees\\nmishandling[,] and (3) the wrong choice by an employee will\\nfrequently cause deprivation of constitutional rights.” Doe v.\\nLuzerne County, 660 F.3d 169, 180 (3d Cir. 2011) (internal\\nquotation marks omitted) (quoting Carter v. City of\\nPhiladelphia, 181 F.3d 339, 357 (3d Cir. 1999)).\\n\\n In view of this case law, Roman has not pled a\\nmunicipal policy, as his amended complaint fails to refer to\\n“an official proclamation, policy, or [an] edict.” Andrews,\\n895 F.2d at 1480. However, he has sufficiently alleged a\\ncustom of warrantless or nonconsensual searches. He has\\nalso adequately pled that the City failed to train, supervise,\\nand discipline its police officers.7\\n\\n\\n 7\\n We consider allegations of failure to train, supervise,\\nand discipline together because they fall under the same\\nspecies of municipal liability. See Rosalie Berger Levinson,\\nWho Will Supervise the Supervisors? Establishing Liability\\nfor Failure to Train, Supervise, or Discipline in a Post-\\n\\n\\n\\n\\n 14\\n\\n We start with Roman’s allegations on municipal\\ncustom. He asserts the City had “a pattern or practice of\\nconstitutional violations in areas including . . . arrest\\npractices.” App. at 137. He further contends it had notice of\\nthis practice, as it received “complaints against officers\\naccused of . . . conducting improper searches and false\\narrests.” Id. at 134. The amended complaint, along with the\\npress release and Star Ledger article, note that Newark was\\nunder the supervision of a federal monitor after Roman’s\\narrest. Am. Compl. ¶ 68; App. at 133, 137. According to the\\npress release, the monitor would oversee reforms in several\\nareas, including searches, arrests, and the intake and\\ninvestigation of misconduct complaints. App. at 137.\\n The consent decree echoes these points. It covers the\\nsame type of conduct Roman alleges, as it “prohibit[s]\\nofficers from relying on information known to be materially\\nfalse or incorrect to justify a warrantless search . . . [or to]\\neffect[] an arrest.” Id. at 158; see also id. at 163 (mandating\\nofficers to collect data on consent, the type of search, and “a\\nbrief description of the facts creating probable cause”). The\\ndecree also requires the Police Department to investigate\\npolice misconduct, see generally id. at 184-92, with special\\nemphasis on allegations of criminal misconduct, false arrest,\\nplanting evidence, and unlawful searches, see id. at 150, 186.\\n While the consent decree was not in place during\\nRoman’s search and arrest, we may fairly infer that the\\nproblems that led to it were occurring during the time of his\\nallegations and for some time before that. See id. at 133-34\\n(noting the investigation that resulted in the consent decree\\nand federal supervision began in May 2011 and ended in July\\n2014). With this mind, the decree fortifies Roman’s\\n\\nIqbal/Connick World, 47 Harv. C.R.-C.L. L. Rev. 273, 280\\n(2012).\\n\\n\\n\\n\\n 15\\n\\nallegations of unlawful custom because it acknowledges “a\\npattern or practice of conduct by the Newark Police\\n[Department] that deprives individuals of rights, privileges,\\nand immunities secured by the Constitution.” Id. at 144.\\nWhen viewed in conjunction with the Star Ledger article, it\\nreferences the types of constitutional violations mentioned in\\nthe amended complaint: warrantless searches, id. at 134, and\\nfalse arrests, id. at 158. These violations were widespread\\nand causally linked to Roman’s alleged injury, as the Police\\nDepartment was aware of them but “rare[ly] . . . acted” on\\ncitizen complaints. Id. at 134 (discussing complaints of\\n“improper searches and false arrests”); see also Beck v. City\\nof Pittsburgh, 89 F.3d 966, 974 (3d Cir. 1996) (noting the\\npolice department’s failure to act on complaints\\n“perpetuate[d] the City’s custom of acquiescing in the\\nexcessive use of force by its police officers”). In light of\\nthese allegations, “it is logical to assume that [the City’s]\\ncontinued official tolerance of repeated misconduct\\nfacilitate[d] similar unlawful actions in the future,” including\\nthe search and arrest of Roman. Bielevicz, 915 F.2d at 851. It\\nfollows that he has adequately pled a municipal custom and\\nproximate causation under § 1983.\\n We reach the same conclusion with respect to\\nRoman’s failure-to-train, failure-to-supervise, and failure-to-\\ndiscipline claims. To start, the Star Ledger article includes a\\nstatement on police training from James Stewart, Jr., the head\\nof Newark’s police union. He conceded the “last training [he]\\nreceived” was in 1995, when he first joined the Newark\\nPolice Department. App. at 134 (internal quotation marks\\nomitted). Moreover, Stewart is not some unreliable, rogue\\nofficer—he is the head of the police union. Nor is his\\nexperience isolated: the consent decree indicates Newark\\npolice officers in general were not trained on “the\\nrequirements of [the] Fourth Amendment and related law.”\\nId. at 160 (discussing various Fourth Amendment doctrines\\n\\n\\n\\n\\n 16\\n\\nthat should be included in police training, including “the\\ndifference[] . . . between voluntary consent and mere\\nacquiescence to police authority”). The consent decree also\\ntouches on supervisory review of unlawful searches and\\narrests, requiring desk lieutenants and unit commanders to\\nreview “searches that appear to be without legal justification”\\nand “arrests that are unsupported by probable cause.” Id. at\\n161. Finally, it provides disciplinary measures for police\\nofficers who engage in “unlawful . . . searches” and “false\\narrests.” Id. at 192. At the pleadings stage, a fair inference is\\nthat the consent decree was necessary because of Department-\\nwide failures, not because one officer was last trained in\\n1995.\\n This is enough to prove municipal liability because the\\nCity “[knew] to a moral certainty” that its officers would need\\nto conduct searches. Harris, 489 U.S. at 390 n.10. Yet in at\\nleast one instance it failed to provide training since 1995, see\\nApp. at 134, and per the decree its training did not cover the\\nbasics of the Fourth Amendment, see id. at 158-61. The City\\nalso did not discipline officers for “sustained allegations of\\nmisconduct,” including “prior violations” and other\\n“aggravating factors.” Id. at 192-93. In view of these\\ndeficiencies, one could reasonably infer that the City’s\\ninaction “reflected [its] ‘deliberate indifference’” to Roman’s\\nFourth Amendment rights. Bd. of Cty. Comm’rs v. Brown,\\n520 U.S. 397, 409 (1997); cf. Harris, 489 U.S. at 390 n.10\\n(“[C]ity policymakers know to a moral certainty that their\\npolice officers will be required to arrest fleeing felons. . . .\\nThus, the need to train officers in the constitutional\\nlimitations on the use of deadly force . . . can be said to be ‘so\\nobvious’ . . . that failure to do so could properly be\\ncharacterized as ‘deliberate indifference’ to constitutional\\nrights.” (internal citation omitted)). One could also infer that\\nthe City’s failure to establish an adequate training program\\ncontributed to the specific constitutional violations alleged in\\n\\n\\n\\n\\n 17\\n\\nthe amended complaint. See Brown, 520 U.S. at 409-10\\n(“The likelihood that the situation will recur and the\\npredictability that an officer lacking specific tools to handle\\nthat situation will violate citizens’ rights . . . may also support\\nan inference of causation.”); cf. A.M. ex rel. J.M.K. v. Luzerne\\nCty. Juvenile Detention Ctr., 372 F.3d 572, 582 (3d Cir.\\n2004) (reversing the District Court’s grant of summary\\njudgment in favor of a municipality because of “unrebutted\\ntestimony” that its juvenile detention center “did not have an\\nadequate training program”).\\n We conclude that the allegations regarding Newark’s\\nfailure to train, supervise, and discipline are strong enough to\\nsurvive a motion to dismiss. See Am. Compl. ¶¶ 63-98.\\nAmong them are: a failure to train officers on obtaining a\\nsearch warrant, id. ¶ 67, and on “issuing truthful investigative\\nreports,” id. ¶ 77; a failure to supervise and manage officers,\\nid. ¶¶ 67-68; and a failure to discipline officers, id. ¶ 74, first\\nby “refus[ing]” to create a well-run Internal Affairs\\nDepartment, id. ¶ 81, and second by “inadequately\\ninvestigating, if investigating at all, citizens’ complaints\\nregarding illegal search and seizure, id. ¶ 84. The result was a\\n“complete lack of accountability” and of “record keeping,” id.\\n¶ 92, leading to a culture in which officers “knew there would\\nbe no professional consequences for their action[s],” id. ¶ 94.\\nAs the amended complaint alleges, it should come as no\\nsurprise that these conditions led to a federal investigation.\\nSee id. ¶ 89.\\n The dissent’s attempt to distinguish the consent decree\\nis unpersuasive. First, it misperceives the decree as\\nconcerning only police interactions with “pedestrians or the\\noccupants of vehicles,” not home searches. Dissenting Op. at\\n7 (“The consent decree says nothing about arrests and\\nsearches without consent that occur at residences . . .”). In\\nfact, one concern of the decree was false arrests, see App. at\\n\\n\\n\\n\\n 18\\n\\n158, which can occur both at home and on the street. And the\\ndecree does concern home searches: it sets parameters\\nofficers must follow before searching “a home based upon\\nconsent.” Id. Although Reyes by no means consented to the\\nsearch here, she willingly opened her apartment door only\\nbecause the police had used her friend Isaksem as a Trojan\\nhorse to gain entry.\\n Second, the dissent believes that the consent decree\\ncannot help Roman’s case because Roman was Hispanic. See\\nDissenting Op. at 7 (“[T]he decree addressed police practices\\nthat disparately impacted the black community. But that\\nracial disparity did not apply to Roman, who was Hispanic.”).\\nTo the contrary, the consent decree includes an entire section\\nentitled “Bias-Free Policing,” see App. at 165-67, that never\\nrestricts itself to bias against the black community. Instead, it\\nprovides that police officers must “operate without bias based\\non any demographic category,” id. at 166 (emphasis added),\\nand specifically forbids officers from discriminating based on\\n“proxies for demographic category” such as “language\\nability,” id. at 167. Plainly, the consent decree was meant to\\nprotect all Newark residents, including Hispanic residents.\\n Further, we find it difficult to square the dissent’s\\nreasoning with the record evidence discussing the City’s\\ntroubling practices around the time of Roman’s search and\\narrest. See, e.g., id. at 134 (stating only one complaint out of\\n261 filed was sustained by department investigators); id. at\\n158 (prohibiting officers from relying on materially false\\ninformation to justify a warrantless search); id. at 160\\n(requiring police officers to be trained on “the requirements\\nof [the] Fourth Amendment and related law”); id. at 161\\n(mandating supervisory review of “searches that appear to be\\nwithout legal justification” and “arrests that are unsupported\\nby probable cause”).\\n\\n\\n\\n\\n 19\\n\\n Unable to distinguish the consent decree outright, the\\ndissent offers two narrow readings of the decree. First, it\\nmaintains that the decree can speak only to the Police\\nDepartment’s obligations going forward rather than shed any\\nlight whatsoever on the “status quo” within the Department\\nbefore federal intervention. See Dissenting Op. at 10 (stating\\nthat the decree does not provide “any detail as to the status\\nquo it addressed”). The dissent concedes that the DOJ\\nprobably did not enter into the consent decree because it was\\nimpressed with Newark’s policing practices and wanted to\\nencourage the City to keep up the good work. Id. At this\\nstage, we must draw not only such obvious inferences, but\\nalso all reasonable ones, in favor of Roman. Thus we agree\\nwith the dissent on the “clear” difference between “agreeing\\nto train more” (the consent decree on its face) and “agreeing\\nthat prior training was constitutionally inadequate” (the way\\nin which the decree supports Roman’s claims). Id. We\\nsimply believe that a reasonable inference bridges the gap in\\nthis case. Indeed, no inference is needed because Roman\\nmade the link explicit in the amended complaint. See Am.\\nCompl. ¶ 89 (stating that the Police Department’s “deliberate\\nindifference to citizens’ rights is what led to the imposition of\\na [f]ederal [m]onitor program . . . .”).\\n\\n Second, the dissent believes that the consent decree’s\\ntraining requirements, from which we can reasonably infer\\ninadequate training before the decree, simply amount to\\n“additional training” in, for instance, the requirements of the\\nFourth Amendment. Dissenting Op. at 10. To the contrary,\\nthe consent decree was meant to take the Newark Police\\nDepartment back to basics: Do not lie on a warrant\\napplication or to justify a warrantless search, App. at 158;\\ninvestigate police activities that appear to have lacked legal\\njustification, id. at 161; and at all times follow the\\nrequirements of the Fourth Amendment, id. at 160.\\n\\n\\n\\n\\n 20\\n\\n The theme of the dissent appears to be that we are\\nrefashioning the amended complaint. It claims we are\\nvacating the District Court’s decision based on facts and\\narguments that were not presented to it. But as discussed\\nabove, we are engaged in de novo review of the adequacy of\\nthe amended complaint in light of documents that were before\\nthe District Court and that informed its allegations. See supra\\npp. 8-10. Additionally, and to repeat, the specific events\\nleading up to Roman’s search and arrest are not relevant to\\nthe merits of his municipal liability claim. Thus we are not\\nvacating the Court’s decision for excluding these facts from\\nits analysis.\\n Rather, our focus is directed to Newark’s practice at\\nthe time of Roman’s search and arrest. The Court had notice\\nof them, as it acknowledged that Roman alleged “a ‘pattern or\\npractice of constitutional violations in areas including stop[]\\nand arrest practices, use of force, and theft by officers.’”\\nRoman, 2017 WL 436251, at *4 (quoting Compl. ¶ 59).\\nNonetheless it dismissed the complaint and amended\\ncomplaint because it viewed the City as attempting to change\\nits practices. Even if the record can be read that way—and\\nwe doubt that8—the District Court’s rationale has the wrong\\n\\n\\n 8\\n The record does not support the Court’s inferences,\\nas it tells us the DOJ’s investigation was not completed until\\nJuly 2014, see App. at 137; the Government did not solicit\\napplications for a federal monitor until February 2015, see id.;\\nand the consent decree was not final until May 2016, see id.\\nat 215. By contrast, Roman was arrested in May 2014 and\\nimprisoned until December of that year. As such, it is\\nplausible that Newark’s practices were ongoing when police\\nofficers searched and arrested him. It is also reasonable to\\ninfer that the City’s corrective measures postdated the arrest.\\n\\n\\n\\n\\n 21\\n\\nfocus. The question is not whether some evidence can be\\nviewed as supporting the City. It is whether, viewing the\\npleadings and properly associated documents in the light most\\nfavorable to Roman, there are claims plausible enough to\\nwithstand a motion to dismiss. We think there is one—the\\nmunicipal liability claim. And the Court did not have to look\\nbeyond the amended complaint and supporting documents to\\nglean these facts.\\n\\n In sum, Roman’s municipal liability claim survives\\ndismissal based on the record that was before the District\\nCourt. Because the Court reached the opposite conclusion,\\nwe part with its holding. Thus we vacate and remand this\\nportion of its decision.\\n B. The District Court correctly dismissed the\\n false imprisonment and malicious\\n prosecution claims because they were not\\n pled under § 1983.\\n\\n Roman alleges the Defendants are also liable for false\\nimprisonment and malicious prosecution. As noted, the\\nDistrict Court construed these claims as state-law claims. It\\ndismissed them because Roman did not comply with the New\\nJersey Tort Claims Act’s procedural requirements for\\nbringing claims against public entities and public employees.\\nSee N.J. Stat. Ann. § 59:8-1 et seq.\\n On appeal, Roman contends the Court erred in\\ndismissing his claims because they were pled under § 1983.\\nThe Defendants counter that both claims were presented as\\n\\n\\n\\nHence we do not consider the City’s corrective measures to\\nbe enough to defeat Roman’s allegations.\\n\\n\\n\\n\\n 22\\n\\nstate-law tort claims. They also point out that Roman omitted\\nthem from his amended complaint.9\\n\\n As a preliminary matter, the Defendants correctly\\nobserve that false imprisonment and malicious prosecution\\nare not in the amended complaint. Hence we must first\\ndecide if Roman has waived his right to challenge their\\ndismissal on appeal. If we conclude that waiver does not\\napply, we then determine if the District Court correctly\\nconstrued them as state-law tort claims.\\n We have not applied a strict rule in favor of waiver in\\nthis context. Instead, we have allowed “plaintiffs to appeal\\ndismissals despite amended pleadings that omit the dismissed\\nclaim[,] provided repleading the particular cause of action\\nwould have been futile.” United States ex rel. Atkinson v. Pa.\\nShipbuilding Co., 473 F.3d 506, 516 (3d Cir. 2007) (emphasis\\nin original) (footnote omitted). “Repleading is futile when\\nthe dismissal was ‘on the merits.’ A dismissal is on the\\nmerits when it is with prejudice or based on some legal\\nbarrier other than want of specificity or particularity.” Id. If\\na court is uncertain, “doubt[] should be resolved against the\\nparty asserting waiver.” Id. at 517 (emphasis in original).\\n\\n 9\\n At oral argument, Roman’s counsel stated the false\\nimprisonment claim was repled in Count 13 of the amended\\ncomplaint even though that count alleges “conspiracy to\\ncommit unlawful imprisonment . . . [in violation of] 42\\nU.S.C. § 1985.” App. at 278 (emphasis added); see Audio\\nRecording of Oral Argument held June 12, 2018 at 11:39 to\\n12:06 (http://www2.ca3.uscourts.gov/oralargument/audio/17-\\n2302TheEstateofAdrianoRomanJrvCityofNewarketal.mp3).\\nWe do not consider this contention, as it was raised for the\\nfirst time at oral argument and thus is waived. See In re\\nGrand Jury, 635 F.3d 101, 105 n.4 (3d Cir. 2011).\\n\\n\\n\\n\\n 23\\n\\n Here the District Court analyzed both claims on legal\\ngrounds. It observed that they were based on the New Jersey\\nTort Claims Act, which allows individuals to bring tort claims\\nagainst public entities and employees after complying with\\ncertain procedural and notice requirements, see Tripo v.\\nRobert Wood Johnson Med. Ctr., 845 F. Supp. 2d 621, 626-\\n27 (D.N.J. 2012) (summarizing the Act’s procedures for suing\\na public entity or employee). It concluded Roman did not\\nfollow these requirements and thus dismissed the claims.\\n Although the Court was guided by procedural\\nconcerns, its dismissal was on the merits. The Tort Claims\\nAct bars claims against public entities and employees if a\\nplaintiff waits more than two years to file a “notice of claim.”\\nSee N.J. Stat. Ann. § 59:8-8(b). The two-year mark is\\nmeasured from the day the claim accrues (i.e., the day on\\nwhich the public entity or employee allegedly harmed the\\nplaintiff). In our case, because Roman’s claims accrued in\\nMay 2014, he had until May 2016 to file a notice of claim.\\nAs the Court noted, however, he did not file any type of\\nnotice during the two-year period. See Roman, 2017 WL\\n436251, at *6 (observing that, as of January 31, 2017, the date\\non which the Court dismissed the complaint, Roman had not\\nfiled a notice). Thus Roman’s procedural error morphed into\\na dismissal on the merits, see N.J. Stat. Ann. § 59:8-8(b)\\n(“The claimant shall be forever barred from recovering\\nagainst a public entity or public employee if . . . [t]wo years\\nhave elapsed since the accrual of the claim.”), and he may\\nappeal the District Court’s decision on his false imprisonment\\nand malicious prosecution claims, see Atkinson, 473 F.3d at\\n516-17.\\n In light of this conclusion, we must focus on the\\npleadings and decide if Roman’s claims are based on § 1983.\\nIf we look to the complaint, it suggests both false\\nimprisonment and malicious prosecution are state-law tort\\n\\n\\n\\n\\n 24\\n\\nclaims. It never identifies them as § 1983 or federal claims.\\nRather, it presents them generically, following a series of\\nother state-law tort claims. See, e.g., App. at 44 (“intentional\\ninfliction of emotional distress”); id. at 46 (“negligent\\ninfliction of emotional distress”); id. at 47 (“assault and\\nbattery”); id. at 49 (“unlawful imprisonment”); id. at 51\\n(“malicious prosecution”). This indicates to us that Roman\\npled both claims as state-law claims, not federal claims.\\nWhile the unlawful (i.e., false) imprisonment claim does note\\nthat the Defendants “restrict[ed] [Roman’s] constitutionally\\nguaranteed rights of liberty and freedom of movement,” it is\\nsilent as to whether it refers to the United States or New\\nJersey Constitution. Compl. ¶ 114. This is too facile to\\nimply the former when but a few identifying words would do.\\nThe default is New Jersey law, which defines false\\nimprisonment as “an[y] unlawful restraint that interferes with\\na victim’s liberty” and requires “[n]o further wrongful\\npurpose” for a prima facie showing. State v. Savage, 799\\nA.2d 477, 494 (N.J. 2009).\\n Accordingly, the District Court correctly construed the\\nfalse imprisonment and malicious prosecution claims as state-\\nlaw tort claims, and we affirm this portion of its holding.10\\n C. The doctrines of res judicata, collateral\\n estoppel, and judicial estoppel do not require\\n us to dismiss Roman’s § 1983 claims.\\n Finally, the Defendants invoke the doctrines of res\\njudicata, collateral estoppel, and judicial estoppel. According\\n\\n\\n 10\\n We also affirm the dismissal of Roman’s unlawful-\\nsearch claims because they were not adequately pled. We do\\nnot opine on whether a plaintiff may allege joint and several\\nliability in connection with an unlawful-search claim.\\n\\n\\n\\n\\n 25\\n\\nto them, each doctrine compels us to dismiss Roman’s § 1983\\nclaims.\\n\\n We start with res judicata. The Defendants contend it\\nbars Roman’s claims because “the criminal matter and the\\nsuppression hearing were based on the exact same facts” as\\nthose alleged in Roman’s pleadings. Defendants’ Br. at 64.\\nIn their view, criminal proceedings are enough to preclude a\\ncivil suit seeking damages under § 1983.\\n\\n We disagree. “A party seeking to invoke res judicata\\nmust establish three elements: (1) a final judgment on the\\nmerits in a prior suit involving (2) the same parties or their\\nprivies and (3) a subsequent suit based on the same cause of\\naction.” Duhaney v. Att’y Gen., 621 F.3d 340, 347 (3d Cir.\\n2010) (internal quotation marks omitted). Roman’s suit is not\\nbased on the same cause of action as the criminal complaint\\nand suppression hearing. Nor are his current claims of the\\ntype “that could have been brought” in the earlier criminal\\nproceeding. Id. (internal quotation marks omitted); see also\\nHelvering v. Mitchell, 303 U.S. 391, 397 (1938) (“The\\ndifference in degree of the burden of proof in criminal and\\ncivil cases precludes application of the doctrine of res\\njudicata.”). New Jersey initiated the criminal case. Roman\\nwas not at liberty to assert any claims except for defenses\\nagainst the prosecution’s case-in-chief. See Leather v. Eyck,\\n180 F.3d 420, 425 (2d Cir. 1999) (“[B]ecause the nature of\\nthe prior state[-]court proceeding was such that [the\\nAppellant] could not have sought damages for his alleged\\nconstitutional injuries (while defending himself on [a\\ncriminal] charge . . . ), res judicata does not bar his federal §\\n1983 suit for damages.”). Moreover, he was not free to raise\\nhis § 1983 claims in the same criminal case; indeed, he could\\nnot bring them until the criminal proceeding concluded. See\\nHeck v. Humphrey, 512 U.S. 477, 486 (1994) (“[T]he . . .\\nprinciple that civil tort actions are not appropriate vehicles for\\n\\n\\n\\n\\n 26\\n\\nchallenging the validity of outstanding criminal judgments\\napplies to § 1983 damages actions that necessarily require the\\nplaintiff to prove the unlawfulness of his conviction or\\nconfinement. . . .”). Accordingly, res judicata does not bar\\nRoman’s claims.\\n\\n Moving on to collateral estoppel, the Defendants argue\\nit (1) absolves Officer Mendes of liability because the\\nSuperior Court made a factual finding that Roman possessed\\nthe contraband that was seized from the apartment, (2)\\nabsolves Sergeant Joyce Hill because nothing in the Superior\\nCourt’s transcript indicates she was present for the search and\\narrest, and (3) absolves the other named defendants because\\nthe Superior Court’s transcript suggests they only handled the\\ncontraband. According to the Defendants, the Superior Court\\ndecided all of these issues in their favor during the\\nsuppression hearing. See Bd. of Trs. of Trucking Emps. of N.\\nJersey Welfare Fund, Inc. v. Centra, 983 F.2d 495, 505 (3d\\nCir. 1992) (stating a party is collaterally estopped from\\nlitigating a specific issue if, among other things, “[an]\\nidentical issue was decided in a prior adjudication”). Again\\nwe disagree. Contrary to the Defendants’ assertions, the\\nSuperior Court never decided any of these issues during the\\nsuppression hearing. While it did find that Roman had a\\npossessory interest in the apartment, that is not enough for us\\nto conclude that he had actual or constructive possession over\\nthe contraband. Collateral estoppel is not appropriate in this\\ncontext.\\n Last, the Defendants assert that judicial estoppel\\nprecludes Roman’s claims because he admitted that (1) drugs\\nwere found in the apartment, (2) he had a possessory interest\\nin the apartment, (3) Officer Mendes was the only officer who\\ninitiated the prosecution, and (4) the remaining officers only\\nhandled the contraband and had no other roles. They insist\\nthese concessions “are sufficient to establish that [Roman’s]\\n\\n\\n\\n\\n 27\\n\\narrest and prosecution arise out of his possession of\\nincriminating evidence[.]” Defendants’ Br. at 65. As noted,\\n“[j]udicial estoppel, sometimes called the ‘doctrine against\\nthe assertion of inconsistent positions,’ is a judge-made\\ndoctrine that . . . prevent[s] a litigant from asserting a position\\ninconsistent with one that []he has previously asserted . . . in a\\nprevious proceeding.” Ryan Operations G.P., 81 F.3d at 358.\\nThis doctrine is not in play here, as Roman never stipulated\\nthat Officer Mendes was the only officer to bring the\\nprosecution or that the remaining officers only handled the\\ncontraband. While the Court found that Roman had a\\npossessory interest in the apartment, that interest (we repeat)\\nis not enough to establish that he possessed the contraband.\\nAccordingly, judicial estoppel does not require us to dismiss\\nRoman’s claims.\\n * * * * *\\n Roman has sufficiently alleged a municipal liability\\nclaim against the City of Newark under § 1983. He cites\\nvarious examples of inadequate police training, poor police\\ndiscipline, and unheeded citizen complaints. He tells us\\ncertain police officers did not receive training for over 20\\nyears, and their training did not cover the basic requirements\\nof the Fourth Amendment. In his pleadings, he states the\\nNewark Police Department did not discipline officers who\\nengaged in police misconduct, Am. Compl. ¶¶ 84-86,\\nincluding unlawful searches and false arrests, App. at 134.\\nHe also notes the public filed formal complaints about\\nimproper searches and false arrests that were disregarded\\nalmost wholesale. Id. These alleged practices were ongoing\\nwhen Roman’s search and arrest occurred, and the City had\\nnotice of them at that time. While the proof developed to\\nsupport these allegations may or may not be persuasive to a\\nfinder of fact, they are enough to survive dismissal at this\\nstage. Based on this conclusion, we part with the District\\n\\n\\n\\n\\n 28\\n\\nCourt’s holding that Roman failed to state a § 1983 claim\\nagainst the City. Though we affirm otherwise, we vacate and\\nremand its decision on municipal liability.\\n\\n\\n\\n\\n 29\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4362697/\", \"author_raw\": \"AMBRO, Circuit Judge\"}, {\"author\": \"JORDAN, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"JORDAN, Circuit Judge, concurring.\\n\\n I join the majority opinion and write separately only to\\nnote that, even if we were to ignore the suppression hearing\\ntranscript and the press release and the Star Ledger article,\\nthere is still a sound basis to conclude that Roman has stated\\nplausible claims for municipal liability. Our panel is united in\\nunderstanding that we can properly consider the consent decree\\nbecause it was provided to the District Court and was\\nreferenced and relied upon in Roman’s amended complaint.\\nThose two sources – the consent decree and the amended\\ncomplaint – are sufficient to overcome the motion to dismiss\\nthe claims against the City of Newark.\\n\\n The consent decree supports the allegations in the\\namended complaint in a number of respects. For example, it\\nexpressly prohibits Newark Police officers “from relying on\\ninformation known to be materially false or incorrect to justify\\na warrantless search or to seek a search warrant[.]” (App. at\\n158). A fair inference from that prohibition is that it was\\nneeded precisely because the police were often relying on false\\ninformation to justify warrantless searches. That inference\\nbolsters Roman’s allegation that “[n]o drugs were found in\\n[his] possession” and yet the police “arrested [him] and falsely\\ncharged him with possession of a controlled dangerous\\nsubstance[.]” (App. at 263 ¶¶ 28-29).\\n\\n In another instance, the consent decree suggests that\\nthere has been a lack of training and supervision in the Newark\\nPolice Department. To remedy that deficiency, the consent\\ndecree requires the Department to “provide all officers with at\\nleast 16 hours of training on stops, searches, arrests, ... [and]\\n\\n\\n\\n\\n 1\\n\\ntraining ... in ... Fourth Amendment issues” as well as\\nmandating “desk lieutenant[s] or unit commander[s] [to]\\nreview each arrest report by officers under their command[.]”\\n(App. at 159-61). The inference that there was inadequate\\ntraining supports Roman’s allegation that the Department’s\\nofficers, “through their actions, inactions, course of conduct,\\npoor or non-existent training and deficient supervision[,]\\ncaused ... [the] illegal deprivation of [his] liberty[.]” (App. at\\n265 ¶ 48).\\n\\n As a final example, the consent decree says that the\\nDepartment must “conduct integrity audits and compliance\\nreviews to identify and investigate all officers who have\\nengaged in misconduct including unlawful ... searches[] and\\nseizures[.]” (App. at 192). The need for such audits and\\nreviews lends plausibility to Roman’s allegation that the “City\\nhad a custom and practice of inadequately investigating ...\\ncitizens’ complaints regarding illegal search and seizure[.]”\\n(App. at 272 ¶ 84).\\n\\n Thus, looking only at the amended complaint together\\nwith the consent decree, and giving Roman the benefit of all\\nfavorable inferences, as we must at this stage, there is a\\nsufficient basis to say that Roman has stated plausible claims\\nfor municipal liability under 42 U.S.C. § 1983. Dismissal of\\nthose claims was therefore an error.\\n\\n\\n\\n\\n 2\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4362697/\", \"author_raw\": \"JORDAN, Circuit Judge, concurring\"}, {\"author\": \"HARDIMAN, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"HARDIMAN, Circuit Judge, concurring in part and dissenting\\nin part.\\n\\n The District Court dismissed Roman’s case after giving\\nhim two opportunities to state a claim upon which relief may\\nbe granted and after reconsidering its order of dismissal. Based\\non the record presented to it, the District Court’s decision was\\ncorrect and should be affirmed as to all but one of Roman’s\\nclaims (the municipal liability claim for failure to train,\\nsupervise, or discipline).\\n\\n The Majority vacates part of the District Court’s\\njudgment by reciting facts found nowhere in Roman’s\\namended complaint and by adding facts of its own creation that\\nwere neither pleaded nor argued to the District Court with\\nsufficient specificity. The Majority’s deviation from standard\\ncivil practice and procedure compels this partial dissent.\\n\\n I\\n\\n This dissent results principally from a disagreement\\nwith my colleagues about which facts were properly before the\\nDistrict Court. First, the Majority proffers a narrative that\\nRoman never gave the District Court and which has no\\nrelevance to the claims it revives. This Court need not (and\\nshould not) recite these “facts” and “background” as true.\\nSecond, Roman did not sufficiently plead a municipal liability\\nclaim based on Newark’s alleged pattern or practice of Fourth\\nAmendment violations. If the facts as pleaded (or subject to\\njudicial notice) were as the Majority recites them, I would\\nagree that Roman stated a claim for relief. But since the actual\\nfacts before the District Court were quite different from those\\nenunciated by the Majority, the District Court did not err by\\ndismissing this claim.\\n\\n\\n\\n\\n 1\\n\\n Despite these disagreements with my colleagues, I\\nagree with them that Roman’s amended complaint sufficiently\\nstated a municipal liability claim for failure to train, supervise,\\nor discipline. Yet I cannot agree with their reasoning in toto\\nbecause we should not extrapolate—and the District Court did\\nnot err by declining to extrapolate—from extraneous\\ndocuments (like the consent decree Roman never provided nor\\ncited to the District Court) to reach that conclusion. This single\\nclaim should be resuscitated, but only based on the face of the\\namended complaint.\\n\\n A\\n\\n The Majority purports to recount the facts of this case\\n“as set out in the amended complaint and the transcript of the\\n[state court] suppression hearing.” Maj. Op. 4 n.1. Yet precious\\nfew of those facts were actually pleaded, primarily because the\\nstate court transcript was not proffered to the District Court by\\nRoman. Moreover, the Majority’s narrative of Roman’s\\nalleged mistreatment has effectively no bearing on the\\nmunicipal liability claims it revives.\\n\\n The lion’s share of the troubling facts recited by the\\nMajority were taken from sources other than Roman’s\\namended complaint. Those sources—including the state-court\\nproceedings and subsequent briefs—paint a picture the District\\nCourt never observed while considering the motion to dismiss.\\nIn truth, the amended complaint says nothing about how the\\ninvestigation began, or the surveillance of Roman’s apartment,\\nor the initial interaction between police and Melissa Isaksem,\\nor the officers’ use of Isaksem as a decoy to gain entry into the\\napartment, or the fact that drugs were seized from a common\\narea, or the expletives and threats that specific officers yelled\\nat both Roman and his father, or Officer Mendes’s use of\\n\\n\\n\\n\\n 2\\n\\nphysical force. Unlike those graphic and specific facts the\\nMajority extracts, the amended complaint is replete with\\nconclusory and generalized assertions. See App. 261–63.\\n\\n Here are some examples of the Majority’s approach:\\nInstead of averring that Officer Mendes flipped Roman on his\\nstomach and put a knee in Roman’s neck, Maj. Op. 5, the\\namended complaint merely states that “[t]he Defendant\\nOfficers and Defendant John Does 1–20 (fictitious names)\\nillegally assaulted the Plaintiff, throwing him against a wall\\nand handcuffing him,” App. 262. And rather than recounting a\\ndetailed plan to initiate an illegal search that included using an\\nunwitting friend as a decoy, Maj. Op. 5, the amended\\ncomplaint states only that “‘Defendant Officers’ . . . and\\nDefendant John Does 1–20 (fictitious names), after having the\\nopportunity to observe that the Plaintiff was a person of Latino\\ndescent, initiated an illegal search and seizure of the Plaintiff’s\\nresidence,” App. 261.\\n\\n Now on appeal, for the first time Roman cites facts\\nestablishing how the police gained entry into the apartment, the\\nthreatening words they spoke, and the actions of Officer\\nMendes. Roman Br. 10–12. We should not endorse this\\nunpleaded narrative, nor suggest the District Court erred by\\nfailing to manufacture it in the first place.\\n\\n B\\n\\n The Majority concludes that Roman’s amended\\ncomplaint (supplemented by the consent decree, a news article,\\nand a press release) contains enough facts to make plausible\\nhis claims that his injuries were proximately caused by\\nNewark’s: (1) pattern or practice of constitutional violations in\\nthe area of arrest practices; and (2) failure to adequately train,\\n\\n\\n\\n\\n 3\\n\\nsupervise, or discipline its officers. Maj. Op. 15–16. The first\\nconclusion is unwarranted. And while the second conclusion is\\ncorrect, the Majority still errs in its reliance on a document\\nRoman never cited and inferential leaps that Roman’s\\npleadings themselves do not admit.\\n\\n 1\\n\\n On its face, the amended complaint contains very few\\nfacts related to Roman’s arrest or Newark’s alleged pattern or\\npractice of rights violations, and what it does contain amount\\nonly to conclusory statements. See Ashcroft v. Iqbal, 556 U.S.\\n662, 678 (2009) (noting that a court’s duty to “accept as true\\nall of the allegations contained in a complaint is inapplicable\\nto legal conclusions,” and that “[t]hreadbare recitals of the\\nelements of a cause of action, supported by mere conclusory\\nstatements, do not suffice”). When we excise from the\\nMajority’s narrative all facts that were neither pleaded nor\\npresented to the District Court and the complaints’ legal\\nconclusions, it becomes clear that the District Court did not err\\nby twice deeming Roman’s complaint deficient regarding a\\npattern or practice of rights violations.\\n\\n This Court should not fault the trial judge for failing to\\ntake cognizance of facts or arguments never presented to her,\\nespecially here, where Roman chose not to include in his\\namended pleading facts that could have been gleaned from\\nDefendants’ first motion to dismiss and the consent decree\\nattached to it. See Snyder v. Pascack Valley Hosp., 303 F.3d\\n271, 276 (3d Cir. 2002) (noting that “[a]n amended complaint\\nsupercedes the original version in providing the blueprint for\\nthe future course of a lawsuit”).\\n\\n\\n\\n\\n 4\\n\\n The Majority primarily (and incorrectly) relies on that\\nconsent decree to buttress Roman’s pattern-or-practice claim.\\nAlthough the District Court could take notice of the consent\\ndecree’s existence, it’s quite another matter to hold it\\naccountable for not accepting as true everything its contents\\ncould possibly imply—especially when Roman neither\\npleaded nor relied upon the decree’s contents.\\n\\n What is crucial is whether Roman’s complaint was\\n“based” on the consent decree.1 In re Burlington Coat Factory\\nSec. Litig., 114 F.3d 1410, 1426 (3d Cir. 1997). Only to the\\nextent the Majority refashions Roman’s pattern-or-practice\\nclaim such that it is now based on implausible inferences from\\nthe consent decree is it “based on” the consent decree. For\\nRoman did not explicitly reference, quote, or rely on the\\ndocument in his amended complaint—even after the City\\nprovided it. The amended complaint merely references the\\ndecree’s announcement by the Department of Justice months\\nafter his arrest.2 See App. 270 ¶ 68. The District Court, though\\nit must draw all reasonable inferences in Roman’s favor, had\\nno obligation to abstract facts or inferences or claims Roman\\n\\n\\n 1\\n His appellate briefs’ references to the document are\\nnot determinative, no matter how many times they cite the\\ndecree.\\n 2\\n This timing further complicates the Majority’s reliance\\non the consent decree. The decree’s announcement months\\nafter Roman’s arrest requires yet another “infer[ence] that the\\nproblems that led to it were occurring during the time of his\\nallegations and for some time before that.” Maj. Op. 15. It also\\nrequires an inference that all of the City’s “corrective measures\\npostdated the arrest.” Id. at 21 n.8.\\n\\n\\n\\n\\n 5\\n\\nchose not to plead.3 Instead, he was the master of his own\\ncomplaint. See Judon v. Travelers Prop. Cas. Co. of Am., 773\\nF.3d 495, 505 (3d Cir. 2014).\\n\\n And even if we accept as true all the consent decree\\ncontains, Roman’s arrest was not plausibly part of the pattern\\nor practice of rights violations the decree addressed, except\\nperhaps at the highest level of generality.4 For starters, the\\ndecree addressed police stops and arrests of pedestrians or the\\noccupants of vehicles. See App. 79 (detailing the pattern or\\npractice investigated by the DOJ that led to the consent\\n\\n 3\\n The document’s undisputed authenticity as a\\ngovernment document says nothing about the reasonableness\\nof the inferences the Majority abstracts from the consent\\ndecree. Nor does it speak to the contents’ relevance to Roman’s\\ncase. Such authenticity merely provides one reason for\\njudicially noticing the decree’s existence and eliminates one\\npotential reason for not relying on it. It does not follow that it\\nis “especially important” for district courts to rely on and\\nextrapolate from such documents. Maj. Op. 11.\\n 4\\n The consent decree itself admits no specific pattern or\\npractice of rights violations. Although it followed a DOJ report\\nthat “revealed a pattern or practice of constitutional violations\\nin areas including stop and arrest practices, use of force, and\\ntheft by officers,” that report was never provided to the District\\nCourt. App. 137; see Maj. Op. 11–12. Instead, the consent\\ndecree only outlines measures Newark agreed to take—not any\\npattern or practice of rights violations, let alone one that\\nplausibly caused Roman’s injuries. In fact, that report actually\\ndemonstrates that even the pattern or practice that led to the\\nconsent decree could not plausibly have caused Roman’s\\ninjuries.\\n\\n\\n\\n\\n 6\\n\\ndecree’s adoption). The consent decree says nothing about\\narrests or searches without consent that occur at residences,\\nwhich is what Roman complains of in this case.\\n\\n Another problem that distinguishes Roman’s complaint\\nfrom the problems that led to the consent decree is the fact that\\nthe decree addressed police practices that disparately impacted\\nthe black community. See App. 93–98 (detailing same).5 But\\nthat racial disparity did not apply to Roman, who was Hispanic.\\nSee App. 261 ¶ 16. While the consent decree may have been\\n“meant to protect all Newark residents,” Maj. Op. 19, the point\\nremains that the pattern or practice giving rise to it was not one\\nthat plausibly caused Roman’s injuries.\\n\\n Finally, the consent decree addressed erroneous\\nnarcotics arrest reports where “individuals often were\\npurportedly seated in cars holding clear plastic baggies in front\\nof them or on their laps and officers could ‘immediately’ see\\nthe contraband, even though the report indicated that the\\nsubject’s back was to an officer, or that the officer had not yet\\napproached the car.” App. 92 (detailing the pattern or practice\\ninvestigated by the DOJ that led to the consent decree’s\\nadoption). Wholly unrelated to those erroneous reports, Roman\\nalleges that officers exhaustively searched the apartment\\n\\n 5\\n In his motion for reconsideration, Roman claimed his\\nmunicipal liability argument was based on “the City’s\\nwidespread and systemic misuse of police powers to treat\\nmembers of a protected racial class different from those of\\nwhite citizens.” ECF 43-3 at 8. Unlike the pattern or practice\\nof Fourth Amendment violations the Majority now remands,\\nhe argued “racial profiling, racial discrimination, or other\\nwidespread discrimination of minorities” gave rise to his\\nmunicipal liability cause of action. Id.\\n\\n\\n\\n\\n 7\\n\\nwithout a warrant, and he is silent as to where and when the\\nofficers found the drugs. See App. 30–31, 262–63.\\n\\n In sum, Roman’s arrest was too dissimilar from the\\npattern or practice addressed by the consent decree to plausibly\\nallege proximate causation for his injuries. While clear that the\\nDOJ did not enter into the consent decree “because it was\\nimpressed with Newark’s policing practices,” Maj. Op. 20, it\\nwas not the District Court’s duty to imagine all possible\\ninferences from the document. It was Roman’s duty to plead\\nthem. See Judon, 773 F.3d at 505. For the Majority to conclude\\notherwise, it must derive that pattern or practice from sources\\nnot before the District Court and define it at the highest level\\nof generality: Fourth Amendment violations writ large. In other\\nwords, my colleagues conclude that because Newark police\\nallegedly engaged in a pattern or practice of Fourth\\nAmendment violations of type x, it follows that they plausibly\\ncommitted this violation of type y—all based on a document\\nthey cannot claim the District Court must have considered. The\\nDistrict Court did not err in failing to perform the Majority’s\\ninferential leaps to reach that conclusion based on a document\\nit need not have considered in the first place. It properly\\ndismissed this claim rather than indulge such speculation. See\\nIqbal, 556 U.S. at 679–80.\\n\\n With or without these sources, the amended complaint’s\\nbare legal conclusions need not be accepted as true. Id. at 678.\\nSo Roman failed to state a pattern-or-practice claim on which\\nrelief could be granted.\\n\\n\\n\\n\\n 8\\n\\n 2\\n\\n Roman’s failure-to-train, failure-to-supervise, and\\nfailure-to-discipline claim was sufficiently pleaded. But the\\nMajority’s method for arriving at this conclusion suffers from\\nsimilar deficiencies to its pattern-or-practice reasoning. The\\nMajority’s reliance on the consent decree is again misplaced\\nfor the reasons discussed above.6 And even if such reliance\\nwere appropriate, the consent decree does not make Roman’s\\nclaim plausible.\\n\\n Roman’s arrest was not plausibly caused by the failures\\nto train, supervise, or discipline Newark officers the Majority\\ncites in the consent decree because no such failures appear in\\nthe document. The Majority claims “the consent decree\\nindicates Newark police officers were not trained on ‘the\\nrequirements of [the] Fourth Amendment and related law.’”\\nMaj. Op. 16. And “per the decree” the City’s “training did not\\ncover the basics of the Fourth Amendment.” Id. at 17. It does\\nno such thing. Rather, it indicates that Newark agreed to\\n\\n 6\\n The Majority’s reliance on the news article and press\\nrelease hyperlinked in Roman’s complaints is likewise\\ninappropriate. The news article’s identification of one\\nofficer—who may or may not have been involved in Roman’s\\narrest—who told a reporter he “think[s]” he did not receive\\ntraining for 20 years is not enough to subject the City to\\nliability for failure to adequately train its entire police force.\\nApp. 134 (emphasis added). This demonstrates no custom; nor\\ndoes it plausibly demonstrate the police academy training all\\nofficers receive was constitutionally inadequate without more\\nfollow-up. Nor does the article address supervision or\\ndiscipline. Similarly, the press release addresses none of the\\nthree.\\n\\n\\n\\n\\n 9\\n\\nimplement additional training on “the requirements of [the]\\nFourth Amendment and related law” without any detail as to\\nthe status quo it addressed. App. 160. While it’s safe to say that\\nthe DOJ did not endorse that status quo, the difference between\\nagreeing to train more and agreeing that prior training was\\nconstitutionally inadequate regarding the Fourth Amendment\\nwrit large should be clear. And, as discussed above, the consent\\ndecree arose from a host of policing practices unlike those\\nRoman alleged (except at the highest level of generality).\\nNewark could not plausibly have agreed to the extraordinary\\nliability that would come from admitting that its police training\\nviolated the Fourth Amendment in every instance, or in every\\ninstance possibly connected to Roman’s arrest. Indeed, the\\ndecree says no such thing about any instance.\\n\\n The consent decree is even thinner as it relates to\\nsupervisory and disciplinary issues. From the City’s agreement\\nto adhere to certain review processes and disciplinary measures\\nregarding unlawful searches and false arrests, the Majority\\nperceives a “deliberate indifference to Roman’s Fourth\\nAmendment rights.” Maj. Op. 17 (internal quotations and\\ncitation omitted). That does not follow. The decree does not\\ndescribe or admit any processes or measures already in place\\nor any existing pattern of unlawful searches or false arrests.\\n\\n Instead, Roman’s amended complaint directly alleged\\ntraining, supervision, and discipline problems with adequate\\nspecificity to survive a motion to dismiss. See, e.g., App. 270–\\n72 ¶¶ 68, 70, 71, 78, 80, 82; see also Doe v. Luzerne Cty., 660\\nF.3d 169, 179–80 (3d Cir. 2011) (quoting Carter v. City of\\nPhila., 181 F.3d 339, 357 (3d Cir.1999)) (detailing standard at\\nsummary judgment for failure-to-train claim). The Majority’s\\nimproper reliance on the consent decree and inferential leaps\\n\\n\\n\\n\\n 10\\n\\nfrom that and other sources outside the amended complaint are,\\nin my view, erroneous and unnecessary.\\n\\n * * *\\n\\n As we have noted many times before, we are a court of\\nreview, not a court of first view. See, e.g., In Re: J & S Props.,\\nLLC, 872 F.3d 138, 148 (3d Cir. 2017). Our review is based on\\nthe record as presented by counsel in our adversary system. We\\nshould not fault the District Court for failing to manufacture\\nfacts and craft arguments that Roman neglected to plead. By\\nconjuring its own facts repackaged as if pleaded in the\\namended complaint, the Majority imposes a new duty upon\\ndistrict judges within the Third Circuit. It does so without\\nciting precedent for the proposition that a district court must\\nconsider facts and arguments never pleaded or argued by the\\nplaintiff. I cannot subscribe to this new rule.\\n\\n This appeal implicates a fundamental legal principle:\\nthe plaintiff is the master of his complaint. Because of that\\ntime-honored principle, Roman’s failure to state a policy-or-\\npractice claim upon which relief may be granted requires the\\nharsh sanction of dismissal. After his initial complaint was\\nfound inadequate, Roman failed to file an amended complaint\\nthat cured the deficiencies identified by the District Court.\\nEven assuming Roman might have had a legitimate claim, it\\nwould have been improper for the District Court to try to make\\nRoman’s case for him. And it’s especially inappropriate for us\\nto overrule the decision of a district judge because of a failure\\nto apprehend facts and arguments never presented to her. I\\nrespectfully dissent.\\n\\n\\n\\n\\n 11\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4362697/\", \"author_raw\": \"HARDIMAN, Circuit Judge, concurring\"}]}"},"judge1":{"kind":"string","value":"JORDAN"},"judge2":{"kind":"string","value":"HARDIMAN"},"judge3":{"kind":"string","value":"JORDAN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":6,"string":"6"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":4,"string":"4"},"other_count":{"kind":"number","value":2,"string":"2"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4585444/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":1,"string":"1"},"035concurrenceinpart_count":{"kind":"number","value":1,"string":"1"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: *The ESTATE OF Adriano ROMAN, Jr., Appellant v. CITY OF NEWARK; City of Newark Police Department; Anthony Campos, Chief of Police; Rodger C. Mendes; Albano Ferreira ; Onofre H. Cabezas; Joseph Cueto; FNU Ressureicao; FNU Golpe; Joyce Hill, Individually and in Their Capacity as Police Officers; John Does 1-20, as Fictitious Names for Presently Unknown Agents Member Commissioners and Chiefs *(Amended Pursuant to Clerk's Order Dated 1/25/2018)\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-29\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n ________________\n No. 17-2302\n ________________\n\n *THE ESTATE OF ADRIANO ROMAN, JR.,\n Appellant\n\n v.\n\n CITY OF NEWARK;\n CITY OF NEWARK POLICE DEPARTMENT;\n ANTHONY CAMPOS, Chief of Police;\n RODGER C. MENDES;\n ALBANO FERREIRA; ONOFRE H. CABEZAS;\n JOSEPH CUETO;\n FNU RESSUREICAO; FNU GOLPE; JOYCE HILL,\n Individually and in their capacity as police officers;\nJOHN DOES 1-20, as fictitious names for presently unknown\n agents member commissioners and chiefs\n\n *(Amended pursuant to Clerk’s Order dated 1/25/18)\n ________________\n Appeal from the United States District Court\n for the District of New Jersey\n (D.C. Civil Action No. 2-16-cv-01110)\n District Judge: Honorable Susan D. Wigenton\n ________________\n\n Argued June 12, 2018\n\n Before: AMBRO, JORDAN, and\n HARDIMAN, Circuit Judges\n\n (Opinion filed: January 29, 2019)\n\nJustin D. Santagata (Argued)\nKaufman Semeraro & Leibman\nTwo Executive Drive, Suite 530\nFort Lee, NJ 07024\n\n Counsel for Appellant\n\nKenyatta K. Stewart, Acting Corporation Counsel\nWilson D. Antoine (Argued)\nCity of Newark–Department of Law\n920 Broad Street, Room 316\nNewark, NJ 07102\n\n Counsel for Appellees\n\n ________________\n OPINION OF THE COURT\n ________________\n\nAMBRO, Circuit Judge\n\n Newark police officers forcibly entered and searched\nthe apartment of Adriano Roman’s girlfriend. App. at 386,\n391, 459, 486. They arrested Roman, who was present in the\napartment, after they found drugs in a common area that was\nshared by multiple tenants. Id. at 399, 479. Though he was\nimprisoned for over six months and indicted for various drug\n\n\n\n\n 2\n\noffenses, the New Jersey Superior Court found the search to\nbe unlawful and the charges were dropped.\n\n Roman now brings claims against the City of Newark\n(which includes its Police Department) and various police\nofficers under 42 U.S.C. § 1983 (which gives a federal\nremedy against state officials who, acting under color of state\nlaw, deprive “any citizen of the United States . . . of any\nrights, privileges, or immunities secured by the [U.S.]\nConstitution and laws”) and New Jersey tort law. He alleges\nthe City had a pattern or practice of constitutional violations\nand failed to train, supervise, and discipline its officers. He\nalso pleads an unlawful search claim against the officers and\ncontends they are liable for false imprisonment and malicious\nprosecution. The District Court dismissed all of the claims\nbecause they were inadequately pled. It also held the City did\nnot have an ongoing practice of unconstitutional searches and\narrests.\n While most of Roman’s claims do not withstand\ndismissal, his § 1983 claims against the City do. He has\nadequately alleged that its Police Department had a custom of\nwarrantless searches and false arrests. He also sufficiently\npled that the Department failed to train, supervise, and\ndiscipline its officers, specifically with respect to “the\nrequirements of [the] Fourth Amendment and related law.”\nApp. at 160. Because Roman has stated a plausible claim\nagainst the City, we vacate and remand the District Court’s\nholding on municipal liability. We affirm in all other\nrespects.\n\n\n\n\n 3\n\nI. Background1\n On May 2, 2014, Roman and his girlfriend Tiffany\nReyes were watching a movie in her apartment’s bedroom.\nApp. at 386, 389, 395. Unbeknownst to them, four Newark\npolice officers had set up surveillance outside of her building\nbecause of complaints about narcotics activity. Id. at 338.\nThe officers heard an argument between a man and a woman,\nid. at 340-42, and decided to enter Reyes’ apartment without\na warrant, id. at 491.\n After they stepped inside the building, they discovered\nthat the front door of the apartment was locked. They also\n\n 1\n As noted below, we must, while reviewing a ruling\non a motion to dismiss, view the facts in the light most\nfavorable to the plaintiff. Accordingly, without judging the\nfacts, we recount them as set out in the amended complaint\nand the transcript of the suppression hearing referred to\nbelow. Although Roman did not attach the transcript to the\namended complaint, the Defendants included it in their\nmotion to dismiss and told the District Court it was “capable\nof judicial notice” and “integral to the [c]omplaint.” App. at\n130. Thus we consider it at this stage.\n\n In any event, both the amended complaint and\ntranscript note that the officers forcibly entered the apartment,\nassaulted Roman, and falsely charged him with possession of\na controlled substance. See Am. Compl. ¶¶ 17, 22, 28. Any\nminor differences in the two documents do not affect our\nanalysis of his municipal liability claim. See infra Section\nIII.A (explaining that the events leading up to Roman’s\nsearch and arrest are not relevant to the merits of his\nmunicipal liability claim).\n\n\n\n\n 4\n\nnoticed Melissa Isaksem, Reyes’ friend, walking inside the\nbuilding. Id. at 417-20. They stopped and questioned her.\nId. at 417, 419. When she told them she was visiting Reyes,\nid. at 419, they ordered her to knock on the apartment door\nfor them and threatened to arrest her if she did not comply, id.\nat 419-20. Isaksem led them to the apartment and stood\ndirectly in front of the peephole. Id. at 421. The police stood\nto her left, presumably out of the peephole’s range. Id. An\nofficer knocked on her behalf. Id. Reyes asked who was at\nthe door, and Isaksem announced her presence. Id.\n Reyes opened the door, expecting to see only Isaksem.\nId. at 386, 400, 501. Instead, several officers rushed inside.\nId. at 387, 400, 501. They handcuffed Roman, Reyes, and\nIsaksem, then demanded Roman “call someone to bring drugs\nto the [apartment].” Am. Compl. ¶ 30 (internal quotation\nmarks omitted). If he did, they assured him they would\n“‘make a deal’ and ‘let him go.’” Id. Roman refused the\nofficers’ demands, id. ¶ 33, and the police searched the\napartment. Eventually they found drugs in a common-area\nspace that was shared by multiple tenants and located in the\nback of the apartment. App. at 399, 479. After seizing the\ncontraband, they yelled, “[W]e got you, motherfucker[;] . . .\nyou’re fucked now.” Id. at 427. Officer Rodger Mendes\nwalked back to Roman, “flipped him . . . on[]to his stomach\n. . . , put his knee in his neck[,] and . . . said he was going to\nget raped [in prison].” Id. at 428. Another officer informed\nRoman’s father, who lived next door and observed parts of\nthe search, that his son “would go away for a long time.” Id.\nat 454.\n Roman was arrested and imprisoned on the same night.\nThe officers filed a criminal complaint against him for\npossession of, as well as intent to distribute, heroin and\ncocaine. A New Jersey grand jury returned a six-count\nindictment against him for the same offenses.\n\n\n\n\n 5\n\n In response, Roman moved to suppress the evidence\nseized from the apartment. He argued the search was invalid\nunder the Fourth Amendment because the contraband was not\nin plain view and thus a warrant was needed. The New Jersey\nSuperior Court agreed. It concluded the plain-view exception\ndid not apply and suppressed the contraband.\n The State of New Jersey did not appeal the ruling and\ninstead moved to dismiss the case. The Superior Court\ngranted its motion in December 2014 and issued a final\njudgment of dismissal. Roman was released from prison\nduring the same month.\n Approximately a year later, Roman brought § 1983\nand state-law tort claims against the City of Newark and\nvarious police officers (for simplicity, the City and the\nofficers are jointly referred to as the “Defendants”). Among\nother things, he alleged the City had a custom or policy of\nunconstitutional searches, inadequate training, and poor\nsupervision and discipline.2 He also claimed the officers\nunlawfully searched his apartment and were liable for the\ntorts of unlawful imprisonment and malicious prosecution.3\n\n\n 2\n Roman’s amended complaint also included\nallegations of discrimination of national origin in violation of\n42 U.S.C. § 1983, civil conspiracy in violation of 42 U.S.C.\n§ 1985, conspiracy to commit an unlawful search in violation\nof the New Jersey Constitution and 42 U.S.C. § 1985, and\nconspiracy to commit unlawful imprisonment in violation of\n42 U.S.C. § 1985. We do not address these claims, as Roman\ndoes not press them on appeal.\n 3\n We construe Roman’s claim for unlawful\nimprisonment as a claim for false imprisonment. Although\n\n\n\n\n 6\n\n The Defendants responded with a motion to dismiss.\nThe District Court sided with them, dismissing the complaint\nin its entirety. It first addressed Roman’s claim against the\nCity and concluded the complaint “fail[ed] to plead . . . a\ncustom or policy” of unlawful searches and a failure to train\nor supervise officers. Roman v. City of Newark, Civil Action\nNo. 16-1110-SDW-LDW, 2017 WL 436251, at *4 (D.N.J.\nJan. 30, 2017). Although the complaint alleged “a pattern or\npractice of constitutional violations in areas including stop[]\nand arrest practices, use of force, and theft by officers,” the\nCourt did not consider that sufficient to state a claim. Id.\n(internal quotation marks omitted) (quoting Compl. ¶ 59).\nInstead, it viewed those practices as predating Roman’s arrest\nand observed that “the imposition of a [f]ederal [m]onitor\nindicate[d] [the City’s] attempts to change any wrongful\npolicies or practices.” Id.\n The Court also held the unlawful search claim was\ninadequately pled, as Roman did not “explain which\n[Defendant(s)] committed the allegedly wrongful acts” during\nthe search and arrest. Id. Turning to the false imprisonment\nand malicious prosecution claims, it construed them as state-\nlaw claims and noted that plaintiffs must comply with the\n\nNew Jersey lacks a cause of action for “unlawful\nimprisonment,” it has codified the elements of a false\nimprisonment claim. See N.J. Stat. Ann. § 2C:13-3; Mallery\nv. Erie R. Co., 92 A. 371, 371 (N.J. 1914) (“This appeal\nbrings up a judgment recovered by the respondent in an\naction for false imprisonment. The declaration described\nthe unlawful imprisonment. . . .”); see also 8 American Law\nof Torts § 27:1 (“False imprisonment, sometimes called\ncriminal restraint or unlawful imprisonment, is committed\nwhen a defendant so restrains another person as to interfere\nsubstantially with his liberty.”).\n\n\n\n\n 7\n\nNew Jersey Tort Claims Act before bringing them against\npublic entities. See N.J. Stat. Ann. § 59:8-1 et seq. Because\nthe “[c]omplaint nowhere allege[d]” Roman complied with\nthe Act’s procedures, the Court dismissed those claims as\nwell. Roman, 2017 WL 436251, at *6.\n\n The Court’s dismissal was without prejudice, and it\ngranted Roman leave to amend. He did so by omitting his\ntort claims and retaining his other allegations in almost\nidentical form. The Court dismissed his amended complaint\nand reaffirmed its ruling on reconsideration. This appeal\nfollowed.4\nII. Jurisdiction and Standard of Review\n The District Court had federal-question and\nsupplemental jurisdiction per 28 U.S.C. §§ 1331 and 1367(a),\nrespectively, and we have jurisdiction over its final orders\nunder 28 U.S.C. § 1291.\n We review de novo its dismissal of a complaint under\nFederal Rule of Civil Procedure 12(b)(6). See Phillips v.\nCounty of Allegheny, 515 F.3d 224, 230 (3d Cir. 2008).\nWhen conducting our review, “we accept all factual\nallegations as true [and] construe the complaint in the light\nmost favorable to the plaintiff.” Warren Gen. Hosp. v.\nAmgen Inc., 643 F.3d 77, 84 (3d Cir. 2011) (internal\nquotation marks omitted). However, “we are not compelled\nto accept unsupported conclusions and unwarranted\ninferences . . . or a legal conclusion couched as a factual\nallegation[.]” Baraka v. McGreevey, 481 F.3d 187, 195 (3d\n\n\n 4\n Roman passed away while this appeal was pending,\nand his estate brings the claims on his behalf. We do not\ndistinguish between Roman and his estate in this opinion.\n\n\n\n\n 8\n\nCir. 2007) (internal quotation marks omitted) (internal\ncitation omitted).\n\nIII. Discussion\n A. Roman sufficiently pled a municipal liability\n claim against Newark.\n\n As noted, Roman alleges the City is liable under\n§ 1983 because it “engaged in a pattern or practice of\nconstitutional violations,” “failed to properly train and/or\nsupervise” its police force, and “failed to properly and\nadequately control and discipline” its police officers.5 Am.\nCompl. ¶¶ 68, 73-74. Before discussing the merits of his\nclaims, Roman directs our attention to the types of documents\nwe may consider on a motion to dismiss. He contends we\nmay review three sources that were provided to the District\nCourt: an article published in the Newark Star Ledger (the\n“Star Ledger article”), a press release issued by the U.S.\nAttorney’s Office (the “press release”), and a consent decree\nbetween the United States and the City of Newark (the\n“consent decree”). The Star Ledger article and press release\nwere referenced in the amended complaint, see id. ¶¶ 68-69\n(including hyperlinks to both), but the consent decree was\nattached to the Defendants’ motion to dismiss, see App. at\n129. Roman also asks us to look at one other document: the\nDepartment of Justice’s Report on the investigation of the\nNewark Police Department (the “DOJ Report”). Although he\n\n 5\n Roman brings his municipal liability claims under\n§ 1983 and the New Jersey Civil Rights Act, N.J. Stat. Ann.\n§ 10:6-1 et seq. Because the latter “is interpreted analogously\nto . . . § 1983,” we consider his New Jersey Civil Rights Act\nclaims along with his § 1983 claim. Coles v. Carlini, 162 F.\nSupp. 3d 380, 404 (D.N.J. 2015).\n\n\n\n\n 9\n\nacknowledges the DOJ Report was never provided to the\nDistrict Court, he now claims it is integral to the pleadings.\n\n Though the Defendants dispute that we may consider\nthe DOJ Report, they add that we also cannot consider the\nconsent decree because “no relevant provisions of [it] . . .\nwere ever cited . . . to the District Court” and it is\ninadmissible settlement material. Defendants’ Br. at 42.\nThey assert as well, without any citation to the record, that\nRoman may not rely on the decree because he asked the\nDistrict Court to confine its analysis to the pleadings.\n We disagree with the Defendants’ view of the consent\ndecree. Although we examine the “complaint, exhibits\nattached to the complaint, [and] matters of public record,”\nMayer v. Belichick, 605 F.3d 223, 230 (3d Cir. 2010), we can\nalso consider documents “that a defendant attaches as an\nexhibit to a motion to dismiss,” Pension Benefits Guar. Corp.\nv. White Consol. Indus., Inc., 998 F.2d 1192, 1196 (3d Cir.\n1993), if they are “undisputedly authentic” and “the\n[plaintiff’s] claims are based [on them],” Mayer, 605 F.3d at\n230. That holding extends to settlement material because\nplaintiffs “need not provide admissible proof at th[e] [motion-\nto-dismiss] stage.” In re OSG Sec. Litig., 12 F. Supp. 3d 619,\n622 (S.D.N.Y. 2014); see also In re MyFord Touch Consumer\nLitig., 46 F. Supp. 3d 936, 961 n.5 (N.D. Cal. 2014) (same).\nMoreover, the Supreme Court has been clear about the scope\nof our review, stating we “must consider the complaint in its\nentirety, as well as other sources [we] ordinarily examine\nwhen ruling on . . . motions to dismiss, in particular,\ndocuments incorporated into the complaint by reference, and\nmatters of which a court may take judicial notice.” Tellabs,\nInc. v. Makor Issues & Rights, Ltd., 551 U.S. 308, 322 (2007)\n(emphasis added).\n\n\n\n\n 10\n\n Here, although the consent decree was not attached to\nRoman’s amended complaint, we are free to review its\ncontents for three reasons.6 First, the Defendants attached the\ndecree to their motion to dismiss and affirmed that it is\n“capable of judicial notice” as an indisputably authentic\ngovernment document. App. at 129. Second, contrary to the\ndissent’s assertion, the Defendants themselves argued (and\ncorrectly) before the District Court that Roman’s claims were\nbased on the consent decree. Compare Dissenting Op. at 5\n(“What is crucial is whether Roman’s complaint was ‘based’\non the consent decree.”), with App. at 129 (filing from\nDefendants characterizing the consent decree as “integral to\nthe Complaint”). Third, the amended complaint cited, and the\nDistrict Court discussed, the DOJ investigation and federal\nmonitor that eventually led to the consent decree. See\nRoman, 2017 WL 436251, at *4; see also Am. Compl. ¶¶ 68-\n71. Thus it was especially important for the Court to have\nconsidered the decree as well, given that it provides essential\ncontext to Roman’s claims. That it did not was an abuse of\ndiscretion.\n\n That said, we may not consider the DOJ Report at this\nstage because it was not provided to the District Court in the\nfirst instance by any party. Nor is it apparent that the Court\nconsidered it sua sponte. See United States ex rel. Wilkins v.\n\n 6\n Though the Defendants and our dissenting colleague\ndo not challenge the Star Ledger article or the press release,\nwe note that we consider them because they are referenced in\nthe amended complaint. See Tellabs, 551 U.S. at 322. As\nJudge Jordan explains in his concurrence, however, Roman\ndoes not need either document or the suppression hearing\ntranscript to state a municipal liability claim; the consent\ndecree gives his allegations enough plausibility to survive\ndismissal.\n\n\n\n\n 11\n\nUnited Health Grp., Inc., 659 F.3d 295, 302 (3d Cir. 2011)\n(“Though we do not doubt the authenticity of\nthese documents, nevertheless we will not consider them\nbecause the parties did not present them to the District Court\nand we do not find any indication in the record that the Court\nconsidered them on its own initiative.”). Hence it cannot\ncarry any weight in our analysis.\n Turning to the amended complaint, Roman claims the\nCity is liable for his unlawful search because it “failed to train\nits officers in the use of search and seizure techniques,\nprobable cause, and/or methods to properly obtain a search\nwarrant.” Am. Compl. ¶ 95. He alleges the Newark Police\nDepartment “engaged in a pattern or practice of constitutional\nviolations” and asserts the Department of Justice appointed a\nfederal monitor to oversee the reforms to which the City\nconsented. Id. ¶ 68. His allegations also touch on the City’s\nfailure to “control and discipline” its police force, id. ¶ 74,\nand failure to “investigate . . . instances of . . . police\nmisconduct,” id. ¶ 81. He characterizes the City’s practices in\nthese areas as “tantamount to a[n] [unconstitutional] custom\nand/or policy,” id. ¶ 82, thus indicating its “deliberate\nindifference to [its citizens’ constitutional] rights,” id. ¶ 83.\n The Defendants respond that Roman has failed to\nallege a municipal liability claim, as no part of the Star\nLedger article, press release, or consent decree references the\ntypes of constitutional violations pled in the amended\ncomplaint. They also contend the City had no notice “of any\npattern of constitutional violations with respect to forced\nentry and searches of homes.” Defendants’ Br. at 50.\n To plead a municipal liability claim, a plaintiff must\nallege that “a [local] government’s policy or custom . . .\ninflict[ed] the injury” in question. Monell v. Dep’t of Soc.\nServs., 436 U.S. 658, 694 (1978). “Policy is made when a\n\n\n\n\n 12\n\ndecisionmaker possess[ing] final authority to establish\nmunicipal policy with respect to the action issues an official\nproclamation, policy, or edict.” Andrews v. City of\nPhiladelphia, 895 F.2d 1469, 1480 (3d Cir. 1990) (alteration\nin original) (internal quotation marks omitted). “Custom, on\nthe other hand, can be proven by showing that a given course\nof conduct, although not specifically endorsed or authorized\nby law, is so well-settled and permanent as virtually to\nconstitute law.” Bielevicz v. Dubinon, 915 F.2d 845, 850 (3d\nCir. 1990) (Becker, J.); see also Brown v. Muhlenberg Twp.,\n269 F.3d 205, 215 (3d Cir. 2001) (“A custom . . . must have\nthe force of law by virtue of the persistent practices of state\n[or municipal] officials.” (internal quotation marks omitted)).\n Although a policy or custom is necessary to plead a\nmunicipal claim, it is not sufficient to survive a motion to\ndismiss. A plaintiff must also allege that the policy or custom\nwas the “proximate cause” of his injuries. See Kneipp v.\nTedder, 95 F.3d 1199, 1213 (3d Cir. 1996). He may do so by\ndemonstrating an “affirmative link” between the policy or\ncustom and the particular constitutional violation he alleges.\nBielevicz, 915 F.2d at 850 (internal quotation marks omitted).\nThis is done for a custom if Roman demonstrates that Newark\nhad knowledge of “similar unlawful conduct in the past, . . .\nfailed to take precautions against future violations, and that\n[its] failure, at least in part, led to [his] injury.” Id. at 851.\nDespite these requirements, Roman does not need to identify\na responsible decisionmaker in his pleadings. See id. at 850.\nNor is he required to prove that the custom had the City’s\nformal approval. See Anela v. City of Wildwood, 790 F.2d\n1063, 1067 (3d Cir. 1986).\n The pleading requirements are different for failure-to-\ntrain claims because a plaintiff need not allege an\nunconstitutional policy. See Reitz v. County of Bucks, 125\nF.3d 139, 145 (3d Cir. 1997) (“[I]n the absence of an\n\n\n\n\n 13\n\nunconstitutional policy, a municipality’s failure to properly\ntrain its employees and officers can create an actionable\nviolation . . . under § 1983.”). Instead, he must demonstrate\nthat a city’s failure to train its employees “reflects a deliberate\nor conscious choice.” Brown, 269 F.3d at 215 (internal\nquotation marks omitted). For claims involving police\nofficers, the Supreme Court has held that the failure to train\n“serve[s] as [a] basis for § 1983 liability only where [it] . . .\namounts to deliberate indifference to the rights of persons\nwith whom the police come into contact.” City of Canton v.\nHarris, 489 U.S. 378, 388 (1989) (footnote omitted). A\nplaintiff sufficiently pleads deliberate indifference by\nshowing that “(1) municipal policymakers know that\nemployees will confront a particular situation[,] (2) the\nsituation involves a difficult choice or a history of employees\nmishandling[,] and (3) the wrong choice by an employee will\nfrequently cause deprivation of constitutional rights.” Doe v.\nLuzerne County, 660 F.3d 169, 180 (3d Cir. 2011) (internal\nquotation marks omitted) (quoting Carter v. City of\nPhiladelphia, 181 F.3d 339, 357 (3d Cir. 1999)).\n\n In view of this case law, Roman has not pled a\nmunicipal policy, as his amended complaint fails to refer to\n“an official proclamation, policy, or [an] edict.” Andrews,\n895 F.2d at 1480. However, he has sufficiently alleged a\ncustom of warrantless or nonconsensual searches. He has\nalso adequately pled that the City failed to train, supervise,\nand discipline its police officers.7\n\n\n 7\n We consider allegations of failure to train, supervise,\nand discipline together because they fall under the same\nspecies of municipal liability. See Rosalie Berger Levinson,\nWho Will Supervise the Supervisors? Establishing Liability\nfor Failure to Train, Supervise, or Discipline in a Post-\n\n\n\n\n 14\n\n We start with Roman’s allegations on municipal\ncustom. He asserts the City had “a pattern or practice of\nconstitutional violations in areas including . . . arrest\npractices.” App. at 137. He further contends it had notice of\nthis practice, as it received “complaints against officers\naccused of . . . conducting improper searches and false\narrests.” Id. at 134. The amended complaint, along with the\npress release and Star Ledger article, note that Newark was\nunder the supervision of a federal monitor after Roman’s\narrest. Am. Compl. ¶ 68; App. at 133, 137. According to the\npress release, the monitor would oversee reforms in several\nareas, including searches, arrests, and the intake and\ninvestigation of misconduct complaints. App. at 137.\n The consent decree echoes these points. It covers the\nsame type of conduct Roman alleges, as it “prohibit[s]\nofficers from relying on information known to be materially\nfalse or incorrect to justify a warrantless search . . . [or to]\neffect[] an arrest.” Id. at 158; see also id. at 163 (mandating\nofficers to collect data on consent, the type of search, and “a\nbrief description of the facts creating probable cause”). The\ndecree also requires the Police Department to investigate\npolice misconduct, see generally id. at 184-92, with special\nemphasis on allegations of criminal misconduct, false arrest,\nplanting evidence, and unlawful searches, see id. at 150, 186.\n While the consent decree was not in place during\nRoman’s search and arrest, we may fairly infer that the\nproblems that led to it were occurring during the time of his\nallegations and for some time before that. See id. at 133-34\n(noting the investigation that resulted in the consent decree\nand federal supervision began in May 2011 and ended in July\n2014). With this mind, the decree fortifies Roman’s\n\nIqbal/Connick World, 47 Harv. C.R.-C.L. L. Rev. 273, 280\n(2012).\n\n\n\n\n 15\n\nallegations of unlawful custom because it acknowledges “a\npattern or practice of conduct by the Newark Police\n[Department] that deprives individuals of rights, privileges,\nand immunities secured by the Constitution.” Id. at 144.\nWhen viewed in conjunction with the Star Ledger article, it\nreferences the types of constitutional violations mentioned in\nthe amended complaint: warrantless searches, id. at 134, and\nfalse arrests, id. at 158. These violations were widespread\nand causally linked to Roman’s alleged injury, as the Police\nDepartment was aware of them but “rare[ly] . . . acted” on\ncitizen complaints. Id. at 134 (discussing complaints of\n“improper searches and false arrests”); see also Beck v. City\nof Pittsburgh, 89 F.3d 966, 974 (3d Cir. 1996) (noting the\npolice department’s failure to act on complaints\n“perpetuate[d] the City’s custom of acquiescing in the\nexcessive use of force by its police officers”). In light of\nthese allegations, “it is logical to assume that [the City’s]\ncontinued official tolerance of repeated misconduct\nfacilitate[d] similar unlawful actions in the future,” including\nthe search and arrest of Roman. Bielevicz, 915 F.2d at 851. It\nfollows that he has adequately pled a municipal custom and\nproximate causation under § 1983.\n We reach the same conclusion with respect to\nRoman’s failure-to-train, failure-to-supervise, and failure-to-\ndiscipline claims. To start, the Star Ledger article includes a\nstatement on police training from James Stewart, Jr., the head\nof Newark’s police union. He conceded the “last training [he]\nreceived” was in 1995, when he first joined the Newark\nPolice Department. App. at 134 (internal quotation marks\nomitted). Moreover, Stewart is not some unreliable, rogue\nofficer—he is the head of the police union. Nor is his\nexperience isolated: the consent decree indicates Newark\npolice officers in general were not trained on “the\nrequirements of [the] Fourth Amendment and related law.”\nId. at 160 (discussing various Fourth Amendment doctrines\n\n\n\n\n 16\n\nthat should be included in police training, including “the\ndifference[] . . . between voluntary consent and mere\nacquiescence to police authority”). The consent decree also\ntouches on supervisory review of unlawful searches and\narrests, requiring desk lieutenants and unit commanders to\nreview “searches that appear to be without legal justification”\nand “arrests that are unsupported by probable cause.” Id. at\n161. Finally, it provides disciplinary measures for police\nofficers who engage in “unlawful . . . searches” and “false\narrests.” Id. at 192. At the pleadings stage, a fair inference is\nthat the consent decree was necessary because of Department-\nwide failures, not because one officer was last trained in\n1995.\n This is enough to prove municipal liability because the\nCity “[knew] to a moral certainty” that its officers would need\nto conduct searches. Harris, 489 U.S. at 390 n.10. Yet in at\nleast one instance it failed to provide training since 1995, see\nApp. at 134, and per the decree its training did not cover the\nbasics of the Fourth Amendment, see id. at 158-61. The City\nalso did not discipline officers for “sustained allegations of\nmisconduct,” including “prior violations” and other\n“aggravating factors.” Id. at 192-93. In view of these\ndeficiencies, one could reasonably infer that the City’s\ninaction “reflected [its] ‘deliberate indifference’” to Roman’s\nFourth Amendment rights. Bd. of Cty. Comm’rs v. Brown,\n520 U.S. 397, 409 (1997); cf. Harris, 489 U.S. at 390 n.10\n(“[C]ity policymakers know to a moral certainty that their\npolice officers will be required to arrest fleeing felons. . . .\nThus, the need to train officers in the constitutional\nlimitations on the use of deadly force . . . can be said to be ‘so\nobvious’ . . . that failure to do so could properly be\ncharacterized as ‘deliberate indifference’ to constitutional\nrights.” (internal citation omitted)). One could also infer that\nthe City’s failure to establish an adequate training program\ncontributed to the specific constitutional violations alleged in\n\n\n\n\n 17\n\nthe amended complaint. See Brown, 520 U.S. at 409-10\n(“The likelihood that the situation will recur and the\npredictability that an officer lacking specific tools to handle\nthat situation will violate citizens’ rights . . . may also support\nan inference of causation.”); cf. A.M. ex rel. J.M.K. v. Luzerne\nCty. Juvenile Detention Ctr., 372 F.3d 572, 582 (3d Cir.\n2004) (reversing the District Court’s grant of summary\njudgment in favor of a municipality because of “unrebutted\ntestimony” that its juvenile detention center “did not have an\nadequate training program”).\n We conclude that the allegations regarding Newark’s\nfailure to train, supervise, and discipline are strong enough to\nsurvive a motion to dismiss. See Am. Compl. ¶¶ 63-98.\nAmong them are: a failure to train officers on obtaining a\nsearch warrant, id. ¶ 67, and on “issuing truthful investigative\nreports,” id. ¶ 77; a failure to supervise and manage officers,\nid. ¶¶ 67-68; and a failure to discipline officers, id. ¶ 74, first\nby “refus[ing]” to create a well-run Internal Affairs\nDepartment, id. ¶ 81, and second by “inadequately\ninvestigating, if investigating at all, citizens’ complaints\nregarding illegal search and seizure, id. ¶ 84. The result was a\n“complete lack of accountability” and of “record keeping,” id.\n¶ 92, leading to a culture in which officers “knew there would\nbe no professional consequences for their action[s],” id. ¶ 94.\nAs the amended complaint alleges, it should come as no\nsurprise that these conditions led to a federal investigation.\nSee id. ¶ 89.\n The dissent’s attempt to distinguish the consent decree\nis unpersuasive. First, it misperceives the decree as\nconcerning only police interactions with “pedestrians or the\noccupants of vehicles,” not home searches. Dissenting Op. at\n7 (“The consent decree says nothing about arrests and\nsearches without consent that occur at residences . . .”). In\nfact, one concern of the decree was false arrests, see App. at\n\n\n\n\n 18\n\n158, which can occur both at home and on the street. And the\ndecree does concern home searches: it sets parameters\nofficers must follow before searching “a home based upon\nconsent.” Id. Although Reyes by no means consented to the\nsearch here, she willingly opened her apartment door only\nbecause the police had used her friend Isaksem as a Trojan\nhorse to gain entry.\n Second, the dissent believes that the consent decree\ncannot help Roman’s case because Roman was Hispanic. See\nDissenting Op. at 7 (“[T]he decree addressed police practices\nthat disparately impacted the black community. But that\nracial disparity did not apply to Roman, who was Hispanic.”).\nTo the contrary, the consent decree includes an entire section\nentitled “Bias-Free Policing,” see App. at 165-67, that never\nrestricts itself to bias against the black community. Instead, it\nprovides that police officers must “operate without bias based\non any demographic category,” id. at 166 (emphasis added),\nand specifically forbids officers from discriminating based on\n“proxies for demographic category” such as “language\nability,” id. at 167. Plainly, the consent decree was meant to\nprotect all Newark residents, including Hispanic residents.\n Further, we find it difficult to square the dissent’s\nreasoning with the record evidence discussing the City’s\ntroubling practices around the time of Roman’s search and\narrest. See, e.g., id. at 134 (stating only one complaint out of\n261 filed was sustained by department investigators); id. at\n158 (prohibiting officers from relying on materially false\ninformation to justify a warrantless search); id. at 160\n(requiring police officers to be trained on “the requirements\nof [the] Fourth Amendment and related law”); id. at 161\n(mandating supervisory review of “searches that appear to be\nwithout legal justification” and “arrests that are unsupported\nby probable cause”).\n\n\n\n\n 19\n\n Unable to distinguish the consent decree outright, the\ndissent offers two narrow readings of the decree. First, it\nmaintains that the decree can speak only to the Police\nDepartment’s obligations going forward rather than shed any\nlight whatsoever on the “status quo” within the Department\nbefore federal intervention. See Dissenting Op. at 10 (stating\nthat the decree does not provide “any detail as to the status\nquo it addressed”). The dissent concedes that the DOJ\nprobably did not enter into the consent decree because it was\nimpressed with Newark’s policing practices and wanted to\nencourage the City to keep up the good work. Id. At this\nstage, we must draw not only such obvious inferences, but\nalso all reasonable ones, in favor of Roman. Thus we agree\nwith the dissent on the “clear” difference between “agreeing\nto train more” (the consent decree on its face) and “agreeing\nthat prior training was constitutionally inadequate” (the way\nin which the decree supports Roman’s claims). Id. We\nsimply believe that a reasonable inference bridges the gap in\nthis case. Indeed, no inference is needed because Roman\nmade the link explicit in the amended complaint. See Am.\nCompl. ¶ 89 (stating that the Police Department’s “deliberate\nindifference to citizens’ rights is what led to the imposition of\na [f]ederal [m]onitor program . . . .”).\n\n Second, the dissent believes that the consent decree’s\ntraining requirements, from which we can reasonably infer\ninadequate training before the decree, simply amount to\n“additional training” in, for instance, the requirements of the\nFourth Amendment. Dissenting Op. at 10. To the contrary,\nthe consent decree was meant to take the Newark Police\nDepartment back to basics: Do not lie on a warrant\napplication or to justify a warrantless search, App. at 158;\ninvestigate police activities that appear to have lacked legal\njustification, id. at 161; and at all times follow the\nrequirements of the Fourth Amendment, id. at 160.\n\n\n\n\n 20\n\n The theme of the dissent appears to be that we are\nrefashioning the amended complaint. It claims we are\nvacating the District Court’s decision based on facts and\narguments that were not presented to it. But as discussed\nabove, we are engaged in de novo review of the adequacy of\nthe amended complaint in light of documents that were before\nthe District Court and that informed its allegations. See supra\npp. 8-10. Additionally, and to repeat, the specific events\nleading up to Roman’s search and arrest are not relevant to\nthe merits of his municipal liability claim. Thus we are not\nvacating the Court’s decision for excluding these facts from\nits analysis.\n Rather, our focus is directed to Newark’s practice at\nthe time of Roman’s search and arrest. The Court had notice\nof them, as it acknowledged that Roman alleged “a ‘pattern or\npractice of constitutional violations in areas including stop[]\nand arrest practices, use of force, and theft by officers.’”\nRoman, 2017 WL 436251, at *4 (quoting Compl. ¶ 59).\nNonetheless it dismissed the complaint and amended\ncomplaint because it viewed the City as attempting to change\nits practices. Even if the record can be read that way—and\nwe doubt that8—the District Court’s rationale has the wrong\n\n\n 8\n The record does not support the Court’s inferences,\nas it tells us the DOJ’s investigation was not completed until\nJuly 2014, see App. at 137; the Government did not solicit\napplications for a federal monitor until February 2015, see id.;\nand the consent decree was not final until May 2016, see id.\nat 215. By contrast, Roman was arrested in May 2014 and\nimprisoned until December of that year. As such, it is\nplausible that Newark’s practices were ongoing when police\nofficers searched and arrested him. It is also reasonable to\ninfer that the City’s corrective measures postdated the arrest.\n\n\n\n\n 21\n\nfocus. The question is not whether some evidence can be\nviewed as supporting the City. It is whether, viewing the\npleadings and properly associated documents in the light most\nfavorable to Roman, there are claims plausible enough to\nwithstand a motion to dismiss. We think there is one—the\nmunicipal liability claim. And the Court did not have to look\nbeyond the amended complaint and supporting documents to\nglean these facts.\n\n In sum, Roman’s municipal liability claim survives\ndismissal based on the record that was before the District\nCourt. Because the Court reached the opposite conclusion,\nwe part with its holding. Thus we vacate and remand this\nportion of its decision.\n B. The District Court correctly dismissed the\n false imprisonment and malicious\n prosecution claims because they were not\n pled under § 1983.\n\n Roman alleges the Defendants are also liable for false\nimprisonment and malicious prosecution. As noted, the\nDistrict Court construed these claims as state-law claims. It\ndismissed them because Roman did not comply with the New\nJersey Tort Claims Act’s procedural requirements for\nbringing claims against public entities and public employees.\nSee N.J. Stat. Ann. § 59:8-1 et seq.\n On appeal, Roman contends the Court erred in\ndismissing his claims because they were pled under § 1983.\nThe Defendants counter that both claims were presented as\n\n\n\nHence we do not consider the City’s corrective measures to\nbe enough to defeat Roman’s allegations.\n\n\n\n\n 22\n\nstate-law tort claims. They also point out that Roman omitted\nthem from his amended complaint.9\n\n As a preliminary matter, the Defendants correctly\nobserve that false imprisonment and malicious prosecution\nare not in the amended complaint. Hence we must first\ndecide if Roman has waived his right to challenge their\ndismissal on appeal. If we conclude that waiver does not\napply, we then determine if the District Court correctly\nconstrued them as state-law tort claims.\n We have not applied a strict rule in favor of waiver in\nthis context. Instead, we have allowed “plaintiffs to appeal\ndismissals despite amended pleadings that omit the dismissed\nclaim[,] provided repleading the particular cause of action\nwould have been futile.” United States ex rel. Atkinson v. Pa.\nShipbuilding Co., 473 F.3d 506, 516 (3d Cir. 2007) (emphasis\nin original) (footnote omitted). “Repleading is futile when\nthe dismissal was ‘on the merits.’ A dismissal is on the\nmerits when it is with prejudice or based on some legal\nbarrier other than want of specificity or particularity.” Id. If\na court is uncertain, “doubt[] should be resolved against the\nparty asserting waiver.” Id. at 517 (emphasis in original).\n\n 9\n At oral argument, Roman’s counsel stated the false\nimprisonment claim was repled in Count 13 of the amended\ncomplaint even though that count alleges “conspiracy to\ncommit unlawful imprisonment . . . [in violation of] 42\nU.S.C. § 1985.” App. at 278 (emphasis added); see Audio\nRecording of Oral Argument held June 12, 2018 at 11:39 to\n12:06 (http://www2.ca3.uscourts.gov/oralargument/audio/17-\n2302TheEstateofAdrianoRomanJrvCityofNewarketal.mp3).\nWe do not consider this contention, as it was raised for the\nfirst time at oral argument and thus is waived. See In re\nGrand Jury, 635 F.3d 101, 105 n.4 (3d Cir. 2011).\n\n\n\n\n 23\n\n Here the District Court analyzed both claims on legal\ngrounds. It observed that they were based on the New Jersey\nTort Claims Act, which allows individuals to bring tort claims\nagainst public entities and employees after complying with\ncertain procedural and notice requirements, see Tripo v.\nRobert Wood Johnson Med. Ctr., 845 F. Supp. 2d 621, 626-\n27 (D.N.J. 2012) (summarizing the Act’s procedures for suing\na public entity or employee). It concluded Roman did not\nfollow these requirements and thus dismissed the claims.\n Although the Court was guided by procedural\nconcerns, its dismissal was on the merits. The Tort Claims\nAct bars claims against public entities and employees if a\nplaintiff waits more than two years to file a “notice of claim.”\nSee N.J. Stat. Ann. § 59:8-8(b). The two-year mark is\nmeasured from the day the claim accrues (i.e., the day on\nwhich the public entity or employee allegedly harmed the\nplaintiff). In our case, because Roman’s claims accrued in\nMay 2014, he had until May 2016 to file a notice of claim.\nAs the Court noted, however, he did not file any type of\nnotice during the two-year period. See Roman, 2017 WL\n436251, at *6 (observing that, as of January 31, 2017, the date\non which the Court dismissed the complaint, Roman had not\nfiled a notice). Thus Roman’s procedural error morphed into\na dismissal on the merits, see N.J. Stat. Ann. § 59:8-8(b)\n(“The claimant shall be forever barred from recovering\nagainst a public entity or public employee if . . . [t]wo years\nhave elapsed since the accrual of the claim.”), and he may\nappeal the District Court’s decision on his false imprisonment\nand malicious prosecution claims, see Atkinson, 473 F.3d at\n516-17.\n In light of this conclusion, we must focus on the\npleadings and decide if Roman’s claims are based on § 1983.\nIf we look to the complaint, it suggests both false\nimprisonment and malicious prosecution are state-law tort\n\n\n\n\n 24\n\nclaims. It never identifies them as § 1983 or federal claims.\nRather, it presents them generically, following a series of\nother state-law tort claims. See, e.g., App. at 44 (“intentional\ninfliction of emotional distress”); id. at 46 (“negligent\ninfliction of emotional distress”); id. at 47 (“assault and\nbattery”); id. at 49 (“unlawful imprisonment”); id. at 51\n(“malicious prosecution”). This indicates to us that Roman\npled both claims as state-law claims, not federal claims.\nWhile the unlawful (i.e., false) imprisonment claim does note\nthat the Defendants “restrict[ed] [Roman’s] constitutionally\nguaranteed rights of liberty and freedom of movement,” it is\nsilent as to whether it refers to the United States or New\nJersey Constitution. Compl. ¶ 114. This is too facile to\nimply the former when but a few identifying words would do.\nThe default is New Jersey law, which defines false\nimprisonment as “an[y] unlawful restraint that interferes with\na victim’s liberty” and requires “[n]o further wrongful\npurpose” for a prima facie showing. State v. Savage, 799\nA.2d 477, 494 (N.J. 2009).\n Accordingly, the District Court correctly construed the\nfalse imprisonment and malicious prosecution claims as state-\nlaw tort claims, and we affirm this portion of its holding.10\n C. The doctrines of res judicata, collateral\n estoppel, and judicial estoppel do not require\n us to dismiss Roman’s § 1983 claims.\n Finally, the Defendants invoke the doctrines of res\njudicata, collateral estoppel, and judicial estoppel. According\n\n\n 10\n We also affirm the dismissal of Roman’s unlawful-\nsearch claims because they were not adequately pled. We do\nnot opine on whether a plaintiff may allege joint and several\nliability in connection with an unlawful-search claim.\n\n\n\n\n 25\n\nto them, each doctrine compels us to dismiss Roman’s § 1983\nclaims.\n\n We start with res judicata. The Defendants contend it\nbars Roman’s claims because “the criminal matter and the\nsuppression hearing were based on the exact same facts” as\nthose alleged in Roman’s pleadings. Defendants’ Br. at 64.\nIn their view, criminal proceedings are enough to preclude a\ncivil suit seeking damages under § 1983.\n\n We disagree. “A party seeking to invoke res judicata\nmust establish three elements: (1) a final judgment on the\nmerits in a prior suit involving (2) the same parties or their\nprivies and (3) a subsequent suit based on the same cause of\naction.” Duhaney v. Att’y Gen., 621 F.3d 340, 347 (3d Cir.\n2010) (internal quotation marks omitted). Roman’s suit is not\nbased on the same cause of action as the criminal complaint\nand suppression hearing. Nor are his current claims of the\ntype “that could have been brought” in the earlier criminal\nproceeding. Id. (internal quotation marks omitted); see also\nHelvering v. Mitchell, 303 U.S. 391, 397 (1938) (“The\ndifference in degree of the burden of proof in criminal and\ncivil cases precludes application of the doctrine of res\njudicata.”). New Jersey initiated the criminal case. Roman\nwas not at liberty to assert any claims except for defenses\nagainst the prosecution’s case-in-chief. See Leather v. Eyck,\n180 F.3d 420, 425 (2d Cir. 1999) (“[B]ecause the nature of\nthe prior state[-]court proceeding was such that [the\nAppellant] could not have sought damages for his alleged\nconstitutional injuries (while defending himself on [a\ncriminal] charge . . . ), res judicata does not bar his federal §\n1983 suit for damages.”). Moreover, he was not free to raise\nhis § 1983 claims in the same criminal case; indeed, he could\nnot bring them until the criminal proceeding concluded. See\nHeck v. Humphrey, 512 U.S. 477, 486 (1994) (“[T]he . . .\nprinciple that civil tort actions are not appropriate vehicles for\n\n\n\n\n 26\n\nchallenging the validity of outstanding criminal judgments\napplies to § 1983 damages actions that necessarily require the\nplaintiff to prove the unlawfulness of his conviction or\nconfinement. . . .”). Accordingly, res judicata does not bar\nRoman’s claims.\n\n Moving on to collateral estoppel, the Defendants argue\nit (1) absolves Officer Mendes of liability because the\nSuperior Court made a factual finding that Roman possessed\nthe contraband that was seized from the apartment, (2)\nabsolves Sergeant Joyce Hill because nothing in the Superior\nCourt’s transcript indicates she was present for the search and\narrest, and (3) absolves the other named defendants because\nthe Superior Court’s transcript suggests they only handled the\ncontraband. According to the Defendants, the Superior Court\ndecided all of these issues in their favor during the\nsuppression hearing. See Bd. of Trs. of Trucking Emps. of N.\nJersey Welfare Fund, Inc. v. Centra, 983 F.2d 495, 505 (3d\nCir. 1992) (stating a party is collaterally estopped from\nlitigating a specific issue if, among other things, “[an]\nidentical issue was decided in a prior adjudication”). Again\nwe disagree. Contrary to the Defendants’ assertions, the\nSuperior Court never decided any of these issues during the\nsuppression hearing. While it did find that Roman had a\npossessory interest in the apartment, that is not enough for us\nto conclude that he had actual or constructive possession over\nthe contraband. Collateral estoppel is not appropriate in this\ncontext.\n Last, the Defendants assert that judicial estoppel\nprecludes Roman’s claims because he admitted that (1) drugs\nwere found in the apartment, (2) he had a possessory interest\nin the apartment, (3) Officer Mendes was the only officer who\ninitiated the prosecution, and (4) the remaining officers only\nhandled the contraband and had no other roles. They insist\nthese concessions “are sufficient to establish that [Roman’s]\n\n\n\n\n 27\n\narrest and prosecution arise out of his possession of\nincriminating evidence[.]” Defendants’ Br. at 65. As noted,\n“[j]udicial estoppel, sometimes called the ‘doctrine against\nthe assertion of inconsistent positions,’ is a judge-made\ndoctrine that . . . prevent[s] a litigant from asserting a position\ninconsistent with one that []he has previously asserted . . . in a\nprevious proceeding.” Ryan Operations G.P., 81 F.3d at 358.\nThis doctrine is not in play here, as Roman never stipulated\nthat Officer Mendes was the only officer to bring the\nprosecution or that the remaining officers only handled the\ncontraband. While the Court found that Roman had a\npossessory interest in the apartment, that interest (we repeat)\nis not enough to establish that he possessed the contraband.\nAccordingly, judicial estoppel does not require us to dismiss\nRoman’s claims.\n * * * * *\n Roman has sufficiently alleged a municipal liability\nclaim against the City of Newark under § 1983. He cites\nvarious examples of inadequate police training, poor police\ndiscipline, and unheeded citizen complaints. He tells us\ncertain police officers did not receive training for over 20\nyears, and their training did not cover the basic requirements\nof the Fourth Amendment. In his pleadings, he states the\nNewark Police Department did not discipline officers who\nengaged in police misconduct, Am. Compl. ¶¶ 84-86,\nincluding unlawful searches and false arrests, App. at 134.\nHe also notes the public filed formal complaints about\nimproper searches and false arrests that were disregarded\nalmost wholesale. Id. These alleged practices were ongoing\nwhen Roman’s search and arrest occurred, and the City had\nnotice of them at that time. While the proof developed to\nsupport these allegations may or may not be persuasive to a\nfinder of fact, they are enough to survive dismissal at this\nstage. Based on this conclusion, we part with the District\n\n\n\n\n 28\n\nCourt’s holding that Roman failed to state a § 1983 claim\nagainst the City. Though we affirm otherwise, we vacate and\nremand its decision on municipal liability.\n\n\n\n\n 29\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: *The ESTATE OF Adriano ROMAN, Jr., Appellant v. CITY OF NEWARK; City of Newark Police Department; Anthony Campos, Chief of Police; Rodger C. Mendes; Albano Ferreira ; Onofre H. Cabezas; Joseph Cueto; FNU Ressureicao; FNU Golpe; Joyce Hill, Individually and in Their Capacity as Police Officers; John Does 1-20, as Fictitious Names for Presently Unknown Agents Member Commissioners and Chiefs *(Amended Pursuant to Clerk's Order Dated 1/25/2018)\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-29\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n ________________\\n No. 17-2302\\n ________________\\n\\n *THE ESTATE OF ADRIANO ROMAN, JR.,\\n Appellant\\n\\n v.\\n\\n CITY OF NEWARK;\\n CITY OF NEWARK POLICE DEPARTMENT;\\n ANTHONY CAMPOS, Chief of Police;\\n RODGER C. MENDES;\\n ALBANO FERREIRA; ONOFRE H. CABEZAS;\\n JOSEPH CUETO;\\n FNU RESSUREICAO; FNU GOLPE; JOYCE HILL,\\n Individually and in their capacity as police officers;\\nJOHN DOES 1-20, as fictitious names for presently unknown\\n agents member commissioners and chiefs\\n\\n *(Amended pursuant to Clerk’s Order dated 1/25/18)\\n ________________\\n Appeal from the United States District Court\\n for the District of New Jersey\\n (D.C. Civil Action No. 2-16-cv-01110)\\n District Judge: Honorable Susan D. Wigenton\\n ________________\\n\\n Argued June 12, 2018\\n\\n Before: AMBRO, JORDAN, and\\n HARDIMAN, Circuit Judges\\n\\n (Opinion filed: January 29, 2019)\\n\\nJustin D. Santagata (Argued)\\nKaufman Semeraro & Leibman\\nTwo Executive Drive, Suite 530\\nFort Lee, NJ 07024\\n\\n Counsel for Appellant\\n\\nKenyatta K. Stewart, Acting Corporation Counsel\\nWilson D. Antoine (Argued)\\nCity of Newark–Department of Law\\n920 Broad Street, Room 316\\nNewark, NJ 07102\\n\\n Counsel for Appellees\\n\\n ________________\\n OPINION OF THE COURT\\n ________________\\n\\nAMBRO, Circuit Judge\\n\\n Newark police officers forcibly entered and searched\\nthe apartment of Adriano Roman’s girlfriend. App. at 386,\\n391, 459, 486. They arrested Roman, who was present in the\\napartment, after they found drugs in a common area that was\\nshared by multiple tenants. Id. at 399, 479. Though he was\\nimprisoned for over six months and indicted for various drug\\n\\n\\n\\n\\n 2\\n\\noffenses, the New Jersey Superior Court found the search to\\nbe unlawful and the charges were dropped.\\n\\n Roman now brings claims against the City of Newark\\n(which includes its Police Department) and various police\\nofficers under 42 U.S.C. § 1983 (which gives a federal\\nremedy against state officials who, acting under color of state\\nlaw, deprive “any citizen of the United States . . . of any\\nrights, privileges, or immunities secured by the [U.S.]\\nConstitution and laws”) and New Jersey tort law. He alleges\\nthe City had a pattern or practice of constitutional violations\\nand failed to train, supervise, and discipline its officers. He\\nalso pleads an unlawful search claim against the officers and\\ncontends they are liable for false imprisonment and malicious\\nprosecution. The District Court dismissed all of the claims\\nbecause they were inadequately pled. It also held the City did\\nnot have an ongoing practice of unconstitutional searches and\\narrests.\\n While most of Roman’s claims do not withstand\\ndismissal, his § 1983 claims against the City do. He has\\nadequately alleged that its Police Department had a custom of\\nwarrantless searches and false arrests. He also sufficiently\\npled that the Department failed to train, supervise, and\\ndiscipline its officers, specifically with respect to “the\\nrequirements of [the] Fourth Amendment and related law.”\\nApp. at 160. Because Roman has stated a plausible claim\\nagainst the City, we vacate and remand the District Court’s\\nholding on municipal liability. We affirm in all other\\nrespects.\\n\\n\\n\\n\\n 3\\n\\nI. Background1\\n On May 2, 2014, Roman and his girlfriend Tiffany\\nReyes were watching a movie in her apartment’s bedroom.\\nApp. at 386, 389, 395. Unbeknownst to them, four Newark\\npolice officers had set up surveillance outside of her building\\nbecause of complaints about narcotics activity. Id. at 338.\\nThe officers heard an argument between a man and a woman,\\nid. at 340-42, and decided to enter Reyes’ apartment without\\na warrant, id. at 491.\\n After they stepped inside the building, they discovered\\nthat the front door of the apartment was locked. They also\\n\\n 1\\n As noted below, we must, while reviewing a ruling\\non a motion to dismiss, view the facts in the light most\\nfavorable to the plaintiff. Accordingly, without judging the\\nfacts, we recount them as set out in the amended complaint\\nand the transcript of the suppression hearing referred to\\nbelow. Although Roman did not attach the transcript to the\\namended complaint, the Defendants included it in their\\nmotion to dismiss and told the District Court it was “capable\\nof judicial notice” and “integral to the [c]omplaint.” App. at\\n130. Thus we consider it at this stage.\\n\\n In any event, both the amended complaint and\\ntranscript note that the officers forcibly entered the apartment,\\nassaulted Roman, and falsely charged him with possession of\\na controlled substance. See Am. Compl. ¶¶ 17, 22, 28. Any\\nminor differences in the two documents do not affect our\\nanalysis of his municipal liability claim. See infra Section\\nIII.A (explaining that the events leading up to Roman’s\\nsearch and arrest are not relevant to the merits of his\\nmunicipal liability claim).\\n\\n\\n\\n\\n 4\\n\\nnoticed Melissa Isaksem, Reyes’ friend, walking inside the\\nbuilding. Id. at 417-20. They stopped and questioned her.\\nId. at 417, 419. When she told them she was visiting Reyes,\\nid. at 419, they ordered her to knock on the apartment door\\nfor them and threatened to arrest her if she did not comply, id.\\nat 419-20. Isaksem led them to the apartment and stood\\ndirectly in front of the peephole. Id. at 421. The police stood\\nto her left, presumably out of the peephole’s range. Id. An\\nofficer knocked on her behalf. Id. Reyes asked who was at\\nthe door, and Isaksem announced her presence. Id.\\n Reyes opened the door, expecting to see only Isaksem.\\nId. at 386, 400, 501. Instead, several officers rushed inside.\\nId. at 387, 400, 501. They handcuffed Roman, Reyes, and\\nIsaksem, then demanded Roman “call someone to bring drugs\\nto the [apartment].” Am. Compl. ¶ 30 (internal quotation\\nmarks omitted). If he did, they assured him they would\\n“‘make a deal’ and ‘let him go.’” Id. Roman refused the\\nofficers’ demands, id. ¶ 33, and the police searched the\\napartment. Eventually they found drugs in a common-area\\nspace that was shared by multiple tenants and located in the\\nback of the apartment. App. at 399, 479. After seizing the\\ncontraband, they yelled, “[W]e got you, motherfucker[;] . . .\\nyou’re fucked now.” Id. at 427. Officer Rodger Mendes\\nwalked back to Roman, “flipped him . . . on[]to his stomach\\n. . . , put his knee in his neck[,] and . . . said he was going to\\nget raped [in prison].” Id. at 428. Another officer informed\\nRoman’s father, who lived next door and observed parts of\\nthe search, that his son “would go away for a long time.” Id.\\nat 454.\\n Roman was arrested and imprisoned on the same night.\\nThe officers filed a criminal complaint against him for\\npossession of, as well as intent to distribute, heroin and\\ncocaine. A New Jersey grand jury returned a six-count\\nindictment against him for the same offenses.\\n\\n\\n\\n\\n 5\\n\\n In response, Roman moved to suppress the evidence\\nseized from the apartment. He argued the search was invalid\\nunder the Fourth Amendment because the contraband was not\\nin plain view and thus a warrant was needed. The New Jersey\\nSuperior Court agreed. It concluded the plain-view exception\\ndid not apply and suppressed the contraband.\\n The State of New Jersey did not appeal the ruling and\\ninstead moved to dismiss the case. The Superior Court\\ngranted its motion in December 2014 and issued a final\\njudgment of dismissal. Roman was released from prison\\nduring the same month.\\n Approximately a year later, Roman brought § 1983\\nand state-law tort claims against the City of Newark and\\nvarious police officers (for simplicity, the City and the\\nofficers are jointly referred to as the “Defendants”). Among\\nother things, he alleged the City had a custom or policy of\\nunconstitutional searches, inadequate training, and poor\\nsupervision and discipline.2 He also claimed the officers\\nunlawfully searched his apartment and were liable for the\\ntorts of unlawful imprisonment and malicious prosecution.3\\n\\n\\n 2\\n Roman’s amended complaint also included\\nallegations of discrimination of national origin in violation of\\n42 U.S.C. § 1983, civil conspiracy in violation of 42 U.S.C.\\n§ 1985, conspiracy to commit an unlawful search in violation\\nof the New Jersey Constitution and 42 U.S.C. § 1985, and\\nconspiracy to commit unlawful imprisonment in violation of\\n42 U.S.C. § 1985. We do not address these claims, as Roman\\ndoes not press them on appeal.\\n 3\\n We construe Roman’s claim for unlawful\\nimprisonment as a claim for false imprisonment. Although\\n\\n\\n\\n\\n 6\\n\\n The Defendants responded with a motion to dismiss.\\nThe District Court sided with them, dismissing the complaint\\nin its entirety. It first addressed Roman’s claim against the\\nCity and concluded the complaint “fail[ed] to plead . . . a\\ncustom or policy” of unlawful searches and a failure to train\\nor supervise officers. Roman v. City of Newark, Civil Action\\nNo. 16-1110-SDW-LDW, 2017 WL 436251, at *4 (D.N.J.\\nJan. 30, 2017). Although the complaint alleged “a pattern or\\npractice of constitutional violations in areas including stop[]\\nand arrest practices, use of force, and theft by officers,” the\\nCourt did not consider that sufficient to state a claim. Id.\\n(internal quotation marks omitted) (quoting Compl. ¶ 59).\\nInstead, it viewed those practices as predating Roman’s arrest\\nand observed that “the imposition of a [f]ederal [m]onitor\\nindicate[d] [the City’s] attempts to change any wrongful\\npolicies or practices.” Id.\\n The Court also held the unlawful search claim was\\ninadequately pled, as Roman did not “explain which\\n[Defendant(s)] committed the allegedly wrongful acts” during\\nthe search and arrest. Id. Turning to the false imprisonment\\nand malicious prosecution claims, it construed them as state-\\nlaw claims and noted that plaintiffs must comply with the\\n\\nNew Jersey lacks a cause of action for “unlawful\\nimprisonment,” it has codified the elements of a false\\nimprisonment claim. See N.J. Stat. Ann. § 2C:13-3; Mallery\\nv. Erie R. Co., 92 A. 371, 371 (N.J. 1914) (“This appeal\\nbrings up a judgment recovered by the respondent in an\\naction for false imprisonment. The declaration described\\nthe unlawful imprisonment. . . .”); see also 8 American Law\\nof Torts § 27:1 (“False imprisonment, sometimes called\\ncriminal restraint or unlawful imprisonment, is committed\\nwhen a defendant so restrains another person as to interfere\\nsubstantially with his liberty.”).\\n\\n\\n\\n\\n 7\\n\\nNew Jersey Tort Claims Act before bringing them against\\npublic entities. See N.J. Stat. Ann. § 59:8-1 et seq. Because\\nthe “[c]omplaint nowhere allege[d]” Roman complied with\\nthe Act’s procedures, the Court dismissed those claims as\\nwell. Roman, 2017 WL 436251, at *6.\\n\\n The Court’s dismissal was without prejudice, and it\\ngranted Roman leave to amend. He did so by omitting his\\ntort claims and retaining his other allegations in almost\\nidentical form. The Court dismissed his amended complaint\\nand reaffirmed its ruling on reconsideration. This appeal\\nfollowed.4\\nII. Jurisdiction and Standard of Review\\n The District Court had federal-question and\\nsupplemental jurisdiction per 28 U.S.C. §§ 1331 and 1367(a),\\nrespectively, and we have jurisdiction over its final orders\\nunder 28 U.S.C. § 1291.\\n We review de novo its dismissal of a complaint under\\nFederal Rule of Civil Procedure 12(b)(6). See Phillips v.\\nCounty of Allegheny, 515 F.3d 224, 230 (3d Cir. 2008).\\nWhen conducting our review, “we accept all factual\\nallegations as true [and] construe the complaint in the light\\nmost favorable to the plaintiff.” Warren Gen. Hosp. v.\\nAmgen Inc., 643 F.3d 77, 84 (3d Cir. 2011) (internal\\nquotation marks omitted). However, “we are not compelled\\nto accept unsupported conclusions and unwarranted\\ninferences . . . or a legal conclusion couched as a factual\\nallegation[.]” Baraka v. McGreevey, 481 F.3d 187, 195 (3d\\n\\n\\n 4\\n Roman passed away while this appeal was pending,\\nand his estate brings the claims on his behalf. We do not\\ndistinguish between Roman and his estate in this opinion.\\n\\n\\n\\n\\n 8\\n\\nCir. 2007) (internal quotation marks omitted) (internal\\ncitation omitted).\\n\\nIII. Discussion\\n A. Roman sufficiently pled a municipal liability\\n claim against Newark.\\n\\n As noted, Roman alleges the City is liable under\\n§ 1983 because it “engaged in a pattern or practice of\\nconstitutional violations,” “failed to properly train and/or\\nsupervise” its police force, and “failed to properly and\\nadequately control and discipline” its police officers.5 Am.\\nCompl. ¶¶ 68, 73-74. Before discussing the merits of his\\nclaims, Roman directs our attention to the types of documents\\nwe may consider on a motion to dismiss. He contends we\\nmay review three sources that were provided to the District\\nCourt: an article published in the Newark Star Ledger (the\\n“Star Ledger article”), a press release issued by the U.S.\\nAttorney’s Office (the “press release”), and a consent decree\\nbetween the United States and the City of Newark (the\\n“consent decree”). The Star Ledger article and press release\\nwere referenced in the amended complaint, see id. ¶¶ 68-69\\n(including hyperlinks to both), but the consent decree was\\nattached to the Defendants’ motion to dismiss, see App. at\\n129. Roman also asks us to look at one other document: the\\nDepartment of Justice’s Report on the investigation of the\\nNewark Police Department (the “DOJ Report”). Although he\\n\\n 5\\n Roman brings his municipal liability claims under\\n§ 1983 and the New Jersey Civil Rights Act, N.J. Stat. Ann.\\n§ 10:6-1 et seq. Because the latter “is interpreted analogously\\nto . . . § 1983,” we consider his New Jersey Civil Rights Act\\nclaims along with his § 1983 claim. Coles v. Carlini, 162 F.\\nSupp. 3d 380, 404 (D.N.J. 2015).\\n\\n\\n\\n\\n 9\\n\\nacknowledges the DOJ Report was never provided to the\\nDistrict Court, he now claims it is integral to the pleadings.\\n\\n Though the Defendants dispute that we may consider\\nthe DOJ Report, they add that we also cannot consider the\\nconsent decree because “no relevant provisions of [it] . . .\\nwere ever cited . . . to the District Court” and it is\\ninadmissible settlement material. Defendants’ Br. at 42.\\nThey assert as well, without any citation to the record, that\\nRoman may not rely on the decree because he asked the\\nDistrict Court to confine its analysis to the pleadings.\\n We disagree with the Defendants’ view of the consent\\ndecree. Although we examine the “complaint, exhibits\\nattached to the complaint, [and] matters of public record,”\\nMayer v. Belichick, 605 F.3d 223, 230 (3d Cir. 2010), we can\\nalso consider documents “that a defendant attaches as an\\nexhibit to a motion to dismiss,” Pension Benefits Guar. Corp.\\nv. White Consol. Indus., Inc., 998 F.2d 1192, 1196 (3d Cir.\\n1993), if they are “undisputedly authentic” and “the\\n[plaintiff’s] claims are based [on them],” Mayer, 605 F.3d at\\n230. That holding extends to settlement material because\\nplaintiffs “need not provide admissible proof at th[e] [motion-\\nto-dismiss] stage.” In re OSG Sec. Litig., 12 F. Supp. 3d 619,\\n622 (S.D.N.Y. 2014); see also In re MyFord Touch Consumer\\nLitig., 46 F. Supp. 3d 936, 961 n.5 (N.D. Cal. 2014) (same).\\nMoreover, the Supreme Court has been clear about the scope\\nof our review, stating we “must consider the complaint in its\\nentirety, as well as other sources [we] ordinarily examine\\nwhen ruling on . . . motions to dismiss, in particular,\\ndocuments incorporated into the complaint by reference, and\\nmatters of which a court may take judicial notice.” Tellabs,\\nInc. v. Makor Issues & Rights, Ltd., 551 U.S. 308, 322 (2007)\\n(emphasis added).\\n\\n\\n\\n\\n 10\\n\\n Here, although the consent decree was not attached to\\nRoman’s amended complaint, we are free to review its\\ncontents for three reasons.6 First, the Defendants attached the\\ndecree to their motion to dismiss and affirmed that it is\\n“capable of judicial notice” as an indisputably authentic\\ngovernment document. App. at 129. Second, contrary to the\\ndissent’s assertion, the Defendants themselves argued (and\\ncorrectly) before the District Court that Roman’s claims were\\nbased on the consent decree. Compare Dissenting Op. at 5\\n(“What is crucial is whether Roman’s complaint was ‘based’\\non the consent decree.”), with App. at 129 (filing from\\nDefendants characterizing the consent decree as “integral to\\nthe Complaint”). Third, the amended complaint cited, and the\\nDistrict Court discussed, the DOJ investigation and federal\\nmonitor that eventually led to the consent decree. See\\nRoman, 2017 WL 436251, at *4; see also Am. Compl. ¶¶ 68-\\n71. Thus it was especially important for the Court to have\\nconsidered the decree as well, given that it provides essential\\ncontext to Roman’s claims. That it did not was an abuse of\\ndiscretion.\\n\\n That said, we may not consider the DOJ Report at this\\nstage because it was not provided to the District Court in the\\nfirst instance by any party. Nor is it apparent that the Court\\nconsidered it sua sponte. See United States ex rel. Wilkins v.\\n\\n 6\\n Though the Defendants and our dissenting colleague\\ndo not challenge the Star Ledger article or the press release,\\nwe note that we consider them because they are referenced in\\nthe amended complaint. See Tellabs, 551 U.S. at 322. As\\nJudge Jordan explains in his concurrence, however, Roman\\ndoes not need either document or the suppression hearing\\ntranscript to state a municipal liability claim; the consent\\ndecree gives his allegations enough plausibility to survive\\ndismissal.\\n\\n\\n\\n\\n 11\\n\\nUnited Health Grp., Inc., 659 F.3d 295, 302 (3d Cir. 2011)\\n(“Though we do not doubt the authenticity of\\nthese documents, nevertheless we will not consider them\\nbecause the parties did not present them to the District Court\\nand we do not find any indication in the record that the Court\\nconsidered them on its own initiative.”). Hence it cannot\\ncarry any weight in our analysis.\\n Turning to the amended complaint, Roman claims the\\nCity is liable for his unlawful search because it “failed to train\\nits officers in the use of search and seizure techniques,\\nprobable cause, and/or methods to properly obtain a search\\nwarrant.” Am. Compl. ¶ 95. He alleges the Newark Police\\nDepartment “engaged in a pattern or practice of constitutional\\nviolations” and asserts the Department of Justice appointed a\\nfederal monitor to oversee the reforms to which the City\\nconsented. Id. ¶ 68. His allegations also touch on the City’s\\nfailure to “control and discipline” its police force, id. ¶ 74,\\nand failure to “investigate . . . instances of . . . police\\nmisconduct,” id. ¶ 81. He characterizes the City’s practices in\\nthese areas as “tantamount to a[n] [unconstitutional] custom\\nand/or policy,” id. ¶ 82, thus indicating its “deliberate\\nindifference to [its citizens’ constitutional] rights,” id. ¶ 83.\\n The Defendants respond that Roman has failed to\\nallege a municipal liability claim, as no part of the Star\\nLedger article, press release, or consent decree references the\\ntypes of constitutional violations pled in the amended\\ncomplaint. They also contend the City had no notice “of any\\npattern of constitutional violations with respect to forced\\nentry and searches of homes.” Defendants’ Br. at 50.\\n To plead a municipal liability claim, a plaintiff must\\nallege that “a [local] government’s policy or custom . . .\\ninflict[ed] the injury” in question. Monell v. Dep’t of Soc.\\nServs., 436 U.S. 658, 694 (1978). “Policy is made when a\\n\\n\\n\\n\\n 12\\n\\ndecisionmaker possess[ing] final authority to establish\\nmunicipal policy with respect to the action issues an official\\nproclamation, policy, or edict.” Andrews v. City of\\nPhiladelphia, 895 F.2d 1469, 1480 (3d Cir. 1990) (alteration\\nin original) (internal quotation marks omitted). “Custom, on\\nthe other hand, can be proven by showing that a given course\\nof conduct, although not specifically endorsed or authorized\\nby law, is so well-settled and permanent as virtually to\\nconstitute law.” Bielevicz v. Dubinon, 915 F.2d 845, 850 (3d\\nCir. 1990) (Becker, J.); see also Brown v. Muhlenberg Twp.,\\n269 F.3d 205, 215 (3d Cir. 2001) (“A custom . . . must have\\nthe force of law by virtue of the persistent practices of state\\n[or municipal] officials.” (internal quotation marks omitted)).\\n Although a policy or custom is necessary to plead a\\nmunicipal claim, it is not sufficient to survive a motion to\\ndismiss. A plaintiff must also allege that the policy or custom\\nwas the “proximate cause” of his injuries. See Kneipp v.\\nTedder, 95 F.3d 1199, 1213 (3d Cir. 1996). He may do so by\\ndemonstrating an “affirmative link” between the policy or\\ncustom and the particular constitutional violation he alleges.\\nBielevicz, 915 F.2d at 850 (internal quotation marks omitted).\\nThis is done for a custom if Roman demonstrates that Newark\\nhad knowledge of “similar unlawful conduct in the past, . . .\\nfailed to take precautions against future violations, and that\\n[its] failure, at least in part, led to [his] injury.” Id. at 851.\\nDespite these requirements, Roman does not need to identify\\na responsible decisionmaker in his pleadings. See id. at 850.\\nNor is he required to prove that the custom had the City’s\\nformal approval. See Anela v. City of Wildwood, 790 F.2d\\n1063, 1067 (3d Cir. 1986).\\n The pleading requirements are different for failure-to-\\ntrain claims because a plaintiff need not allege an\\nunconstitutional policy. See Reitz v. County of Bucks, 125\\nF.3d 139, 145 (3d Cir. 1997) (“[I]n the absence of an\\n\\n\\n\\n\\n 13\\n\\nunconstitutional policy, a municipality’s failure to properly\\ntrain its employees and officers can create an actionable\\nviolation . . . under § 1983.”). Instead, he must demonstrate\\nthat a city’s failure to train its employees “reflects a deliberate\\nor conscious choice.” Brown, 269 F.3d at 215 (internal\\nquotation marks omitted). For claims involving police\\nofficers, the Supreme Court has held that the failure to train\\n“serve[s] as [a] basis for § 1983 liability only where [it] . . .\\namounts to deliberate indifference to the rights of persons\\nwith whom the police come into contact.” City of Canton v.\\nHarris, 489 U.S. 378, 388 (1989) (footnote omitted). A\\nplaintiff sufficiently pleads deliberate indifference by\\nshowing that “(1) municipal policymakers know that\\nemployees will confront a particular situation[,] (2) the\\nsituation involves a difficult choice or a history of employees\\nmishandling[,] and (3) the wrong choice by an employee will\\nfrequently cause deprivation of constitutional rights.” Doe v.\\nLuzerne County, 660 F.3d 169, 180 (3d Cir. 2011) (internal\\nquotation marks omitted) (quoting Carter v. City of\\nPhiladelphia, 181 F.3d 339, 357 (3d Cir. 1999)).\\n\\n In view of this case law, Roman has not pled a\\nmunicipal policy, as his amended complaint fails to refer to\\n“an official proclamation, policy, or [an] edict.” Andrews,\\n895 F.2d at 1480. However, he has sufficiently alleged a\\ncustom of warrantless or nonconsensual searches. He has\\nalso adequately pled that the City failed to train, supervise,\\nand discipline its police officers.7\\n\\n\\n 7\\n We consider allegations of failure to train, supervise,\\nand discipline together because they fall under the same\\nspecies of municipal liability. See Rosalie Berger Levinson,\\nWho Will Supervise the Supervisors? Establishing Liability\\nfor Failure to Train, Supervise, or Discipline in a Post-\\n\\n\\n\\n\\n 14\\n\\n We start with Roman’s allegations on municipal\\ncustom. He asserts the City had “a pattern or practice of\\nconstitutional violations in areas including . . . arrest\\npractices.” App. at 137. He further contends it had notice of\\nthis practice, as it received “complaints against officers\\naccused of . . . conducting improper searches and false\\narrests.” Id. at 134. The amended complaint, along with the\\npress release and Star Ledger article, note that Newark was\\nunder the supervision of a federal monitor after Roman’s\\narrest. Am. Compl. ¶ 68; App. at 133, 137. According to the\\npress release, the monitor would oversee reforms in several\\nareas, including searches, arrests, and the intake and\\ninvestigation of misconduct complaints. App. at 137.\\n The consent decree echoes these points. It covers the\\nsame type of conduct Roman alleges, as it “prohibit[s]\\nofficers from relying on information known to be materially\\nfalse or incorrect to justify a warrantless search . . . [or to]\\neffect[] an arrest.” Id. at 158; see also id. at 163 (mandating\\nofficers to collect data on consent, the type of search, and “a\\nbrief description of the facts creating probable cause”). The\\ndecree also requires the Police Department to investigate\\npolice misconduct, see generally id. at 184-92, with special\\nemphasis on allegations of criminal misconduct, false arrest,\\nplanting evidence, and unlawful searches, see id. at 150, 186.\\n While the consent decree was not in place during\\nRoman’s search and arrest, we may fairly infer that the\\nproblems that led to it were occurring during the time of his\\nallegations and for some time before that. See id. at 133-34\\n(noting the investigation that resulted in the consent decree\\nand federal supervision began in May 2011 and ended in July\\n2014). With this mind, the decree fortifies Roman’s\\n\\nIqbal/Connick World, 47 Harv. C.R.-C.L. L. Rev. 273, 280\\n(2012).\\n\\n\\n\\n\\n 15\\n\\nallegations of unlawful custom because it acknowledges “a\\npattern or practice of conduct by the Newark Police\\n[Department] that deprives individuals of rights, privileges,\\nand immunities secured by the Constitution.” Id. at 144.\\nWhen viewed in conjunction with the Star Ledger article, it\\nreferences the types of constitutional violations mentioned in\\nthe amended complaint: warrantless searches, id. at 134, and\\nfalse arrests, id. at 158. These violations were widespread\\nand causally linked to Roman’s alleged injury, as the Police\\nDepartment was aware of them but “rare[ly] . . . acted” on\\ncitizen complaints. Id. at 134 (discussing complaints of\\n“improper searches and false arrests”); see also Beck v. City\\nof Pittsburgh, 89 F.3d 966, 974 (3d Cir. 1996) (noting the\\npolice department’s failure to act on complaints\\n“perpetuate[d] the City’s custom of acquiescing in the\\nexcessive use of force by its police officers”). In light of\\nthese allegations, “it is logical to assume that [the City’s]\\ncontinued official tolerance of repeated misconduct\\nfacilitate[d] similar unlawful actions in the future,” including\\nthe search and arrest of Roman. Bielevicz, 915 F.2d at 851. It\\nfollows that he has adequately pled a municipal custom and\\nproximate causation under § 1983.\\n We reach the same conclusion with respect to\\nRoman’s failure-to-train, failure-to-supervise, and failure-to-\\ndiscipline claims. To start, the Star Ledger article includes a\\nstatement on police training from James Stewart, Jr., the head\\nof Newark’s police union. He conceded the “last training [he]\\nreceived” was in 1995, when he first joined the Newark\\nPolice Department. App. at 134 (internal quotation marks\\nomitted). Moreover, Stewart is not some unreliable, rogue\\nofficer—he is the head of the police union. Nor is his\\nexperience isolated: the consent decree indicates Newark\\npolice officers in general were not trained on “the\\nrequirements of [the] Fourth Amendment and related law.”\\nId. at 160 (discussing various Fourth Amendment doctrines\\n\\n\\n\\n\\n 16\\n\\nthat should be included in police training, including “the\\ndifference[] . . . between voluntary consent and mere\\nacquiescence to police authority”). The consent decree also\\ntouches on supervisory review of unlawful searches and\\narrests, requiring desk lieutenants and unit commanders to\\nreview “searches that appear to be without legal justification”\\nand “arrests that are unsupported by probable cause.” Id. at\\n161. Finally, it provides disciplinary measures for police\\nofficers who engage in “unlawful . . . searches” and “false\\narrests.” Id. at 192. At the pleadings stage, a fair inference is\\nthat the consent decree was necessary because of Department-\\nwide failures, not because one officer was last trained in\\n1995.\\n This is enough to prove municipal liability because the\\nCity “[knew] to a moral certainty” that its officers would need\\nto conduct searches. Harris, 489 U.S. at 390 n.10. Yet in at\\nleast one instance it failed to provide training since 1995, see\\nApp. at 134, and per the decree its training did not cover the\\nbasics of the Fourth Amendment, see id. at 158-61. The City\\nalso did not discipline officers for “sustained allegations of\\nmisconduct,” including “prior violations” and other\\n“aggravating factors.” Id. at 192-93. In view of these\\ndeficiencies, one could reasonably infer that the City’s\\ninaction “reflected [its] ‘deliberate indifference’” to Roman’s\\nFourth Amendment rights. Bd. of Cty. Comm’rs v. Brown,\\n520 U.S. 397, 409 (1997); cf. Harris, 489 U.S. at 390 n.10\\n(“[C]ity policymakers know to a moral certainty that their\\npolice officers will be required to arrest fleeing felons. . . .\\nThus, the need to train officers in the constitutional\\nlimitations on the use of deadly force . . . can be said to be ‘so\\nobvious’ . . . that failure to do so could properly be\\ncharacterized as ‘deliberate indifference’ to constitutional\\nrights.” (internal citation omitted)). One could also infer that\\nthe City’s failure to establish an adequate training program\\ncontributed to the specific constitutional violations alleged in\\n\\n\\n\\n\\n 17\\n\\nthe amended complaint. See Brown, 520 U.S. at 409-10\\n(“The likelihood that the situation will recur and the\\npredictability that an officer lacking specific tools to handle\\nthat situation will violate citizens’ rights . . . may also support\\nan inference of causation.”); cf. A.M. ex rel. J.M.K. v. Luzerne\\nCty. Juvenile Detention Ctr., 372 F.3d 572, 582 (3d Cir.\\n2004) (reversing the District Court’s grant of summary\\njudgment in favor of a municipality because of “unrebutted\\ntestimony” that its juvenile detention center “did not have an\\nadequate training program”).\\n We conclude that the allegations regarding Newark’s\\nfailure to train, supervise, and discipline are strong enough to\\nsurvive a motion to dismiss. See Am. Compl. ¶¶ 63-98.\\nAmong them are: a failure to train officers on obtaining a\\nsearch warrant, id. ¶ 67, and on “issuing truthful investigative\\nreports,” id. ¶ 77; a failure to supervise and manage officers,\\nid. ¶¶ 67-68; and a failure to discipline officers, id. ¶ 74, first\\nby “refus[ing]” to create a well-run Internal Affairs\\nDepartment, id. ¶ 81, and second by “inadequately\\ninvestigating, if investigating at all, citizens’ complaints\\nregarding illegal search and seizure, id. ¶ 84. The result was a\\n“complete lack of accountability” and of “record keeping,” id.\\n¶ 92, leading to a culture in which officers “knew there would\\nbe no professional consequences for their action[s],” id. ¶ 94.\\nAs the amended complaint alleges, it should come as no\\nsurprise that these conditions led to a federal investigation.\\nSee id. ¶ 89.\\n The dissent’s attempt to distinguish the consent decree\\nis unpersuasive. First, it misperceives the decree as\\nconcerning only police interactions with “pedestrians or the\\noccupants of vehicles,” not home searches. Dissenting Op. at\\n7 (“The consent decree says nothing about arrests and\\nsearches without consent that occur at residences . . .”). In\\nfact, one concern of the decree was false arrests, see App. at\\n\\n\\n\\n\\n 18\\n\\n158, which can occur both at home and on the street. And the\\ndecree does concern home searches: it sets parameters\\nofficers must follow before searching “a home based upon\\nconsent.” Id. Although Reyes by no means consented to the\\nsearch here, she willingly opened her apartment door only\\nbecause the police had used her friend Isaksem as a Trojan\\nhorse to gain entry.\\n Second, the dissent believes that the consent decree\\ncannot help Roman’s case because Roman was Hispanic. See\\nDissenting Op. at 7 (“[T]he decree addressed police practices\\nthat disparately impacted the black community. But that\\nracial disparity did not apply to Roman, who was Hispanic.”).\\nTo the contrary, the consent decree includes an entire section\\nentitled “Bias-Free Policing,” see App. at 165-67, that never\\nrestricts itself to bias against the black community. Instead, it\\nprovides that police officers must “operate without bias based\\non any demographic category,” id. at 166 (emphasis added),\\nand specifically forbids officers from discriminating based on\\n“proxies for demographic category” such as “language\\nability,” id. at 167. Plainly, the consent decree was meant to\\nprotect all Newark residents, including Hispanic residents.\\n Further, we find it difficult to square the dissent’s\\nreasoning with the record evidence discussing the City’s\\ntroubling practices around the time of Roman’s search and\\narrest. See, e.g., id. at 134 (stating only one complaint out of\\n261 filed was sustained by department investigators); id. at\\n158 (prohibiting officers from relying on materially false\\ninformation to justify a warrantless search); id. at 160\\n(requiring police officers to be trained on “the requirements\\nof [the] Fourth Amendment and related law”); id. at 161\\n(mandating supervisory review of “searches that appear to be\\nwithout legal justification” and “arrests that are unsupported\\nby probable cause”).\\n\\n\\n\\n\\n 19\\n\\n Unable to distinguish the consent decree outright, the\\ndissent offers two narrow readings of the decree. First, it\\nmaintains that the decree can speak only to the Police\\nDepartment’s obligations going forward rather than shed any\\nlight whatsoever on the “status quo” within the Department\\nbefore federal intervention. See Dissenting Op. at 10 (stating\\nthat the decree does not provide “any detail as to the status\\nquo it addressed”). The dissent concedes that the DOJ\\nprobably did not enter into the consent decree because it was\\nimpressed with Newark’s policing practices and wanted to\\nencourage the City to keep up the good work. Id. At this\\nstage, we must draw not only such obvious inferences, but\\nalso all reasonable ones, in favor of Roman. Thus we agree\\nwith the dissent on the “clear” difference between “agreeing\\nto train more” (the consent decree on its face) and “agreeing\\nthat prior training was constitutionally inadequate” (the way\\nin which the decree supports Roman’s claims). Id. We\\nsimply believe that a reasonable inference bridges the gap in\\nthis case. Indeed, no inference is needed because Roman\\nmade the link explicit in the amended complaint. See Am.\\nCompl. ¶ 89 (stating that the Police Department’s “deliberate\\nindifference to citizens’ rights is what led to the imposition of\\na [f]ederal [m]onitor program . . . .”).\\n\\n Second, the dissent believes that the consent decree’s\\ntraining requirements, from which we can reasonably infer\\ninadequate training before the decree, simply amount to\\n“additional training” in, for instance, the requirements of the\\nFourth Amendment. Dissenting Op. at 10. To the contrary,\\nthe consent decree was meant to take the Newark Police\\nDepartment back to basics: Do not lie on a warrant\\napplication or to justify a warrantless search, App. at 158;\\ninvestigate police activities that appear to have lacked legal\\njustification, id. at 161; and at all times follow the\\nrequirements of the Fourth Amendment, id. at 160.\\n\\n\\n\\n\\n 20\\n\\n The theme of the dissent appears to be that we are\\nrefashioning the amended complaint. It claims we are\\nvacating the District Court’s decision based on facts and\\narguments that were not presented to it. But as discussed\\nabove, we are engaged in de novo review of the adequacy of\\nthe amended complaint in light of documents that were before\\nthe District Court and that informed its allegations. See supra\\npp. 8-10. Additionally, and to repeat, the specific events\\nleading up to Roman’s search and arrest are not relevant to\\nthe merits of his municipal liability claim. Thus we are not\\nvacating the Court’s decision for excluding these facts from\\nits analysis.\\n Rather, our focus is directed to Newark’s practice at\\nthe time of Roman’s search and arrest. The Court had notice\\nof them, as it acknowledged that Roman alleged “a ‘pattern or\\npractice of constitutional violations in areas including stop[]\\nand arrest practices, use of force, and theft by officers.’”\\nRoman, 2017 WL 436251, at *4 (quoting Compl. ¶ 59).\\nNonetheless it dismissed the complaint and amended\\ncomplaint because it viewed the City as attempting to change\\nits practices. Even if the record can be read that way—and\\nwe doubt that8—the District Court’s rationale has the wrong\\n\\n\\n 8\\n The record does not support the Court’s inferences,\\nas it tells us the DOJ’s investigation was not completed until\\nJuly 2014, see App. at 137; the Government did not solicit\\napplications for a federal monitor until February 2015, see id.;\\nand the consent decree was not final until May 2016, see id.\\nat 215. By contrast, Roman was arrested in May 2014 and\\nimprisoned until December of that year. As such, it is\\nplausible that Newark’s practices were ongoing when police\\nofficers searched and arrested him. It is also reasonable to\\ninfer that the City’s corrective measures postdated the arrest.\\n\\n\\n\\n\\n 21\\n\\nfocus. The question is not whether some evidence can be\\nviewed as supporting the City. It is whether, viewing the\\npleadings and properly associated documents in the light most\\nfavorable to Roman, there are claims plausible enough to\\nwithstand a motion to dismiss. We think there is one—the\\nmunicipal liability claim. And the Court did not have to look\\nbeyond the amended complaint and supporting documents to\\nglean these facts.\\n\\n In sum, Roman’s municipal liability claim survives\\ndismissal based on the record that was before the District\\nCourt. Because the Court reached the opposite conclusion,\\nwe part with its holding. Thus we vacate and remand this\\nportion of its decision.\\n B. The District Court correctly dismissed the\\n false imprisonment and malicious\\n prosecution claims because they were not\\n pled under § 1983.\\n\\n Roman alleges the Defendants are also liable for false\\nimprisonment and malicious prosecution. As noted, the\\nDistrict Court construed these claims as state-law claims. It\\ndismissed them because Roman did not comply with the New\\nJersey Tort Claims Act’s procedural requirements for\\nbringing claims against public entities and public employees.\\nSee N.J. Stat. Ann. § 59:8-1 et seq.\\n On appeal, Roman contends the Court erred in\\ndismissing his claims because they were pled under § 1983.\\nThe Defendants counter that both claims were presented as\\n\\n\\n\\nHence we do not consider the City’s corrective measures to\\nbe enough to defeat Roman’s allegations.\\n\\n\\n\\n\\n 22\\n\\nstate-law tort claims. They also point out that Roman omitted\\nthem from his amended complaint.9\\n\\n As a preliminary matter, the Defendants correctly\\nobserve that false imprisonment and malicious prosecution\\nare not in the amended complaint. Hence we must first\\ndecide if Roman has waived his right to challenge their\\ndismissal on appeal. If we conclude that waiver does not\\napply, we then determine if the District Court correctly\\nconstrued them as state-law tort claims.\\n We have not applied a strict rule in favor of waiver in\\nthis context. Instead, we have allowed “plaintiffs to appeal\\ndismissals despite amended pleadings that omit the dismissed\\nclaim[,] provided repleading the particular cause of action\\nwould have been futile.” United States ex rel. Atkinson v. Pa.\\nShipbuilding Co., 473 F.3d 506, 516 (3d Cir. 2007) (emphasis\\nin original) (footnote omitted). “Repleading is futile when\\nthe dismissal was ‘on the merits.’ A dismissal is on the\\nmerits when it is with prejudice or based on some legal\\nbarrier other than want of specificity or particularity.” Id. If\\na court is uncertain, “doubt[] should be resolved against the\\nparty asserting waiver.” Id. at 517 (emphasis in original).\\n\\n 9\\n At oral argument, Roman’s counsel stated the false\\nimprisonment claim was repled in Count 13 of the amended\\ncomplaint even though that count alleges “conspiracy to\\ncommit unlawful imprisonment . . . [in violation of] 42\\nU.S.C. § 1985.” App. at 278 (emphasis added); see Audio\\nRecording of Oral Argument held June 12, 2018 at 11:39 to\\n12:06 (http://www2.ca3.uscourts.gov/oralargument/audio/17-\\n2302TheEstateofAdrianoRomanJrvCityofNewarketal.mp3).\\nWe do not consider this contention, as it was raised for the\\nfirst time at oral argument and thus is waived. See In re\\nGrand Jury, 635 F.3d 101, 105 n.4 (3d Cir. 2011).\\n\\n\\n\\n\\n 23\\n\\n Here the District Court analyzed both claims on legal\\ngrounds. It observed that they were based on the New Jersey\\nTort Claims Act, which allows individuals to bring tort claims\\nagainst public entities and employees after complying with\\ncertain procedural and notice requirements, see Tripo v.\\nRobert Wood Johnson Med. Ctr., 845 F. Supp. 2d 621, 626-\\n27 (D.N.J. 2012) (summarizing the Act’s procedures for suing\\na public entity or employee). It concluded Roman did not\\nfollow these requirements and thus dismissed the claims.\\n Although the Court was guided by procedural\\nconcerns, its dismissal was on the merits. The Tort Claims\\nAct bars claims against public entities and employees if a\\nplaintiff waits more than two years to file a “notice of claim.”\\nSee N.J. Stat. Ann. § 59:8-8(b). The two-year mark is\\nmeasured from the day the claim accrues (i.e., the day on\\nwhich the public entity or employee allegedly harmed the\\nplaintiff). In our case, because Roman’s claims accrued in\\nMay 2014, he had until May 2016 to file a notice of claim.\\nAs the Court noted, however, he did not file any type of\\nnotice during the two-year period. See Roman, 2017 WL\\n436251, at *6 (observing that, as of January 31, 2017, the date\\non which the Court dismissed the complaint, Roman had not\\nfiled a notice). Thus Roman’s procedural error morphed into\\na dismissal on the merits, see N.J. Stat. Ann. § 59:8-8(b)\\n(“The claimant shall be forever barred from recovering\\nagainst a public entity or public employee if . . . [t]wo years\\nhave elapsed since the accrual of the claim.”), and he may\\nappeal the District Court’s decision on his false imprisonment\\nand malicious prosecution claims, see Atkinson, 473 F.3d at\\n516-17.\\n In light of this conclusion, we must focus on the\\npleadings and decide if Roman’s claims are based on § 1983.\\nIf we look to the complaint, it suggests both false\\nimprisonment and malicious prosecution are state-law tort\\n\\n\\n\\n\\n 24\\n\\nclaims. It never identifies them as § 1983 or federal claims.\\nRather, it presents them generically, following a series of\\nother state-law tort claims. See, e.g., App. at 44 (“intentional\\ninfliction of emotional distress”); id. at 46 (“negligent\\ninfliction of emotional distress”); id. at 47 (“assault and\\nbattery”); id. at 49 (“unlawful imprisonment”); id. at 51\\n(“malicious prosecution”). This indicates to us that Roman\\npled both claims as state-law claims, not federal claims.\\nWhile the unlawful (i.e., false) imprisonment claim does note\\nthat the Defendants “restrict[ed] [Roman’s] constitutionally\\nguaranteed rights of liberty and freedom of movement,” it is\\nsilent as to whether it refers to the United States or New\\nJersey Constitution. Compl. ¶ 114. This is too facile to\\nimply the former when but a few identifying words would do.\\nThe default is New Jersey law, which defines false\\nimprisonment as “an[y] unlawful restraint that interferes with\\na victim’s liberty” and requires “[n]o further wrongful\\npurpose” for a prima facie showing. State v. Savage, 799\\nA.2d 477, 494 (N.J. 2009).\\n Accordingly, the District Court correctly construed the\\nfalse imprisonment and malicious prosecution claims as state-\\nlaw tort claims, and we affirm this portion of its holding.10\\n C. The doctrines of res judicata, collateral\\n estoppel, and judicial estoppel do not require\\n us to dismiss Roman’s § 1983 claims.\\n Finally, the Defendants invoke the doctrines of res\\njudicata, collateral estoppel, and judicial estoppel. According\\n\\n\\n 10\\n We also affirm the dismissal of Roman’s unlawful-\\nsearch claims because they were not adequately pled. We do\\nnot opine on whether a plaintiff may allege joint and several\\nliability in connection with an unlawful-search claim.\\n\\n\\n\\n\\n 25\\n\\nto them, each doctrine compels us to dismiss Roman’s § 1983\\nclaims.\\n\\n We start with res judicata. The Defendants contend it\\nbars Roman’s claims because “the criminal matter and the\\nsuppression hearing were based on the exact same facts” as\\nthose alleged in Roman’s pleadings. Defendants’ Br. at 64.\\nIn their view, criminal proceedings are enough to preclude a\\ncivil suit seeking damages under § 1983.\\n\\n We disagree. “A party seeking to invoke res judicata\\nmust establish three elements: (1) a final judgment on the\\nmerits in a prior suit involving (2) the same parties or their\\nprivies and (3) a subsequent suit based on the same cause of\\naction.” Duhaney v. Att’y Gen., 621 F.3d 340, 347 (3d Cir.\\n2010) (internal quotation marks omitted). Roman’s suit is not\\nbased on the same cause of action as the criminal complaint\\nand suppression hearing. Nor are his current claims of the\\ntype “that could have been brought” in the earlier criminal\\nproceeding. Id. (internal quotation marks omitted); see also\\nHelvering v. Mitchell, 303 U.S. 391, 397 (1938) (“The\\ndifference in degree of the burden of proof in criminal and\\ncivil cases precludes application of the doctrine of res\\njudicata.”). New Jersey initiated the criminal case. Roman\\nwas not at liberty to assert any claims except for defenses\\nagainst the prosecution’s case-in-chief. See Leather v. Eyck,\\n180 F.3d 420, 425 (2d Cir. 1999) (“[B]ecause the nature of\\nthe prior state[-]court proceeding was such that [the\\nAppellant] could not have sought damages for his alleged\\nconstitutional injuries (while defending himself on [a\\ncriminal] charge . . . ), res judicata does not bar his federal §\\n1983 suit for damages.”). Moreover, he was not free to raise\\nhis § 1983 claims in the same criminal case; indeed, he could\\nnot bring them until the criminal proceeding concluded. See\\nHeck v. Humphrey, 512 U.S. 477, 486 (1994) (“[T]he . . .\\nprinciple that civil tort actions are not appropriate vehicles for\\n\\n\\n\\n\\n 26\\n\\nchallenging the validity of outstanding criminal judgments\\napplies to § 1983 damages actions that necessarily require the\\nplaintiff to prove the unlawfulness of his conviction or\\nconfinement. . . .”). Accordingly, res judicata does not bar\\nRoman’s claims.\\n\\n Moving on to collateral estoppel, the Defendants argue\\nit (1) absolves Officer Mendes of liability because the\\nSuperior Court made a factual finding that Roman possessed\\nthe contraband that was seized from the apartment, (2)\\nabsolves Sergeant Joyce Hill because nothing in the Superior\\nCourt’s transcript indicates she was present for the search and\\narrest, and (3) absolves the other named defendants because\\nthe Superior Court’s transcript suggests they only handled the\\ncontraband. According to the Defendants, the Superior Court\\ndecided all of these issues in their favor during the\\nsuppression hearing. See Bd. of Trs. of Trucking Emps. of N.\\nJersey Welfare Fund, Inc. v. Centra, 983 F.2d 495, 505 (3d\\nCir. 1992) (stating a party is collaterally estopped from\\nlitigating a specific issue if, among other things, “[an]\\nidentical issue was decided in a prior adjudication”). Again\\nwe disagree. Contrary to the Defendants’ assertions, the\\nSuperior Court never decided any of these issues during the\\nsuppression hearing. While it did find that Roman had a\\npossessory interest in the apartment, that is not enough for us\\nto conclude that he had actual or constructive possession over\\nthe contraband. Collateral estoppel is not appropriate in this\\ncontext.\\n Last, the Defendants assert that judicial estoppel\\nprecludes Roman’s claims because he admitted that (1) drugs\\nwere found in the apartment, (2) he had a possessory interest\\nin the apartment, (3) Officer Mendes was the only officer who\\ninitiated the prosecution, and (4) the remaining officers only\\nhandled the contraband and had no other roles. They insist\\nthese concessions “are sufficient to establish that [Roman’s]\\n\\n\\n\\n\\n 27\\n\\narrest and prosecution arise out of his possession of\\nincriminating evidence[.]” Defendants’ Br. at 65. As noted,\\n“[j]udicial estoppel, sometimes called the ‘doctrine against\\nthe assertion of inconsistent positions,’ is a judge-made\\ndoctrine that . . . prevent[s] a litigant from asserting a position\\ninconsistent with one that []he has previously asserted . . . in a\\nprevious proceeding.” Ryan Operations G.P., 81 F.3d at 358.\\nThis doctrine is not in play here, as Roman never stipulated\\nthat Officer Mendes was the only officer to bring the\\nprosecution or that the remaining officers only handled the\\ncontraband. While the Court found that Roman had a\\npossessory interest in the apartment, that interest (we repeat)\\nis not enough to establish that he possessed the contraband.\\nAccordingly, judicial estoppel does not require us to dismiss\\nRoman’s claims.\\n * * * * *\\n Roman has sufficiently alleged a municipal liability\\nclaim against the City of Newark under § 1983. He cites\\nvarious examples of inadequate police training, poor police\\ndiscipline, and unheeded citizen complaints. He tells us\\ncertain police officers did not receive training for over 20\\nyears, and their training did not cover the basic requirements\\nof the Fourth Amendment. In his pleadings, he states the\\nNewark Police Department did not discipline officers who\\nengaged in police misconduct, Am. Compl. ¶¶ 84-86,\\nincluding unlawful searches and false arrests, App. at 134.\\nHe also notes the public filed formal complaints about\\nimproper searches and false arrests that were disregarded\\nalmost wholesale. Id. These alleged practices were ongoing\\nwhen Roman’s search and arrest occurred, and the City had\\nnotice of them at that time. While the proof developed to\\nsupport these allegations may or may not be persuasive to a\\nfinder of fact, they are enough to survive dismissal at this\\nstage. Based on this conclusion, we part with the District\\n\\n\\n\\n\\n 28\\n\\nCourt’s holding that Roman failed to state a § 1983 claim\\nagainst the City. Though we affirm otherwise, we vacate and\\nremand its decision on municipal liability.\\n\\n\\n\\n\\n 29\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":80,"cells":{"id":{"kind":"number","value":4578632,"string":"4,578,632"},"name":{"kind":"string","value":"Clarence GRIFFIN, Plaintiff - Appellant, v. DEPARTMENT OF LABOR FEDERAL CREDIT UNION, A/K/A DOLFCU, Defendant - Appellee, National Association of Federally-Insured Credit Unions; Credit Union National Association, Amici Supporting Appellee."},"name_abbreviation":{"kind":"string","value":"Griffin v. Dep't of Labor Fed. Credit Union"},"decision_date":{"kind":"string","value":"2019-01-03"},"docket_number":{"kind":"string","value":"18-1312"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Wilkinson, King, Quattlebaum\", \"parties\": \"\", \"opinions\": [{\"author\": \"WILKINSON, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1312\\n\\n\\nCLARENCE GRIFFIN,\\n\\n Plaintiff – Appellant,\\n\\n v.\\n\\nDEPARTMENT OF LABOR FEDERAL CREDIT UNION, a/k/a DOLFCU,\\n\\n Defendant – Appellee,\\n\\n------------------------------\\n\\nNATIONAL ASSOCIATION OF FEDERALLY-INSURED CREDIT UNIONS;\\nCREDIT UNION NATIONAL ASSOCIATION,\\n\\n Amici Supporting Appellee.\\n\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. T.S. Ellis, III, Senior District Judge. (1:17-cv-01419-TSE-IDD)\\n\\n\\nArgued: October 30, 2018 Decided: January 3, 2019\\n\\n\\nBefore WILKINSON, KING, and QUATTLEBAUM, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Wilkinson wrote the opinion, in which Judge\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4355885/\", \"author_raw\": \"WILKINSON, Circuit Judge:\"}, {\"author\": \"Quattlebaum joined. Judge King wrote an opinion concurring\", \"type\": \"concurrence\", \"text\": \"Quattlebaum joined. Judge King wrote an opinion concurring in the judgment.\\n\\nARGUED: Thomas Eugene Strelka, STRELKA LAW OFFICE, Roanoke, Virginia, for\\nAppellant. John Michael Bredehoft, KAUFMAN & CANOLES, PC, Norfolk, Virginia,\\nfor Appellee. ON BRIEF: L. Leigh Strelka, Norvell W. West IV, STRELKA LAW\\nOFFICE, Roanoke, Virginia; Scott J. Ferrell, Victoria C. Knowles, PACIFIC TRIAL\\nATTORNEYS, P.C., Newport Beach, California, for Appellant. Edward Lee Isler, Mark\\nE. Papadopoulos, ISLER DARE, P.C., Vienna, Virginia, for Amicus National\\nAssociation of Federally-Insured Credit Unions. Jonathan C. Sandler, Los Angeles,\\nCalifornia, Christine A. Samsel, Denver, Colorado, Michael H. Pryor, BROWNSTEIN\\nHYATT FARBER SCHRECK, LLP, Washington, D.C., for Amicus Credit Union\\nNational Association.\\n\\n\\n\\n\\n 2\\n\\nWILKINSON, Circuit Judge:\\n\\n Appellant here has asserted that he has standing to challenge various aspects of the\\n\\nDepartment of Labor Federal Credit Union’s website under the Americans with\\n\\nDisabilities Act. 42 U.S.C. § 12101 et seq. The district court granted the Credit Union’s\\n\\nFederal Rule of Civil Procedure 12(b)(1) motion to dismiss. Because we agree that\\n\\nappellant lacks constitutional standing, we now affirm the judgment.\\n\\n I.\\n\\n The Department of Labor Federal Credit Union, the appellee, is a federal credit\\n\\nunion that, under the Federal Credit Union Act of 1934, accepts as members only those\\n\\nwho share the “common bond” of being current and former employees of the Department\\n\\nof Labor and their immediate families and households. 12 U.S.C. § 1759(b). Only\\n\\nmembers can take advantage of the Credit Union’s products or services; only members\\n\\nmay open an account or take out a loan or enjoy in any way the benefits of the Credit\\n\\nUnion. The Credit Union maintains a website that describes its services and products.\\n\\n Clarence Griffin, the appellant, is a blind resident of Virginia. Because of his\\n\\nvisual impairment, Griffin uses a screen reader to access the Internet. As he explains in\\n\\nhis complaint, screen readers help the blind access the Internet by reading aloud the text\\n\\nthat appears on a website. Website operators often take special care to ensure their sites\\n\\nare legible to screen readers. Many visually impaired people like Griffin also rely more\\n\\nheavily on keyboards than mouses to navigate the Internet. Because of this, it is\\n\\nrecommended that website operators avoid “redundant links,” which can be tedious and\\n\\ntime-consuming for keyboard users to navigate.\\n\\n 3\\n\\n Griffin is not eligible for membership in the Credit Union. He does not work for\\n\\nthe Department of Labor and never has in the past. No one in his immediate family has\\n\\never worked for the Department of Labor, nor has any member of his household. He\\n\\nmakes no allegation in his complaint that he is legally permitted to make use of the Credit\\n\\nUnion’s benefits. *\\n\\n According to his complaint, Griffin tried to access the Credit Union’s website in\\n\\nOctober of 2017. He alleges his attempt was stymied in three ways. First, there were\\n\\nlinked images that lacked “alternative text.” As a consequence, Griffin’s screen reader\\n\\ncould not describe those images to him and he could not navigate to the linked content.\\n\\nSecond, there were “redundant links.” This meant Griffin had to take additional,\\n\\nunnecessary steps to make full use of the site. And third, “form labels” were missing.\\n\\nGriffin could not tell when the website wanted him to input information that is often\\n\\nnecessary to access the site further.\\n\\n Griffin sued, arguing that the Credit Union’s failure to make reasonable\\n\\nmodifications to its policies and practices that would make its site accessible to the\\n\\ndisabled violated the Americans with Disabilities Act, 42 U.S.C. §12101 et seq. The\\n\\ncomplaint sought injunctive relief as well as costs and attorney’s fees. The Credit Union\\n\\n\\n\\n *\\n Questions surfaced at oral argument regarding Griffin’s eligibility to make use of\\nthe Credit Union’s ATMs. This argument appears nowhere in the briefing, perhaps\\nbecause it is tangential or an afterthought to the central inquiry. Plaintiff does mention\\nATMs in his complaint, stating that they are “available to Defendant’s members,” J.A.\\n15, which, as noted, Griffin plainly is not.\\n\\n\\n 4\\n\\nmoved to dismiss for lack of standing, pursuant to Federal Rule of Civil Procedure\\n\\n12(b)(1), which the district court granted. Griffin now appeals this dismissal.\\n\\n II.\\n\\n Griffin puts his case in broad terms, claiming that the rights generally of people\\n\\nwith disabilities to sue for Internet-based harms under the ADA are at stake. But that\\n\\nquestion is not before us. This case concerns the application of standing doctrine in an\\n\\nelectronic age and it is important that we move narrowly in exploring this new territory.\\n\\nAccordingly, we address only whether this plaintiff who is barred by law from making\\n\\nuse of defendant’s services may sue under the ADA for an allegedly deficient website.\\n\\nThe answer to this narrow question here is no.\\n\\n Article III limits the judicial power of the United States to “Cases” and\\n\\n“Controversies.” Embedded in this limitation is a “set of requirements that together make\\n\\nup the ‘irreducible constitutional minimum of standing.’” Lexmark Intern., Inc. v. Static\\n\\nControl Components, Inc., 572 U.S. 118, 125 (2014) (quoting Lujan v. Defenders of\\n\\nWildlife, 504 U.S. 555, 560 (1992)). Where these requirements are not met, this court\\n\\nwould “exceed [its] authority” if it adjudicated the merits of a dispute. Spokeo, Inc. v.\\n\\nRobins, 136 S. Ct. 1540, 1547 (2016).\\n\\n An injury in fact is an indispensable aspect of constitutional standing; no “Case”\\n\\nor “Controvers[y]” exists without injury. It is “[f]irst and foremost” of the three\\n\\nrequirements of constitutional standing. Spokeo, 136 S. Ct. at 1547 (quoting Steel Co. v.\\n\\nCitizens for Better Environment, 523 U.S. 83, 103 (1998)) (describing the other two\\n\\nrequirements as causation and redressability). A wrong suffered by a party is only an\\n\\n 5\\n\\ninjury in fact if it is sufficiently “concrete and particularized.” Id. at 1545 (quoting\\n\\nFriends of the Earth, Inc. v. Laidlaw Environmental Services (TOC), Inc., 528 U.S. 167\\n\\n180-81 (2000)) (emphasis in original). These are separate criteria which must both be\\n\\nsatisfied. Id. And when a party seeks injunctive relief, as Griffin does, there is the\\n\\nadditional requirement of a “real or immediate threat” that the party will suffer an injury\\n\\nin the future. City of Los Angeles v. Lyons, 461 U.S. 95, 111 (1983).\\n\\n Thus, in order to prevail, Griffin must allege an injury that is concrete,\\n\\nparticularized, and immediately threatening. It is important that we do not take a cramped\\n\\nview of standing in civil rights cases, lest we impair the remedial purpose Congress had\\n\\nin mind when enacting civil rights statutes. But even under this broad view Griffin’s\\n\\ncomplaint fails to satisfy each of the Supreme Court’s requirements. We address them in\\n\\nturn.\\n\\n A.\\n\\n Griffin’s alleged injury is not concrete. An injury is “concrete” when it is “real and\\n\\nnot abstract.” Spokeo, 136 S. Ct. at 1548. But an injury may be concrete without being\\n\\n“tangible.” Id. at 1549. In deciding what intangible injuries are concrete, we consult the\\n\\n“judgment of Congress” because “Congress is well positioned to identify intangible\\n\\nharms that meet minimum Article III requirements.” Id. See also Moore v. Blibaum &\\n\\nAssociates, P.A., 693 Fed. Appx. 205, 206 (4th Cir. 2017) (“In particular, the injury-in-\\n\\nfact requirement is not limited simply to financial or economic losses.”). Dignitary harms\\n\\nor “stigmatic injur[ies],” while not tangible, may be sufficiently concrete to constitute\\n\\n\\n\\n 6\\n\\ninjury in fact, Allen v. Wright, 468 U.S. 737, 754-55 (1984), and therefore may\\n\\nconstitutionally be protected by statute.\\n\\n Griffin has alleged just such a dignitary harm. It is true that his complaint does not\\n\\ninclude the phrases “dignitary harm” or “stigmatic injury.” But such a ritual incantation is\\n\\nunnecessary; dignitary harms are readily inferred by allegations of unequal treatment. See\\n\\nAllen, 468 U.S. 752-53. And Congress, in enacting the ADA, intended in part to protect\\n\\npeople with disabilities against stigmatic injury. Tennessee v. Lane, 541 U.S. 509, 536\\n\\n(2004) (Ginsburg, J., concurring); Shaver v. Independent Stave Co., 350 F.3d 716, 724\\n\\n(8th Cir. 2003).\\n\\n But not all dignitary harms are sufficiently concrete to serve as injuries in fact. As\\n\\nJustice O’Connor explained in Allen v. Wright, geographic separation between the\\n\\nchallenged conduct and the stigmatic injury can reduce the “personal” impact of the\\n\\ninjury and render it too “abstract.” Allen, 468 U.S. at 756-57. “A black person in\\n\\nHawaii,” for example, cannot challenge “a racially discriminatory school in Maine.” Id.\\n\\nat 757. Otherwise, the federal courts would “transform” into a “vehicle for the\\n\\nvindication of value interests of concerned bystanders.” Id. at 756 (quoting United States\\n\\nv. SCRAP, 412 U.S. 669, 687 (1973)).\\n\\n The legal barriers between Griffin and the Credit Union render his injury\\n\\n“abstract” just as the geographic barriers did in Allen. Allen’s hypothetical Hawaiian\\n\\nlitigant could not sue the Maine school because geography made it impossible for the\\n\\nplaintiff to interact directly with the school and be “personally subject” to its\\n\\ndiscrimination. Allen 468 U.S. at 757 n.22. Here, a neutral proposition of federal law\\n\\n 7\\n\\nmakes it impossible for Griffin to interact directly with the Credit Union. The Federal\\n\\nCredit Union Act of 1934 expressly forbids the provision of any products or services to\\n\\nhim. 12 U.S.C. § 1759. It is therefore impossible—absent a violation of federal law—for\\n\\nGriffin to be “personally subject” to the dignitary harms allegedly occasioned by the\\n\\nCredit Union’s website.\\n\\n Griffin’s assertion of informational harm fares no better than his assertion of\\n\\ndignitary harm, for the same reason. Inability to obtain information is sufficiently\\n\\nconcrete to constitute injury in fact only when the information has some relevance to the\\n\\nlitigant. In Federal Election Commission v. Akins, the Supreme Court explained that\\n\\nplaintiffs who sought information that would “help them . . . evaluate candidates for\\n\\npublic office” suffered a concrete injury when they failed to receive it. 524 U.S. 11, 21\\n\\n(1998). The information was relevant to the plaintiffs’ fulfillment of their civic\\n\\nresponsibility. See also Dreher v. Experian Information Solutions, Inc., 856 F.3d 337,\\n\\n345 (4th Cir. 2017). Here, on the other hand, the information Griffin failed to obtain\\n\\nlacks a comparable relevance to him. Griffin sought information on the Credit Union’s\\n\\n“services, privileges, advantages, and accommodations and amenities,” as well as the\\n\\nphysical locations where those services are provided. J.A. 13. But this information lacks\\n\\nthe requisite relevance to Griffin; a federal law closes the door of the Credit Union to\\n\\nGriffin whether or not he obtains the information he seeks. 12 U.S.C. § 1759.\\n\\n B.\\n\\n Griffin’s injury is also not particularized. For an injury to be particularized, it must\\n\\naffect the plaintiff in a way that is “individual.” Lujan v. Defenders of Wildlife, 504 U.S.\\n\\n 8\\n\\n555, 560 n.1 (1992); Daniels v. Arcade, L.P., 477 Fed. Appx. 125, 129 (4th Cir. 2012).\\n\\nThere must be some connection between the plaintiff and the defendant that\\n\\n“[]differentiate[s]” the plaintiff so that his injury is not “common to all members of the\\n\\npublic.” United States v. Richardson, 418 U.S. 166, 177 (1974) (quoting Ex parte Levitt,\\n\\n302 U.S. 633, 634 (1937)). Thus, as the Supreme Court explained in Lujan v. Defenders\\n\\nof Wildlife, just “anyone who goes to see Asian elephants in the Bronx Zoo” cannot sue a\\n\\ndefendant whose actions have harmed that species in a particular part of the world. 504\\n\\nU.S. at 566. His injury is not particularized. But, a person who, as a vocation, studies\\n\\nAsian elephants in the part of the world in question “plausib[ly]” has enough of a\\n\\nconnection to convert the general harm to the species into a particular harm to the\\n\\nplaintiff. Id.\\n\\n Griffin has not pointed to any connection between the defendant and himself that\\n\\ntransforms the general harms he alleges into particularized ones. Again, the law of credit\\n\\nunions is dispositive on this point. The Federal Credit Union Act of 1934 positively\\n\\nforbids Griffin from taking advantage of any of the Credit Union’s products or services\\n\\nbecause he does not share the “common bond” of those who may become its members.\\n\\n12 U.S.C.§ 1759(b). That law severs any connection between the Credit Union and\\n\\nGriffin that could plausibly serve to particularize his alleged injury.\\n\\n The cases Griffin points to do not counsel the opposite conclusion. In Menkowitz\\n\\nv. Pottstown Memorial Medical Center, the plaintiff was a doctor with “staff privileges”\\n\\nat the defendant hospital. 154 F.3d 113, 115 (3d Cir. 1998). Those staff privileges\\n\\nsupplied the requisite connection between plaintiff and defendant that converted an\\n\\n 9\\n\\notherwise general harm into a particular one. Likewise, visits to a physical location may\\n\\nsupply a particularizing connection, as they differentiate the plaintiff from the general\\n\\npublic who are barred by distance from ever making such a visit. Griffin’s reference to\\n\\nthose cases in which a visit was actually made or plausibly contemplated is therefore\\n\\ninapt. Br. for the Appellant at 25-32 (citing Houston v. Marod Supermarkets, Inc., 733\\n\\nF.3d 1323, 1326 (11th Cir. 2013); Molski v. M.J. Cable, 481 F.3d 724, 727 (9th Cir.\\n\\n2007); Civil Rights Education and Enforcement Center. v. Hospitality Props. Trust, 867\\n\\nF.3d 1093, 1096 (9th Cir. 2017).\\n\\n C.\\n\\n Griffin has not suffered a concrete and particular injury in the past. There is also\\n\\nnot an immediate threat that Griffin will suffer an injury in fact in the future. A plaintiff\\n\\nhas standing to sue for injunctive relief when there is “real or immediate threat” that the\\n\\nparty will suffer an injury in the future. City of Los Angeles v. Lyons, 461 U.S. 95, 111\\n\\n(1983). Such an injury must be “imminent.” Clapper v. Amnesty Intern. USA, 568 U.S.\\n\\n398, 409 (2013). “[I]mminence is concededly a somewhat elastic concept,” but it “cannot\\n\\nbe stretched beyond its purpose.” Id. (quoting Lujan, 504 U.S. at 565, n. 2). In short, an\\n\\ninjury should be “certainly impending” to serve as the basis for standing in a suit for\\n\\ninjunctive relief. Whitmore v. Arkansas, 495 U.S. 149, 158 (1990).\\n\\n This court’s opinion in Nanni v. Aberdeen Marketplace is both insightful and\\n\\ninstructive on this point as it pertains to injuries under ADA. 878 F.3d 447 (4th Cir.\\n\\n2017). There we explained that a plaintiff who experienced a past injury from a visit to a\\n\\nphysical location need only show a plausible intent to return to that location in order to\\n\\n 10\\n\\nhave standing to sue for injunctive relief. Id. at 455. Nanni, the plaintiff, visited the\\n\\ndefendant Marketplace and allegedly discovered that the Marketplace’s various ADA\\n\\nviolations impeded his use of a wheelchair. Id. We held that this was a sufficiently\\n\\nconcrete and particular past injury. Id. at 456. We further held that Nanni’s intent to\\n\\nreturn to the Marketplace was plausible because he passed the store several times a year\\n\\non visits to Baltimore and Washington from his home in Delaware. Id. And so, despite\\n\\nthe distance between the Marketplace and Nanni’s home, we held that he had standing to\\n\\nsue. See also Houston v. Marod Supermarkets, Inc., 733 F.3d 1323, 1329 (11th Cir. 2013)\\n\\n(relying on the “totality of facts” to determine the plausibility of an asserted intent to\\n\\nreturn to an ADA-noncompliant location).\\n\\n Griffin’s complaint does not satisfy the requirements of Nanni. The first\\n\\nrequirement, a past injury that is concrete and particular, is not met for reasons explained\\n\\nabove. And the second requirement is unmet because, unlike the plaintiff in Nanni,\\n\\nGriffin has not demonstrated that his intent to return to the Credit Union’s website is\\n\\nplausible. Indeed, there are reasons to think it is objectively implausible: why would an\\n\\nindividual with no hope of ever making use of the Credit Union’s services want to visit a\\n\\nwebsite describing those services? In short, Nanni could take advantage of the store’s\\n\\nwares and accommodations. Griffin, by contrast, is ineligible for perfectly neutral reasons\\n\\nto utilize the Credit Union’s services.\\n\\n Griffin points to his status as an ADA tester. It is true that tester status does not\\n\\ndestroy standing. Nanni, 878 F.3d at 457. But by the same token it cannot create standing\\n\\nin the absence of an otherwise plausible assertion that a return to the website would allow\\n\\n 11\\n\\nGriffin to avail himself of its services. Even in Houston v. Marod Supermarkets, a case\\n\\nrelied on heavily by Griffin, tester status, while a factor in favor of the plaintiff, was\\n\\ninsufficient to show a threat of future injury without more. 733 F.3d 1323, 1334 (11th\\n\\nCir. 2013). The Eleventh Circuit explained that the tester-plaintiff’s assertion that he\\n\\nwould return to the ADA-noncompliant supermarket was plausible only because, even\\n\\nthough it was not the closest market to his home, the plaintiff passed the store “regularly”\\n\\non his trips to Miami-Dade County. Id. at 1336. If, however the plaintiff “live[d]\\n\\nhundreds of miles away from the store with no particular reason to return” the facts “may\\n\\ndemand a different conclusion.” Id. Those are the facts here. Griffin may not live\\n\\nhundreds of miles away from the Credit Union, but the legal barriers between the two\\n\\nparties serve the same role as geographic ones. And those same legal barriers mean that\\n\\nGriffin has “no particular reason”—other than his role as a tester, which alone is\\n\\ninsufficient—to ever return.\\n\\n III.\\n\\n Our decision is not born of any lack of sympathy for people with visual\\n\\nimpairments. Those who do not suffer from impairments of this nature must be alert and\\n\\nsensitive to the formidable challenges such impairments impose on the navigation of\\n\\neveryday life. We must be sensitive as well to the wealth of talent that, before the passage\\n\\nof the ADA, was locked behind society’s unthinking exclusion of people with disabilities.\\n\\nWe thus recognize and respect the Americans with Disabilities Act’s transformative goal\\n\\nof “the elimination or reduction of physical and social structures that impede people with\\n\\nsome present, past, or perceived impairments from contributing, according to their\\n\\n 12\\n\\ntalents, to our Nation’s social, economic, and civic life.” Tennessee v. Lane, 541 U.S.\\n\\n509, 536 (2004) (Ginsburg, J., concurring).\\n\\n But to ignore the requirement of an injury in fact in this case would be to\\n\\ntransform constitutional standing into a null item. Spokeo requires a concrete and\\n\\nparticularized harm to find Article III standing, something greater than “a bare procedural\\n\\nviolation, divorced from any concrete harm.” 136 S. Ct. 1540, 1549 (2016). We are not at\\n\\nliberty to assail the basic principles of Spokeo here. Standing doctrine will doubtless pose\\n\\ncomplicated questions as it is applied to Internet-based harms in the future, but the case\\n\\nbefore us today is straightforward and narrow. Griffin is not a member of the Credit\\n\\nUnion, he is not eligible to become a member of the Credit Union, he has no plans to\\n\\nbecome eligible to be a member of the Credit Union, and no action we take could\\n\\npossibly make him eligible to become a member of the Credit Union. Under these\\n\\nspecific circumstances there can be no injury in fact. We have no occasion to consider\\n\\nhere, for example, a case brought by a similarly disabled individual who was eligible for\\n\\ncredit union membership in the defendant.\\n\\n This narrow holding stands in stark contrast to the broad position Griffin would\\n\\nhave us adopt. His argument admits of no limiting principle. If adopted, it would allow\\n\\nany aggrieved person to challenge any allegedly deficient website belonging to anyone in\\n\\nthe country. It would require us to open the courthouse doors to abstract and hypothetical\\n\\ncontroversies, in brazen violation of Supreme Court precedent.\\n\\n Five different district judges in Virginia alone have reached the same conclusion\\n\\nthat we reach here. See Carroll v. Roanoke Valley Community Federal Credit Union,\\n\\n 13\\n\\n2018 WL 2921106 (W.D. Va. June 11, 2018); Carroll v. 1st Advantage Federal Credit\\n\\nUnion, 2018 WL 2933411 (E.D. Va. April 9, 2018); Carroll v. Washington Gas Light\\n\\nFederal Credit Union, 2018 WL 2933412 (E.D. Va. April 4, 2018); Carroll v. ABNB\\n\\nFederal Credit Union, 2018 WL 1180317 (E.D. Va. March 5, 2018); Carroll v.\\n\\nNorthwest Federal Credit Union, 2018 WL 2933407 (E.D. Va. Jan. 26, 2018), adhered to\\n\\non reconsideration, 2018 WL 2933408 (E.D. Va. April 16, 2018). The Constitution\\n\\ncontemplates a crucial albeit limited role for the federal judiciary. Our trial court\\n\\ncolleagues’ fidelity to this vision betrays no lack of feeling, only the presence of a\\n\\nprofound respect for law.\\n\\n For the foregoing reasons, the judgment of the district court is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 14\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4355885/\", \"author_raw\": \"Quattlebaum joined. Judge King wrote an opinion concurring\"}, {\"author\": \"KING, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"KING, Circuit Judge, concurring in the judgment:\\n\\n I write separately and concur in the determination of my fine colleagues to affirm\\n\\nthe district court. I agree with my friends that either a dignitary harm, or a harm in the\\n\\nform of the denial of access to information, can confer Article III standing under the\\n\\nAmericans with Disabilities Act of 1990, 42 U.S.C. § 12101 et seq. See Allen v. Wright,\\n\\n468 U.S. 737, 754-55 (1984) (recognizing that dignitary harm or stigmatic injury can\\n\\nconfer standing), abrogated on other grounds by Lexmark Int’l, Inc. v. Static Control\\n\\nComponents, Inc., 572 U.S. 118 (2014); Havens Realty Corp. v. Coleman, 455 U.S. 363,\\n\\n373-74 (1982) (concluding that “tester” had standing to pursue claim when deprived of\\n\\nstatutorily-required information). I disagree, however, that we need to assess and\\n\\ndelineate the boundaries of those principles.\\n\\n In my view, we should resolve this appeal by concluding only that the Complaint\\n\\nfails to sufficiently allege Griffin’s intent or plan to return to the Credit Union’s website,\\n\\nand that Griffin is therefore not entitled to the sole form of relief being sought, that is,\\n\\ninjunctive relief. See Nanni v. Aberdeen Marketplace, Inc., 878 F.3d 447, 455 (4th Cir.\\n\\n2017) (explaining that, to possess standing to seek injunctive relief, plaintiff must\\n\\nplausibly allege future injury). At bottom, the Complaint offers no plausible suggestion\\n\\nas to why Griffin would ever again visit the Credit Union’s website and suffer a future\\n\\ninjury. As I see it, that is all we need to say in order to decide his appeal.\\n\\n\\n\\n\\n 15\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4355885/\", \"author_raw\": \"KING, Circuit Judge, concurring\"}]}"},"judge1":{"kind":"string","value":"WILKINSON"},"judge2":{"kind":"string","value":"KING"},"judge3":{"kind":"string","value":"QUATTLEBAUM"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":3,"string":"3"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":2,"string":"2"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4578632/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Clarence GRIFFIN, Plaintiff - Appellant, v. DEPARTMENT OF LABOR FEDERAL CREDIT UNION, A/K/A DOLFCU, Defendant - Appellee, National Association of Federally-Insured Credit Unions; Credit Union National Association, Amici Supporting Appellee.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-03\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1312\n\n\nCLARENCE GRIFFIN,\n\n Plaintiff – Appellant,\n\n v.\n\nDEPARTMENT OF LABOR FEDERAL CREDIT UNION, a/k/a DOLFCU,\n\n Defendant – Appellee,\n\n------------------------------\n\nNATIONAL ASSOCIATION OF FEDERALLY-INSURED CREDIT UNIONS;\nCREDIT UNION NATIONAL ASSOCIATION,\n\n Amici Supporting Appellee.\n\n\n\nAppeal from the United States District Court for the Eastern District of Virginia, at\nAlexandria. T.S. Ellis, III, Senior District Judge. (1:17-cv-01419-TSE-IDD)\n\n\nArgued: October 30, 2018 Decided: January 3, 2019\n\n\nBefore WILKINSON, KING, and QUATTLEBAUM, Circuit Judges.\n\n\nAffirmed by published opinion. Judge Wilkinson wrote the opinion, in which Judge\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Clarence GRIFFIN, Plaintiff - Appellant, v. DEPARTMENT OF LABOR FEDERAL CREDIT UNION, A/K/A DOLFCU, Defendant - Appellee, National Association of Federally-Insured Credit Unions; Credit Union National Association, Amici Supporting Appellee.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-03\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1312\\n\\n\\nCLARENCE GRIFFIN,\\n\\n Plaintiff – Appellant,\\n\\n v.\\n\\nDEPARTMENT OF LABOR FEDERAL CREDIT UNION, a/k/a DOLFCU,\\n\\n Defendant – Appellee,\\n\\n------------------------------\\n\\nNATIONAL ASSOCIATION OF FEDERALLY-INSURED CREDIT UNIONS;\\nCREDIT UNION NATIONAL ASSOCIATION,\\n\\n Amici Supporting Appellee.\\n\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. T.S. Ellis, III, Senior District Judge. (1:17-cv-01419-TSE-IDD)\\n\\n\\nArgued: October 30, 2018 Decided: January 3, 2019\\n\\n\\nBefore WILKINSON, KING, and QUATTLEBAUM, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Wilkinson wrote the opinion, in which Judge\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":81,"cells":{"id":{"kind":"number","value":4578972,"string":"4,578,972"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff - Appellee, v. Thomas Anthony HAMMOND, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Thomas Hammond"},"decision_date":{"kind":"string","value":"2019-01-04"},"docket_number":{"kind":"string","value":"17-4702"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Agee, Keenan, Richardson\", \"parties\": \"\", \"opinions\": [{\"author\": \"BARBARA MILANO KEENAN, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-4702\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nTHOMAS ANTHONY HAMMOND,\\n\\n Defendant - Appellant.\\n\\n\\nAppeal from the United States District Court for the Western District of North Carolina,\\nat Charlotte. Robert J. Conrad, Jr., District Judge. (3:17-cr-00044-RJC-DSC-1)\\n\\n\\nArgued: November 1, 2018 Decided: January 4, 2019\\n\\n\\nBefore AGEE, KEENAN, and RICHARDSON, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Keenan wrote the opinion, in which Judge Agee\\nand Judge Richardson joined.\\n\\n\\nARGUED: Ann Loraine Hester, FEDERAL DEFENDERS OF WESTERN NORTH\\nCAROLINA, INC., Charlotte, North Carolina, for Appellant. Anthony Joseph Enright,\\nOFFICE OF THE UNITED STATES ATTORNEY, Charlotte, North Carolina, for\\nAppellee. ON BRIEF: Anthony Martinez, Federal Public Defender, FEDERAL\\nDEFENDERS OF WESTERN NORTH CAROLINA, INC., Charlotte, North Carolina,\\nfor Appellant. R. Andrew Murray, United States Attorney, OFFICE OF THE UNITED\\nSTATES ATTORNEY, Charlotte, North Carolina, for Appellee.\\n\\fBARBARA MILANO KEENAN, Circuit Judge:\\n\\n In this appeal, we consider whether the offense of New York first-degree robbery,\\n\\nin violation of New York Penal Law § 160.15, qualifies as a “crime of violence” for\\n\\npurposes of the United States Sentencing Guidelines § 4B1.1 “career offender”\\n\\nenhancement. Thomas Anthony Hammond contends that the district court erred in\\n\\nsentencing him as a career offender, in part based on his prior conviction for that offense.\\n\\nAmong other things, Hammond argues that the crime of first-degree robbery under New\\n\\nYork law does not qualify as a crime of violence under the Guidelines’ “force clause.”\\n\\nWe disagree and, upon our review, conclude that New York statutory robbery,\\n\\nirrespective of the degree of the offense, is a crime of violence, because it necessarily\\n\\ninvolves the “use, attempted use, or threatened use of physical force against the person of\\n\\nanother.” U.S.S.G. § 4B1.2(a)(1). Accordingly, we affirm the district court’s judgment.\\n\\n\\n\\n I.\\n\\n In 2017, Hammond pleaded guilty to one count of attempted bank robbery and one\\n\\ncount of bank robbery, both in violation of 18 U.S.C. § 2113(a). Before sentencing, the\\n\\nprobation officer prepared a presentence report, which included a summary of\\n\\nHammond’s criminal history. The criminal history showed that Hammond previously\\n\\nhad been convicted of North Carolina common law robbery, and of New York first-\\n\\ndegree robbery, in violation of New York Penal Law § 160.15.\\n\\n Based on these convictions, the probation officer recommended that the district\\n\\ncourt impose the career offender sentencing enhancement under Guidelines § 4B1.1(a).\\n\\n 2\\n\\fApplying this enhancement, the probation officer calculated a Guidelines range of\\n\\nbetween 151 and 188 months’ imprisonment. Hammond contends that without the career\\n\\noffender enhancement, his advisory sentencing range would have been between 84 and\\n\\n105 months’ imprisonment.\\n\\n Hammond objected to his classification as a career offender, arguing that his\\n\\nconviction for New York first-degree robbery did not qualify as a crime of violence under\\n\\nthe Guidelines. 1 The district court rejected Hammond’s argument and imposed a\\n\\nsentence of 168 months’ imprisonment, followed by three years of supervised release.\\n\\nHammond now appeals.\\n\\n\\n\\n II.\\n\\n Hammond advances the same argument on appeal that he raised in the district\\n\\ncourt. Thus, we consider whether the offense of New York first-degree robbery, in\\n\\nviolation of New York Penal Law § 160.15, qualifies as a crime of violence within the\\n\\nmeaning of Guidelines § 4B1.1. This question presents an issue of law, which we review\\n\\nde novo. United States v. Jenkins, 631 F.3d 680, 682 (4th Cir. 2011).\\n\\n A.\\n\\n Before addressing Hammond’s arguments, we begin with an overview of the\\n\\nGuidelines’ career offender enhancement. Under Guidelines § 4B1.1, a defendant\\n\\n 1\\n Because we have concluded that North Carolina common law robbery “qualifies\\nas ‘robbery,’ as that term is used in U.S.S.G. § 4B1.2(a)(2),” Hammond concedes that his\\nconviction for North Carolina common law robbery qualifies as a predicate offense under\\nthe Guidelines. See United States v. Gattis, 877 F.3d 150, 160 (4th Cir. 2017).\\n\\n 3\\n\\fqualifies as a career offender if he has “at least two prior felony convictions for either a\\n\\ncrime of violence or a controlled substance offense.” U.S.S.G. § 4B1.1(a)(3). A “crime\\n\\nof violence” is defined as any state or federal offense punishable by imprisonment for a\\n\\nterm exceeding one year, that\\n\\n (1) has as an element the use, attempted use, or threatened use of physical\\n force against the person of another [the force clause], or\\n\\n (2) is murder, voluntary manslaughter, kidnapping, aggravated assault, a\\n forcible sex offense, robbery, arson, extortion or the use or unlawful\\n possession of a firearm . . . or explosive material [the enumerated\\n offense clause].\\n\\nId. § 4B1.2(a).\\n\\n We focus our analysis on the force clause of subparagraph (1) set forth above,\\n\\nbecause that clause provides the most direct route to answering the question before us.\\n\\nTo determine whether a conviction for a state offense is a crime of violence under the\\n\\nforce clause, we apply the “categorical approach.” United States v. Gardner, 823 F.3d\\n\\n793, 802 (4th Cir. 2016). Under that approach, the state crime necessarily must have as\\n\\nan element the “use, attempted use, or threatened use of physical force against the person\\n\\nof another” to qualify as a crime of violence under the force clause. U.S.S.G. §\\n\\n4B1.2(a)(1). The Supreme Court has interpreted the term “physical force” as “violent\\n\\nforce—that is, force capable of causing physical pain or injury to another person.”\\n\\nJohnson v. United States, 559 U.S. 133, 140 (2010). If the elements of the state offense\\n\\ncan be satisfied by “de minimis physical contact,” the offense does not qualify\\n\\ncategorically as a crime of violence. See United States v. Burns-Johnson, 864 F.3d 313,\\n\\n316 (4th Cir. 2017).\\n\\n 4\\n\\f In making this assessment, we review the elements of the offense and “the\\n\\nminimum conduct necessary for a violation” as defined by state law. See Gardner, 823\\n\\nF.3d at 803 (citation omitted). To determine the “minimum conduct” required for the\\n\\nstate offense, this Court must ensure that there is “a realistic probability, not a theoretical\\n\\npossibility, that a state would actually punish that conduct.” United States v. Doctor, 842\\n\\nF.3d 306, 308 (4th Cir. 2016) (internal quotation marks and citation omitted). With this\\n\\nframework in mind, we turn to consider Hammond’s arguments.\\n\\n B.\\n\\n Hammond raises two arguments in support of his contention that New York first-\\n\\ndegree robbery does not constitute a crime of violence. He contends (1) that New York\\n\\nrobbery, regardless of degree, does not include as an element the use of violent physical\\n\\nforce as defined by the Supreme Court, and (2) that New York first-degree robbery in\\n\\nparticular can be committed without the use of any force. We address each argument in\\n\\nturn.\\n\\n 1.\\n\\n Hammond first argues that New York robbery does not qualify categorically as a\\n\\ncrime of violence, because the offense does not require the use of violent physical force\\n\\n“capable of causing physical pain or injury to another person.” Johnson, 559 U.S. at 140.\\n\\nHe contends that New York courts have interpreted New York’s robbery statutes to\\n\\nrequire only de minimis force, such as “mere snatching.” We disagree with Hammond’s\\n\\nargument.\\n\\n\\n\\n 5\\n\\f At the outset, we note that this Court, in an unpublished decision, recently\\n\\nconcluded that New York second- and third-degree robbery constitute violent felonies\\n\\nunder the identically-worded force clause of the Armed Career Criminal Act (ACCA), 18\\n\\nU.S.C. § 924(e). United States v. Bowles, 733 F. App’x 699, 702 (4th Cir. 2018).\\n\\nBecause unpublished decisions may constitute persuasive, but not binding, authority, we\\n\\nindependently examine the New York statutes. See Collins v. Pond Creek Mining Co.,\\n\\n468 F.3d 213, 219 (4th Cir. 2006).\\n\\n New York has divided its robbery offense into three distinct statutes (the New\\n\\nYork robbery statutes), each involving an increasing degree of culpable conduct. N.Y.\\n\\nPenal Law §§ 160.00-160.15; see People v. Miller, 661 N.E.2d 1358, 1360-61 (N.Y.\\n\\n1995). All the New York robbery statutes, however, require the same element of force,\\n\\nnamely, “forcible stealing.” See N.Y. Penal Law § 160.00. Stated differently, the “core\\n\\ncrime” of New York robbery, irrespective of degree, is defined as “forcibly steal[ing]\\n\\nproperty.” Id.; Miller, 661 N.E.2d at 1360 (“The essence of the [New York] crime of\\n\\nrobbery is forcible stealing.”). Accordingly, if “forcible stealing” requires the use of\\n\\n“force capable of causing physical pain or injury,” Johnson, 559 U.S. at 140, the New\\n\\nYork robbery statutes all qualify as predicate offenses under the Guidelines’ force clause.\\n\\n A person “forcibly steals property” under New York law when\\n\\n in the course of committing a larceny, he uses or threatens the immediate\\n use of physical force upon another person for the purpose of:\\n\\n 1. Preventing or overcoming resistance to the taking of the property or\\n to the retention thereof immediately after the taking; or\\n\\n\\n\\n 6\\n\\f 2. Compelling the owner of such property or another person to deliver\\n up the property or to engage in other conduct which aids in the commission\\n of the larceny.\\n\\nN.Y. Penal Law § 160.00 (emphasis added). Although “physical force” in this context is\\n\\nnot defined, New York law gives common-law terms their common-law meanings, unless\\n\\ncontext suggests otherwise. People v. King, 463 N.E.2d 601, 603 (N.Y. 1984). “Physical\\n\\nforce” as used to define robbery under the common law has “long been understood to\\n\\nrequire violent force or intimidation of violent force.” Perez v. United States, 885 F.3d\\n\\n984, 988-89 (6th Cir. 2018) (citations omitted). Thus, the plain language of the New\\n\\nYork robbery statutes suggests that the use or threat of violent physical force is required\\n\\nfor all degrees of the offense. See United States v. Pereira-Gomez, 903 F.3d 155, 165 (2d\\n\\nCir. 2018) (“By its plain language . . . New York’s robbery statute includes as an element\\n\\nthe use of violent force.”).\\n\\n This interpretation is supported by New York case law applying the New York\\n\\nrobbery statutes. New York courts have interpreted “forcible stealing” to require\\n\\n“significantly more [force] than mere unwanted physical contact.” People v. Curet, 683\\n\\nN.Y.S.2d 602, 603 (N.Y. App. Div. 1998); see People v. Chatman, 833 N.Y.S.2d 794,\\n\\n795 (N.Y. App. Div. 2007) (affirming second-degree robbery conviction when the\\n\\ndefendant pushed the victim aside and entered her vehicle, later breaking the victim’s\\n\\nhold by driving away); People v. Dixon, 648 N.Y.S.2d 1009, 1010 (N.Y. App. Div. 1996)\\n\\n(concluding that evidence that a victim “experienced pain in her neck and suffered a\\n\\nscratch” as a result of the defendant pulling the victim’s necklaces was sufficient to\\n\\nsupport the defendant’s conviction for third-degree robbery). Indeed, New York courts\\n\\n 7\\n\\fconsistently have reversed robbery convictions when the taking at issue was committed\\n\\nwithout the use or threat of significant physical force. See, e.g., People v. Dobbs, 805\\n\\nN.Y.S.2d 734, 735-36 (N.Y. App. Div. 2005) (affirming reduction in charge from third-\\n\\ndegree robbery to petit larceny because there was “no indication” that the victim was\\n\\nthreatened or injured by the defendant); People v. Middleton, 623 N.Y.S.2d 298, 299\\n\\n(N.Y. App. Div. 1995) (reversing a third-degree robbery conviction when the victim was\\n\\nnot “intimidated, knocked down, struck, or injured”). Thus, we do not discern any\\n\\nmaterial difference between the amount of force required under the New York robbery\\n\\nstatutes and the violent physical force necessary to satisfy the Guidelines’ force clause.\\n\\nSee Johnson, 559 U.S. at 142 (recognizing that violent force requires more than “a mere\\n\\nunwanted touching”).\\n\\n Contrary to Hammond’s contention, the great weight of New York authority\\n\\nestablishes that the act of merely “snatching” property from a victim does not amount to\\n\\n“forcibly steal[ing] property” from a person. See, e.g., People v. Chessman, 429\\n\\nN.Y.S.2d 224, 227-29 (N.Y. App. Div. 1980) (holding that a purse snatching when the\\n\\nvictim “did not feel anything on her body” did not constitute third-degree robbery under\\n\\nNew York law); People v. Davis, 418 N.Y.S.2d 127, 128 (N.Y. App. Div. 1979)\\n\\n(concluding that a purse snatching did not amount to third-degree robbery in the absence\\n\\nof evidence that the victim “was injured or was in danger of injury”). Indeed, the New\\n\\nYork Court of Appeals recently stated that “a taking ‘by sudden or stealthy seizure or\\n\\nsnatching,’” such as “pickpocketing” or “jostling” a victim, is insufficient to support a\\n\\nconviction for New York second-degree robbery. People v. Jurgins, 46 N.E.3d 1048,\\n\\n 8\\n\\f1052-53 (N.Y. 2015). Based on the foregoing, we conclude that all the New York\\n\\nrobbery statutes have as an element the use or threatened use of violent physical force\\n\\nsufficient to satisfy the force clause of Guidelines § 4B2.1(a)(1). 2\\n\\n Notably, none of the decisions on which Hammond relies suggests a different\\n\\nresult. Hammond first cites to a decision in which a defendant and a victim had “tugged\\n\\nat each other” until the defendant was able to pull his hand away. People v. Safon, 560\\n\\nN.Y.S.2d 552, 552 (N.Y. App. Div. 1990). The court in Safon concluded that the\\n\\ninteraction between the defendant and the victim was sufficient to uphold a conviction for\\n\\nNew York third-degree robbery. Id.\\n\\n We recognize that an offense that requires only a “slight degree of force” does not\\n\\nqualify as a crime of violence under the Guidelines’ force clause. See United States v.\\n\\nWinston, 850 F.3d 677, 685 (4th Cir. 2017) (internal quotation marks and citation\\n\\nomitted). Nonetheless, the Supreme Court has emphasized that, to constitute a crime of\\n\\nviolence, a state offense need only require force that is “capable of causing physical pain\\n\\nor injury,” such as a “slap in the face.” Johnson, 559 U.S. at 140, 143 (emphasis added).\\n\\nIf a slap constitutes enough physical force to satisfy Johnson, we cannot say that a pull,\\n\\n\\n 2\\n We note that our conclusion is consistent with the majority of courts of appeals\\nto consider whether the New York robbery statutes require, as an element, the use or\\nthreatened use of violent physical force. See United States v. Pereira-Gomez, 903 F.3d\\n155, 166 (2d Cir. 2018) (concluding that New York second-degree robbery qualifies as a\\ncrime of violence under Section 2L1.2 of the Guidelines); United States v. Williams, 899\\nF.3d 659, 663-65 (8th Cir. 2018) (same); Perez, 855 F.3d at 989 (holding that New York\\nsecond-degree robbery qualifies as a violent felony for purposes of the ACCA). But see\\nUnited States v. Steed, 879 F.3d 440, 448-50 (1st Cir. 2018) (concluding that New York\\nsecond-degree robbery is not a crime of violence under Guidelines § 4B2.1(a)).\\n\\n 9\\n\\fpowerful enough to break a person’s grip, would not be “capable of causing physical\\n\\npain.” 3 Id. at 140.\\n\\n Hammond next cites to a New York state case in which the defendant and three\\n\\nothers “formed a human wall that blocked the victim’s path as the victim attempted to\\n\\npursue” the defendant, who had “picked” the victim’s “pocket,” People v. Bennett, 631\\n\\nN.Y.S.2d 834, 834 (N.Y. App. Div. 1995), and to another case in which the defendant\\n\\nphysically “block[ed] the victim’s passage,” People v. Patton, 585 N.Y.S.2d 431, 431\\n\\n(N.Y. App. Div. 1992). Hammond contends that because there was no actual force\\n\\nemployed against the victims in those cases, yet the defendants were convicted of New\\n\\nYork second-degree robbery, the decisions in Bennett and Patton demonstrate that\\n\\n“forcible stealing” can be committed without any use or threatened use of force.\\n\\n Hammond, however, minimizes the defendants’ conduct in those cases. In Patton,\\n\\nthe defendant not only blocked the victim’s path, but “persistently shoved [the victim]\\n\\nback” multiple times. Id. The codefendant in that case also stole the victim’s gold chain\\n\\nby “yank[ing]” it from the victim’s neck, “scratching the victim and tearing his shirt.” Id.\\n\\n\\n 3\\n We disagree with Hammond’s argument that this Court’s decisions in Winston,\\n850 F.3d 677, and Gardner, 823 F.3d 793, require a different result here. In Winston and\\nGardner, we considered whether Virginia’s and North Carolina’s respective common law\\nrobbery crimes constituted “violent felonies” under the ACCA. See Winston, 850 F.3d at\\n685; Gardner, 823 F.3d at 803-04. Based on each states’ interpretation of its own\\nrobbery offense, we concluded that each respective crime could be committed without the\\nforce required by the Supreme Court. See Winston, 850 F.3d at 685; Gardner, 823 F.3d\\nat 803-04. We conduct the same analysis in the present case, applying the same legal\\nstandards. That we reach a different conclusion based on New York courts’\\ninterpretation of the New York robbery statutes does not create a tension among our\\ncases.\\n\\n 10\\n\\fTaken as a whole, the conduct at issue in Patton plainly involved the use or threatened\\n\\nuse of violent physical force.\\n\\n With respect to Bennett, Hammond correctly observes that the defendant in that\\n\\ncase did not use actual force against the victim. Nonetheless, Hammond fails to\\n\\nrecognize that the defendant’s action with others of forming the “human wall” involved\\n\\nthe “threatened use of physical force.” See Bennett, 631 N.Y.S.2d at 834. Stated\\n\\ndifferently, the actions of the defendant and his accomplices involved a threat of violent\\n\\nforce that dissuaded the victim from attempting to break through the human wall or\\n\\notherwise to pursue the defendant. Accord Pereira-Gomez, 903 F.3d at 166; Perez, 885\\n\\nF.3d at 989-90. Because the Guidelines’ force clause includes the “threatened use of\\n\\nphysical force,” U.S.S.G. § 4B2.1(a)(1), the cases on which Hammond relies involve a\\n\\ndegree of threatened force sufficient to come within the scope of the Guidelines’ career\\n\\noffender enhancement.\\n\\n 2.\\n\\n In a related argument, Hammond contends that, regardless of New York’s\\n\\nstatutory definition of robbery, New York first-degree robbery is not a crime of violence\\n\\nbecause that statute can be violated by merely possessing, without displaying, a deadly\\n\\nweapon. See N.Y. Penal Law § 160.15(2) (“A person is guilty of robbery in the first\\n\\ndegree when he forcibly steals property and when . . . [he] is armed with a deadly\\n\\nweapon.”). However, Hammond misconstrues New York’s first-degree robbery statute.\\n\\n As we have explained, the New York robbery statutes all require that the\\n\\nprosecution prove the same element of “forcible stealing.” See People v. Gordon, 16\\n\\n 11\\n\\fN.E.3d 1178, 1183-84 (N.Y. 2014). A person is guilty of New York first-degree robbery\\n\\nwhen he “forcibly steals property,” as defined in New York Penal Law § 160.00, and his\\n\\nconduct satisfies one of four additional aggravating circumstances, such as being armed\\n\\nwith a deadly weapon. 4 See N.Y. Penal Law § 160.15. Thus, anyone convicted of New\\n\\nYork first-degree robbery necessarily has been convicted of “us[ing] or threaten[ing] the\\n\\nimmediate use of physical force upon another person.” Id. § 160.00; see Miller, 661\\n\\nN.E.2d at 1360-62.\\n\\n The aggravating factors necessary to commit New York first-degree robbery do\\n\\nnot eliminate the “core” physical force element of New York robbery, but merely elevate\\n\\nthe crime based on additional culpable conduct. See Miller, 661 N.E.2d at 1360-61; see\\n\\nalso Perez, 885 F.3d at 988. Accordingly, because all the New York robbery statutes\\n\\nrequire the same element of violent physical force or threatened violent force, New York\\n\\nfirst-degree robbery qualifies as a crime of violence under Guidelines § 4B1.2(a)(1). 5\\n\\n\\n\\n\\n 4\\n The other aggravating circumstances are when the defendant: (1) “[c]auses\\nserious physical injury to any person who is not a participant in the crime;” (2) “[u]ses or\\nthreatens the immediate use of a dangerous instrument;” or (3) displays certain types of\\noperable firearms. N.Y. Penal Law § 160.15.\\n 5\\n For the same reason, we reject Hammond’s contention that we must apply the\\nmodified categorical approach to New York’s first-degree robbery statute. The modified\\ncategorical approach is not required when each of the crimes into which a statute may be\\ndivided constitutes a crime of violence. See United States v. Cabrera-Umanzor, 728 F.3d\\n347, 352 (4th Cir. 2013) (citing Descamps v. United States, 570 U.S. 254, 264 (2013)).\\nBecause we conclude that all subsections of New York first-degree robbery qualify as\\ncrimes of violence, we need not apply the modified categorical approach.\\n\\n 12\\n\\f III.\\n\\n For these reasons, we hold that Hammond’s conviction for New York first-degree\\n\\nrobbery qualifies as a crime of violence under the force clause of Guidelines §\\n\\n4B1.2(a)(1). 6 We therefore affirm the district court’s judgment.\\n\\n AFFIRMED\\n\\n\\n\\n\\n 6\\n Based on our holding, we need not address Hammond’s alternative argument\\nconcerning whether New York first-degree robbery qualifies as a crime of violence under\\nthe “enumerated offense” clause of Guidelines § 4B1.2(a)(2).\\n\\n\\n 13\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4356225/\", \"author_raw\": \"BARBARA MILANO KEENAN, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"AGEE"},"judge2":{"kind":"string","value":"KEENAN"},"judge3":{"kind":"string","value":"RICHARDSON"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4578972/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Thomas Anthony HAMMOND, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-04\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-4702\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff - Appellee,\n\n v.\n\nTHOMAS ANTHONY HAMMOND,\n\n Defendant - Appellant.\n\n\nAppeal from the United States District Court for the Western District of North Carolina,\nat Charlotte. Robert J. Conrad, Jr., District Judge. (3:17-cr-00044-RJC-DSC-1)\n\n\nArgued: November 1, 2018 Decided: January 4, 2019\n\n\nBefore AGEE, KEENAN, and RICHARDSON, Circuit Judges.\n\n\nAffirmed by published opinion. Judge Keenan wrote the opinion, in which Judge Agee\nand Judge Richardson joined.\n\n\nARGUED: Ann Loraine Hester, FEDERAL DEFENDERS OF WESTERN NORTH\nCAROLINA, INC., Charlotte, North Carolina, for Appellant. Anthony Joseph Enright,\nOFFICE OF THE UNITED STATES ATTORNEY, Charlotte, North Carolina, for\nAppellee. ON BRIEF: Anthony Martinez, Federal Public Defender, FEDERAL\nDEFENDERS OF WESTERN NORTH CAROLINA, INC., Charlotte, North Carolina,\nfor Appellant. R. Andrew Murray, United States Attorney, OFFICE OF THE UNITED\nSTATES ATTORNEY, Charlotte, North Carolina, for Appellee.\n\fBARBARA MILANO KEENAN, Circuit Judge:\n\n In this appeal, we consider whether the offense of New York first-degree robbery,\n\nin violation of New York Penal Law § 160.15, qualifies as a “crime of violence” for\n\npurposes of the United States Sentencing Guidelines § 4B1.1 “career offender”\n\nenhancement. Thomas Anthony Hammond contends that the district court erred in\n\nsentencing him as a career offender, in part based on his prior conviction for that offense.\n\nAmong other things, Hammond argues that the crime of first-degree robbery under New\n\nYork law does not qualify as a crime of violence under the Guidelines’ “force clause.”\n\nWe disagree and, upon our review, conclude that New York statutory robbery,\n\nirrespective of the degree of the offense, is a crime of violence, because it necessarily\n\ninvolves the “use, attempted use, or threatened use of physical force against the person of\n\nanother.” U.S.S.G. § 4B1.2(a)(1). Accordingly, we affirm the district court’s judgment.\n\n\n\n I.\n\n In 2017, Hammond pleaded guilty to one count of attempted bank robbery and one\n\ncount of bank robbery, both in violation of 18 U.S.C. § 2113(a). Before sentencing, the\n\nprobation officer prepared a presentence report, which included a summary of\n\nHammond’s criminal history. The criminal history showed that Hammond previously\n\nhad been convicted of North Carolina common law robbery, and of New York first-\n\ndegree robbery, in violation of New York Penal Law § 160.15.\n\n Based on these convictions, the probation officer recommended that the district\n\ncourt impose the career offender sentencing enhancement under Guidelines § 4B1.1(a).\n\n 2\n\fApplying this enhancement, the probation officer calculated a Guidelines range of\n\nbetween 151 and 188 months’ imprisonment. Hammond contends that without the career\n\noffender enhancement, his advisory sentencing range would have been between 84 and\n\n105 months’ imprisonment.\n\n Hammond objected to his classification as a career offender, arguing that his\n\nconviction for New York first-degree robbery did not qualify as a crime of violence under\n\nthe Guidelines. 1 The district court rejected Hammond’s argument and imposed a\n\nsentence of 168 months’ imprisonment, followed by three years of supervised release.\n\nHammond now appeals.\n\n\n\n II.\n\n Hammond advances the same argument on appeal that he raised in the district\n\ncourt. Thus, we consider whether the offense of New York first-degree robbery, in\n\nviolation of New York Penal Law § 160.15, qualifies as a crime of violence within the\n\nmeaning of Guidelines § 4B1.1. This question presents an issue of law, which we review\n\nde novo. United States v. Jenkins, 631 F.3d 680, 682 (4th Cir. 2011).\n\n A.\n\n Before addressing Hammond’s arguments, we begin with an overview of the\n\nGuidelines’ career offender enhancement. Under Guidelines § 4B1.1, a defendant\n\n 1\n Because we have concluded that North Carolina common law robbery “qualifies\nas ‘robbery,’ as that term is used in U.S.S.G. § 4B1.2(a)(2),” Hammond concedes that his\nconviction for North Carolina common law robbery qualifies as a predicate offense under\nthe Guidelines. See United States v. Gattis, 877 F.3d 150, 160 (4th Cir. 2017).\n\n 3\n\fqualifies as a career offender if he has “at least two prior felony convictions for either a\n\ncrime of violence or a controlled substance offense.” U.S.S.G. § 4B1.1(a)(3). A “crime\n\nof violence” is defined as any state or federal offense punishable by imprisonment for a\n\nterm exceeding one year, that\n\n (1) has as an element the use, attempted use, or threatened use of physical\n force against the person of another [the force clause], or\n\n (2) is murder, voluntary manslaughter, kidnapping, aggravated assault, a\n forcible sex offense, robbery, arson, extortion or the use or unlawful\n possession of a firearm . . . or explosive material [the enumerated\n offense clause].\n\nId. § 4B1.2(a).\n\n We focus our analysis on the force clause of subparagraph (1) set forth above,\n\nbecause that clause provides the most direct route to answering the question before us.\n\nTo determine whether a conviction for a state offense is a crime of violence under the\n\nforce clause, we apply the “categorical approach.” United States v. Gardner, 823 F.3d\n\n793, 802 (4th Cir. 2016). Under that approach, the state crime necessarily must have as\n\nan element the “use, attempted use, or threatened use of physical force against the person\n\nof another” to qualify as a crime of violence under the force clause. U.S.S.G. §\n\n4B1.2(a)(1). The Supreme Court has interpreted the term “physical force” as “violent\n\nforce—that is, force capable of causing physical pain or injury to another person.”\n\nJohnson v. United States, 559 U.S. 133, 140 (2010). If the elements of the state offense\n\ncan be satisfied by “de minimis physical contact,” the offense does not qualify\n\ncategorically as a crime of violence. See United States v. Burns-Johnson, 864 F.3d 313,\n\n316 (4th Cir. 2017).\n\n 4\n\f In making this assessment, we review the elements of the offense and “the\n\nminimum conduct necessary for a violation” as defined by state law. See Gardner, 823\n\nF.3d at 803 (citation omitted). To determine the “minimum conduct” required for the\n\nstate offense, this Court must ensure that there is “a realistic probability, not a theoretical\n\npossibility, that a state would actually punish that conduct.” United States v. Doctor, 842\n\nF.3d 306, 308 (4th Cir. 2016) (internal quotation marks and citation omitted). With this\n\nframework in mind, we turn to consider Hammond’s arguments.\n\n B.\n\n Hammond raises two arguments in support of his contention that New York first-\n\ndegree robbery does not constitute a crime of violence. He contends (1) that New York\n\nrobbery, regardless of degree, does not include as an element the use of violent physical\n\nforce as defined by the Supreme Court, and (2) that New York first-degree robbery in\n\nparticular can be committed without the use of any force. We address each argument in\n\nturn.\n\n 1.\n\n Hammond first argues that New York robbery does not qualify categorically as a\n\ncrime of violence, because the offense does not require the use of violent physical force\n\n“capable of causing physical pain or injury to another person.” Johnson, 559 U.S. at 140.\n\nHe contends that New York courts have interpreted New York’s robbery statutes to\n\nrequire only de minimis force, such as “mere snatching.” We disagree with Hammond’s\n\nargument.\n\n\n\n 5\n\f At the outset, we note that this Court, in an unpublished decision, recently\n\nconcluded that New York second- and third-degree robbery constitute violent felonies\n\nunder the identically-worded force clause of the Armed Career Criminal Act (ACCA), 18\n\nU.S.C. § 924(e). United States v. Bowles, 733 F. App’x 699, 702 (4th Cir. 2018).\n\nBecause unpublished decisions may constitute persuasive, but not binding, authority, we\n\nindependently examine the New York statutes. See Collins v. Pond Creek Mining Co.,\n\n468 F.3d 213, 219 (4th Cir. 2006).\n\n New York has divided its robbery offense into three distinct statutes (the New\n\nYork robbery statutes), each involving an increasing degree of culpable conduct. N.Y.\n\nPenal Law §§ 160.00-160.15; see People v. Miller, 661 N.E.2d 1358, 1360-61 (N.Y.\n\n1995). All the New York robbery statutes, however, require the same element of force,\n\nnamely, “forcible stealing.” See N.Y. Penal Law § 160.00. Stated differently, the “core\n\ncrime” of New York robbery, irrespective of degree, is defined as “forcibly steal[ing]\n\nproperty.” Id.; Miller, 661 N.E.2d at 1360 (“The essence of the [New York] crime of\n\nrobbery is forcible stealing.”). Accordingly, if “forcible stealing” requires the use of\n\n“force capable of causing physical pain or injury,” Johnson, 559 U.S. at 140, the New\n\nYork robbery statutes all qualify as predicate offenses under the Guidelines’ force clause.\n\n A person “forcibly steals property” under New York law when\n\n in the course of committing a larceny, he uses or threatens the immediate\n use of physical force upon another person for the purpose of:\n\n 1. Preventing or overcoming resistance to the taking of the property or\n to the retention thereof immediately after the taking; or\n\n\n\n 6\n\f 2. Compelling the owner of such property or another person to deliver\n up the property or to engage in other conduct which aids in the commission\n of the larceny.\n\nN.Y. Penal Law § 160.00 (emphasis added). Although “physical force” in this context is\n\nnot defined, New York law gives common-law terms their common-law meanings, unless\n\ncontext suggests otherwise. People v. King, 463 N.E.2d 601, 603 (N.Y. 1984). “Physical\n\nforce” as used to define robbery under the common law has “long been understood to\n\nrequire violent force or intimidation of violent force.” Perez v. United States, 885 F.3d\n\n984, 988-89 (6th Cir. 2018) (citations omitted). Thus, the plain language of the New\n\nYork robbery statutes suggests that the use or threat of violent physical force is required\n\nfor all degrees of the offense. See United States v. Pereira-Gomez, 903 F.3d 155, 165 (2d\n\nCir. 2018) (“By its plain language . . . New York’s robbery statute includes as an element\n\nthe use of violent force.”).\n\n This interpretation is supported by New York case law applying the New York\n\nrobbery statutes. New York courts have interpreted “forcible stealing” to require\n\n“significantly more [force] than mere unwanted physical contact.” People v. Curet, 683\n\nN.Y.S.2d 602, 603 (N.Y. App. Div. 1998); see People v. Chatman, 833 N.Y.S.2d 794,\n\n795 (N.Y. App. Div. 2007) (affirming second-degree robbery conviction when the\n\ndefendant pushed the victim aside and entered her vehicle, later breaking the victim’s\n\nhold by driving away); People v. Dixon, 648 N.Y.S.2d 1009, 1010 (N.Y. App. Div. 1996)\n\n(concluding that evidence that a victim “experienced pain in her neck and suffered a\n\nscratch” as a result of the defendant pulling the victim’s necklaces was sufficient to\n\nsupport the defendant’s conviction for third-degree robbery). Indeed, New York courts\n\n 7\n\fconsistently have reversed robbery convictions when the taking at issue was committed\n\nwithout the use or threat of significant physical force. See, e.g., People v. Dobbs, 805\n\nN.Y.S.2d 734, 735-36 (N.Y. App. Div. 2005) (affirming reduction in charge from third-\n\ndegree robbery to petit larceny because there was “no indication” that the victim was\n\nthreatened or injured by the defendant); People v. Middleton, 623 N.Y.S.2d 298, 299\n\n(N.Y. App. Div. 1995) (reversing a third-degree robbery conviction when the victim was\n\nnot “intimidated, knocked down, struck, or injured”). Thus, we do not discern any\n\nmaterial difference between the amount of force required under the New York robbery\n\nstatutes and the violent physical force necessary to satisfy the Guidelines’ force clause.\n\nSee Johnson, 559 U.S. at 142 (recognizing that violent force requires more than “a mere\n\nunwanted touching”).\n\n Contrary to Hammond’s contention, the great weight of New York authority\n\nestablishes that the act of merely “snatching” property from a victim does not amount to\n\n“forcibly steal[ing] property” from a person. See, e.g., People v. Chessman, 429\n\nN.Y.S.2d 224, 227-29 (N.Y. App. Div. 1980) (holding that a purse snatching when the\n\nvictim “did not feel anything on her body” did not constitute third-degree robbery under\n\nNew York law); People v. Davis, 418 N.Y.S.2d 127, 128 (N.Y. App. Div. 1979)\n\n(concluding that a purse snatching did not amount to third-degree robbery in the absence\n\nof evidence that the victim “was injured or was in danger of injury”). Indeed, the New\n\nYork Court of Appeals recently stated that “a taking ‘by sudden or stealthy seizure or\n\nsnatching,’” such as “pickpocketing” or “jostling” a victim, is insufficient to support a\n\nconviction for New York second-degree robbery. People v. Jurgins, 46 N.E.3d 1048,\n\n 8\n\f1052-53 (N.Y. 2015). Based on the foregoing, we conclude that all the New York\n\nrobbery statutes have as an element the use or threatened use of violent physical force\n\nsufficient to satisfy the force clause of Guidelines § 4B2.1(a)(1). 2\n\n Notably, none of the decisions on which Hammond relies suggests a different\n\nresult. Hammond first cites to a decision in which a defendant and a victim had “tugged\n\nat each other” until the defendant was able to pull his hand away. People v. Safon, 560\n\nN.Y.S.2d 552, 552 (N.Y. App. Div. 1990). The court in Safon concluded that the\n\ninteraction between the defendant and the victim was sufficient to uphold a conviction for\n\nNew York third-degree robbery. Id.\n\n We recognize that an offense that requires only a “slight degree of force” does not\n\nqualify as a crime of violence under the Guidelines’ force clause. See United States v.\n\nWinston, 850 F.3d 677, 685 (4th Cir. 2017) (internal quotation marks and citation\n\nomitted). Nonetheless, the Supreme Court has emphasized that, to constitute a crime of\n\nviolence, a state offense need only require force that is “capable of causing physical pain\n\nor injury,” such as a “slap in the face.” Johnson, 559 U.S. at 140, 143 (emphasis added).\n\nIf a slap constitutes enough physical force to satisfy Johnson, we cannot say that a pull,\n\n\n 2\n We note that our conclusion is consistent with the majority of courts of appeals\nto consider whether the New York robbery statutes require, as an element, the use or\nthreatened use of violent physical force. See United States v. Pereira-Gomez, 903 F.3d\n155, 166 (2d Cir. 2018) (concluding that New York second-degree robbery qualifies as a\ncrime of violence under Section 2L1.2 of the Guidelines); United States v. Williams, 899\nF.3d 659, 663-65 (8th Cir. 2018) (same); Perez, 855 F.3d at 989 (holding that New York\nsecond-degree robbery qualifies as a violent felony for purposes of the ACCA). But see\nUnited States v. Steed, 879 F.3d 440, 448-50 (1st Cir. 2018) (concluding that New York\nsecond-degree robbery is not a crime of violence under Guidelines § 4B2.1(a)).\n\n 9\n\fpowerful enough to break a person’s grip, would not be “capable of causing physical\n\npain.” 3 Id. at 140.\n\n Hammond next cites to a New York state case in which the defendant and three\n\nothers “formed a human wall that blocked the victim’s path as the victim attempted to\n\npursue” the defendant, who had “picked” the victim’s “pocket,” People v. Bennett, 631\n\nN.Y.S.2d 834, 834 (N.Y. App. Div. 1995), and to another case in which the defendant\n\nphysically “block[ed] the victim’s passage,” People v. Patton, 585 N.Y.S.2d 431, 431\n\n(N.Y. App. Div. 1992). Hammond contends that because there was no actual force\n\nemployed against the victims in those cases, yet the defendants were convicted of New\n\nYork second-degree robbery, the decisions in Bennett and Patton demonstrate that\n\n“forcible stealing” can be committed without any use or threatened use of force.\n\n Hammond, however, minimizes the defendants’ conduct in those cases. In Patton,\n\nthe defendant not only blocked the victim’s path, but “persistently shoved [the victim]\n\nback” multiple times. Id. The codefendant in that case also stole the victim’s gold chain\n\nby “yank[ing]” it from the victim’s neck, “scratching the victim and tearing his shirt.” Id.\n\n\n 3\n We disagree with Hammond’s argument that this Court’s decisions in Winston,\n850 F.3d 677, and Gardner, 823 F.3d 793, require a different result here. In Winston and\nGardner, we considered whether Virginia’s and North Carolina’s respective common law\nrobbery crimes constituted “violent felonies” under the ACCA. See Winston, 850 F.3d at\n685; Gardner, 823 F.3d at 803-04. Based on each states’ interpretation of its own\nrobbery offense, we concluded that each respective crime could be committed without the\nforce required by the Supreme Court. See Winston, 850 F.3d at 685; Gardner, 823 F.3d\nat 803-04. We conduct the same analysis in the present case, applying the same legal\nstandards. That we reach a different conclusion based on New York courts’\ninterpretation of the New York robbery statutes does not create a tension among our\ncases.\n\n 10\n\fTaken as a whole, the conduct at issue in Patton plainly involved the use or threatened\n\nuse of violent physical force.\n\n With respect to Bennett, Hammond correctly observes that the defendant in that\n\ncase did not use actual force against the victim. Nonetheless, Hammond fails to\n\nrecognize that the defendant’s action with others of forming the “human wall” involved\n\nthe “threatened use of physical force.” See Bennett, 631 N.Y.S.2d at 834. Stated\n\ndifferently, the actions of the defendant and his accomplices involved a threat of violent\n\nforce that dissuaded the victim from attempting to break through the human wall or\n\notherwise to pursue the defendant. Accord Pereira-Gomez, 903 F.3d at 166; Perez, 885\n\nF.3d at 989-90. Because the Guidelines’ force clause includes the “threatened use of\n\nphysical force,” U.S.S.G. § 4B2.1(a)(1), the cases on which Hammond relies involve a\n\ndegree of threatened force sufficient to come within the scope of the Guidelines’ career\n\noffender enhancement.\n\n 2.\n\n In a related argument, Hammond contends that, regardless of New York’s\n\nstatutory definition of robbery, New York first-degree robbery is not a crime of violence\n\nbecause that statute can be violated by merely possessing, without displaying, a deadly\n\nweapon. See N.Y. Penal Law § 160.15(2) (“A person is guilty of robbery in the first\n\ndegree when he forcibly steals property and when . . . [he] is armed with a deadly\n\nweapon.”). However, Hammond misconstrues New York’s first-degree robbery statute.\n\n As we have explained, the New York robbery statutes all require that the\n\nprosecution prove the same element of “forcible stealing.” See People v. Gordon, 16\n\n 11\n\fN.E.3d 1178, 1183-84 (N.Y. 2014). A person is guilty of New York first-degree robbery\n\nwhen he “forcibly steals property,” as defined in New York Penal Law § 160.00, and his\n\nconduct satisfies one of four additional aggravating circumstances, such as being armed\n\nwith a deadly weapon. 4 See N.Y. Penal Law § 160.15. Thus, anyone convicted of New\n\nYork first-degree robbery necessarily has been convicted of “us[ing] or threaten[ing] the\n\nimmediate use of physical force upon another person.” Id. § 160.00; see Miller, 661\n\nN.E.2d at 1360-62.\n\n The aggravating factors necessary to commit New York first-degree robbery do\n\nnot eliminate the “core” physical force element of New York robbery, but merely elevate\n\nthe crime based on additional culpable conduct. See Miller, 661 N.E.2d at 1360-61; see\n\nalso Perez, 885 F.3d at 988. Accordingly, because all the New York robbery statutes\n\nrequire the same element of violent physical force or threatened violent force, New York\n\nfirst-degree robbery qualifies as a crime of violence under Guidelines § 4B1.2(a)(1). 5\n\n\n\n\n 4\n The other aggravating circumstances are when the defendant: (1) “[c]auses\nserious physical injury to any person who is not a participant in the crime;” (2) “[u]ses or\nthreatens the immediate use of a dangerous instrument;” or (3) displays certain types of\noperable firearms. N.Y. Penal Law § 160.15.\n 5\n For the same reason, we reject Hammond’s contention that we must apply the\nmodified categorical approach to New York’s first-degree robbery statute. The modified\ncategorical approach is not required when each of the crimes into which a statute may be\ndivided constitutes a crime of violence. See United States v. Cabrera-Umanzor, 728 F.3d\n347, 352 (4th Cir. 2013) (citing Descamps v. United States, 570 U.S. 254, 264 (2013)).\nBecause we conclude that all subsections of New York first-degree robbery qualify as\ncrimes of violence, we need not apply the modified categorical approach.\n\n 12\n\f III.\n\n For these reasons, we hold that Hammond’s conviction for New York first-degree\n\nrobbery qualifies as a crime of violence under the force clause of Guidelines §\n\n4B1.2(a)(1). 6 We therefore affirm the district court’s judgment.\n\n AFFIRMED\n\n\n\n\n 6\n Based on our holding, we need not address Hammond’s alternative argument\nconcerning whether New York first-degree robbery qualifies as a crime of violence under\nthe “enumerated offense” clause of Guidelines § 4B1.2(a)(2).\n\n\n 13\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Thomas Anthony HAMMOND, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-04\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-4702\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nTHOMAS ANTHONY HAMMOND,\\n\\n Defendant - Appellant.\\n\\n\\nAppeal from the United States District Court for the Western District of North Carolina,\\nat Charlotte. Robert J. Conrad, Jr., District Judge. (3:17-cr-00044-RJC-DSC-1)\\n\\n\\nArgued: November 1, 2018 Decided: January 4, 2019\\n\\n\\nBefore AGEE, KEENAN, and RICHARDSON, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Keenan wrote the opinion, in which Judge Agee\\nand Judge Richardson joined.\\n\\n\\nARGUED: Ann Loraine Hester, FEDERAL DEFENDERS OF WESTERN NORTH\\nCAROLINA, INC., Charlotte, North Carolina, for Appellant. Anthony Joseph Enright,\\nOFFICE OF THE UNITED STATES ATTORNEY, Charlotte, North Carolina, for\\nAppellee. ON BRIEF: Anthony Martinez, Federal Public Defender, FEDERAL\\nDEFENDERS OF WESTERN NORTH CAROLINA, INC., Charlotte, North Carolina,\\nfor Appellant. R. Andrew Murray, United States Attorney, OFFICE OF THE UNITED\\nSTATES ATTORNEY, Charlotte, North Carolina, for Appellee.\\n\\fBARBARA MILANO KEENAN, Circuit Judge:\\n\\n In this appeal, we consider whether the offense of New York first-degree robbery,\\n\\nin violation of New York Penal Law § 160.15, qualifies as a “crime of violence” for\\n\\npurposes of the United States Sentencing Guidelines § 4B1.1 “career offender”\\n\\nenhancement. Thomas Anthony Hammond contends that the district court erred in\\n\\nsentencing him as a career offender, in part based on his prior conviction for that offense.\\n\\nAmong other things, Hammond argues that the crime of first-degree robbery under New\\n\\nYork law does not qualify as a crime of violence under the Guidelines’ “force clause.”\\n\\nWe disagree and, upon our review, conclude that New York statutory robbery,\\n\\nirrespective of the degree of the offense, is a crime of violence, because it necessarily\\n\\ninvolves the “use, attempted use, or threatened use of physical force against the person of\\n\\nanother.” U.S.S.G. § 4B1.2(a)(1). Accordingly, we affirm the district court’s judgment.\\n\\n\\n\\n I.\\n\\n In 2017, Hammond pleaded guilty to one count of attempted bank robbery and one\\n\\ncount of bank robbery, both in violation of 18 U.S.C. § 2113(a). Before sentencing, the\\n\\nprobation officer prepared a presentence report, which included a summary of\\n\\nHammond’s criminal history. The criminal history showed that Hammond previously\\n\\nhad been convicted of North Carolina common law robbery, and of New York first-\\n\\ndegree robbery, in violation of New York Penal Law § 160.15.\\n\\n Based on these convictions, the probation officer recommended that the district\\n\\ncourt impose the career offender sentencing enhancement under Guidelines § 4B1.1(a).\\n\\n 2\\n\\fApplying this enhancement, the probation officer calculated a Guidelines range of\\n\\nbetween 151 and 188 months’ imprisonment. Hammond contends that without the career\\n\\noffender enhancement, his advisory sentencing range would have been between 84 and\\n\\n105 months’ imprisonment.\\n\\n Hammond objected to his classification as a career offender, arguing that his\\n\\nconviction for New York first-degree robbery did not qualify as a crime of violence under\\n\\nthe Guidelines. 1 The district court rejected Hammond’s argument and imposed a\\n\\nsentence of 168 months’ imprisonment, followed by three years of supervised release.\\n\\nHammond now appeals.\\n\\n\\n\\n II.\\n\\n Hammond advances the same argument on appeal that he raised in the district\\n\\ncourt. Thus, we consider whether the offense of New York first-degree robbery, in\\n\\nviolation of New York Penal Law § 160.15, qualifies as a crime of violence within the\\n\\nmeaning of Guidelines § 4B1.1. This question presents an issue of law, which we review\\n\\nde novo. United States v. Jenkins, 631 F.3d 680, 682 (4th Cir. 2011).\\n\\n A.\\n\\n Before addressing Hammond’s arguments, we begin with an overview of the\\n\\nGuidelines’ career offender enhancement. Under Guidelines § 4B1.1, a defendant\\n\\n 1\\n Because we have concluded that North Carolina common law robbery “qualifies\\nas ‘robbery,’ as that term is used in U.S.S.G. § 4B1.2(a)(2),” Hammond concedes that his\\nconviction for North Carolina common law robbery qualifies as a predicate offense under\\nthe Guidelines. See United States v. Gattis, 877 F.3d 150, 160 (4th Cir. 2017).\\n\\n 3\\n\\fqualifies as a career offender if he has “at least two prior felony convictions for either a\\n\\ncrime of violence or a controlled substance offense.” U.S.S.G. § 4B1.1(a)(3). A “crime\\n\\nof violence” is defined as any state or federal offense punishable by imprisonment for a\\n\\nterm exceeding one year, that\\n\\n (1) has as an element the use, attempted use, or threatened use of physical\\n force against the person of another [the force clause], or\\n\\n (2) is murder, voluntary manslaughter, kidnapping, aggravated assault, a\\n forcible sex offense, robbery, arson, extortion or the use or unlawful\\n possession of a firearm . . . or explosive material [the enumerated\\n offense clause].\\n\\nId. § 4B1.2(a).\\n\\n We focus our analysis on the force clause of subparagraph (1) set forth above,\\n\\nbecause that clause provides the most direct route to answering the question before us.\\n\\nTo determine whether a conviction for a state offense is a crime of violence under the\\n\\nforce clause, we apply the “categorical approach.” United States v. Gardner, 823 F.3d\\n\\n793, 802 (4th Cir. 2016). Under that approach, the state crime necessarily must have as\\n\\nan element the “use, attempted use, or threatened use of physical force against the person\\n\\nof another” to qualify as a crime of violence under the force clause. U.S.S.G. §\\n\\n4B1.2(a)(1). The Supreme Court has interpreted the term “physical force” as “violent\\n\\nforce—that is, force capable of causing physical pain or injury to another person.”\\n\\nJohnson v. United States, 559 U.S. 133, 140 (2010). If the elements of the state offense\\n\\ncan be satisfied by “de minimis physical contact,” the offense does not qualify\\n\\ncategorically as a crime of violence. See United States v. Burns-Johnson, 864 F.3d 313,\\n\\n316 (4th Cir. 2017).\\n\\n 4\\n\\f In making this assessment, we review the elements of the offense and “the\\n\\nminimum conduct necessary for a violation” as defined by state law. See Gardner, 823\\n\\nF.3d at 803 (citation omitted). To determine the “minimum conduct” required for the\\n\\nstate offense, this Court must ensure that there is “a realistic probability, not a theoretical\\n\\npossibility, that a state would actually punish that conduct.” United States v. Doctor, 842\\n\\nF.3d 306, 308 (4th Cir. 2016) (internal quotation marks and citation omitted). With this\\n\\nframework in mind, we turn to consider Hammond’s arguments.\\n\\n B.\\n\\n Hammond raises two arguments in support of his contention that New York first-\\n\\ndegree robbery does not constitute a crime of violence. He contends (1) that New York\\n\\nrobbery, regardless of degree, does not include as an element the use of violent physical\\n\\nforce as defined by the Supreme Court, and (2) that New York first-degree robbery in\\n\\nparticular can be committed without the use of any force. We address each argument in\\n\\nturn.\\n\\n 1.\\n\\n Hammond first argues that New York robbery does not qualify categorically as a\\n\\ncrime of violence, because the offense does not require the use of violent physical force\\n\\n“capable of causing physical pain or injury to another person.” Johnson, 559 U.S. at 140.\\n\\nHe contends that New York courts have interpreted New York’s robbery statutes to\\n\\nrequire only de minimis force, such as “mere snatching.” We disagree with Hammond’s\\n\\nargument.\\n\\n\\n\\n 5\\n\\f At the outset, we note that this Court, in an unpublished decision, recently\\n\\nconcluded that New York second- and third-degree robbery constitute violent felonies\\n\\nunder the identically-worded force clause of the Armed Career Criminal Act (ACCA), 18\\n\\nU.S.C. § 924(e). United States v. Bowles, 733 F. App’x 699, 702 (4th Cir. 2018).\\n\\nBecause unpublished decisions may constitute persuasive, but not binding, authority, we\\n\\nindependently examine the New York statutes. See Collins v. Pond Creek Mining Co.,\\n\\n468 F.3d 213, 219 (4th Cir. 2006).\\n\\n New York has divided its robbery offense into three distinct statutes (the New\\n\\nYork robbery statutes), each involving an increasing degree of culpable conduct. N.Y.\\n\\nPenal Law §§ 160.00-160.15; see People v. Miller, 661 N.E.2d 1358, 1360-61 (N.Y.\\n\\n1995). All the New York robbery statutes, however, require the same element of force,\\n\\nnamely, “forcible stealing.” See N.Y. Penal Law § 160.00. Stated differently, the “core\\n\\ncrime” of New York robbery, irrespective of degree, is defined as “forcibly steal[ing]\\n\\nproperty.” Id.; Miller, 661 N.E.2d at 1360 (“The essence of the [New York] crime of\\n\\nrobbery is forcible stealing.”). Accordingly, if “forcible stealing” requires the use of\\n\\n“force capable of causing physical pain or injury,” Johnson, 559 U.S. at 140, the New\\n\\nYork robbery statutes all qualify as predicate offenses under the Guidelines’ force clause.\\n\\n A person “forcibly steals property” under New York law when\\n\\n in the course of committing a larceny, he uses or threatens the immediate\\n use of physical force upon another person for the purpose of:\\n\\n 1. Preventing or overcoming resistance to the taking of the property or\\n to the retention thereof immediately after the taking; or\\n\\n\\n\\n 6\\n\\f 2. Compelling the owner of such property or another person to deliver\\n up the property or to engage in other conduct which aids in the commission\\n of the larceny.\\n\\nN.Y. Penal Law § 160.00 (emphasis added). Although “physical force” in this context is\\n\\nnot defined, New York law gives common-law terms their common-law meanings, unless\\n\\ncontext suggests otherwise. People v. King, 463 N.E.2d 601, 603 (N.Y. 1984). “Physical\\n\\nforce” as used to define robbery under the common law has “long been understood to\\n\\nrequire violent force or intimidation of violent force.” Perez v. United States, 885 F.3d\\n\\n984, 988-89 (6th Cir. 2018) (citations omitted). Thus, the plain language of the New\\n\\nYork robbery statutes suggests that the use or threat of violent physical force is required\\n\\nfor all degrees of the offense. See United States v. Pereira-Gomez, 903 F.3d 155, 165 (2d\\n\\nCir. 2018) (“By its plain language . . . New York’s robbery statute includes as an element\\n\\nthe use of violent force.”).\\n\\n This interpretation is supported by New York case law applying the New York\\n\\nrobbery statutes. New York courts have interpreted “forcible stealing” to require\\n\\n“significantly more [force] than mere unwanted physical contact.” People v. Curet, 683\\n\\nN.Y.S.2d 602, 603 (N.Y. App. Div. 1998); see People v. Chatman, 833 N.Y.S.2d 794,\\n\\n795 (N.Y. App. Div. 2007) (affirming second-degree robbery conviction when the\\n\\ndefendant pushed the victim aside and entered her vehicle, later breaking the victim’s\\n\\nhold by driving away); People v. Dixon, 648 N.Y.S.2d 1009, 1010 (N.Y. App. Div. 1996)\\n\\n(concluding that evidence that a victim “experienced pain in her neck and suffered a\\n\\nscratch” as a result of the defendant pulling the victim’s necklaces was sufficient to\\n\\nsupport the defendant’s conviction for third-degree robbery). Indeed, New York courts\\n\\n 7\\n\\fconsistently have reversed robbery convictions when the taking at issue was committed\\n\\nwithout the use or threat of significant physical force. See, e.g., People v. Dobbs, 805\\n\\nN.Y.S.2d 734, 735-36 (N.Y. App. Div. 2005) (affirming reduction in charge from third-\\n\\ndegree robbery to petit larceny because there was “no indication” that the victim was\\n\\nthreatened or injured by the defendant); People v. Middleton, 623 N.Y.S.2d 298, 299\\n\\n(N.Y. App. Div. 1995) (reversing a third-degree robbery conviction when the victim was\\n\\nnot “intimidated, knocked down, struck, or injured”). Thus, we do not discern any\\n\\nmaterial difference between the amount of force required under the New York robbery\\n\\nstatutes and the violent physical force necessary to satisfy the Guidelines’ force clause.\\n\\nSee Johnson, 559 U.S. at 142 (recognizing that violent force requires more than “a mere\\n\\nunwanted touching”).\\n\\n Contrary to Hammond’s contention, the great weight of New York authority\\n\\nestablishes that the act of merely “snatching” property from a victim does not amount to\\n\\n“forcibly steal[ing] property” from a person. See, e.g., People v. Chessman, 429\\n\\nN.Y.S.2d 224, 227-29 (N.Y. App. Div. 1980) (holding that a purse snatching when the\\n\\nvictim “did not feel anything on her body” did not constitute third-degree robbery under\\n\\nNew York law); People v. Davis, 418 N.Y.S.2d 127, 128 (N.Y. App. Div. 1979)\\n\\n(concluding that a purse snatching did not amount to third-degree robbery in the absence\\n\\nof evidence that the victim “was injured or was in danger of injury”). Indeed, the New\\n\\nYork Court of Appeals recently stated that “a taking ‘by sudden or stealthy seizure or\\n\\nsnatching,’” such as “pickpocketing” or “jostling” a victim, is insufficient to support a\\n\\nconviction for New York second-degree robbery. People v. Jurgins, 46 N.E.3d 1048,\\n\\n 8\\n\\f1052-53 (N.Y. 2015). Based on the foregoing, we conclude that all the New York\\n\\nrobbery statutes have as an element the use or threatened use of violent physical force\\n\\nsufficient to satisfy the force clause of Guidelines § 4B2.1(a)(1). 2\\n\\n Notably, none of the decisions on which Hammond relies suggests a different\\n\\nresult. Hammond first cites to a decision in which a defendant and a victim had “tugged\\n\\nat each other” until the defendant was able to pull his hand away. People v. Safon, 560\\n\\nN.Y.S.2d 552, 552 (N.Y. App. Div. 1990). The court in Safon concluded that the\\n\\ninteraction between the defendant and the victim was sufficient to uphold a conviction for\\n\\nNew York third-degree robbery. Id.\\n\\n We recognize that an offense that requires only a “slight degree of force” does not\\n\\nqualify as a crime of violence under the Guidelines’ force clause. See United States v.\\n\\nWinston, 850 F.3d 677, 685 (4th Cir. 2017) (internal quotation marks and citation\\n\\nomitted). Nonetheless, the Supreme Court has emphasized that, to constitute a crime of\\n\\nviolence, a state offense need only require force that is “capable of causing physical pain\\n\\nor injury,” such as a “slap in the face.” Johnson, 559 U.S. at 140, 143 (emphasis added).\\n\\nIf a slap constitutes enough physical force to satisfy Johnson, we cannot say that a pull,\\n\\n\\n 2\\n We note that our conclusion is consistent with the majority of courts of appeals\\nto consider whether the New York robbery statutes require, as an element, the use or\\nthreatened use of violent physical force. See United States v. Pereira-Gomez, 903 F.3d\\n155, 166 (2d Cir. 2018) (concluding that New York second-degree robbery qualifies as a\\ncrime of violence under Section 2L1.2 of the Guidelines); United States v. Williams, 899\\nF.3d 659, 663-65 (8th Cir. 2018) (same); Perez, 855 F.3d at 989 (holding that New York\\nsecond-degree robbery qualifies as a violent felony for purposes of the ACCA). But see\\nUnited States v. Steed, 879 F.3d 440, 448-50 (1st Cir. 2018) (concluding that New York\\nsecond-degree robbery is not a crime of violence under Guidelines § 4B2.1(a)).\\n\\n 9\\n\\fpowerful enough to break a person’s grip, would not be “capable of causing physical\\n\\npain.” 3 Id. at 140.\\n\\n Hammond next cites to a New York state case in which the defendant and three\\n\\nothers “formed a human wall that blocked the victim’s path as the victim attempted to\\n\\npursue” the defendant, who had “picked” the victim’s “pocket,” People v. Bennett, 631\\n\\nN.Y.S.2d 834, 834 (N.Y. App. Div. 1995), and to another case in which the defendant\\n\\nphysically “block[ed] the victim’s passage,” People v. Patton, 585 N.Y.S.2d 431, 431\\n\\n(N.Y. App. Div. 1992). Hammond contends that because there was no actual force\\n\\nemployed against the victims in those cases, yet the defendants were convicted of New\\n\\nYork second-degree robbery, the decisions in Bennett and Patton demonstrate that\\n\\n“forcible stealing” can be committed without any use or threatened use of force.\\n\\n Hammond, however, minimizes the defendants’ conduct in those cases. In Patton,\\n\\nthe defendant not only blocked the victim’s path, but “persistently shoved [the victim]\\n\\nback” multiple times. Id. The codefendant in that case also stole the victim’s gold chain\\n\\nby “yank[ing]” it from the victim’s neck, “scratching the victim and tearing his shirt.” Id.\\n\\n\\n 3\\n We disagree with Hammond’s argument that this Court’s decisions in Winston,\\n850 F.3d 677, and Gardner, 823 F.3d 793, require a different result here. In Winston and\\nGardner, we considered whether Virginia’s and North Carolina’s respective common law\\nrobbery crimes constituted “violent felonies” under the ACCA. See Winston, 850 F.3d at\\n685; Gardner, 823 F.3d at 803-04. Based on each states’ interpretation of its own\\nrobbery offense, we concluded that each respective crime could be committed without the\\nforce required by the Supreme Court. See Winston, 850 F.3d at 685; Gardner, 823 F.3d\\nat 803-04. We conduct the same analysis in the present case, applying the same legal\\nstandards. That we reach a different conclusion based on New York courts’\\ninterpretation of the New York robbery statutes does not create a tension among our\\ncases.\\n\\n 10\\n\\fTaken as a whole, the conduct at issue in Patton plainly involved the use or threatened\\n\\nuse of violent physical force.\\n\\n With respect to Bennett, Hammond correctly observes that the defendant in that\\n\\ncase did not use actual force against the victim. Nonetheless, Hammond fails to\\n\\nrecognize that the defendant’s action with others of forming the “human wall” involved\\n\\nthe “threatened use of physical force.” See Bennett, 631 N.Y.S.2d at 834. Stated\\n\\ndifferently, the actions of the defendant and his accomplices involved a threat of violent\\n\\nforce that dissuaded the victim from attempting to break through the human wall or\\n\\notherwise to pursue the defendant. Accord Pereira-Gomez, 903 F.3d at 166; Perez, 885\\n\\nF.3d at 989-90. Because the Guidelines’ force clause includes the “threatened use of\\n\\nphysical force,” U.S.S.G. § 4B2.1(a)(1), the cases on which Hammond relies involve a\\n\\ndegree of threatened force sufficient to come within the scope of the Guidelines’ career\\n\\noffender enhancement.\\n\\n 2.\\n\\n In a related argument, Hammond contends that, regardless of New York’s\\n\\nstatutory definition of robbery, New York first-degree robbery is not a crime of violence\\n\\nbecause that statute can be violated by merely possessing, without displaying, a deadly\\n\\nweapon. See N.Y. Penal Law § 160.15(2) (“A person is guilty of robbery in the first\\n\\ndegree when he forcibly steals property and when . . . [he] is armed with a deadly\\n\\nweapon.”). However, Hammond misconstrues New York’s first-degree robbery statute.\\n\\n As we have explained, the New York robbery statutes all require that the\\n\\nprosecution prove the same element of “forcible stealing.” See People v. Gordon, 16\\n\\n 11\\n\\fN.E.3d 1178, 1183-84 (N.Y. 2014). A person is guilty of New York first-degree robbery\\n\\nwhen he “forcibly steals property,” as defined in New York Penal Law § 160.00, and his\\n\\nconduct satisfies one of four additional aggravating circumstances, such as being armed\\n\\nwith a deadly weapon. 4 See N.Y. Penal Law § 160.15. Thus, anyone convicted of New\\n\\nYork first-degree robbery necessarily has been convicted of “us[ing] or threaten[ing] the\\n\\nimmediate use of physical force upon another person.” Id. § 160.00; see Miller, 661\\n\\nN.E.2d at 1360-62.\\n\\n The aggravating factors necessary to commit New York first-degree robbery do\\n\\nnot eliminate the “core” physical force element of New York robbery, but merely elevate\\n\\nthe crime based on additional culpable conduct. See Miller, 661 N.E.2d at 1360-61; see\\n\\nalso Perez, 885 F.3d at 988. Accordingly, because all the New York robbery statutes\\n\\nrequire the same element of violent physical force or threatened violent force, New York\\n\\nfirst-degree robbery qualifies as a crime of violence under Guidelines § 4B1.2(a)(1). 5\\n\\n\\n\\n\\n 4\\n The other aggravating circumstances are when the defendant: (1) “[c]auses\\nserious physical injury to any person who is not a participant in the crime;” (2) “[u]ses or\\nthreatens the immediate use of a dangerous instrument;” or (3) displays certain types of\\noperable firearms. N.Y. Penal Law § 160.15.\\n 5\\n For the same reason, we reject Hammond’s contention that we must apply the\\nmodified categorical approach to New York’s first-degree robbery statute. The modified\\ncategorical approach is not required when each of the crimes into which a statute may be\\ndivided constitutes a crime of violence. See United States v. Cabrera-Umanzor, 728 F.3d\\n347, 352 (4th Cir. 2013) (citing Descamps v. United States, 570 U.S. 254, 264 (2013)).\\nBecause we conclude that all subsections of New York first-degree robbery qualify as\\ncrimes of violence, we need not apply the modified categorical approach.\\n\\n 12\\n\\f III.\\n\\n For these reasons, we hold that Hammond’s conviction for New York first-degree\\n\\nrobbery qualifies as a crime of violence under the force clause of Guidelines §\\n\\n4B1.2(a)(1). 6 We therefore affirm the district court’s judgment.\\n\\n AFFIRMED\\n\\n\\n\\n\\n 6\\n Based on our holding, we need not address Hammond’s alternative argument\\nconcerning whether New York first-degree robbery qualifies as a crime of violence under\\nthe “enumerated offense” clause of Guidelines § 4B1.2(a)(2).\\n\\n\\n 13\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":82,"cells":{"id":{"kind":"number","value":4579294,"string":"4,579,294"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff - Appellee, v. Gary Giovon LYNN, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Gary Giovon Lynn"},"decision_date":{"kind":"string","value":"2019-01-07"},"docket_number":{"kind":"string","value":"17-4232"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Motz, Floyd, Jones, Western, Virginia\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9887832/\", \"author_raw\": \"\"}, {\"author\": \"\", \"type\": \"035concurrenceinpart\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9887833/\", \"author_raw\": \"\"}, {\"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-4232\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nGARY GIOVON LYNN,\\n\\n Defendant - Appellant.\\n\\n\\n\\nAppeal from the United States District Court for the Middle District of North Carolina, at\\nGreensboro. William L. Osteen, Jr., District Judge. (1:16-cr-00287-WO-1)\\n\\n\\nArgued: September 26, 2018 Decided: January 7, 2019\\n\\n\\nBefore MOTZ and FLOYD, Circuit Judges, and James P. JONES, United States District\\nJudge for the Western District of Virginia, sitting by designation.\\n\\n\\nAffirmed by published opinion. Judge Jones wrote the majority opinion, in which Judge\\nMotz joined. Judge Floyd wrote a separate opinion, in which he concurred in part and\\ndissented in part.\\n\\n\\nARGUED: John Arthur Duberstein, OFFICE OF THE FEDERAL PUBLIC\\nDEFENDER, Greensboro, North Carolina, for Appellant. Kimberly Furr Davis, OFFICE\\nOF THE UNITED STATES ATTORNEY, Winston-Salem, North Carolina, for\\nAppellee. ON BRIEF: Louis C. Allen, Federal Public Defender, OFFICE OF THE\\nFEDERAL PUBLIC DEFENDER, Greensboro, North Carolina, for Appellant. Matthew\\nG.T. Martin, United States Attorney, OFFICE OF THE UNITED STATES ATTORNEY,\\n\\nGreensboro, North Carolina, for Appellee.\\n\\n\\n\\n\\n 2\\n\\nJONES, District Judge:\\n\\n Gary Giovon Lynn pled guilty to being a felon in possession of a firearm, in\\n\\nviolation of 18 U.S.C. §§ 922(g)(l), 924(a)(2). The district court sentenced Lynn to 120\\n\\nmonths’ imprisonment. On appeal, counsel filed a brief pursuant to Anders v. California,\\n\\n386 U.S. 738 (1967), questioning whether the district court erred in applying a cross-\\n\\nreference to the attempted murder Sentencing Guideline. U.S. Sentencing Guidelines\\n\\nManual (USSG) §§ 2A2.1, 2K2.1(c)(l)(A), 2X1.l(a) (2016). We directed supplemental\\n\\nbriefing on the additional issue of whether in light of USSG § 5G3.1(c), the district court\\n\\nerred in failing to impose its sentence to run concurrently with an anticipated term of\\n\\nstate imprisonment. We now affirm the district court’s judgment.\\n\\n I.\\n\\n On January 4, 2016, Officer A.D. Gardner of the Winston-Salem Police\\n\\nDepartment stopped a speeding vehicle occupied by Lynn along with two other\\n\\nindividuals. While standing near the vehicle, Officer Gardner smelled marijuana, and he\\n\\nrequested additional officers for assistance. When the other officers arrived, Officer\\n\\nGardner asked each of the occupants to exit the vehicle. After Officer Gardner frisked\\n\\nLynn, Gardner instructed him to stand by a guardrail with the driver of the vehicle. As\\n\\nOfficer Nicholas Powell was frisking another passenger, Lynn jumped into the driver’s\\n\\nside of the vehicle and Officer Powell followed, landing on top of him. The two\\n\\nstruggled over control of the vehicle, with Lynn putting the vehicle into drive, and\\n\\nOfficer Powell pulling the emergency brake. The vehicle rolled away, and Officer\\n\\nGardner pursued it. He heard a gunshot, and when he reached the vehicle, he saw Officer\\n\\n 3\\n\\nPowell lying on top of Lynn and holding Lynn’s left hand, in which Lynn had a pistol\\n\\npointed at Officer Powell. Officer Powell had suffered gunshot wounds to his arms and\\n\\nchest. Lynn had also suffered a gunshot wound, although Officer Powell had not fired\\n\\nhis weapon during the struggle.\\n\\n Lynn was arrested and charged in state court with attempted first-degree murder,\\n\\npossession of a firearm by a felon, and fleeing or eluding arrest with a motor vehicle.\\n\\nWhile Lynn was detained in state custody, he was indicted on a federal charge of being a\\n\\nfelon in possession of a firearm, stemming from the same conduct as the state charges.\\n\\nLynn was obtained by the district court on a writ of habeas corpus ad prosequendum\\n\\nwhile his state charges were pending, and he eventually pleaded guilty to the federal\\n\\nfirearms charge.\\n\\n At Lynn’s federal sentencing hearing on February 28, 2017, he and Officer Powell\\n\\nboth testified about what had occurred in the vehicle. Officer Powell stated that after he\\n\\nhad been able to bring the vehicle to a stop, Lynn dove between the front seats, and as\\n\\nOfficer Powell had turned to face Lynn, he felt gun shots hit him. On the other hand,\\n\\nLynn testified that he and Officer Powell had struggled over possession of the firearm,\\n\\nand it went off accidentally during the struggle. The district court found that Officer\\n\\nPowell’s testimony was credible while Lynn’s was not, and it determined that a sentence\\n\\nof 120 months’ imprisonment —the statutory maximum—was appropriate.\\n\\n The court also heard argument as to whether this sentence should run concurrently\\n\\nwith or consecutive to Lynn’s future anticipated state sentence. Because Lynn was in\\n\\nprimary state custody, that state sentence would be served in its entirety before he entered\\n\\n 4\\n\\nthe federal prison system. The district court stated that it would be “terribly difficult” for\\n\\nit to calculate what portion, if any, of Lynn’s sentence should run concurrently with his\\n\\nanticipated state sentence in light of the variety of state charges he faced, along with the\\n\\ndispute as to the facts surrounding the shooting. J.A. 153. The court explained:\\n\\n [L]et’s say that a state court jury finds beyond a reasonable doubt . . . that\\n there was a struggle and this constitutes some kind of aggravated assault.\\n I’m not sure I would want this sentence to be imposed to run concurrently\\n based on the facts that I found.\\n\\n On the other hand, if there’s an attempted second degree murder\\n conviction and some 288-month sentence is imposed, then I think, in\\n fairness, the circumstances might merit some overlapping consideration,\\n but I just don’t know at this point.\\n\\nJ.A. 154. The court also suggested that, in light of its uncertainty regarding the extent to\\n\\nwhich its sentence should run concurrently with the anticipated state sentence, the state\\n\\ncourt could take the federal sentence into account in fashioning its sentence, and Lynn\\n\\ncould also request the Bureau of Prisons (BOP) to designate the state prison as his place\\n\\nof confinement, thus effectively running his federal sentence concurrently with the state\\n\\nsentence. Ultimately, the court stated:\\n\\n I am not able to make a determination as to how much of this sentence\\n should be imposed to run concurrently with the state court prosecution that\\n is now pending. . . . Therefore, at this time I will decline to make a finding\\n with respect to running any part of this sentence concurrently to any\\n sentence imposed in the state court.\\n\\nJ.A. 159.\\n\\n Thereafter, on May 4, 2017, Lynn pleaded guilty in North Carolina Superior Court\\n\\nto assault with a deadly weapon with intent to kill, inflicting serious bodily injury,\\n\\n\\n\\n 5\\n\\npossession of a firearm by a felon, and fleeing or eluding arrest with a motor vehicle.\\n\\nThe state court imposed a total sentence of 104 to 137 months’ imprisonment.\\n\\n II.\\n\\n A.\\n\\n Before resolving the issue that was the subject of supplemental briefing and oral\\n\\nargument, we can easily dispose of the question raised in the Anders brief.\\n\\n We review a defendant’s sentence “under a deferential abuse-of-discretion\\n\\nstandard.” Gall v. United States, 552 U.S. 38, 41 (2007). Under the Gall standard, a\\n\\nsentence is reviewed for both procedural and substantive reasonableness. Id. at 51. In\\n\\ndetermining procedural reasonableness, we consider, among other things, whether the\\n\\ncourt properly determined the Sentencing Guidelines range, considered the 18 U.S.C. §\\n\\n3553(a) factors, and sufficiently explained the selected sentence. Id. at 49–51.\\n\\n We review the factual findings underlying a district court’s application of a\\n\\nGuidelines cross-reference for clear error and the court’s legal conclusions de novo.\\n\\nUnited States v. Ashford, 718 F.3d 377, 380, 383–84 (4th Cir. 2013). “In the event of a\\n\\nconviction for illegal possession of a firearm, USSG § 2K2.1(c) authorizes a district court\\n\\nto substitute the offense level for any criminal offense that the defendant committed or\\n\\nattempted to commit in connection with the possession of the firearm.” Id. at 381. Here,\\n\\nthe district court found that Lynn committed attempted murder with the firearm at issue.\\n\\nSentencing Guideline § 2A2.l(a) provides for a base offense level of 33 if the attempted\\n\\nmurder would have constituted first-degree murder; otherwise, the offense level is 27.\\n\\n“[S]econd-degree murder simply requires proof of malice aforethought, which may be\\n\\n 6\\n\\nestablished by evidence of conduct which is reckless and wanton and a gross deviation\\n\\nfrom a reasonable standard of care, of such a nature that a jury is warranted in inferring\\n\\nthat defendant was aware of a serious risk of death or serious bodily harm.” Ashford, 718\\n\\nF.3d at 384 (internal quotation marks, citation, and alterations omitted).\\n\\n We conclude that the district court did not err in finding that the murder cross-\\n\\nreference applied. The district court based its ruling on finding that the victim’s\\n\\ntestimony was credible and that Lynn’s testimony was not.\\n\\n [W]hen a trial judge’s finding is based on his decision to credit the\\n testimony of one of two or more witnesses, each of whom has told a\\n coherent and facially plausible story that is not contradicted by extrinsic\\n evidence, that finding, if not internally inconsistent, can virtually never be\\n clear error.\\n\\nUnited States v. Hall, 664 F.3d 456, 462 (4th Cir. 2012) (internal quotation marks and\\n\\ncitation omitted). Moreover, ballistic evidence indicated that multiple shots were fired\\n\\nfrom Lynn’s firearm and that more would have been fired had it not malfunctioned. The\\n\\ndistrict court’s decision not to credit Lynn’s testimony is likewise supported by the\\n\\nrecord—the firing of multiple shots is arguably inconsistent with Lynn’s explanation that\\n\\nthe shooting was an accident.\\n\\n B.\\n\\n Relying on Setser v. United States, 566 U.S. 231 (2012), Lynn contends that the\\n\\ndistrict court erred in declining to run its sentence concurrently, in whole or in part, with\\n\\nthe yet-to-be-imposed state sentence. In light of the now-imposed state sentence, he\\n\\nseeks a remand for reconsideration of that issue by the district court.\\n\\n\\n\\n 7\\n\\n In Setser, noting that sentencing judges “have discretion to select whether the\\n\\nsentences they impose will run concurrently or consecutively with respect to other\\n\\nsentences that they impose, or that have been imposed in other proceedings,” id. at 236,\\n\\nthe Court held that 18 U.S.C. § 3584(a) allows judges to impose a federal sentence\\n\\nconcurrently or consecutively to an anticipated, but unimposed, state sentence, id. at 236–\\n\\n39.\\n\\n The relevant Sentencing Guideline, added after Setser by USSG amendment 787,\\n\\neffective November 1, 2014, provides that if “a state term of imprisonment is anticipated\\n\\nto result from another offense that is relevant conduct to the instant offense of\\n\\nconviction . . . , the sentence for the instant offense shall be imposed to run concurrently\\n\\nto the anticipated term of imprisonment.” USSG § 5G1.3(c). There is no question but\\n\\nthat Lynn’s state charges were relevant conduct to his federal conviction. However,\\n\\nbecause the Guidelines are advisory, a district court is not obligated to impose a\\n\\nconcurrent sentence pursuant to USSG § 5G1.3. United States v. Nania, 724 F.3d 824,\\n\\n830 (7th Cir. 2013). Rather, the district court is required to consider the 18 U.S.C. §\\n\\n3553(a) factors in determining whether to run sentences consecutively or concurrently.\\n\\n18 U.S.C. § 3584(b).\\n\\n Here the district court provided a thorough explanation of the sentence. The court\\n\\nfound that Lynn’s offense conduct was extremely serious. The court then explained that\\n\\nit would not order its sentence to run concurrently with the anticipated state sentence in\\n\\nlight of this seriousness, remarking that a lengthy term of imprisonment was necessary in\\n\\nthis case. The court recognized its discretion to order the sentence to run concurrently,\\n\\n 8\\n\\nbut simply declined to exercise its discretion after considering the required factors. Thus,\\n\\nwe discern no abuse of discretion in the district court’s decision. See United States v.\\n\\nHall, 825 F.3d 373, 375–76 (8th Cir. 2016) (upholding decision not to run sentence\\n\\nconcurrent to anticipated state sentence based on district court’s consideration of the §\\n\\n3553(a) factors and its explanation that the possibility of a relatively short state sentence\\n\\nthat would result in an inappropriate period of imprisonment).\\n\\n Lynn argues that by declining to order the sentence to run concurrently, the district\\n\\ncourt treaded on the separation-of-powers issue outlined in Setser. See 566 U.S. at 242–\\n\\n43. In holding that 18 U.S.C. § 3584(a) allows a district court to impose a federal\\n\\nsentence concurrently or consecutively to an anticipated state sentence, the Court in\\n\\nSetser rejected the parties’ argument that when a future state sentence is anticipated, the\\n\\nBOP should decide after the federal sentence has been imposed whether it runs\\n\\nconcurrently with or consecutive to the state sentence, based upon its authority granted\\n\\nunder 18 U.S.C. § 3621(b). 1 The Court rejected this argument in part out of concern that\\n\\nit would leave sentencing in the hands of “the same Department of Justice that conducts\\n\\nthe prosecution.” Setser, 566 U.S. at 242. Instead, the Court determined that in the first\\n\\ninstance, the district court, rather than the BOP, should decide whether a federal sentence\\n\\nruns concurrently with or consecutive to an anticipated state sentence. Id. at 242–43.\\n\\nHowever, recognizing an exception to this determination, the Court stated that “a district\\n\\n 1\\n That statute provides that the BOP “may designate any available penal or\\ncorrectional facility . . ., whether maintained by the Federal Government or otherwise . . .,\\nthat the Bureau determines to be appropriate and suitable.” 18 U.S.C. § 3621(b).\\n\\n\\n 9\\n\\ncourt should exercise the power to impose anticipatory consecutive (or concurrent)\\n\\nsentences intelligently. In some situations, a district court may have inadequate\\n\\ninformation and may forbear, but in other situations, that will not be the case.” Id. at 242\\n\\nn.6.\\n\\n Lynn’s argument requires us to consider the boundaries of this exception—in what\\n\\nsituations does a district court’s lack of information permit it to decline to order its\\n\\nsentence to run concurrently with an anticipated state sentence? To be sure, these\\n\\nsituations will be limited. When a state sentence is anticipated, the district court will\\n\\nnormally lack definite information about that sentence, and if this alone were sufficient to\\n\\npermit the district court to forbear, the exception would swallow the rule. Thus, in most\\n\\ncases, the district court should decide whether its sentence will run concurrently with or\\n\\nconsecutive to an anticipated state sentence involving relevant conduct. But as pointed\\n\\nout by the Sentencing Commission with regard to USSG § 5G1.3, “[d]etermining\\n\\nwhether, and how, to use this discretion will depend on the adequacy of the information\\n\\navailable.” USSG Amend. 776 (Nov. 1, 2013).\\n\\n It is clear that Lynn’s case was not routine. First, the conduct at issue was\\n\\nextremely serious. As the district court stated, “this is . . . one of the most, if not the\\n\\nmost, serious forms of a 922(g)(1) offense. The only thing more serious is a shooting in\\n\\nwhich an individual is actually killed.” J.A. 158. Further, the variety of state charges\\n\\nagainst Lynn, along with his dispute as to the facts surrounding the shooting—in\\n\\nparticular, his testimony that the shooting was accidental—made it possible for his\\n\\nanticipated state sentence to range from relatively short to over double his federal\\n\\n 10\\n\\nsentence. The district court considered this possibility and the effect it would have on\\n\\nany concurrent sentence it might order, ultimately determining that the uncertainty it\\n\\ncreated prevented the court from accomplishing its proper sentencing objectives.\\n\\n Of course, we know by now the sentence imposed on Lynn by the state court. But\\n\\nit was not unreasonable at the time of imposing sentence for the district court to have\\n\\njustified doubts as to the scope of that state sentence. As noted by the Court in Setser, the\\n\\nfact that the later state sentence may be unexpected, “does not establish that the District\\n\\nCourt abused its discretion by imposing an unreasonable sentence.” 566 U.S. at 244. The\\n\\ndistrict court attempted to exercise its power to impose a concurrent or consecutive\\n\\nsentence intelligently, but, for the reasons discussed above, it lacked adequate\\n\\ninformation to do so. Accordingly, the district court did not err in declining to run its\\n\\nsentence concurrently with the anticipated state sentence. 2\\n\\n\\n 2\\n Shortly before oral argument, the government submitted additional authority\\npursuant to Federal Rule of Appellate Procedure 28(j) and Local Rule 28(e), arguing that\\nwhen Lynn agreed that his state court sentence “shall run consecutively to any other\\nsentence the defendant is now subject to,” Lynn waived the issues he raises on appeal,\\nand any error by the district court must be disregarded. We disagree.\\n\\n Lynn’s agreement regarding his state court sentence has no effect on his federal\\nsentence. As previously noted, Lynn was in primary state custody when he was\\nsentenced on the federal charge, and as a result, he will serve his state sentence in its\\nentirety before he serves his federal sentence. “In our American system of dual\\nsovereignty, each sovereign—whether the Federal Government or a State—is responsible\\nfor the administration of its own criminal justice system.” Setser, 566 U.S. at 241\\n(internal quotation marks, citation, and alterations omitted). “If a prisoner like [Lynn]\\nstarts in state custody, serves his state sentence, and then moves to federal custody, it will\\nalways be the Federal Government . . . that decides whether he will receive credit for the\\ntime served in state custody.” Id. Thus, Lynn’s state court sentence cannot run\\nconsecutively to his federal sentence, and the state court cannot dictate that his federal\\n(Continued)\\n 11\", \"author\": \"JONES, District Judge:\"}, {\"type\": \"dissent\", \"author\": \"Our\", \"text\": \"Our dissenting colleague parts company with us based upon the contention that the\\n\\ndistrict court violated its procedural duty by failing to expressly accept or reject the\\n\\nadvisory language of § 5G1.3(c). But the court satisfied its procedural duty when it\\n\\nconsidered the Guideline and fully explained its rationale for declining to exercise its\\n\\ndiscretion. For the reasons given above, we find that the district court’s explanation\\n\\ngiven in this case was sufficient, and as authorized by Setser.\\n\\n\\n\\n AFFIRMED\\n\\n\\n\\n\\nsentence will run consecutively to his state sentence. Accordingly, Lynn could not—and\\nhas not—waived his argument regarding his federal sentence.\\n\\n 12\"}, {\"author\": \"FLOYD, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"FLOYD, Circuit Judge, concurring in part and dissenting in part:\\n\\n I join with all parts of the majority opinion save one: I disagree with my\\n\\ncolleagues’ conclusion that the district court had the discretion to make no decision at all\\n\\non whether Lynn’s federal sentence would run concurrently with his anticipated state\\n\\nsentence. I would hold that because U.S.S.G. § 5G1.3 was a “pertinent Sentencing\\n\\nCommission policy statement,” United States v. Olmeda, 894 F.3d 89, 93 (2d Cir. 2018)\\n\\n(quoting United States v. Cavera, 550 F.3d 180, 188–89 (2d Cir. 2008) (en banc)), the\\n\\ndistrict court was required to decide whether to adopt § 5G1.3’s recommendation that\\n\\nLynn’s sentences run concurrently. That is, the district court had the discretion either to\\n\\nfollow or depart from the Sentencing Commission’s recommendation on concurrency.\\n\\nBut the district court did not have the discretion to make no decision on concurrency at\\n\\nall. Therefore, I respectfully dissent as to Part II.B of the majority opinion.\\n\\n\\n\\n I.\\n\\n Lynn’s federal sentencing hearing took place before his pending state charges\\n\\nwere resolved. During the sentencing, the government raised U.S.S.G. § 5G3.1(c) and its\\n\\nrecommendation that Lynn’s federal sentence run concurrently with his anticipated state\\n\\nsentence. Both government and defense counsel argued that § 5G3.1(c) applied and that\\n\\nat least a portion of Lynn’s federal sentence should run concurrently with his anticipated\\n\\nstate sentence.\\n\\n In response, the district court stated that it was “terribly difficult” to calculate how\\n\\nmuch of Lynn’s federal sentence should run concurrently with a yet-to-be-determined\\n\\n\\n 13\\n\\nstate sentence. J.A. 153. The length of Lynn’s future state sentence could vary widely,\\n\\nfrom a relatively short sentence for aggravated assault to a far longer sentence for\\n\\nattempted murder. Should Lynn receive a short sentence, the court was “not sure” that it\\n\\nwanted any of the federal sentence to be served concurrently with the state sentence. J.A.\\n\\n154. If, however, Lynn received a long state sentence, the court believed that “in\\n\\nfairness, the circumstances might merit some overlapping” of the sentences. Id.\\n\\n The district court then opined that it need not decide the § 5G3.1(c) question\\n\\nbecause “ultimately, the Bureau of Prisons has the authority to come back in and handle\\n\\n[this situation] through one of those retroactive designations.” J.A. 153. When defense\\n\\ncounsel expressed confusion regarding what the court meant by retroactive designations,\\n\\nthe court replied: “When an individual does finally arrive at the Bureau of Prisons,”\\n\\nmeaning after the defendant has served his state sentence and is transferred to federal\\n\\ncustody to serve his federal sentence for related conduct, “there is an administrative\\n\\nprocess where [offenders] can apply and ask for that overlap – the overlapping sentences\\n\\nto be taken into consideration and the Bureau of Prisons backdate the start of the federal\\n\\nsentence to some date during the state sentence that’s been served.” J.A. 156. When\\n\\nsuch a request is made, the district court continued, “I usually get a letter that asks for my\\n\\nposition on that, and if it is truly a circumstance where there was overlapping conduct\\n\\nthat enhanced both sentences, I usually tell that to the Bureau of Prisons, but I don’t know\\n\\nwhat they do with that once I’ve made my comment.” Id.\\n\\n Ultimately, the district court declined to decide whether to apply § 5G3.1(c)’s\\n\\nrecommendation that Lynn’s sentences be served concurrently, stating:\\n\\n\\n 14\\n\\n I am not able to make a determination as to how much of this sentence\\n should be imposed to run concurrently with the state court prosecution that\\n is now pending. Certainly, to the extent Mr. Lynn was ultimately either\\n found guilty or pled guilty to an attempted second-degree murder [in state\\n court], there would be significant overlap between these two sentences that\\n are imposed in this case, but, ultimately . . . should Mr. Lynn ultimately be\\n convicted of a [weapons possession] offense or some other offense, I would\\n not be inclined to run any of this sentence concurrent to the sentence that\\n may be imposed in state court. Therefore, at this time I will decline to\\n make a finding with respect to running any part of this sentence\\n concurrently to any sentence imposed in the state court.\\n\\nJ.A. 159 (emphasis added). I thus disagree with my colleagues in the majority to the\\n\\nextent that they understand the district court’s ruling as a decision to not adopt\\n\\n§ 5G3.1(c)’s concurrency recommendation. Rather, we are faced here with a case in\\n\\nwhich the district court refrained from making any decision at all on a pertinent\\n\\nSentencing Guideline.\\n\\n\\n\\n II.\\n\\n The Bureau of Prisons’ (BOP) role in making concurrency determinations serves\\n\\nas important background here. The BOP is empowered by statute to decide where federal\\n\\ninmates serve their sentences. 18 U.S.C. § 3621(b) (2012). When making that\\n\\ndetermination, the BOP may “designate any available penal or correctional facility that\\n\\nmeets minimum standards . . . whether maintained by the Federal Government or\\n\\notherwise.” Id. Thus, “when a federal defendant is already serving a state sentence, BOP\\n\\nhas the practical power to ‘make the federal sentence run concurrently by designating the\\n\\nstate prison as a place of federal confinement, so that the clock would start to tick on the\\n\\nfederal sentence.’” Fegans v. United States, 506 F.3d 1101, 1103 (8th Cir. 2007)\\n\\n\\n 15\\n\\n(quoting Romandine v. United States, 206 F.3d 731, 738 (7th Cir. 2000)). Congress’s\\n\\ngrant of power to the BOP to select a place of confinement for federal prisoners has\\n\\ntherefore become a de facto power to determine whether a federal sentence will be served\\n\\nconcurrently with a state sentence.\\n\\n When a district court has made the concurrency determination already, the BOP\\n\\nenforces the court’s order. See BOP Program Statement 5160.05 ¶ 7 (“When a federal\\n\\njudge orders or recommends a federal sentence run concurrently with a state sentence\\n\\nalready imposed, the Bureau implements such order or recommendation . . . .”); Fegans,\\n\\n506 F.3d at 1105. When, however, a federal judge fails to make a concurrency\\n\\ndetermination, the BOP refers to 18 U.S.C. § 3584(a), which states:\\n\\n If multiple terms of imprisonment are imposed on a defendant at the same\\n time, or if a term of imprisonment is imposed on a defendant who is already\\n subject to an undischarged term of imprisonment, the terms may run\\n concurrently or consecutively . . . . Multiple terms of imprisonment\\n imposed at the same time run concurrently unless the court orders or the\\n statute mandates that the terms are to run consecutively. Multiple terms of\\n imprisonment imposed at different times run consecutively unless the court\\n orders that the terms are to run concurrently.\\n\\nSee Mangum v. Hallembaek, 824 F.3d 98, 101–02 (4th Cir. 2016) (explaining the BOP’s\\n\\nreliance on 18 U.S.C. § 3584). Hence, when a district court is silent as to whether a\\n\\nsentence should be served concurrently with or consecutively to another sentence, the\\n\\nBOP uses § 3584(a) to fill in the gaps.\\n\\n The plain text of § 3584(a), however, contains its own gap: It says nothing about\\n\\nwhether a district court may order a federal sentence to be served concurrently with a yet-\\n\\n\\n\\n\\n 16\\n\\nto-be-imposed state sentence. 1 After § 3584(a) was enacted, some circuits interpreted\\n\\nthat gap to mean that district courts could not order a federal sentence to be served\\n\\nconcurrently with a yet-to-be-imposed state sentence. See Abdul-Malik v. Hawk-Sawyer,\\n\\n403 F.3d 72, 75–76 (2d Cir. 2005) (collecting cases); Fegans, 506 F.3d at 1104 (noting\\n\\nexistence of circuit split). In those circuits, a pragmatic problem arose: once the state\\n\\nsentence was imposed, who could decide whether the federal sentence would run\\n\\nconcurrently or consecutively? The Third Circuit was the first to address that question\\n\\nand held that the BOP should fill this void by reviewing applications from prisoners who\\n\\nhad been transferred to federal custody after serving a state sentence, and then deciding\\n\\nwhether the federal sentence should run concurrently or consecutively with the state\\n\\nsentence through a nunc pro tunc designation. Barden v. Keohane, 921 F.2d 476, 480–81\\n\\n(3d Cir. 1990). Subsequently, multiple federal courts of appeals followed the Third\\n\\nCircuit’s lead. Fegans, 506 F.3d at 1104; Mangum, 824 F.3d at 101–02; Abdul-Malik,\\n\\n403 F.3d at 75–76; Taylor v. Sawyer, 284 F.3d 1143, 1149 (9th Cir. 2002); Romandine,\\n\\n206 F.3d at 738; McCarthy v. Doe, 146 F.3d 118, 122 (2d Cir. 1998).\\n\\n In 2012, the U.S. Supreme Court closed the gap in § 3584(a), holding that district\\n\\ncourts have the inherent authority to order that federal sentences be served concurrently\\n\\n\\n1\\n When § 3584(a)’s final sentence refers to “[m]ultiple terms of imprisonment imposed at\\ndifferent times,” it means the situation described in the first sentence, where a second\\nprison term is “imposed on a defendant who is already subject to an undischarged term of\\nimprisonment.” Setser v. United States, 566 U.S. 231, 234–35 (2012). Section 3584(a)\\ndoes not address the situation here, where the federal sentence was imposed before the\\nstate sentence.\\n\\n\\n\\n 17\\n\\nwith anticipated state sentences. Setser v. United States, 566 U.S. 231, 237–39 (2012).\\n\\nSoon after Setser, U.S.S.G. § 5G1.3(c), which advises district court judges to make\\n\\nfederal sentences concurrent with not-yet-imposed state sentences for related conduct,\\n\\nwas added to the Guidelines. See Olmeda, 894 F.3d at 92–93 (describing history). The\\n\\ncommentary to § 5G1.3(c) states:\\n\\n This amendment is a . . . . response to the Supreme Court’s decision in\\n Setser . . . . [It] reflects the Commission’s determination that the concurrent\\n sentence benefits of subsection (b) of § 5G1.3 should be available not only\\n in cases in which the state sentence has already been imposed at the time of\\n federal sentencing (as subsection (b) provides), but also in cases in which\\n the state sentence is anticipated but has not yet been imposed . . . . By\\n requiring courts to impose a concurrent sentence in these cases, the\\n amendment reduces disparities between defendants whose state sentences\\n have already been imposed and those whose state sentences have not yet\\n been imposed.\\n\\nU.S.S.G. § 5G1.3, Historical Notes, 2014 Amendments.\\n\\n Setser and § 5G1.3 eliminated the pragmatic problem that originally led to the\\n\\nBOP’s power to make concurrency determinations. Nevertheless, the BOP has continued\\n\\nto make concurrency determinations in cases where district courts have neglected to do\\n\\nso. See, e.g., Mangum, 824 F.3d at 99 (deciding a 2016 challenge to the BOP’s refusal to\\n\\ngrant an inmate a nunc pro tunc designation that his federal sentence had started while he\\n\\nwas in state custody). The district court in this case relied upon the BOP’s ongoing\\n\\npractice of making concurrency determinations to justify its refusal to decide whether\\n\\n§ 5G1.3(c) should apply to Lynn’s sentence.\\n\\n\\n\\n\\n 18\\n\\n III.\\n\\n The BOP originally assumed the power to make concurrency determinations for\\n\\ndefendants, like Lynn, who faced a later-imposed state sentence because § 3584(a) left a\\n\\nvoid that some district courts were forbidden to fill. Post-Setser, that void no longer\\n\\nexists, which brings the troubling implications of the BOP’s practice to the forefront:\\n\\nThe BOP is exercising a power that clearly belongs to the judiciary. Additionally, since\\n\\nthe Guidelines have been amended post-Setser to include § 5G1.3(c)’s recommendation\\n\\nthat defendants in Lynn’s position should serve concurrent sentences, district courts have\\n\\nan obligation, as part of their mandatory consideration of all relevant Guidelines, to\\n\\ndecide whether they will accept § 5G1.3(c)’s recommendation during sentencing. The\\n\\ndistrict court did not do so here, and so I would reverse.\\n\\n Setser squarely addressed whether the concurrent-versus-consecutive decision\\n\\nrests with the BOP or the judiciary. In Setser, a defendant was indicted for drug charges\\n\\nin both state and federal court. Setser, 566 U.S. at 233. Setser received his federal\\n\\nsentence first, and the district court ruled that his federal sentence would run concurrently\\n\\nwith any state sentence he received for his drug charge, but consecutive to any future\\n\\nstate sentence he would receive for a then-outstanding probation violation. Id. Setser\\n\\nappealed, arguing that the district court lacked the power to make that concurrency\\n\\ndetermination because the case fell into the above-described § 3584(a) gap. Id. at 234–\\n\\n35. Specifically, he argued that the § 3584(a) gap meant that any concurrency\\n\\ndetermination should be left exclusively to the BOP through its nunc pro tunc designation\\n\\n\\n\\n\\n 19\\n\\nprocess, as district courts lacked any power not explicitly granted by § 3584(a). Id. at\\n\\n235. The Supreme Court disagreed:\\n\\n That is an odd parsing of [§ 3584], which makes no distinction between the\\n district court and the Bureau of Prisons. The placement of § 3584 does\\n indeed suggest that it is directed at district courts—but that is likely because\\n Congress contemplated that only district courts would have the authority to\\n make the concurrent-vs.-consecutive decision, not because Congress meant\\n to leave the Bureau unfettered. Indeed, the Bureau already follows the\\n other directives in § 3584(a). For example, if the district court imposes\\n multiple terms of imprisonment at the same time, but fails to address the\\n concurrent-vs.-consecutive issue, the terms “run concurrently,” [as\\n provided by] § 3584(a), and the Bureau is not free to use its “place of\\n imprisonment” authority to achieve a different result.\\n\\nId. at 237–38 (citations omitted) (emphasis added). The Court went on to explain that, by\\n\\nrelying on the maxim of expressio unius est exclusion alterius, or the explicit mention of\\n\\none thing is the exclusion of another,\\n\\n Setser . . . suggests that, because § 3584(a) recognizes judicial discretion in\\n scenario A and scenario B, there is no such discretion in scenario C. But\\n the same maxim shows much more convincingly why § 3621(b) [which\\n grants the BOP the power to designate state prisons as a federal inmate’s\\n place of confinement] cannot be read to give the Bureau of Prisons\\n exclusive authority to make the sort of decision committed to the district\\n court in § 3584(a). When § 3584(a) specifically addresses decisions about\\n concurrent and consecutive sentences, and makes no mention of the\\n Bureau’s role in the process, the implication is that no such role exists.\\n And that conclusion is reinforced by application of the same maxim\\n (properly, in this instance) to § 3621(b)—which is a conferral of authority\\n on the Bureau of Prisons, but does not confer authority to choose between\\n concurrent and consecutive sentences. Put to the choice, we believe it is\\n much more natural to read § 3584(a) as not containing an implied “only,”\\n leaving room for the exercise of judicial discretion in the situations not\\n covered, than it is to read § 3621(b) as giving the Bureau of Prisons what\\n amounts to sentencing authority.\\n\\nId. at 238–39 (second emphasis added).\\n\\n\\n\\n\\n 20\\n\\n While the Setser Court held that district courts have the authority to decide that a\\n\\nfederal sentence should run concurrently with an anticipated state sentence, it stopped\\n\\nshort of deciding that the BOP’s decades-old nunc pro tunc designation process is itself\\n\\nunlawful. It did, however, express concern about giving sentencing authority to a federal\\n\\nagency. Id. at 239, 242 n.5. Such concern has been echoed by other Courts of Appeals.\\n\\nThe Second Circuit, for example, has explained that “[a] separation of powers issue arises\\n\\nwhen the same branch of government that prosecutes federal prisoners determines\\n\\nconcurrency in lieu of the judge.” Abdul-Malik, 403 F.3d at 76; see also Fegans, 506\\n\\nF.3d at 1104 (“[W]e agree with the Second Circuit that Congress should examine the\\n\\n[BOP’s practice of making concurrency determinations] because it implicates important\\n\\nfederalism and separation of powers concerns[.]”). I agree that the BOP’s practice raises\\n\\ntroubling separation-of-powers concerns.\\n\\n\\n\\n IV.\\n\\n Although district courts are not mandated to comply with the recommendations in\\n\\nthe Guidelines, they still “must give due consideration” to any relevant Guideline policy\\n\\nstatements and explain any deviation therefrom. United States v. Engle, 592 F.3d 495,\\n\\n502–04 (4th Cir. 2010). Section 5G1.3(c) was a “pertinent Sentencing Commission\\n\\npolicy statement” at Lynn’s sentencing, so it should have been “take[n] into account.”\\n\\nOlmeda, 894 F.3d at 93 (quoting Cavera, 550 F.3d at 188–89); 18 U.S.C. § 3553(a)(5)\\n\\n(2012) (listing “pertinent policy statement[s]” as a factor that sentencing judges must\\n\\nconsider). However, while the district court acknowledged § 5G1.3(c)’s existence, heard\\n\\n\\n 21\\n\\nargument on it, and discussed its application at some length during the sentencing\\n\\nhearing, the district court ultimately decided to neither adopt nor reject the Guidelines’\\n\\nrecommendation. Typically, this result would not be possible: When imposing a federal\\n\\nsentence, district courts necessarily decide whether to accept or reject the pertinent\\n\\nSentencing Guidelines whenever they decide the length of a sentence. Section 5G1.3(c),\\n\\nhowever, uniquely provides an opportunity to make no decision at all because a district\\n\\ncourt’s failure to rule in situations where § 5G1.3(c) applies creates no presumption one\\n\\nway or another regarding whether the prisoner’s two sentences should be served\\n\\nconcurrently. See Mangum, 824 F.3d at 101–02. The decision is simply left to the BOP.\\n\\n The majority opines that Setser already acknowledged and condoned the very\\n\\nsame failure to decide that occurred here, citing the footnote in which the Supreme Court\\n\\nstates: “Of course, a district court should exercise the power to impose anticipatory\\n\\nconsecutive (or concurrent) sentences intelligently. In some situations, a district court\\n\\nmay have inadequate information and may forbear, but in other situations, that will not\\n\\nbe the case.” Setser, 566 U.S. at 243 n.6 (emphasis added). This language, however, was\\n\\nwritten before the U.S. Sentencing Commission adopted § 5G1.3(c). It does not change\\n\\nthe district court’s obligation to rule on each pertinent Sentencing Guideline.\\n\\n Criminal sentencing has been entrusted to the judicial branch, and deciding\\n\\nwhether multiple sentences should run concurrently is intrinsically a determination of the\\n\\nlength of imprisonment. Such decisions should be made by the district court just like any\\n\\nother determination about the number of months that a defendant will serve. Therefore,\\n\\nthe district court’s failure to rule on § 5G1.3(c)’s applicability to Lynn’s sentence punts\\n\\n\\n 22\\n\\nthe determination on the length of his sentence to the BOP. That result is an\\n\\ninappropriate delegation of the courts’ judicial power, and I must dissent.\\n\\n\\n\\n V.\\n\\n Because U.S.S.G. § 5G1.3 is a pertinent Sentencing Commission policy statement,\\n\\nthe district court was required to decide whether to adopt its recommendation that Lynn’s\\n\\nsentences run concurrently. It erred in leaving that decision to the BOP. I therefore\\n\\nrespectfully dissent.\\n\\n\\n\\n\\n 23\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4356547/\", \"author_raw\": \"FLOYD, Circuit Judge, concurring\"}]}"},"judge1":{"kind":"string","value":"MOTZ"},"judge2":{"kind":"string","value":"FLOYD"},"judge3":{"kind":"string","value":"JONES"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":5,"string":"5"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":1,"string":"1"},"concurrence_count":{"kind":"number","value":2,"string":"2"},"other_count":{"kind":"number","value":2,"string":"2"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4579294/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":1,"string":"1"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Gary Giovon LYNN, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-07\nOpinion type: majority\nHas dissenting opinion: Yes\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-4232\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff - Appellee,\n\n v.\n\nGARY GIOVON LYNN,\n\n Defendant - Appellant.\n\n\n\nAppeal from the United States District Court for the Middle District of North Carolina, at\nGreensboro. William L. Osteen, Jr., District Judge. (1:16-cr-00287-WO-1)\n\n\nArgued: September 26, 2018 Decided: January 7, 2019\n\n\nBefore MOTZ and FLOYD, Circuit Judges, and James P. JONES, United States District\nJudge for the Western District of Virginia, sitting by designation.\n\n\nAffirmed by published opinion. Judge Jones wrote the majority opinion, in which Judge\nMotz joined. Judge Floyd wrote a separate opinion, in which he concurred in part and\ndissented in part.\n\n\nARGUED: John Arthur Duberstein, OFFICE OF THE FEDERAL PUBLIC\nDEFENDER, Greensboro, North Carolina, for Appellant. Kimberly Furr Davis, OFFICE\nOF THE UNITED STATES ATTORNEY, Winston-Salem, North Carolina, for\nAppellee. ON BRIEF: Louis C. Allen, Federal Public Defender, OFFICE OF THE\nFEDERAL PUBLIC DEFENDER, Greensboro, North Carolina, for Appellant. Matthew\nG.T. Martin, United States Attorney, OFFICE OF THE UNITED STATES ATTORNEY,\n\nGreensboro, North Carolina, for Appellee.\n\n\n\n\n 2\n\nJONES, District Judge:\n\n Gary Giovon Lynn pled guilty to being a felon in possession of a firearm, in\n\nviolation of 18 U.S.C. §§ 922(g)(l), 924(a)(2). The district court sentenced Lynn to 120\n\nmonths’ imprisonment. On appeal, counsel filed a brief pursuant to Anders v. California,\n\n386 U.S. 738 (1967), questioning whether the district court erred in applying a cross-\n\nreference to the attempted murder Sentencing Guideline. U.S. Sentencing Guidelines\n\nManual (USSG) §§ 2A2.1, 2K2.1(c)(l)(A), 2X1.l(a) (2016). We directed supplemental\n\nbriefing on the additional issue of whether in light of USSG § 5G3.1(c), the district court\n\nerred in failing to impose its sentence to run concurrently with an anticipated term of\n\nstate imprisonment. We now affirm the district court’s judgment.\n\n I.\n\n On January 4, 2016, Officer A.D. Gardner of the Winston-Salem Police\n\nDepartment stopped a speeding vehicle occupied by Lynn along with two other\n\nindividuals. While standing near the vehicle, Officer Gardner smelled marijuana, and he\n\nrequested additional officers for assistance. When the other officers arrived, Officer\n\nGardner asked each of the occupants to exit the vehicle. After Officer Gardner frisked\n\nLynn, Gardner instructed him to stand by a guardrail with the driver of the vehicle. As\n\nOfficer Nicholas Powell was frisking another passenger, Lynn jumped into the driver’s\n\nside of the vehicle and Officer Powell followed, landing on top of him. The two\n\nstruggled over control of the vehicle, with Lynn putting the vehicle into drive, and\n\nOfficer Powell pulling the emergency brake. The vehicle rolled away, and Officer\n\nGardner pursued it. He heard a gunshot, and when he reached the vehicle, he saw Officer\n\n 3\n\nPowell lying on top of Lynn and holding Lynn’s left hand, in which Lynn had a pistol\n\npointed at Officer Powell. Officer Powell had suffered gunshot wounds to his arms and\n\nchest. Lynn had also suffered a gunshot wound, although Officer Powell had not fired\n\nhis weapon during the struggle.\n\n Lynn was arrested and charged in state court with attempted first-degree murder,\n\npossession of a firearm by a felon, and fleeing or eluding arrest with a motor vehicle.\n\nWhile Lynn was detained in state custody, he was indicted on a federal charge of being a\n\nfelon in possession of a firearm, stemming from the same conduct as the state charges.\n\nLynn was obtained by the district court on a writ of habeas corpus ad prosequendum\n\nwhile his state charges were pending, and he eventually pleaded guilty to the federal\n\nfirearms charge.\n\n At Lynn’s federal sentencing hearing on February 28, 2017, he and Officer Powell\n\nboth testified about what had occurred in the vehicle. Officer Powell stated that after he\n\nhad been able to bring the vehicle to a stop, Lynn dove between the front seats, and as\n\nOfficer Powell had turned to face Lynn, he felt gun shots hit him. On the other hand,\n\nLynn testified that he and Officer Powell had struggled over possession of the firearm,\n\nand it went off accidentally during the struggle. The district court found that Officer\n\nPowell’s testimony was credible while Lynn’s was not, and it determined that a sentence\n\nof 120 months’ imprisonment —the statutory maximum—was appropriate.\n\n The court also heard argument as to whether this sentence should run concurrently\n\nwith or consecutive to Lynn’s future anticipated state sentence. Because Lynn was in\n\nprimary state custody, that state sentence would be served in its entirety before he entered\n\n 4\n\nthe federal prison system. The district court stated that it would be “terribly difficult” for\n\nit to calculate what portion, if any, of Lynn’s sentence should run concurrently with his\n\nanticipated state sentence in light of the variety of state charges he faced, along with the\n\ndispute as to the facts surrounding the shooting. J.A. 153. The court explained:\n\n [L]et’s say that a state court jury finds beyond a reasonable doubt . . . that\n there was a struggle and this constitutes some kind of aggravated assault.\n I’m not sure I would want this sentence to be imposed to run concurrently\n based on the facts that I found.\n\n On the other hand, if there’s an attempted second degree murder\n conviction and some 288-month sentence is imposed, then I think, in\n fairness, the circumstances might merit some overlapping consideration,\n but I just don’t know at this point.\n\nJ.A. 154. The court also suggested that, in light of its uncertainty regarding the extent to\n\nwhich its sentence should run concurrently with the anticipated state sentence, the state\n\ncourt could take the federal sentence into account in fashioning its sentence, and Lynn\n\ncould also request the Bureau of Prisons (BOP) to designate the state prison as his place\n\nof confinement, thus effectively running his federal sentence concurrently with the state\n\nsentence. Ultimately, the court stated:\n\n I am not able to make a determination as to how much of this sentence\n should be imposed to run concurrently with the state court prosecution that\n is now pending. . . . Therefore, at this time I will decline to make a finding\n with respect to running any part of this sentence concurrently to any\n sentence imposed in the state court.\n\nJ.A. 159.\n\n Thereafter, on May 4, 2017, Lynn pleaded guilty in North Carolina Superior Court\n\nto assault with a deadly weapon with intent to kill, inflicting serious bodily injury,\n\n\n\n 5\n\npossession of a firearm by a felon, and fleeing or eluding arrest with a motor vehicle.\n\nThe state court imposed a total sentence of 104 to 137 months’ imprisonment.\n\n II.\n\n A.\n\n Before resolving the issue that was the subject of supplemental briefing and oral\n\nargument, we can easily dispose of the question raised in the Anders brief.\n\n We review a defendant’s sentence “under a deferential abuse-of-discretion\n\nstandard.” Gall v. United States, 552 U.S. 38, 41 (2007). Under the Gall standard, a\n\nsentence is reviewed for both procedural and substantive reasonableness. Id. at 51. In\n\ndetermining procedural reasonableness, we consider, among other things, whether the\n\ncourt properly determined the Sentencing Guidelines range, considered the 18 U.S.C. §\n\n3553(a) factors, and sufficiently explained the selected sentence. Id. at 49–51.\n\n We review the factual findings underlying a district court’s application of a\n\nGuidelines cross-reference for clear error and the court’s legal conclusions de novo.\n\nUnited States v. Ashford, 718 F.3d 377, 380, 383–84 (4th Cir. 2013). “In the event of a\n\nconviction for illegal possession of a firearm, USSG § 2K2.1(c) authorizes a district court\n\nto substitute the offense level for any criminal offense that the defendant committed or\n\nattempted to commit in connection with the possession of the firearm.” Id. at 381. Here,\n\nthe district court found that Lynn committed attempted murder with the firearm at issue.\n\nSentencing Guideline § 2A2.l(a) provides for a base offense level of 33 if the attempted\n\nmurder would have constituted first-degree murder; otherwise, the offense level is 27.\n\n“[S]econd-degree murder simply requires proof of malice aforethought, which may be\n\n 6\n\nestablished by evidence of conduct which is reckless and wanton and a gross deviation\n\nfrom a reasonable standard of care, of such a nature that a jury is warranted in inferring\n\nthat defendant was aware of a serious risk of death or serious bodily harm.” Ashford, 718\n\nF.3d at 384 (internal quotation marks, citation, and alterations omitted).\n\n We conclude that the district court did not err in finding that the murder cross-\n\nreference applied. The district court based its ruling on finding that the victim’s\n\ntestimony was credible and that Lynn’s testimony was not.\n\n [W]hen a trial judge’s finding is based on his decision to credit the\n testimony of one of two or more witnesses, each of whom has told a\n coherent and facially plausible story that is not contradicted by extrinsic\n evidence, that finding, if not internally inconsistent, can virtually never be\n clear error.\n\nUnited States v. Hall, 664 F.3d 456, 462 (4th Cir. 2012) (internal quotation marks and\n\ncitation omitted). Moreover, ballistic evidence indicated that multiple shots were fired\n\nfrom Lynn’s firearm and that more would have been fired had it not malfunctioned. The\n\ndistrict court’s decision not to credit Lynn’s testimony is likewise supported by the\n\nrecord—the firing of multiple shots is arguably inconsistent with Lynn’s explanation that\n\nthe shooting was an accident.\n\n B.\n\n Relying on Setser v. United States, 566 U.S. 231 (2012), Lynn contends that the\n\ndistrict court erred in declining to run its sentence concurrently, in whole or in part, with\n\nthe yet-to-be-imposed state sentence. In light of the now-imposed state sentence, he\n\nseeks a remand for reconsideration of that issue by the district court.\n\n\n\n 7\n\n In Setser, noting that sentencing judges “have discretion to select whether the\n\nsentences they impose will run concurrently or consecutively with respect to other\n\nsentences that they impose, or that have been imposed in other proceedings,” id. at 236,\n\nthe Court held that 18 U.S.C. § 3584(a) allows judges to impose a federal sentence\n\nconcurrently or consecutively to an anticipated, but unimposed, state sentence, id. at 236–\n\n39.\n\n The relevant Sentencing Guideline, added after Setser by USSG amendment 787,\n\neffective November 1, 2014, provides that if “a state term of imprisonment is anticipated\n\nto result from another offense that is relevant conduct to the instant offense of\n\nconviction . . . , the sentence for the instant offense shall be imposed to run concurrently\n\nto the anticipated term of imprisonment.” USSG § 5G1.3(c). There is no question but\n\nthat Lynn’s state charges were relevant conduct to his federal conviction. However,\n\nbecause the Guidelines are advisory, a district court is not obligated to impose a\n\nconcurrent sentence pursuant to USSG § 5G1.3. United States v. Nania, 724 F.3d 824,\n\n830 (7th Cir. 2013). Rather, the district court is required to consider the 18 U.S.C. §\n\n3553(a) factors in determining whether to run sentences consecutively or concurrently.\n\n18 U.S.C. § 3584(b).\n\n Here the district court provided a thorough explanation of the sentence. The court\n\nfound that Lynn’s offense conduct was extremely serious. The court then explained that\n\nit would not order its sentence to run concurrently with the anticipated state sentence in\n\nlight of this seriousness, remarking that a lengthy term of imprisonment was necessary in\n\nthis case. The court recognized its discretion to order the sentence to run concurrently,\n\n 8\n\nbut simply declined to exercise its discretion after considering the required factors. Thus,\n\nwe discern no abuse of discretion in the district court’s decision. See United States v.\n\nHall, 825 F.3d 373, 375–76 (8th Cir. 2016) (upholding decision not to run sentence\n\nconcurrent to anticipated state sentence based on district court’s consideration of the §\n\n3553(a) factors and its explanation that the possibility of a relatively short state sentence\n\nthat would result in an inappropriate period of imprisonment).\n\n Lynn argues that by declining to order the sentence to run concurrently, the district\n\ncourt treaded on the separation-of-powers issue outlined in Setser. See 566 U.S. at 242–\n\n43. In holding that 18 U.S.C. § 3584(a) allows a district court to impose a federal\n\nsentence concurrently or consecutively to an anticipated state sentence, the Court in\n\nSetser rejected the parties’ argument that when a future state sentence is anticipated, the\n\nBOP should decide after the federal sentence has been imposed whether it runs\n\nconcurrently with or consecutive to the state sentence, based upon its authority granted\n\nunder 18 U.S.C. § 3621(b). 1 The Court rejected this argument in part out of concern that\n\nit would leave sentencing in the hands of “the same Department of Justice that conducts\n\nthe prosecution.” Setser, 566 U.S. at 242. Instead, the Court determined that in the first\n\ninstance, the district court, rather than the BOP, should decide whether a federal sentence\n\nruns concurrently with or consecutive to an anticipated state sentence. Id. at 242–43.\n\nHowever, recognizing an exception to this determination, the Court stated that “a district\n\n 1\n That statute provides that the BOP “may designate any available penal or\ncorrectional facility . . ., whether maintained by the Federal Government or otherwise . . .,\nthat the Bureau determines to be appropriate and suitable.” 18 U.S.C. § 3621(b).\n\n\n 9\n\ncourt should exercise the power to impose anticipatory consecutive (or concurrent)\n\nsentences intelligently. In some situations, a district court may have inadequate\n\ninformation and may forbear, but in other situations, that will not be the case.” Id. at 242\n\nn.6.\n\n Lynn’s argument requires us to consider the boundaries of this exception—in what\n\nsituations does a district court’s lack of information permit it to decline to order its\n\nsentence to run concurrently with an anticipated state sentence? To be sure, these\n\nsituations will be limited. When a state sentence is anticipated, the district court will\n\nnormally lack definite information about that sentence, and if this alone were sufficient to\n\npermit the district court to forbear, the exception would swallow the rule. Thus, in most\n\ncases, the district court should decide whether its sentence will run concurrently with or\n\nconsecutive to an anticipated state sentence involving relevant conduct. But as pointed\n\nout by the Sentencing Commission with regard to USSG § 5G1.3, “[d]etermining\n\nwhether, and how, to use this discretion will depend on the adequacy of the information\n\navailable.” USSG Amend. 776 (Nov. 1, 2013).\n\n It is clear that Lynn’s case was not routine. First, the conduct at issue was\n\nextremely serious. As the district court stated, “this is . . . one of the most, if not the\n\nmost, serious forms of a 922(g)(1) offense. The only thing more serious is a shooting in\n\nwhich an individual is actually killed.” J.A. 158. Further, the variety of state charges\n\nagainst Lynn, along with his dispute as to the facts surrounding the shooting—in\n\nparticular, his testimony that the shooting was accidental—made it possible for his\n\nanticipated state sentence to range from relatively short to over double his federal\n\n 10\n\nsentence. The district court considered this possibility and the effect it would have on\n\nany concurrent sentence it might order, ultimately determining that the uncertainty it\n\ncreated prevented the court from accomplishing its proper sentencing objectives.\n\n Of course, we know by now the sentence imposed on Lynn by the state court. But\n\nit was not unreasonable at the time of imposing sentence for the district court to have\n\njustified doubts as to the scope of that state sentence. As noted by the Court in Setser, the\n\nfact that the later state sentence may be unexpected, “does not establish that the District\n\nCourt abused its discretion by imposing an unreasonable sentence.” 566 U.S. at 244. The\n\ndistrict court attempted to exercise its power to impose a concurrent or consecutive\n\nsentence intelligently, but, for the reasons discussed above, it lacked adequate\n\ninformation to do so. Accordingly, the district court did not err in declining to run its\n\nsentence concurrently with the anticipated state sentence. 2\n\n\n 2\n Shortly before oral argument, the government submitted additional authority\npursuant to Federal Rule of Appellate Procedure 28(j) and Local Rule 28(e), arguing that\nwhen Lynn agreed that his state court sentence “shall run consecutively to any other\nsentence the defendant is now subject to,” Lynn waived the issues he raises on appeal,\nand any error by the district court must be disregarded. We disagree.\n\n Lynn’s agreement regarding his state court sentence has no effect on his federal\nsentence. As previously noted, Lynn was in primary state custody when he was\nsentenced on the federal charge, and as a result, he will serve his state sentence in its\nentirety before he serves his federal sentence. “In our American system of dual\nsovereignty, each sovereign—whether the Federal Government or a State—is responsible\nfor the administration of its own criminal justice system.” Setser, 566 U.S. at 241\n(internal quotation marks, citation, and alterations omitted). “If a prisoner like [Lynn]\nstarts in state custody, serves his state sentence, and then moves to federal custody, it will\nalways be the Federal Government . . . that decides whether he will receive credit for the\ntime served in state custody.” Id. Thus, Lynn’s state court sentence cannot run\nconsecutively to his federal sentence, and the state court cannot dictate that his federal\n(Continued)\n 11\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Gary Giovon LYNN, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-07\\nOpinion type: majority\\nHas dissenting opinion: Yes\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-4232\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nGARY GIOVON LYNN,\\n\\n Defendant - Appellant.\\n\\n\\n\\nAppeal from the United States District Court for the Middle District of North Carolina, at\\nGreensboro. William L. Osteen, Jr., District Judge. (1:16-cr-00287-WO-1)\\n\\n\\nArgued: September 26, 2018 Decided: January 7, 2019\\n\\n\\nBefore MOTZ and FLOYD, Circuit Judges, and James P. JONES, United States District\\nJudge for the Western District of Virginia, sitting by designation.\\n\\n\\nAffirmed by published opinion. Judge Jones wrote the majority opinion, in which Judge\\nMotz joined. Judge Floyd wrote a separate opinion, in which he concurred in part and\\ndissented in part.\\n\\n\\nARGUED: John Arthur Duberstein, OFFICE OF THE FEDERAL PUBLIC\\nDEFENDER, Greensboro, North Carolina, for Appellant. Kimberly Furr Davis, OFFICE\\nOF THE UNITED STATES ATTORNEY, Winston-Salem, North Carolina, for\\nAppellee. ON BRIEF: Louis C. Allen, Federal Public Defender, OFFICE OF THE\\nFEDERAL PUBLIC DEFENDER, Greensboro, North Carolina, for Appellant. Matthew\\nG.T. Martin, United States Attorney, OFFICE OF THE UNITED STATES ATTORNEY,\\n\\nGreensboro, North Carolina, for Appellee.\\n\\n\\n\\n\\n 2\\n\\nJONES, District Judge:\\n\\n Gary Giovon Lynn pled guilty to being a felon in possession of a firearm, in\\n\\nviolation of 18 U.S.C. §§ 922(g)(l), 924(a)(2). The district court sentenced Lynn to 120\\n\\nmonths’ imprisonment. On appeal, counsel filed a brief pursuant to Anders v. California,\\n\\n386 U.S. 738 (1967), questioning whether the district court erred in applying a cross-\\n\\nreference to the attempted murder Sentencing Guideline. U.S. Sentencing Guidelines\\n\\nManual (USSG) §§ 2A2.1, 2K2.1(c)(l)(A), 2X1.l(a) (2016). We directed supplemental\\n\\nbriefing on the additional issue of whether in light of USSG § 5G3.1(c), the district court\\n\\nerred in failing to impose its sentence to run concurrently with an anticipated term of\\n\\nstate imprisonment. We now affirm the district court’s judgment.\\n\\n I.\\n\\n On January 4, 2016, Officer A.D. Gardner of the Winston-Salem Police\\n\\nDepartment stopped a speeding vehicle occupied by Lynn along with two other\\n\\nindividuals. While standing near the vehicle, Officer Gardner smelled marijuana, and he\\n\\nrequested additional officers for assistance. When the other officers arrived, Officer\\n\\nGardner asked each of the occupants to exit the vehicle. After Officer Gardner frisked\\n\\nLynn, Gardner instructed him to stand by a guardrail with the driver of the vehicle. As\\n\\nOfficer Nicholas Powell was frisking another passenger, Lynn jumped into the driver’s\\n\\nside of the vehicle and Officer Powell followed, landing on top of him. The two\\n\\nstruggled over control of the vehicle, with Lynn putting the vehicle into drive, and\\n\\nOfficer Powell pulling the emergency brake. The vehicle rolled away, and Officer\\n\\nGardner pursued it. He heard a gunshot, and when he reached the vehicle, he saw Officer\\n\\n 3\\n\\nPowell lying on top of Lynn and holding Lynn’s left hand, in which Lynn had a pistol\\n\\npointed at Officer Powell. Officer Powell had suffered gunshot wounds to his arms and\\n\\nchest. Lynn had also suffered a gunshot wound, although Officer Powell had not fired\\n\\nhis weapon during the struggle.\\n\\n Lynn was arrested and charged in state court with attempted first-degree murder,\\n\\npossession of a firearm by a felon, and fleeing or eluding arrest with a motor vehicle.\\n\\nWhile Lynn was detained in state custody, he was indicted on a federal charge of being a\\n\\nfelon in possession of a firearm, stemming from the same conduct as the state charges.\\n\\nLynn was obtained by the district court on a writ of habeas corpus ad prosequendum\\n\\nwhile his state charges were pending, and he eventually pleaded guilty to the federal\\n\\nfirearms charge.\\n\\n At Lynn’s federal sentencing hearing on February 28, 2017, he and Officer Powell\\n\\nboth testified about what had occurred in the vehicle. Officer Powell stated that after he\\n\\nhad been able to bring the vehicle to a stop, Lynn dove between the front seats, and as\\n\\nOfficer Powell had turned to face Lynn, he felt gun shots hit him. On the other hand,\\n\\nLynn testified that he and Officer Powell had struggled over possession of the firearm,\\n\\nand it went off accidentally during the struggle. The district court found that Officer\\n\\nPowell’s testimony was credible while Lynn’s was not, and it determined that a sentence\\n\\nof 120 months’ imprisonment —the statutory maximum—was appropriate.\\n\\n The court also heard argument as to whether this sentence should run concurrently\\n\\nwith or consecutive to Lynn’s future anticipated state sentence. Because Lynn was in\\n\\nprimary state custody, that state sentence would be served in its entirety before he entered\\n\\n 4\\n\\nthe federal prison system. The district court stated that it would be “terribly difficult” for\\n\\nit to calculate what portion, if any, of Lynn’s sentence should run concurrently with his\\n\\nanticipated state sentence in light of the variety of state charges he faced, along with the\\n\\ndispute as to the facts surrounding the shooting. J.A. 153. The court explained:\\n\\n [L]et’s say that a state court jury finds beyond a reasonable doubt . . . that\\n there was a struggle and this constitutes some kind of aggravated assault.\\n I’m not sure I would want this sentence to be imposed to run concurrently\\n based on the facts that I found.\\n\\n On the other hand, if there’s an attempted second degree murder\\n conviction and some 288-month sentence is imposed, then I think, in\\n fairness, the circumstances might merit some overlapping consideration,\\n but I just don’t know at this point.\\n\\nJ.A. 154. The court also suggested that, in light of its uncertainty regarding the extent to\\n\\nwhich its sentence should run concurrently with the anticipated state sentence, the state\\n\\ncourt could take the federal sentence into account in fashioning its sentence, and Lynn\\n\\ncould also request the Bureau of Prisons (BOP) to designate the state prison as his place\\n\\nof confinement, thus effectively running his federal sentence concurrently with the state\\n\\nsentence. Ultimately, the court stated:\\n\\n I am not able to make a determination as to how much of this sentence\\n should be imposed to run concurrently with the state court prosecution that\\n is now pending. . . . Therefore, at this time I will decline to make a finding\\n with respect to running any part of this sentence concurrently to any\\n sentence imposed in the state court.\\n\\nJ.A. 159.\\n\\n Thereafter, on May 4, 2017, Lynn pleaded guilty in North Carolina Superior Court\\n\\nto assault with a deadly weapon with intent to kill, inflicting serious bodily injury,\\n\\n\\n\\n 5\\n\\npossession of a firearm by a felon, and fleeing or eluding arrest with a motor vehicle.\\n\\nThe state court imposed a total sentence of 104 to 137 months’ imprisonment.\\n\\n II.\\n\\n A.\\n\\n Before resolving the issue that was the subject of supplemental briefing and oral\\n\\nargument, we can easily dispose of the question raised in the Anders brief.\\n\\n We review a defendant’s sentence “under a deferential abuse-of-discretion\\n\\nstandard.” Gall v. United States, 552 U.S. 38, 41 (2007). Under the Gall standard, a\\n\\nsentence is reviewed for both procedural and substantive reasonableness. Id. at 51. In\\n\\ndetermining procedural reasonableness, we consider, among other things, whether the\\n\\ncourt properly determined the Sentencing Guidelines range, considered the 18 U.S.C. §\\n\\n3553(a) factors, and sufficiently explained the selected sentence. Id. at 49–51.\\n\\n We review the factual findings underlying a district court’s application of a\\n\\nGuidelines cross-reference for clear error and the court’s legal conclusions de novo.\\n\\nUnited States v. Ashford, 718 F.3d 377, 380, 383–84 (4th Cir. 2013). “In the event of a\\n\\nconviction for illegal possession of a firearm, USSG § 2K2.1(c) authorizes a district court\\n\\nto substitute the offense level for any criminal offense that the defendant committed or\\n\\nattempted to commit in connection with the possession of the firearm.” Id. at 381. Here,\\n\\nthe district court found that Lynn committed attempted murder with the firearm at issue.\\n\\nSentencing Guideline § 2A2.l(a) provides for a base offense level of 33 if the attempted\\n\\nmurder would have constituted first-degree murder; otherwise, the offense level is 27.\\n\\n“[S]econd-degree murder simply requires proof of malice aforethought, which may be\\n\\n 6\\n\\nestablished by evidence of conduct which is reckless and wanton and a gross deviation\\n\\nfrom a reasonable standard of care, of such a nature that a jury is warranted in inferring\\n\\nthat defendant was aware of a serious risk of death or serious bodily harm.” Ashford, 718\\n\\nF.3d at 384 (internal quotation marks, citation, and alterations omitted).\\n\\n We conclude that the district court did not err in finding that the murder cross-\\n\\nreference applied. The district court based its ruling on finding that the victim’s\\n\\ntestimony was credible and that Lynn’s testimony was not.\\n\\n [W]hen a trial judge’s finding is based on his decision to credit the\\n testimony of one of two or more witnesses, each of whom has told a\\n coherent and facially plausible story that is not contradicted by extrinsic\\n evidence, that finding, if not internally inconsistent, can virtually never be\\n clear error.\\n\\nUnited States v. Hall, 664 F.3d 456, 462 (4th Cir. 2012) (internal quotation marks and\\n\\ncitation omitted). Moreover, ballistic evidence indicated that multiple shots were fired\\n\\nfrom Lynn’s firearm and that more would have been fired had it not malfunctioned. The\\n\\ndistrict court’s decision not to credit Lynn’s testimony is likewise supported by the\\n\\nrecord—the firing of multiple shots is arguably inconsistent with Lynn’s explanation that\\n\\nthe shooting was an accident.\\n\\n B.\\n\\n Relying on Setser v. United States, 566 U.S. 231 (2012), Lynn contends that the\\n\\ndistrict court erred in declining to run its sentence concurrently, in whole or in part, with\\n\\nthe yet-to-be-imposed state sentence. In light of the now-imposed state sentence, he\\n\\nseeks a remand for reconsideration of that issue by the district court.\\n\\n\\n\\n 7\\n\\n In Setser, noting that sentencing judges “have discretion to select whether the\\n\\nsentences they impose will run concurrently or consecutively with respect to other\\n\\nsentences that they impose, or that have been imposed in other proceedings,” id. at 236,\\n\\nthe Court held that 18 U.S.C. § 3584(a) allows judges to impose a federal sentence\\n\\nconcurrently or consecutively to an anticipated, but unimposed, state sentence, id. at 236–\\n\\n39.\\n\\n The relevant Sentencing Guideline, added after Setser by USSG amendment 787,\\n\\neffective November 1, 2014, provides that if “a state term of imprisonment is anticipated\\n\\nto result from another offense that is relevant conduct to the instant offense of\\n\\nconviction . . . , the sentence for the instant offense shall be imposed to run concurrently\\n\\nto the anticipated term of imprisonment.” USSG § 5G1.3(c). There is no question but\\n\\nthat Lynn’s state charges were relevant conduct to his federal conviction. However,\\n\\nbecause the Guidelines are advisory, a district court is not obligated to impose a\\n\\nconcurrent sentence pursuant to USSG § 5G1.3. United States v. Nania, 724 F.3d 824,\\n\\n830 (7th Cir. 2013). Rather, the district court is required to consider the 18 U.S.C. §\\n\\n3553(a) factors in determining whether to run sentences consecutively or concurrently.\\n\\n18 U.S.C. § 3584(b).\\n\\n Here the district court provided a thorough explanation of the sentence. The court\\n\\nfound that Lynn’s offense conduct was extremely serious. The court then explained that\\n\\nit would not order its sentence to run concurrently with the anticipated state sentence in\\n\\nlight of this seriousness, remarking that a lengthy term of imprisonment was necessary in\\n\\nthis case. The court recognized its discretion to order the sentence to run concurrently,\\n\\n 8\\n\\nbut simply declined to exercise its discretion after considering the required factors. Thus,\\n\\nwe discern no abuse of discretion in the district court’s decision. See United States v.\\n\\nHall, 825 F.3d 373, 375–76 (8th Cir. 2016) (upholding decision not to run sentence\\n\\nconcurrent to anticipated state sentence based on district court’s consideration of the §\\n\\n3553(a) factors and its explanation that the possibility of a relatively short state sentence\\n\\nthat would result in an inappropriate period of imprisonment).\\n\\n Lynn argues that by declining to order the sentence to run concurrently, the district\\n\\ncourt treaded on the separation-of-powers issue outlined in Setser. See 566 U.S. at 242–\\n\\n43. In holding that 18 U.S.C. § 3584(a) allows a district court to impose a federal\\n\\nsentence concurrently or consecutively to an anticipated state sentence, the Court in\\n\\nSetser rejected the parties’ argument that when a future state sentence is anticipated, the\\n\\nBOP should decide after the federal sentence has been imposed whether it runs\\n\\nconcurrently with or consecutive to the state sentence, based upon its authority granted\\n\\nunder 18 U.S.C. § 3621(b). 1 The Court rejected this argument in part out of concern that\\n\\nit would leave sentencing in the hands of “the same Department of Justice that conducts\\n\\nthe prosecution.” Setser, 566 U.S. at 242. Instead, the Court determined that in the first\\n\\ninstance, the district court, rather than the BOP, should decide whether a federal sentence\\n\\nruns concurrently with or consecutive to an anticipated state sentence. Id. at 242–43.\\n\\nHowever, recognizing an exception to this determination, the Court stated that “a district\\n\\n 1\\n That statute provides that the BOP “may designate any available penal or\\ncorrectional facility . . ., whether maintained by the Federal Government or otherwise . . .,\\nthat the Bureau determines to be appropriate and suitable.” 18 U.S.C. § 3621(b).\\n\\n\\n 9\\n\\ncourt should exercise the power to impose anticipatory consecutive (or concurrent)\\n\\nsentences intelligently. In some situations, a district court may have inadequate\\n\\ninformation and may forbear, but in other situations, that will not be the case.” Id. at 242\\n\\nn.6.\\n\\n Lynn’s argument requires us to consider the boundaries of this exception—in what\\n\\nsituations does a district court’s lack of information permit it to decline to order its\\n\\nsentence to run concurrently with an anticipated state sentence? To be sure, these\\n\\nsituations will be limited. When a state sentence is anticipated, the district court will\\n\\nnormally lack definite information about that sentence, and if this alone were sufficient to\\n\\npermit the district court to forbear, the exception would swallow the rule. Thus, in most\\n\\ncases, the district court should decide whether its sentence will run concurrently with or\\n\\nconsecutive to an anticipated state sentence involving relevant conduct. But as pointed\\n\\nout by the Sentencing Commission with regard to USSG § 5G1.3, “[d]etermining\\n\\nwhether, and how, to use this discretion will depend on the adequacy of the information\\n\\navailable.” USSG Amend. 776 (Nov. 1, 2013).\\n\\n It is clear that Lynn’s case was not routine. First, the conduct at issue was\\n\\nextremely serious. As the district court stated, “this is . . . one of the most, if not the\\n\\nmost, serious forms of a 922(g)(1) offense. The only thing more serious is a shooting in\\n\\nwhich an individual is actually killed.” J.A. 158. Further, the variety of state charges\\n\\nagainst Lynn, along with his dispute as to the facts surrounding the shooting—in\\n\\nparticular, his testimony that the shooting was accidental—made it possible for his\\n\\nanticipated state sentence to range from relatively short to over double his federal\\n\\n 10\\n\\nsentence. The district court considered this possibility and the effect it would have on\\n\\nany concurrent sentence it might order, ultimately determining that the uncertainty it\\n\\ncreated prevented the court from accomplishing its proper sentencing objectives.\\n\\n Of course, we know by now the sentence imposed on Lynn by the state court. But\\n\\nit was not unreasonable at the time of imposing sentence for the district court to have\\n\\njustified doubts as to the scope of that state sentence. As noted by the Court in Setser, the\\n\\nfact that the later state sentence may be unexpected, “does not establish that the District\\n\\nCourt abused its discretion by imposing an unreasonable sentence.” 566 U.S. at 244. The\\n\\ndistrict court attempted to exercise its power to impose a concurrent or consecutive\\n\\nsentence intelligently, but, for the reasons discussed above, it lacked adequate\\n\\ninformation to do so. Accordingly, the district court did not err in declining to run its\\n\\nsentence concurrently with the anticipated state sentence. 2\\n\\n\\n 2\\n Shortly before oral argument, the government submitted additional authority\\npursuant to Federal Rule of Appellate Procedure 28(j) and Local Rule 28(e), arguing that\\nwhen Lynn agreed that his state court sentence “shall run consecutively to any other\\nsentence the defendant is now subject to,” Lynn waived the issues he raises on appeal,\\nand any error by the district court must be disregarded. We disagree.\\n\\n Lynn’s agreement regarding his state court sentence has no effect on his federal\\nsentence. As previously noted, Lynn was in primary state custody when he was\\nsentenced on the federal charge, and as a result, he will serve his state sentence in its\\nentirety before he serves his federal sentence. “In our American system of dual\\nsovereignty, each sovereign—whether the Federal Government or a State—is responsible\\nfor the administration of its own criminal justice system.” Setser, 566 U.S. at 241\\n(internal quotation marks, citation, and alterations omitted). “If a prisoner like [Lynn]\\nstarts in state custody, serves his state sentence, and then moves to federal custody, it will\\nalways be the Federal Government . . . that decides whether he will receive credit for the\\ntime served in state custody.” Id. Thus, Lynn’s state court sentence cannot run\\nconsecutively to his federal sentence, and the state court cannot dictate that his federal\\n(Continued)\\n 11\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":83,"cells":{"id":{"kind":"number","value":4579301,"string":"4,579,301"},"name":{"kind":"string","value":"Jose Marcial CORTEZ-MENDEZ, Petitioner, v. Matthew G. WHITAKER, Acting Attorney General, Respondent."},"name_abbreviation":{"kind":"string","value":"Jose Cortez-Mendez v. Matthew Whitaker"},"decision_date":{"kind":"string","value":"2019-01-07"},"docket_number":{"kind":"string","value":"16-2389"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before WILKINSON and AGEE, Circuit Judges, and James P. JONES, United States District Judge for the Western District of Virginia, sitting by designation.\", \"parties\": \"\", \"opinions\": [{\"author\": \"AGEE, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 16-2389\\n\\n\\n\\nJOSE MARCIAL CORTEZ-MENDEZ,\\n\\n Petitioner,\\n\\nv.\\n\\nMATTHEW G. WHITAKER, Acting Attorney General,\\n\\n Respondent.\\n\\n\\nOn Petition for Review of an Order of the Board of Immigration Appeals.\\n\\n\\nArgued: September 25, 2018 Decided: January 7, 2019\\n\\n\\nBefore WILKINSON and AGEE, Circuit Judges, and James P. JONES, United States\\nDistrict Judge for the Western District of Virginia, sitting by designation.\\n\\n\\nPetition for review denied by published opinion. Judge Agee wrote the opinion, in\\nwhich Judge Wilkinson and Judge Jones joined.\\n\\n\\nARGUED: Melissa Jill Mitchell, LAW OFFICES OF PAUL A. SUHR, PLLC, Raleigh,\\nNorth Carolina, for Cortez-Mendez. Robert Michael Stalzer, UNITED STATES\\nDEPARTMENT OF JUSTICE, Washington, D.C., for Respondent. ON BRIEF: Paul\\nA. Suhr, LAW OFFICES OF PAUL A. SUHR, PLLC, Raleigh, North Carolina, for\\nCortez-Mendez. Chad A. Readler, Acting Assistant Attorney General, Kiley Kane,\\nSenior Litigation Counsel, Office of Immigration Litigation, Civil Division, UNITED\\nSTATES DEPARTMENT OF JUSTICE, Washington, D.C., for Respondent.\\n\\fAGEE, Circuit Judge:\\n\\n Jose Cortez-Mendez, a native and citizen of El Salvador, seeks review of an order\\n\\nfrom the Board of Immigration Appeals (“BIA”). The BIA dismissed his appeal\\n\\nfollowing an immigration judge’s (“IJ’s”) denial of his application for withholding of\\n\\nremoval under the Immigration and Nationality Act (“INA”), 8 U.S.C. § 1231(b)(3), and\\n\\nprotection under the United Nations Convention Against Torture (“CAT”), 8 C.F.R.\\n\\n§ 1208.16(c). For the reasons below, we deny the petition for review.\\n\\n\\n\\n I.\\n\\n Cortez-Mendez was born in El Salvador. His father, Marcial Cortez, is deaf and\\n\\nmute. People in El Salvador with these physical impairments have suffered routine\\n\\nridicule and discrimination, despite the existence of anti-discrimination laws. See A.R.\\n\\n422 (containing U.S. Dep’t of State, El Salvador, 2014 Country Reports on Human\\n\\nRights Practices). Because of his disabilities, Marcial Cortez could not provide for his\\n\\nfamily and they moved in with Cortez-Mendez’s aunt. Cortez-Mendez’s mother also\\n\\nabandoned the family when he was seven because of the family’s difficulties.\\n\\n As a teenager, MS-13 and MS-18 gang members began targeting Cortez-Mendez\\n\\nfor gang recruitment. They harassed him and “threatened [him] with death, that if [he] did\\n\\nnot become a gangster, they were going to kill [him].” A.R. 175. Despite this harassment,\\n\\nthe gangs never physically harmed Cortez-Mendez or anyone in his family. To this day,\\n\\nhis father, mother, sisters, and aunt live in El Salvador unharmed.\\n\\n\\n\\n 2\\n\\f Cortez-Mendez illegally entered the United States in 2003. The Department of\\n\\nHomeland Security served him with a Notice to Appear, but he failed to appear at his\\n\\nhearing and was ordered removed to El Salvador in abstentia. Nevertheless, Cortez-\\n\\nMendez settled in North Carolina with his uncle, girlfriend, and two children. In 2005,\\n\\ngang members called Cortez-Mendez’s mother in El Salvador, demanded money, and\\n\\ndemanded Cortez-Mendez’s whereabouts. Through his aunt, Cortez-Mendez learned the\\n\\ngangs told his mother they “remembered [him] as a son of a mute and dumb person” and\\n\\nthreatened to “kill [him] and dismember [him]” if he returned to El Salvador. A.R. 176.\\n\\n In 2015, Cortez-Mendez applied for withholding of removal and CAT protection.\\n\\nAs grounds for protection under the INA, he cited his membership in a particular social\\n\\ngroup: “member[s] of the family of Marcial Cortez who is a disabled person.” A.R. 124;\\n\\nsee 8 U.S.C. § 1101(a)(42). In 2016, the IJ denied Cortez-Mendez’s application for\\n\\nwithholding of removal and CAT protection. The IJ found Cortez-Mendez’s testimony\\n\\nwas credible but held his proposed particular social group did not satisfy the INA’s\\n\\nrequirements. The IJ also held that Cortez-Mendez failed to demonstrate a sufficient\\n\\nnexus—that is, he did not show that the “indeterminate and generalized” threats he had\\n\\nreceived in El Salvador were on account of his membership in that group. A.R. 63.\\n\\n Cortez-Mendez appealed to the BIA. In its own opinion, the BIA affirmed the IJ’s\\n\\nconclusion that “any threats [Cortez-Mendez] received or future harm he fears are the\\n\\nresult of general criminal gang activity,” not membership in his disabled father’s family.\\n\\nA.R. 3. The BIA also affirmed the IJ’s refusal to accept Cortez-Mendez’s “speculat[ion]\\n\\nthat his lower economic status and his father’s disability made him more susceptible to\\n\\n 3\\n\\fgang recruitment” because the record fairly supports the conclusion that the “harm he\\n\\nfears upon return [is] as a result of his rejection of gang membership rather than his\\n\\nfather’s disability.” A.R. 3. The BIA thus dismissed Cortez-Mendez’s appeal, and Cortez-\\n\\nMendez was again ordered removed. He timely appealed, and we have jurisdiction under\\n\\n8 U.S.C. § 1252.\\n\\n\\n\\n II.\\n\\n When, as here, the BIA “adopt[s] and affirm[s]” the IJ’s conclusion but adds\\n\\nadditional reasoning in its own opinion, we review “the factual findings and reasoning\\n\\ncontained in both decisions.” Ai Hua Chen v. Holder, 742 F.3d 171, 177 (4th Cir. 2014);\\n\\nA.R. 3. If the factual findings are supported by substantial evidence, they are conclusive\\n\\n“unless any reasonable adjudicator would be compelled to conclude to the contrary.” 8\\n\\nU.S.C. § 1252(b)(4)(B); Salgado-Sosa v. Sessions, 882 F.3d 451, 456 (4th Cir. 2018). As\\n\\nfor legal determinations, we review them de novo. Salgado-Sosa, 882 F.3d at 456.\\n\\nUltimately, we must affirm the BIA’s decision if it is not “manifestly contrary to law and\\n\\nan abuse of discretion.” 8 U.S.C. § 1252(b)(4)(D).\\n\\n\\n\\n III.\\n\\n In his opening brief, Cortez-Mendez argues only that the BIA erred in denying his\\n\\npetition for withholding of removal. Because he does not address the BIA’s denial of his\\n\\npetition for CAT protection, he has waived his claim for CAT relief. Fed. R. App. P.\\n\\n28(a)(8)(A); see Edwards v. City of Goldsboro, 178 F.3d 231, 241 n.6 (4th Cir. 1999).\\n\\n 4\\n\\f To receive withholding of removal relief, Cortez-Mendez must show that, if\\n\\nremoved to El Salvador, “there is a clear probability that [his] ‘life or freedom would be\\n\\nthreatened . . . because of’” a protected ground—here, his alleged membership in a\\n\\nparticular social group. Marynenka v. Holder, 592 F.3d 594, 600 (4th Cir. 2010) (quoting\\n\\n8 U.S.C. § 1231(b)(3)(A)). This standard requires two showings: First, Cortez-Mendez\\n\\nmust show “it is more likely than not” that his life or freedom will be threatened if he\\n\\nreturns to El Salvador. Lizama v. Holder, 629 F.3d 440, 446 (4th Cir. 2011) (internal\\n\\nquotation marks omitted). Evidence that he suffered past persecution can help to satisfy\\n\\nthis first showing. See 8 C.F.R. § 1208.16(b)(1). Second, Cortez-Mendez must show that\\n\\nthe “probability of persecution” is “link[ed]” to his status in the particular social group,\\n\\nthat is, that the two share a nexus. Singh v. Holder, 699 F.3d 321, 327 (4th Cir. 2012). If\\n\\nhe satisfies his burden of proof, withholding of removal is mandatory. Gomis v. Holder,\\n\\n571 F.3d 353, 359 (4th Cir. 2009).\\n\\n The nexus issue is dispositive of this appeal, so we dispose at the outset of two\\n\\nissues we need not resolve: whether Cortez-Mendez is a member of a particular social\\n\\ngroup and whether he suffered past persecution. See 8 U.S.C. § 1101(a)(42); 8 C.F.R.\\n\\n§ 1208.16(b)(1). We will assume, without deciding, that Cortez-Mendez is a member of a\\n\\nparticular social group comprised of his disabled father’s immediate family members and\\n\\nthat he suffered past persecution in El Salvador. ∗ We will consider only whether Cortez-\\n\\n\\n ∗While “we have expressly held that the threat of death qualifies as persecution,”\\nHernandez-Avalos v. Lynch, 784 F.3d 944, 949 (4th Cir. 2015) (internal quotation marks\\nomitted), we hesitate to conclude that Cortez-Mendez suffered past persecution here. To\\n(Continued)\\n 5\\n\\fMendez established the requisite nexus between any persecution he suffered and his\\n\\nrelation to his disabled father.\\n\\n A.\\n\\n Whether a person’s persecution shares a nexus with his alleged protected ground is\\n\\na question of fact entitled to deference and reviewed for clear error. See Crespin-\\n\\nValladares v. Holder, 632 F.3d 117, 128 (4th Cir. 2011). To establish this nexus, Cortez-\\n\\nMendez must demonstrate that his membership in his disabled father’s family is “at least\\n\\none central reason for” the persecution he experienced or that he fears in El Salvador. 8\\n\\nU.S.C. § 1158(b)(1)(B)(i). His relation to his father cannot be “incidental, tangential,\\n\\nsuperficial, or subordinate to another reason for harm.” Quinteros-Mendoza v. Holder,\\n\\n556 F.3d 159, 164 (4th Cir. 2009) (internal quotation marks omitted) (emphasis added).\\n\\n“[O]ur review of the BIA’s and IJ’s determination of this factual question is limited to\\n\\nconsidering whether their conclusion is ‘supported by reasonable, substantial, and\\n\\n\\n\\n\\nconstitute persecution, actions “must rise above the level of mere harassment,” Qiao Hua\\nLi v. Gonzales, 405 F.3d 171, 177 (4th Cir. 2005), and must be of “sufficient severity,”\\nMirisawo v. Holder, 599 F.3d 391, 396 (4th Cir. 2010), that they “constitute a threat to\\nlife or freedom itself,” née Joseph v. Sessions, No. 17-1403, 2018 WL 3549714, at *3\\n(4th Cir. July 24, 2018) (internal quotation marks omitted). Cortez-Mendez testified that\\nhe was never physically harmed by the gangs; his fears are wholly based on distant verbal\\nthreats and intimidation. We question whether the threats in the record—unspecific gang-\\nrelated threats and one “death threat” communicated through two third parties, across\\ncountry borders, and a decade before Cortez-Mendez sought legal protection—constitute\\nthe “extreme” persecution necessary to support withholding of removal. Molina Mendoza\\nv. Sessions, 712 F. App’x 240, 242 (4th Cir. 2018). Nevertheless, we need not decide the\\npersecution issue here.\\n\\n 6\\n\\fprobative evidence.’” Cruz v. Sessions, 853 F.3d 122, 128 (4th Cir. 2017) (quoting\\n\\nNgarurih v. Ashcroft, 371 F.3d 182, 188 (4th Cir. 2004)). We conclude that it is.\\n\\n B.\\n\\n Cortez-Mendez disputes the IJ and BIA’s conclusion that he was threatened\\n\\nbecause of “general criminal gang activity” in his hometown. A.R. 3; see A.R. 65–66. He\\n\\nasserts the gangs persecuted him because his father’s disabilities caused Cortez-Mendez\\n\\nto be poor, “vulnerable,” and “an easy mark [without] the backing and advice of a\\n\\nfather.” A.R. 148. Cortez-Mendez argues his persecution was pointedly discriminatory\\n\\nbecause he “knew many of his persecutors[ ] and had heard them ridicule his father and\\n\\nthe rest of his family.” Opening Br. 11; see A.R. 56. We find his arguments unpersuasive.\\n\\n Cortez-Mendez presented no direct or circumstantial evidence that the gangs\\n\\nharassed him “on account of” his father’s disabilities as opposed to his own rejection of\\n\\ngang membership. See 8 U.S.C. § 1101(a)(42). He provided no direct evidence that the\\n\\ngangs intimidated him because he was his father’s son. His only evidence of linkage to\\n\\nhis father is that non-gang neighborhood harassers had “made fun of” him because of\\n\\nMarcial Cortez’s disabilities, A.R. 146–47, and the gang members who called his mother\\n\\nin 2005 “remembered [him] as a son of a mute and dumb person,” A.R. 176. Even if\\n\\neither of these groups of taunters knew about Marcial Cortez’s disabilities, it does not\\n\\nfollow that they intimidated Cortez-Mendez because of his relation to his disabled father.\\n\\nSee Hernandez-Avalos, 784 F.3d at 950 n.7 (“[N]ot . . . every threat that references a\\n\\nfamily member is made on account of family ties.”).\\n\\n\\n\\n 7\\n\\f Indeed, the circumstantial evidence in the record reflects a different reason for\\n\\nCortez-Mendez’s harassment: he rejected the gangs’ recruitment efforts. Cortez-Mendez\\n\\ntestified that he feared the gangs would harm him “if [he] did not become a gangster” or\\n\\n“if [he] did not [agree] to become part of the gangs.” A.R. 175. Substantial evidence\\n\\nsupports the IJ’s and BIA’s conclusions that the “neighborhood gangs observed the\\n\\nfamily’s poverty and concluded they could easily recruit” Cortez-Mendez, A.R. 56, and\\n\\nthat it was after Cortez-Mendez refused to join the gangs that they threatened him, A.R.\\n\\n3–4, 66. Cortez-Mendez even admitted that he left El Salvador because had rejected gang\\n\\nmembership: “they kept asking me to join them and be a member of the gang, and that is\\n\\nwhy I fled.” A.R. 140. At most, Cortez-Mendez demonstrated that the gangs may have\\n\\ntargeted him because of his poverty but only threatened him because he would not join\\n\\ntheir ranks. Flight from gang recruitment is not a protected ground under the INA. See\\n\\nZelaya v. Holder, 668 F.3d 159, 166–67 (4th Cir. 2012); Matter of S-E-G-, 24 I. & N.\\n\\nDec. 579, 589 (B.I.A. 2008). Consequently, Cortez-Mendez’s own testimony of his\\n\\ncircumstantial fears defeats his argument that a protected ground like his relation to his\\n\\ndisabled father was “at least one central reason for” his treatment in El Salvador.\\n\\nCrespin-Valladares, 632 F.3d at 127.\\n\\n Furthermore, while it is not dispositive, Cortez-Mendez testified that his father and\\n\\nother family members still live in El Salvador and have suffered no harm. Our decision\\n\\nrelies on whether Cortez-Mendez—and not some other person—was persecuted because\\n\\nof his relation to his father, see Hernandez-Avalos, 784 F.3d at 950; Crespin-Valladares,\\n\\n632 F.3d at 127 n.6, but a fact we may consider with the rest is whether other family\\n\\n 8\\n\\fmembers have been persecuted because of their identical family ties, see Mirisawo, 599\\n\\nF.3d at 398 (“The fact that family members whose political opinions Mirisawo fears will\\n\\nbe imputed to her have not themselves faced harm fatally undermines her claim that she\\n\\nwill suffer persecution because of her association with them.”). The evidence in the\\n\\nrecord that Cortez-Mendez’s family—including his disabled father—remains unharmed\\n\\nsuggests that Cortez-Mendez’s relation to his father is not the reason for the persecution\\n\\nhe fears.\\n\\n Our nexus analyses in Salgado-Sosa, 882 F.3d 451, and Cordova v. Holder, 759\\n\\nF.3d 332 (4th Cir. 2014), support our conclusion. In Salgado-Sosa, the petitioner fled to\\n\\nthe United States from Honduran gangs because his stepfather had angered the gangs, the\\n\\npetitioner defended his stepfather, and the gangs retaliated against the petitioner. 882\\n\\nF.3d at 457–58. There, we found “no meaningful distinction between whether Salgado-\\n\\nSosa was threatened because of his connection to his stepfather [or] because MS-13\\n\\nsought revenge on him for an act committed by his stepfather,” because both were\\n\\nderivative of his stepfather’s dispute with the gangs. Id. at 458. Since the petitioner\\n\\nshared family ties with his stepfather, he had established a sufficient nexus between his\\n\\npersecution and a protected ground. Id. at 458–59. Cortez-Mendez, by contrast, has\\n\\nprovided no evidence that the gangs threatened him because of his father’s disabilities.\\n\\nInstead, he testified that his rejection of gang membership was the impetus for his\\n\\nharassment.\\n\\n Cordova likewise bolsters our conclusion. There, we reversed the BIA’s denial of\\n\\nthe petitioner’s application of asylum and withholding of removal because the BIA had\\n\\n 9\\n\\fignored relevant nexus evidence. Cordova, 759 F.3d at 339. The petitioner in Cordova\\n\\nhad testified that gang members targeted him because he was related to members of a\\n\\nrival gang, but the BIA only considered evidence that he was targeted for rebuffing gang\\n\\nrecruitment. Id. at 339–40. Here, however, the IJ and the BIA ignored no relevant\\n\\nevidence concerning the import of the father’s disabilities because Cortez-Mendez\\n\\npresented none. All he provided was his unsubstantiated speculation that the gangs\\n\\ntargeted him because of his father’s disabilities. Given Cortez-Mendez’s own testimony\\n\\nthat he feared the gangs after refusing to join them, we are not “compelled” to conclude\\n\\nthat the gangs’ threats against Cortez-Mendez were on account of his father’s disabilities,\\n\\nas opposed to Cortez-Mendez’s rejection of gang membership. See Salgado-Sosa, 882\\n\\nF.3d at 456. As such, substantial evidence supported the BIA’s conclusion that Cortez-\\n\\nMendez failed to establish the requisite nexus. Accordingly, the BIA did not err in\\n\\ndenying withholding of removal.\\n\\n C.\\n\\n The INA does not protect every person who rejects gang recruitment efforts. See\\n\\nZelaya, 668 F.3d at 166–67. A petitioner seeking withholding of removal must show\\n\\nmore. Cortez-Mendez has failed to provide either direct or circumstantial evidence that\\n\\nthe gangs’ actions against him were motivated by a protected ground. See I.N.S. v. Elias-\\n\\nZacarias, 502 U.S. 478, 483 (1992). Consequently, Cortez-Mendez’s “[f]ear of\\n\\nretribution over purely personal matters” cannot support his application for withholding\\n\\nof removal. Moreno v. Lynch, 628 F. App’x 862, 866 (4th Cir. 2015).\\n\\n\\n\\n 10\\n\\f If we were to grant withholding of removal based on the slim evidence Cortez-\\n\\nMendez has provided, every family member of a disabled person would be eligible for\\n\\nrefugee status if anyone harassed them in their home country. We have rejected sweeping\\n\\narguments like this before and do so again. See, e.g., Yi Ni v. Holder, 613 F.3d 415, 429–\\n\\n30 (4th Cir. 2010) (“Were the fact that a person is subject to family planning policies\\n\\nsufficient to establish persecution, every Chinese citizen of childbearing age would be\\n\\neligible for relief.”). Therefore, “[u]nder the deferential substantial evidence standard we\\n\\nare bound to apply, we conclude that the absence of any direct evidence establishing that”\\n\\ngang members “intended to persecute [Cortez-Mendez] because of his familial\\n\\nrelationship to his [father]—provided an adequate basis for a reasonable adjudicator to\\n\\ndeny [Cortez-Mendez] relief.” Pacas-Renderos v. Sessions, 691 F. App’x 796, 803 (4th\\n\\nCir. 2017). Substantial evidence supports the IJ’s and BIA’s finding that Cortez-Mendez\\n\\ndid not establish the requisite nexus, and his application for withholding of removal was\\n\\nproperly denied.\\n\\n\\n\\n IV.\\n\\n Accordingly, Cortez-Mendez’s petition for review is\\n\\n DENIED.\\n\\n\\n\\n\\n 11\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4356554/\", \"author_raw\": \"AGEE, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"WILKINSON"},"judge2":{"kind":"string","value":"AGEE"},"judge3":{"kind":"string","value":"JAMES P JONES"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"WILKINSON\": \", Circuit\", \"AGEE\": \", Circuit\", \"P JONES\": \", United States District\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4579301/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Jose Marcial CORTEZ-MENDEZ, Petitioner, v. Matthew G. WHITAKER, Acting Attorney General, Respondent.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-07\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 16-2389\n\n\n\nJOSE MARCIAL CORTEZ-MENDEZ,\n\n Petitioner,\n\nv.\n\nMATTHEW G. WHITAKER, Acting Attorney General,\n\n Respondent.\n\n\nOn Petition for Review of an Order of the Board of Immigration Appeals.\n\n\nArgued: September 25, 2018 Decided: January 7, 2019\n\n\nBefore WILKINSON and AGEE, Circuit Judges, and James P. JONES, United States\nDistrict Judge for the Western District of Virginia, sitting by designation.\n\n\nPetition for review denied by published opinion. Judge Agee wrote the opinion, in\nwhich Judge Wilkinson and Judge Jones joined.\n\n\nARGUED: Melissa Jill Mitchell, LAW OFFICES OF PAUL A. SUHR, PLLC, Raleigh,\nNorth Carolina, for Cortez-Mendez. Robert Michael Stalzer, UNITED STATES\nDEPARTMENT OF JUSTICE, Washington, D.C., for Respondent. ON BRIEF: Paul\nA. Suhr, LAW OFFICES OF PAUL A. SUHR, PLLC, Raleigh, North Carolina, for\nCortez-Mendez. Chad A. Readler, Acting Assistant Attorney General, Kiley Kane,\nSenior Litigation Counsel, Office of Immigration Litigation, Civil Division, UNITED\nSTATES DEPARTMENT OF JUSTICE, Washington, D.C., for Respondent.\n\fAGEE, Circuit Judge:\n\n Jose Cortez-Mendez, a native and citizen of El Salvador, seeks review of an order\n\nfrom the Board of Immigration Appeals (“BIA”). The BIA dismissed his appeal\n\nfollowing an immigration judge’s (“IJ’s”) denial of his application for withholding of\n\nremoval under the Immigration and Nationality Act (“INA”), 8 U.S.C. § 1231(b)(3), and\n\nprotection under the United Nations Convention Against Torture (“CAT”), 8 C.F.R.\n\n§ 1208.16(c). For the reasons below, we deny the petition for review.\n\n\n\n I.\n\n Cortez-Mendez was born in El Salvador. His father, Marcial Cortez, is deaf and\n\nmute. People in El Salvador with these physical impairments have suffered routine\n\nridicule and discrimination, despite the existence of anti-discrimination laws. See A.R.\n\n422 (containing U.S. Dep’t of State, El Salvador, 2014 Country Reports on Human\n\nRights Practices). Because of his disabilities, Marcial Cortez could not provide for his\n\nfamily and they moved in with Cortez-Mendez’s aunt. Cortez-Mendez’s mother also\n\nabandoned the family when he was seven because of the family’s difficulties.\n\n As a teenager, MS-13 and MS-18 gang members began targeting Cortez-Mendez\n\nfor gang recruitment. They harassed him and “threatened [him] with death, that if [he] did\n\nnot become a gangster, they were going to kill [him].” A.R. 175. Despite this harassment,\n\nthe gangs never physically harmed Cortez-Mendez or anyone in his family. To this day,\n\nhis father, mother, sisters, and aunt live in El Salvador unharmed.\n\n\n\n 2\n\f Cortez-Mendez illegally entered the United States in 2003. The Department of\n\nHomeland Security served him with a Notice to Appear, but he failed to appear at his\n\nhearing and was ordered removed to El Salvador in abstentia. Nevertheless, Cortez-\n\nMendez settled in North Carolina with his uncle, girlfriend, and two children. In 2005,\n\ngang members called Cortez-Mendez’s mother in El Salvador, demanded money, and\n\ndemanded Cortez-Mendez’s whereabouts. Through his aunt, Cortez-Mendez learned the\n\ngangs told his mother they “remembered [him] as a son of a mute and dumb person” and\n\nthreatened to “kill [him] and dismember [him]” if he returned to El Salvador. A.R. 176.\n\n In 2015, Cortez-Mendez applied for withholding of removal and CAT protection.\n\nAs grounds for protection under the INA, he cited his membership in a particular social\n\ngroup: “member[s] of the family of Marcial Cortez who is a disabled person.” A.R. 124;\n\nsee 8 U.S.C. § 1101(a)(42). In 2016, the IJ denied Cortez-Mendez’s application for\n\nwithholding of removal and CAT protection. The IJ found Cortez-Mendez’s testimony\n\nwas credible but held his proposed particular social group did not satisfy the INA’s\n\nrequirements. The IJ also held that Cortez-Mendez failed to demonstrate a sufficient\n\nnexus—that is, he did not show that the “indeterminate and generalized” threats he had\n\nreceived in El Salvador were on account of his membership in that group. A.R. 63.\n\n Cortez-Mendez appealed to the BIA. In its own opinion, the BIA affirmed the IJ’s\n\nconclusion that “any threats [Cortez-Mendez] received or future harm he fears are the\n\nresult of general criminal gang activity,” not membership in his disabled father’s family.\n\nA.R. 3. The BIA also affirmed the IJ’s refusal to accept Cortez-Mendez’s “speculat[ion]\n\nthat his lower economic status and his father’s disability made him more susceptible to\n\n 3\n\fgang recruitment” because the record fairly supports the conclusion that the “harm he\n\nfears upon return [is] as a result of his rejection of gang membership rather than his\n\nfather’s disability.” A.R. 3. The BIA thus dismissed Cortez-Mendez’s appeal, and Cortez-\n\nMendez was again ordered removed. He timely appealed, and we have jurisdiction under\n\n8 U.S.C. § 1252.\n\n\n\n II.\n\n When, as here, the BIA “adopt[s] and affirm[s]” the IJ’s conclusion but adds\n\nadditional reasoning in its own opinion, we review “the factual findings and reasoning\n\ncontained in both decisions.” Ai Hua Chen v. Holder, 742 F.3d 171, 177 (4th Cir. 2014);\n\nA.R. 3. If the factual findings are supported by substantial evidence, they are conclusive\n\n“unless any reasonable adjudicator would be compelled to conclude to the contrary.” 8\n\nU.S.C. § 1252(b)(4)(B); Salgado-Sosa v. Sessions, 882 F.3d 451, 456 (4th Cir. 2018). As\n\nfor legal determinations, we review them de novo. Salgado-Sosa, 882 F.3d at 456.\n\nUltimately, we must affirm the BIA’s decision if it is not “manifestly contrary to law and\n\nan abuse of discretion.” 8 U.S.C. § 1252(b)(4)(D).\n\n\n\n III.\n\n In his opening brief, Cortez-Mendez argues only that the BIA erred in denying his\n\npetition for withholding of removal. Because he does not address the BIA’s denial of his\n\npetition for CAT protection, he has waived his claim for CAT relief. Fed. R. App. P.\n\n28(a)(8)(A); see Edwards v. City of Goldsboro, 178 F.3d 231, 241 n.6 (4th Cir. 1999).\n\n 4\n\f To receive withholding of removal relief, Cortez-Mendez must show that, if\n\nremoved to El Salvador, “there is a clear probability that [his] ‘life or freedom would be\n\nthreatened . . . because of’” a protected ground—here, his alleged membership in a\n\nparticular social group. Marynenka v. Holder, 592 F.3d 594, 600 (4th Cir. 2010) (quoting\n\n8 U.S.C. § 1231(b)(3)(A)). This standard requires two showings: First, Cortez-Mendez\n\nmust show “it is more likely than not” that his life or freedom will be threatened if he\n\nreturns to El Salvador. Lizama v. Holder, 629 F.3d 440, 446 (4th Cir. 2011) (internal\n\nquotation marks omitted). Evidence that he suffered past persecution can help to satisfy\n\nthis first showing. See 8 C.F.R. § 1208.16(b)(1). Second, Cortez-Mendez must show that\n\nthe “probability of persecution” is “link[ed]” to his status in the particular social group,\n\nthat is, that the two share a nexus. Singh v. Holder, 699 F.3d 321, 327 (4th Cir. 2012). If\n\nhe satisfies his burden of proof, withholding of removal is mandatory. Gomis v. Holder,\n\n571 F.3d 353, 359 (4th Cir. 2009).\n\n The nexus issue is dispositive of this appeal, so we dispose at the outset of two\n\nissues we need not resolve: whether Cortez-Mendez is a member of a particular social\n\ngroup and whether he suffered past persecution. See 8 U.S.C. § 1101(a)(42); 8 C.F.R.\n\n§ 1208.16(b)(1). We will assume, without deciding, that Cortez-Mendez is a member of a\n\nparticular social group comprised of his disabled father’s immediate family members and\n\nthat he suffered past persecution in El Salvador. ∗ We will consider only whether Cortez-\n\n\n ∗While “we have expressly held that the threat of death qualifies as persecution,”\nHernandez-Avalos v. Lynch, 784 F.3d 944, 949 (4th Cir. 2015) (internal quotation marks\nomitted), we hesitate to conclude that Cortez-Mendez suffered past persecution here. To\n(Continued)\n 5\n\fMendez established the requisite nexus between any persecution he suffered and his\n\nrelation to his disabled father.\n\n A.\n\n Whether a person’s persecution shares a nexus with his alleged protected ground is\n\na question of fact entitled to deference and reviewed for clear error. See Crespin-\n\nValladares v. Holder, 632 F.3d 117, 128 (4th Cir. 2011). To establish this nexus, Cortez-\n\nMendez must demonstrate that his membership in his disabled father’s family is “at least\n\none central reason for” the persecution he experienced or that he fears in El Salvador. 8\n\nU.S.C. § 1158(b)(1)(B)(i). His relation to his father cannot be “incidental, tangential,\n\nsuperficial, or subordinate to another reason for harm.” Quinteros-Mendoza v. Holder,\n\n556 F.3d 159, 164 (4th Cir. 2009) (internal quotation marks omitted) (emphasis added).\n\n“[O]ur review of the BIA’s and IJ’s determination of this factual question is limited to\n\nconsidering whether their conclusion is ‘supported by reasonable, substantial, and\n\n\n\n\nconstitute persecution, actions “must rise above the level of mere harassment,” Qiao Hua\nLi v. Gonzales, 405 F.3d 171, 177 (4th Cir. 2005), and must be of “sufficient severity,”\nMirisawo v. Holder, 599 F.3d 391, 396 (4th Cir. 2010), that they “constitute a threat to\nlife or freedom itself,” née Joseph v. Sessions, No. 17-1403, 2018 WL 3549714, at *3\n(4th Cir. July 24, 2018) (internal quotation marks omitted). Cortez-Mendez testified that\nhe was never physically harmed by the gangs; his fears are wholly based on distant verbal\nthreats and intimidation. We question whether the threats in the record—unspecific gang-\nrelated threats and one “death threat” communicated through two third parties, across\ncountry borders, and a decade before Cortez-Mendez sought legal protection—constitute\nthe “extreme” persecution necessary to support withholding of removal. Molina Mendoza\nv. Sessions, 712 F. App’x 240, 242 (4th Cir. 2018). Nevertheless, we need not decide the\npersecution issue here.\n\n 6\n\fprobative evidence.’” Cruz v. Sessions, 853 F.3d 122, 128 (4th Cir. 2017) (quoting\n\nNgarurih v. Ashcroft, 371 F.3d 182, 188 (4th Cir. 2004)). We conclude that it is.\n\n B.\n\n Cortez-Mendez disputes the IJ and BIA’s conclusion that he was threatened\n\nbecause of “general criminal gang activity” in his hometown. A.R. 3; see A.R. 65–66. He\n\nasserts the gangs persecuted him because his father’s disabilities caused Cortez-Mendez\n\nto be poor, “vulnerable,” and “an easy mark [without] the backing and advice of a\n\nfather.” A.R. 148. Cortez-Mendez argues his persecution was pointedly discriminatory\n\nbecause he “knew many of his persecutors[ ] and had heard them ridicule his father and\n\nthe rest of his family.” Opening Br. 11; see A.R. 56. We find his arguments unpersuasive.\n\n Cortez-Mendez presented no direct or circumstantial evidence that the gangs\n\nharassed him “on account of” his father’s disabilities as opposed to his own rejection of\n\ngang membership. See 8 U.S.C. § 1101(a)(42). He provided no direct evidence that the\n\ngangs intimidated him because he was his father’s son. His only evidence of linkage to\n\nhis father is that non-gang neighborhood harassers had “made fun of” him because of\n\nMarcial Cortez’s disabilities, A.R. 146–47, and the gang members who called his mother\n\nin 2005 “remembered [him] as a son of a mute and dumb person,” A.R. 176. Even if\n\neither of these groups of taunters knew about Marcial Cortez’s disabilities, it does not\n\nfollow that they intimidated Cortez-Mendez because of his relation to his disabled father.\n\nSee Hernandez-Avalos, 784 F.3d at 950 n.7 (“[N]ot . . . every threat that references a\n\nfamily member is made on account of family ties.”).\n\n\n\n 7\n\f Indeed, the circumstantial evidence in the record reflects a different reason for\n\nCortez-Mendez’s harassment: he rejected the gangs’ recruitment efforts. Cortez-Mendez\n\ntestified that he feared the gangs would harm him “if [he] did not become a gangster” or\n\n“if [he] did not [agree] to become part of the gangs.” A.R. 175. Substantial evidence\n\nsupports the IJ’s and BIA’s conclusions that the “neighborhood gangs observed the\n\nfamily’s poverty and concluded they could easily recruit” Cortez-Mendez, A.R. 56, and\n\nthat it was after Cortez-Mendez refused to join the gangs that they threatened him, A.R.\n\n3–4, 66. Cortez-Mendez even admitted that he left El Salvador because had rejected gang\n\nmembership: “they kept asking me to join them and be a member of the gang, and that is\n\nwhy I fled.” A.R. 140. At most, Cortez-Mendez demonstrated that the gangs may have\n\ntargeted him because of his poverty but only threatened him because he would not join\n\ntheir ranks. Flight from gang recruitment is not a protected ground under the INA. See\n\nZelaya v. Holder, 668 F.3d 159, 166–67 (4th Cir. 2012); Matter of S-E-G-, 24 I. & N.\n\nDec. 579, 589 (B.I.A. 2008). Consequently, Cortez-Mendez’s own testimony of his\n\ncircumstantial fears defeats his argument that a protected ground like his relation to his\n\ndisabled father was “at least one central reason for” his treatment in El Salvador.\n\nCrespin-Valladares, 632 F.3d at 127.\n\n Furthermore, while it is not dispositive, Cortez-Mendez testified that his father and\n\nother family members still live in El Salvador and have suffered no harm. Our decision\n\nrelies on whether Cortez-Mendez—and not some other person—was persecuted because\n\nof his relation to his father, see Hernandez-Avalos, 784 F.3d at 950; Crespin-Valladares,\n\n632 F.3d at 127 n.6, but a fact we may consider with the rest is whether other family\n\n 8\n\fmembers have been persecuted because of their identical family ties, see Mirisawo, 599\n\nF.3d at 398 (“The fact that family members whose political opinions Mirisawo fears will\n\nbe imputed to her have not themselves faced harm fatally undermines her claim that she\n\nwill suffer persecution because of her association with them.”). The evidence in the\n\nrecord that Cortez-Mendez’s family—including his disabled father—remains unharmed\n\nsuggests that Cortez-Mendez’s relation to his father is not the reason for the persecution\n\nhe fears.\n\n Our nexus analyses in Salgado-Sosa, 882 F.3d 451, and Cordova v. Holder, 759\n\nF.3d 332 (4th Cir. 2014), support our conclusion. In Salgado-Sosa, the petitioner fled to\n\nthe United States from Honduran gangs because his stepfather had angered the gangs, the\n\npetitioner defended his stepfather, and the gangs retaliated against the petitioner. 882\n\nF.3d at 457–58. There, we found “no meaningful distinction between whether Salgado-\n\nSosa was threatened because of his connection to his stepfather [or] because MS-13\n\nsought revenge on him for an act committed by his stepfather,” because both were\n\nderivative of his stepfather’s dispute with the gangs. Id. at 458. Since the petitioner\n\nshared family ties with his stepfather, he had established a sufficient nexus between his\n\npersecution and a protected ground. Id. at 458–59. Cortez-Mendez, by contrast, has\n\nprovided no evidence that the gangs threatened him because of his father’s disabilities.\n\nInstead, he testified that his rejection of gang membership was the impetus for his\n\nharassment.\n\n Cordova likewise bolsters our conclusion. There, we reversed the BIA’s denial of\n\nthe petitioner’s application of asylum and withholding of removal because the BIA had\n\n 9\n\fignored relevant nexus evidence. Cordova, 759 F.3d at 339. The petitioner in Cordova\n\nhad testified that gang members targeted him because he was related to members of a\n\nrival gang, but the BIA only considered evidence that he was targeted for rebuffing gang\n\nrecruitment. Id. at 339–40. Here, however, the IJ and the BIA ignored no relevant\n\nevidence concerning the import of the father’s disabilities because Cortez-Mendez\n\npresented none. All he provided was his unsubstantiated speculation that the gangs\n\ntargeted him because of his father’s disabilities. Given Cortez-Mendez’s own testimony\n\nthat he feared the gangs after refusing to join them, we are not “compelled” to conclude\n\nthat the gangs’ threats against Cortez-Mendez were on account of his father’s disabilities,\n\nas opposed to Cortez-Mendez’s rejection of gang membership. See Salgado-Sosa, 882\n\nF.3d at 456. As such, substantial evidence supported the BIA’s conclusion that Cortez-\n\nMendez failed to establish the requisite nexus. Accordingly, the BIA did not err in\n\ndenying withholding of removal.\n\n C.\n\n The INA does not protect every person who rejects gang recruitment efforts. See\n\nZelaya, 668 F.3d at 166–67. A petitioner seeking withholding of removal must show\n\nmore. Cortez-Mendez has failed to provide either direct or circumstantial evidence that\n\nthe gangs’ actions against him were motivated by a protected ground. See I.N.S. v. Elias-\n\nZacarias, 502 U.S. 478, 483 (1992). Consequently, Cortez-Mendez’s “[f]ear of\n\nretribution over purely personal matters” cannot support his application for withholding\n\nof removal. Moreno v. Lynch, 628 F. App’x 862, 866 (4th Cir. 2015).\n\n\n\n 10\n\f If we were to grant withholding of removal based on the slim evidence Cortez-\n\nMendez has provided, every family member of a disabled person would be eligible for\n\nrefugee status if anyone harassed them in their home country. We have rejected sweeping\n\narguments like this before and do so again. See, e.g., Yi Ni v. Holder, 613 F.3d 415, 429–\n\n30 (4th Cir. 2010) (“Were the fact that a person is subject to family planning policies\n\nsufficient to establish persecution, every Chinese citizen of childbearing age would be\n\neligible for relief.”). Therefore, “[u]nder the deferential substantial evidence standard we\n\nare bound to apply, we conclude that the absence of any direct evidence establishing that”\n\ngang members “intended to persecute [Cortez-Mendez] because of his familial\n\nrelationship to his [father]—provided an adequate basis for a reasonable adjudicator to\n\ndeny [Cortez-Mendez] relief.” Pacas-Renderos v. Sessions, 691 F. App’x 796, 803 (4th\n\nCir. 2017). Substantial evidence supports the IJ’s and BIA’s finding that Cortez-Mendez\n\ndid not establish the requisite nexus, and his application for withholding of removal was\n\nproperly denied.\n\n\n\n IV.\n\n Accordingly, Cortez-Mendez’s petition for review is\n\n DENIED.\n\n\n\n\n 11\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Jose Marcial CORTEZ-MENDEZ, Petitioner, v. Matthew G. WHITAKER, Acting Attorney General, Respondent.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-07\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 16-2389\\n\\n\\n\\nJOSE MARCIAL CORTEZ-MENDEZ,\\n\\n Petitioner,\\n\\nv.\\n\\nMATTHEW G. WHITAKER, Acting Attorney General,\\n\\n Respondent.\\n\\n\\nOn Petition for Review of an Order of the Board of Immigration Appeals.\\n\\n\\nArgued: September 25, 2018 Decided: January 7, 2019\\n\\n\\nBefore WILKINSON and AGEE, Circuit Judges, and James P. JONES, United States\\nDistrict Judge for the Western District of Virginia, sitting by designation.\\n\\n\\nPetition for review denied by published opinion. Judge Agee wrote the opinion, in\\nwhich Judge Wilkinson and Judge Jones joined.\\n\\n\\nARGUED: Melissa Jill Mitchell, LAW OFFICES OF PAUL A. SUHR, PLLC, Raleigh,\\nNorth Carolina, for Cortez-Mendez. Robert Michael Stalzer, UNITED STATES\\nDEPARTMENT OF JUSTICE, Washington, D.C., for Respondent. ON BRIEF: Paul\\nA. Suhr, LAW OFFICES OF PAUL A. SUHR, PLLC, Raleigh, North Carolina, for\\nCortez-Mendez. Chad A. Readler, Acting Assistant Attorney General, Kiley Kane,\\nSenior Litigation Counsel, Office of Immigration Litigation, Civil Division, UNITED\\nSTATES DEPARTMENT OF JUSTICE, Washington, D.C., for Respondent.\\n\\fAGEE, Circuit Judge:\\n\\n Jose Cortez-Mendez, a native and citizen of El Salvador, seeks review of an order\\n\\nfrom the Board of Immigration Appeals (“BIA”). The BIA dismissed his appeal\\n\\nfollowing an immigration judge’s (“IJ’s”) denial of his application for withholding of\\n\\nremoval under the Immigration and Nationality Act (“INA”), 8 U.S.C. § 1231(b)(3), and\\n\\nprotection under the United Nations Convention Against Torture (“CAT”), 8 C.F.R.\\n\\n§ 1208.16(c). For the reasons below, we deny the petition for review.\\n\\n\\n\\n I.\\n\\n Cortez-Mendez was born in El Salvador. His father, Marcial Cortez, is deaf and\\n\\nmute. People in El Salvador with these physical impairments have suffered routine\\n\\nridicule and discrimination, despite the existence of anti-discrimination laws. See A.R.\\n\\n422 (containing U.S. Dep’t of State, El Salvador, 2014 Country Reports on Human\\n\\nRights Practices). Because of his disabilities, Marcial Cortez could not provide for his\\n\\nfamily and they moved in with Cortez-Mendez’s aunt. Cortez-Mendez’s mother also\\n\\nabandoned the family when he was seven because of the family’s difficulties.\\n\\n As a teenager, MS-13 and MS-18 gang members began targeting Cortez-Mendez\\n\\nfor gang recruitment. They harassed him and “threatened [him] with death, that if [he] did\\n\\nnot become a gangster, they were going to kill [him].” A.R. 175. Despite this harassment,\\n\\nthe gangs never physically harmed Cortez-Mendez or anyone in his family. To this day,\\n\\nhis father, mother, sisters, and aunt live in El Salvador unharmed.\\n\\n\\n\\n 2\\n\\f Cortez-Mendez illegally entered the United States in 2003. The Department of\\n\\nHomeland Security served him with a Notice to Appear, but he failed to appear at his\\n\\nhearing and was ordered removed to El Salvador in abstentia. Nevertheless, Cortez-\\n\\nMendez settled in North Carolina with his uncle, girlfriend, and two children. In 2005,\\n\\ngang members called Cortez-Mendez’s mother in El Salvador, demanded money, and\\n\\ndemanded Cortez-Mendez’s whereabouts. Through his aunt, Cortez-Mendez learned the\\n\\ngangs told his mother they “remembered [him] as a son of a mute and dumb person” and\\n\\nthreatened to “kill [him] and dismember [him]” if he returned to El Salvador. A.R. 176.\\n\\n In 2015, Cortez-Mendez applied for withholding of removal and CAT protection.\\n\\nAs grounds for protection under the INA, he cited his membership in a particular social\\n\\ngroup: “member[s] of the family of Marcial Cortez who is a disabled person.” A.R. 124;\\n\\nsee 8 U.S.C. § 1101(a)(42). In 2016, the IJ denied Cortez-Mendez’s application for\\n\\nwithholding of removal and CAT protection. The IJ found Cortez-Mendez’s testimony\\n\\nwas credible but held his proposed particular social group did not satisfy the INA’s\\n\\nrequirements. The IJ also held that Cortez-Mendez failed to demonstrate a sufficient\\n\\nnexus—that is, he did not show that the “indeterminate and generalized” threats he had\\n\\nreceived in El Salvador were on account of his membership in that group. A.R. 63.\\n\\n Cortez-Mendez appealed to the BIA. In its own opinion, the BIA affirmed the IJ’s\\n\\nconclusion that “any threats [Cortez-Mendez] received or future harm he fears are the\\n\\nresult of general criminal gang activity,” not membership in his disabled father’s family.\\n\\nA.R. 3. The BIA also affirmed the IJ’s refusal to accept Cortez-Mendez’s “speculat[ion]\\n\\nthat his lower economic status and his father’s disability made him more susceptible to\\n\\n 3\\n\\fgang recruitment” because the record fairly supports the conclusion that the “harm he\\n\\nfears upon return [is] as a result of his rejection of gang membership rather than his\\n\\nfather’s disability.” A.R. 3. The BIA thus dismissed Cortez-Mendez’s appeal, and Cortez-\\n\\nMendez was again ordered removed. He timely appealed, and we have jurisdiction under\\n\\n8 U.S.C. § 1252.\\n\\n\\n\\n II.\\n\\n When, as here, the BIA “adopt[s] and affirm[s]” the IJ’s conclusion but adds\\n\\nadditional reasoning in its own opinion, we review “the factual findings and reasoning\\n\\ncontained in both decisions.” Ai Hua Chen v. Holder, 742 F.3d 171, 177 (4th Cir. 2014);\\n\\nA.R. 3. If the factual findings are supported by substantial evidence, they are conclusive\\n\\n“unless any reasonable adjudicator would be compelled to conclude to the contrary.” 8\\n\\nU.S.C. § 1252(b)(4)(B); Salgado-Sosa v. Sessions, 882 F.3d 451, 456 (4th Cir. 2018). As\\n\\nfor legal determinations, we review them de novo. Salgado-Sosa, 882 F.3d at 456.\\n\\nUltimately, we must affirm the BIA’s decision if it is not “manifestly contrary to law and\\n\\nan abuse of discretion.” 8 U.S.C. § 1252(b)(4)(D).\\n\\n\\n\\n III.\\n\\n In his opening brief, Cortez-Mendez argues only that the BIA erred in denying his\\n\\npetition for withholding of removal. Because he does not address the BIA’s denial of his\\n\\npetition for CAT protection, he has waived his claim for CAT relief. Fed. R. App. P.\\n\\n28(a)(8)(A); see Edwards v. City of Goldsboro, 178 F.3d 231, 241 n.6 (4th Cir. 1999).\\n\\n 4\\n\\f To receive withholding of removal relief, Cortez-Mendez must show that, if\\n\\nremoved to El Salvador, “there is a clear probability that [his] ‘life or freedom would be\\n\\nthreatened . . . because of’” a protected ground—here, his alleged membership in a\\n\\nparticular social group. Marynenka v. Holder, 592 F.3d 594, 600 (4th Cir. 2010) (quoting\\n\\n8 U.S.C. § 1231(b)(3)(A)). This standard requires two showings: First, Cortez-Mendez\\n\\nmust show “it is more likely than not” that his life or freedom will be threatened if he\\n\\nreturns to El Salvador. Lizama v. Holder, 629 F.3d 440, 446 (4th Cir. 2011) (internal\\n\\nquotation marks omitted). Evidence that he suffered past persecution can help to satisfy\\n\\nthis first showing. See 8 C.F.R. § 1208.16(b)(1). Second, Cortez-Mendez must show that\\n\\nthe “probability of persecution” is “link[ed]” to his status in the particular social group,\\n\\nthat is, that the two share a nexus. Singh v. Holder, 699 F.3d 321, 327 (4th Cir. 2012). If\\n\\nhe satisfies his burden of proof, withholding of removal is mandatory. Gomis v. Holder,\\n\\n571 F.3d 353, 359 (4th Cir. 2009).\\n\\n The nexus issue is dispositive of this appeal, so we dispose at the outset of two\\n\\nissues we need not resolve: whether Cortez-Mendez is a member of a particular social\\n\\ngroup and whether he suffered past persecution. See 8 U.S.C. § 1101(a)(42); 8 C.F.R.\\n\\n§ 1208.16(b)(1). We will assume, without deciding, that Cortez-Mendez is a member of a\\n\\nparticular social group comprised of his disabled father’s immediate family members and\\n\\nthat he suffered past persecution in El Salvador. ∗ We will consider only whether Cortez-\\n\\n\\n ∗While “we have expressly held that the threat of death qualifies as persecution,”\\nHernandez-Avalos v. Lynch, 784 F.3d 944, 949 (4th Cir. 2015) (internal quotation marks\\nomitted), we hesitate to conclude that Cortez-Mendez suffered past persecution here. To\\n(Continued)\\n 5\\n\\fMendez established the requisite nexus between any persecution he suffered and his\\n\\nrelation to his disabled father.\\n\\n A.\\n\\n Whether a person’s persecution shares a nexus with his alleged protected ground is\\n\\na question of fact entitled to deference and reviewed for clear error. See Crespin-\\n\\nValladares v. Holder, 632 F.3d 117, 128 (4th Cir. 2011). To establish this nexus, Cortez-\\n\\nMendez must demonstrate that his membership in his disabled father’s family is “at least\\n\\none central reason for” the persecution he experienced or that he fears in El Salvador. 8\\n\\nU.S.C. § 1158(b)(1)(B)(i). His relation to his father cannot be “incidental, tangential,\\n\\nsuperficial, or subordinate to another reason for harm.” Quinteros-Mendoza v. Holder,\\n\\n556 F.3d 159, 164 (4th Cir. 2009) (internal quotation marks omitted) (emphasis added).\\n\\n“[O]ur review of the BIA’s and IJ’s determination of this factual question is limited to\\n\\nconsidering whether their conclusion is ‘supported by reasonable, substantial, and\\n\\n\\n\\n\\nconstitute persecution, actions “must rise above the level of mere harassment,” Qiao Hua\\nLi v. Gonzales, 405 F.3d 171, 177 (4th Cir. 2005), and must be of “sufficient severity,”\\nMirisawo v. Holder, 599 F.3d 391, 396 (4th Cir. 2010), that they “constitute a threat to\\nlife or freedom itself,” née Joseph v. Sessions, No. 17-1403, 2018 WL 3549714, at *3\\n(4th Cir. July 24, 2018) (internal quotation marks omitted). Cortez-Mendez testified that\\nhe was never physically harmed by the gangs; his fears are wholly based on distant verbal\\nthreats and intimidation. We question whether the threats in the record—unspecific gang-\\nrelated threats and one “death threat” communicated through two third parties, across\\ncountry borders, and a decade before Cortez-Mendez sought legal protection—constitute\\nthe “extreme” persecution necessary to support withholding of removal. Molina Mendoza\\nv. Sessions, 712 F. App’x 240, 242 (4th Cir. 2018). Nevertheless, we need not decide the\\npersecution issue here.\\n\\n 6\\n\\fprobative evidence.’” Cruz v. Sessions, 853 F.3d 122, 128 (4th Cir. 2017) (quoting\\n\\nNgarurih v. Ashcroft, 371 F.3d 182, 188 (4th Cir. 2004)). We conclude that it is.\\n\\n B.\\n\\n Cortez-Mendez disputes the IJ and BIA’s conclusion that he was threatened\\n\\nbecause of “general criminal gang activity” in his hometown. A.R. 3; see A.R. 65–66. He\\n\\nasserts the gangs persecuted him because his father’s disabilities caused Cortez-Mendez\\n\\nto be poor, “vulnerable,” and “an easy mark [without] the backing and advice of a\\n\\nfather.” A.R. 148. Cortez-Mendez argues his persecution was pointedly discriminatory\\n\\nbecause he “knew many of his persecutors[ ] and had heard them ridicule his father and\\n\\nthe rest of his family.” Opening Br. 11; see A.R. 56. We find his arguments unpersuasive.\\n\\n Cortez-Mendez presented no direct or circumstantial evidence that the gangs\\n\\nharassed him “on account of” his father’s disabilities as opposed to his own rejection of\\n\\ngang membership. See 8 U.S.C. § 1101(a)(42). He provided no direct evidence that the\\n\\ngangs intimidated him because he was his father’s son. His only evidence of linkage to\\n\\nhis father is that non-gang neighborhood harassers had “made fun of” him because of\\n\\nMarcial Cortez’s disabilities, A.R. 146–47, and the gang members who called his mother\\n\\nin 2005 “remembered [him] as a son of a mute and dumb person,” A.R. 176. Even if\\n\\neither of these groups of taunters knew about Marcial Cortez’s disabilities, it does not\\n\\nfollow that they intimidated Cortez-Mendez because of his relation to his disabled father.\\n\\nSee Hernandez-Avalos, 784 F.3d at 950 n.7 (“[N]ot . . . every threat that references a\\n\\nfamily member is made on account of family ties.”).\\n\\n\\n\\n 7\\n\\f Indeed, the circumstantial evidence in the record reflects a different reason for\\n\\nCortez-Mendez’s harassment: he rejected the gangs’ recruitment efforts. Cortez-Mendez\\n\\ntestified that he feared the gangs would harm him “if [he] did not become a gangster” or\\n\\n“if [he] did not [agree] to become part of the gangs.” A.R. 175. Substantial evidence\\n\\nsupports the IJ’s and BIA’s conclusions that the “neighborhood gangs observed the\\n\\nfamily’s poverty and concluded they could easily recruit” Cortez-Mendez, A.R. 56, and\\n\\nthat it was after Cortez-Mendez refused to join the gangs that they threatened him, A.R.\\n\\n3–4, 66. Cortez-Mendez even admitted that he left El Salvador because had rejected gang\\n\\nmembership: “they kept asking me to join them and be a member of the gang, and that is\\n\\nwhy I fled.” A.R. 140. At most, Cortez-Mendez demonstrated that the gangs may have\\n\\ntargeted him because of his poverty but only threatened him because he would not join\\n\\ntheir ranks. Flight from gang recruitment is not a protected ground under the INA. See\\n\\nZelaya v. Holder, 668 F.3d 159, 166–67 (4th Cir. 2012); Matter of S-E-G-, 24 I. & N.\\n\\nDec. 579, 589 (B.I.A. 2008). Consequently, Cortez-Mendez’s own testimony of his\\n\\ncircumstantial fears defeats his argument that a protected ground like his relation to his\\n\\ndisabled father was “at least one central reason for” his treatment in El Salvador.\\n\\nCrespin-Valladares, 632 F.3d at 127.\\n\\n Furthermore, while it is not dispositive, Cortez-Mendez testified that his father and\\n\\nother family members still live in El Salvador and have suffered no harm. Our decision\\n\\nrelies on whether Cortez-Mendez—and not some other person—was persecuted because\\n\\nof his relation to his father, see Hernandez-Avalos, 784 F.3d at 950; Crespin-Valladares,\\n\\n632 F.3d at 127 n.6, but a fact we may consider with the rest is whether other family\\n\\n 8\\n\\fmembers have been persecuted because of their identical family ties, see Mirisawo, 599\\n\\nF.3d at 398 (“The fact that family members whose political opinions Mirisawo fears will\\n\\nbe imputed to her have not themselves faced harm fatally undermines her claim that she\\n\\nwill suffer persecution because of her association with them.”). The evidence in the\\n\\nrecord that Cortez-Mendez’s family—including his disabled father—remains unharmed\\n\\nsuggests that Cortez-Mendez’s relation to his father is not the reason for the persecution\\n\\nhe fears.\\n\\n Our nexus analyses in Salgado-Sosa, 882 F.3d 451, and Cordova v. Holder, 759\\n\\nF.3d 332 (4th Cir. 2014), support our conclusion. In Salgado-Sosa, the petitioner fled to\\n\\nthe United States from Honduran gangs because his stepfather had angered the gangs, the\\n\\npetitioner defended his stepfather, and the gangs retaliated against the petitioner. 882\\n\\nF.3d at 457–58. There, we found “no meaningful distinction between whether Salgado-\\n\\nSosa was threatened because of his connection to his stepfather [or] because MS-13\\n\\nsought revenge on him for an act committed by his stepfather,” because both were\\n\\nderivative of his stepfather’s dispute with the gangs. Id. at 458. Since the petitioner\\n\\nshared family ties with his stepfather, he had established a sufficient nexus between his\\n\\npersecution and a protected ground. Id. at 458–59. Cortez-Mendez, by contrast, has\\n\\nprovided no evidence that the gangs threatened him because of his father’s disabilities.\\n\\nInstead, he testified that his rejection of gang membership was the impetus for his\\n\\nharassment.\\n\\n Cordova likewise bolsters our conclusion. There, we reversed the BIA’s denial of\\n\\nthe petitioner’s application of asylum and withholding of removal because the BIA had\\n\\n 9\\n\\fignored relevant nexus evidence. Cordova, 759 F.3d at 339. The petitioner in Cordova\\n\\nhad testified that gang members targeted him because he was related to members of a\\n\\nrival gang, but the BIA only considered evidence that he was targeted for rebuffing gang\\n\\nrecruitment. Id. at 339–40. Here, however, the IJ and the BIA ignored no relevant\\n\\nevidence concerning the import of the father’s disabilities because Cortez-Mendez\\n\\npresented none. All he provided was his unsubstantiated speculation that the gangs\\n\\ntargeted him because of his father’s disabilities. Given Cortez-Mendez’s own testimony\\n\\nthat he feared the gangs after refusing to join them, we are not “compelled” to conclude\\n\\nthat the gangs’ threats against Cortez-Mendez were on account of his father’s disabilities,\\n\\nas opposed to Cortez-Mendez’s rejection of gang membership. See Salgado-Sosa, 882\\n\\nF.3d at 456. As such, substantial evidence supported the BIA’s conclusion that Cortez-\\n\\nMendez failed to establish the requisite nexus. Accordingly, the BIA did not err in\\n\\ndenying withholding of removal.\\n\\n C.\\n\\n The INA does not protect every person who rejects gang recruitment efforts. See\\n\\nZelaya, 668 F.3d at 166–67. A petitioner seeking withholding of removal must show\\n\\nmore. Cortez-Mendez has failed to provide either direct or circumstantial evidence that\\n\\nthe gangs’ actions against him were motivated by a protected ground. See I.N.S. v. Elias-\\n\\nZacarias, 502 U.S. 478, 483 (1992). Consequently, Cortez-Mendez’s “[f]ear of\\n\\nretribution over purely personal matters” cannot support his application for withholding\\n\\nof removal. Moreno v. Lynch, 628 F. App’x 862, 866 (4th Cir. 2015).\\n\\n\\n\\n 10\\n\\f If we were to grant withholding of removal based on the slim evidence Cortez-\\n\\nMendez has provided, every family member of a disabled person would be eligible for\\n\\nrefugee status if anyone harassed them in their home country. We have rejected sweeping\\n\\narguments like this before and do so again. See, e.g., Yi Ni v. Holder, 613 F.3d 415, 429–\\n\\n30 (4th Cir. 2010) (“Were the fact that a person is subject to family planning policies\\n\\nsufficient to establish persecution, every Chinese citizen of childbearing age would be\\n\\neligible for relief.”). Therefore, “[u]nder the deferential substantial evidence standard we\\n\\nare bound to apply, we conclude that the absence of any direct evidence establishing that”\\n\\ngang members “intended to persecute [Cortez-Mendez] because of his familial\\n\\nrelationship to his [father]—provided an adequate basis for a reasonable adjudicator to\\n\\ndeny [Cortez-Mendez] relief.” Pacas-Renderos v. Sessions, 691 F. App’x 796, 803 (4th\\n\\nCir. 2017). Substantial evidence supports the IJ’s and BIA’s finding that Cortez-Mendez\\n\\ndid not establish the requisite nexus, and his application for withholding of removal was\\n\\nproperly denied.\\n\\n\\n\\n IV.\\n\\n Accordingly, Cortez-Mendez’s petition for review is\\n\\n DENIED.\\n\\n\\n\\n\\n 11\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":84,"cells":{"id":{"kind":"number","value":4579303,"string":"4,579,303"},"name":{"kind":"string","value":"Brian DAVISON, Plaintiff - Appellee, v. Phyllis RANDALL, in Her Official and Individual Capacity, Defendant - Appellant, and Loudoun County Board of Supervisors, in Their Official and Individual Capacities; Leo Rogers, in His Official Capacity; Tony Buffington, in His Official Capacity; Ron Meyer, in His Official Capacity; Geary Higgins, in His Official Capacity, Defendants. Local Government Attorneys of Virginia, Inc.; International Municipal Lawyers Association ; Virginia Association of Counties; Virginia Municipal League, Amici Supporting Appellant, American Civil Liberties Union; ACLU of Virginia ; ACLU of Maryland; ACLU of North Carolina; ACLU of South Carolina; ACLU of West Virginia, Amici Supporting Appellee. Brian C. Davison, Plaintiff - Appellant, v. Phyllis Randall, in Her Official and Individual Capacity; Loudoun County Board of Supervisors, in Their Official and Individual Capacities, Defendants - Appellees, and Leo Rogers, in His Official Capacity; Tony Buffington, in His Official Capacity; Ron Meyer, in His Official Capacity; Geary Higgins, in His Official Capacity, Defendants."},"name_abbreviation":{"kind":"string","value":"Brian Davison v. Phyllis Randall"},"decision_date":{"kind":"string","value":"2019-01-07"},"docket_number":{"kind":"string","value":"17-2002; 17-2003"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Keenan, Wynn, Harris\", \"parties\": \"\", \"opinions\": [{\"author\": \"WYNN, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-2002\\n\\n\\nBRIAN DAVISON,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nPHYLLIS RANDALL, In her official and individual capacity,\\n\\n Defendant - Appellant,\\n\\n and\\n\\nLOUDOUN COUNTY BOARD OF SUPERVISORS, In their official and\\nindividual capacities; LEO ROGERS, In his official capacity; TONY\\nBUFFINGTON, In his official capacity; RON MEYER, In his official capacity;\\nGEARY HIGGINS, In his official capacity,\\n\\n Defendants.\\n\\n------------------------------\\n\\nLOCAL GOVERNMENT ATTORNEYS OF VIRGINIA, INC.;\\nINTERNATIONAL MUNICIPAL LAWYERS ASSOCIATION; VIRGINIA\\nASSOCIATION OF COUNTIES; VIRGINIA MUNICIPAL LEAGUE,\\n\\n Amici Supporting Appellant,\\n\\nAMERICAN CIVIL LIBERTIES UNION; ACLU OF VIRGINIA; ACLU OF\\nMARYLAND; ACLU OF NORTH CAROLINA; ACLU OF SOUTH\\nCAROLINA; ACLU OF WEST VIRGINIA,\\n\\n Amici Supporting Appellee.\\n\\n No. 17-2003\\n\\n\\nBRIAN C. DAVISON,\\n\\n Plaintiff - Appellant,\\n\\n v.\\n\\nPHYLLIS RANDALL, In her official and individual capacity; LOUDOUN\\nCOUNTY BOARD OF SUPERVISORS, In their official and individual\\ncapacities,\\n\\n Defendants - Appellees,\\n\\n and\\n\\nLEO ROGERS, In his official capacity; TONY BUFFINGTON, In his official\\ncapacity; RON MEYER, In his official capacity; GEARY HIGGINS, In his\\nofficial capacity,\\n\\n Defendants.\\n\\n\\nAppeals from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. James C. Cacheris, Senior District Judge. (1:16-cv-00932-JCC-IDD)\\n\\n\\nArgued: September 26, 2018 Decided: January 7, 2019\\n\\n\\nBefore KEENAN, WYNN, and HARRIS, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Wynn wrote the opinion, in which Judge Keenan\\nand Judge Harris concurred. Judge Keenan wrote a separate concurring opinion.\\n\\n\\nARGUED: Scott E. Gant, BOIES SCHILLER FLEXNER, LLP, Washington, D.C.; Leo\\nP. Rogers, LOUDON COUNTY ATTORNEY, Leesburg, Virginia, for Appellant/Cross-\\nAppellee. Katherine A. Fallow, KNIGHT FIRST AMENDMENT INSTITUTE AT\\n\\n\\n 2\\n\\nCOLUMBIA UNIVERSITY, New York, New York, for Appellee/Cross-Appellant. ON\\nBRIEF: Aaron E. Nathan, BOIES SCHILLER FLEXNER LLP, Washington, D.C., for\\nAppellant/Cross-Appellee. Jameel Jaffer, Carrie DeCell, KNIGHT FIRST\\nAMENDMENT INSTITUTE AT COLUMBIA UNIVERSITY, New York, New York,\\nfor Appellee/Cross-Appellant. Vishal Agraharkar, AMERICAN CIVIL LIBERTIES\\nUNION FOUNDATION OF VIRGINIA, Richmond, Virginia; Esha Bhandari, Vera\\nEidelman, AMERICAN CIVIL LIBERTIES UNION FOUNDATION, New York, New\\nYork; Susan K. Dunn, ACLU OF SC FOUNDATION, INC., Charleston, South Carolina;\\nChristopher Brook, AMERICAN CIVIL LIBERTIES UNION OF NORTH CAROLINA\\nLEGAL FOUNDATION, Raleigh, North Carolina; Deborah A. Jeon, ACLU\\nFOUNDATION OF MARYLAND, Baltimore, Maryland; Jennifer D. Oliva, ACLU OF\\nWEST VIRGINIA FOUNDATION, Charleston, West Virginia, for Amici American\\nCivil Liberties Union, ACLU of Virginia, ACLU of Maryland, ACLU of North Carolina,\\nACLU of South Carolina, and ACLU of West Virginia. Joshua A. Geltzer, Douglas\\nLetter, Amy L. Marshak, Mary B. McCord, INSTITUTE FOR CONSTITUTIONAL\\nADVOCACY AND PROTECTION GEORGETOWN UNIVERSITY LAW CENTER,\\nWashington, D.C.; Kwaku A. Akowuah, Christopher C. Fonzone, Kate Heinzelman,\\nSIDLEY AUSTIN LLP, Washington, D.C., for Amici Curiae First Amendment Legal\\nScholars.\\n\\n\\n\\n\\n 3\\n\\nWYNN, Circuit Judge:\\n\\n Phyllis Randall, Chair of the Loudoun County, Virginia, Board of Supervisors (the\\n\\n“Loudoun Board”), brings this appeal, arguing that the district court erred in concluding\\n\\nthat she violated the First Amendment rights of one of her constituents, Brian Davison,\\n\\nwhen she banned Davison from the “Chair Phyllis J. Randall” Facebook page she\\n\\nadministered. In a cross appeal, Davison principally argues that the district court erred\\n\\nin dismissing his procedural due process claim premised on the ban. For the reasons that\\n\\nfollow, we affirm.\\n\\n I.\\n\\n A.\\n\\n Randall has chaired the Loudoun County Board of Supervisors since January 1,\\n\\n2016. The day before she was sworn in as chair, Randall created the “Chair Phyllis J.\\n\\nRandall” Facebook Page (the “Chair’s Facebook Page”). According to Facebook, Inc.,\\n\\nunlike personal Facebook profiles, which are for non-commercial use and represent\\n\\nindividual people, Facebook “Pages”—like the Chair’s Facebook Page—“help\\n\\nbusinesses, organizations, and brands share their stories and connect with people.” J.A.\\n\\n403. “Pages are managed by people who have personal profiles,” the company explains.\\n\\nJ.A. 403. In addition to the Chair’s Facebook Page, Randall created and maintained two\\n\\nother Facebook profiles: a personal profile and a Page devoted to her campaign. Randall\\n\\nclassified her campaign page as belonging to a “politician” and used no designation for\\n\\nher personal profile, but she designated the Chair’s Facebook Page as a “governmental\\n\\nofficial” page. J.A. 209–10.\\n\\n\\n 4\\n\\n Randall and her Chief of Staff, Jeanine Arnett, share administrative control over\\n\\nthe Chair’s Facebook Page, although Randall almost exclusively controls the page’s\\n\\ncontent. On her campaign page, Randall characterized the Chair’s Facebook Page as her\\n\\n“county Facebook page” stating:\\n\\n I really want to hear from ANY Loudoun citizen on ANY issues, request,\\n criticism, complement or just your thoughts. However, I really try to keep\\n back and forth conversations (as opposed to one time information items\\n such as road closures) on my county Facebook page (Chair Phyllis J.\\n Randall) or County email (Phyllis.randall@loudoun.gov). Having back and\\n forth constituent conversations are Foiable ([Freedom of Information Act])\\n so if you could reach out to me on these mediums that would be\\n appreciated.\\n\\nJ.A. 455 (emphasis added).\\n\\n The Chair’s Facebook Page includes three columns. The left column, which is\\n\\ntopped by a picture of Randall, includes several links to allow visitors to quickly navigate\\n\\nthe contents of the Chair’s Facebook Page.\\n\\n The middle column, which is organized in reverse chronological order similar to a\\n\\npersonal profile’s News Feed, is composed of posts by Randall and comments by\\n\\nFacebook users on those posts. Randall’s posts are almost always directed to “Loudoun,”\\n\\nsee, e.g., J.A. 408–10, and deal with numerous aspects of Randall’s official\\n\\nresponsibilities. For example, Randall used the Chair’s Facebook Page to notify the\\n\\npublic about upcoming Loudoun Board meetings, and the subjects to be discussed during\\n\\nthose meetings. Randall also used the page to inform Loudoun County residents about\\n\\nsignificant public safety issues. See, e.g., J.A. 412 (stating that Loudoun Board had\\n\\n“been informed by the Sheriff’s Office about the non-legitimate threat made on social\\n\\n\\n\\n 5\\n\\nmedia toward Dominion High School in Sterling”); J.A. 418 (reporting that she “ha[d]\\n\\nbeen briefed regarding the student falling from the water tower this morning” and\\n\\nadvising the public to “not make any assumptions but wait for information”). And\\n\\nRandall used the Chair’s Facebook Page to coordinate Loudoun County’s response to a\\n\\nlarge snow storm, including to communicate with constituents regarding which municipal\\n\\nstreets required plowing.\\n\\n Other posts by Randall to the Chair’s Facebook Page invited members of the\\n\\npublic to apply to participate on a public commission and to participate in public\\n\\nmeetings regarding key issues facing Loudoun County residents, such as revised flood\\n\\nplain zones and the Zika virus. Randall also authored posts regarding a variety of trips\\n\\nand meetings she had taken in furtherance of Loudoun County business. E.g., J.A. 408\\n\\n(reporting that Randall “address[ed] the (county) role in Treatment” at a “regional\\n\\nconference on Opioid and Substance Abuse Addiction”); J.A. 410 (stating that Randall\\n\\nrepresented Loudoun County at its “annual credit rating presentation” in New York); J.A.\\n\\n415 (informing public of trip to Loudoun’s “Sister City” in Germany); J.A. 426\\n\\n(reporting that Randall was “in Richmond lobbying for [Loudoun County’s] legislative\\n\\nprogram”). Finally, Randall used the page to advise the public regarding official actions\\n\\ntaken by the Loudoun Board. E.g., J.A. 433 (reporting that Loudoun Board “approved\\n\\nfunding for new breathing apparatus for our Loudoun Firefighters”); J.A. 442 (listing\\n\\nseveral “proclamations of note” by the Loudoun Board); J.A. 443 (informing public that\\n\\nLoudoun Board “adopted a budget for Fiscal Year 2017 totaling $2.46 billion for the\\n\\ngeneral county government and schools”). Although Randall’s posts on the Chair’s\\n\\n\\n 6\\n\\nFacebook Page principally addressed her official responsibilities, a few posts addressed\\n\\ntopics less closely related to her official activities such as her affection for the German\\n\\nlanguage or pride in becoming an organ donor.\\n\\n Members of the public, including Davison, “liked” 1 or commented on several of\\n\\nRandall’s posts on the Chair’s Facebook Page. Each “like” or comment identified the\\n\\nname of the personal profile or Page of the authoring party. Many of the comments\\n\\nthanked Randall and the Loudoun Board for representing the public’s interests. Other\\n\\nposts by members of the public offered feedback on various issues faced by Randall and\\n\\nthe Loudoun Board. E.g., J.A. 427 (stating that “[p]utting recreation in a flood plain is\\n\\nnot a good idea”); J.A. 448 (stating that “more needs to be done with the explosion of\\n\\nLyme disease in Loudoun”). And other comments dealt with constituent-specific issues.\\n\\nE.g., J.A. 415 (constituent stating, in response to post by Randall regarding visit to\\n\\nLoudoun County’s “Sister City” in Germany, that constituent’s “daughter is interested in\\n\\nexchange programs”); J.A. 454 (stating that “there [we]re no [snow] plows to be seen” in\\n\\na particular neighborhood). Finally, several comments, including a number authored by\\n\\nDavison, criticized the Loudoun Board, generally, and Randall, in particular, for actions\\n\\ntaken in their official capacities. E.g., J.A. 429–30 (Davison criticizing public school\\n\\nsystem budget and expenditures); J.A. 438–39 (member of public criticizing\\n\\ngovernmental entity’s inspection of farm, claiming it failed to uncover animal abuse);\\n\\n\\n 1\\n “‘Liking’ on Facebook is a way for Facebook users to share information with\\neach other.” Bland v. Roberts, 730 F.3d 368, 385 (4th Cir. 2013).\\n\\n\\n\\n 7\\n\\nJ.A. 449 (Davison characterizing question he posed at Loudoun Board and Loudoun\\n\\nSchool Board joint town hall). On some occasions, Randall responded to these\\n\\ncomments or criticisms.\\n\\n In the right column of the Chair’s Facebook Page, the page is identified as a\\n\\n“government official” page. It provides contact information for Randall’s county office,\\n\\nincluding her office telephone number, Randall’s official county email address, and the\\n\\ninternet address for the official county website. The column also identifies how many\\n\\nand which Facebook personal profiles and Pages “like” and “follow” the Chair’s\\n\\nFacebook Page. 2 And the column includes a list of personal profiles and Pages “liked”\\n\\nby the Chair’s Facebook Page.\\n\\n Randall publicized the Chair’s Facebook Page in her official “Chair Phyllis J.\\n\\nRandall” newsletter, which is prepared by County employees, hosted on the County’s\\n\\nwebsite, and distributed to Loudoun citizens using Randall’s official county email\\n\\naccount. The newsletter ends with the words “STAY CONNECTED” and a Facebook\\n\\nicon that hyperlinks to the Chair’s Facebook Page. Randall also highlighted the Chair’s\\n\\nFacebook Page in “Winter Storm Information” notices emailed from her official county\\n\\naccount to Loudoun County residents, advising recipients to “Visit [the Chair’s Facebook\\n\\nPage] for Updates.” J.A. 341–42, 344.\\n\\n 2\\n According to Facebook, “[l]iking a Facebook Page means you are connecting to\\nthat Page. When you connect to a Page, it will appear in [a user’s] timeline and [the user]\\nwill appear on the page as a person who likes that Page. The Page will also be able to\\npost content into [the user’s] News Feed.” Bland, 730 F.3d at 385 (internal quotation\\nmarks omitted).\\n\\n\\n\\n 8\\n\\n Davison, an outspoken resident of Loudoun County, apparently largely focuses his\\n\\ncivic engagement and expression on “the funding and . . . management of public\\n\\nschools.” J.A. 95. To that end, he has repeatedly expressed concern about “School Board\\n\\nmembers failing to disclose personal conflicts as required by law before voting on\\n\\nfinancial transactions before the School Board.” J.A. 96.\\n\\n On February 3, 2016, Davison attended a Loudoun town hall meeting that\\n\\nincluded the Loudoun County School Board and Randall. At the meeting, Davison\\n\\nsubmitted a question implying that certain School Board members had acted unethically\\n\\nin approving financial transactions. Randall volunteered to answer the question but\\n\\ncharacterized it as a “set-up question” that she did not “appreciate.” J.A. 103. Shortly\\n\\nafter Randall answered the question—and while the town hall meeting was still\\n\\nongoing—Davison posted a message on Twitter in which he tagged Randall:\\n\\n“@ChairRandall ‘set up question’? You might want to strictly follow FOIA and the\\n\\nCOIA as well.” J.A. 470–71.\\n\\n Later that evening, Randall posted about the town hall meeting on the Chair’s\\n\\nFacebook Page, describing “what was generally discussed at the meeting.” J.A. 268. In\\n\\nresponse, Davison then used one of the Facebook Pages he manages through his personal\\n\\nFacebook profile—“Virginia SGP,” which Davison frequently uses to post political\\n\\ncommentary—to comment on Randall’s post about the town hall meeting. Although\\n\\nneither Davison nor Randall remember the precise content of Davison’s comment,\\n\\nRandall testified that it contained “accusations” regarding School Board members’ and\\n\\ntheir families’ putative conflicts of interest related to municipal financial transactions,\\n\\n\\n 9\\n\\nsuggesting, in Randall’s opinion, that School Board members had been “taking kickback\\n\\nmoney.” See J.A. 268–69, 289–90. Randall stated that she “had no idea if any of th[e]\\n\\n[accusations] w[ere] correct,” but she determined that the post was “probably not\\n\\nsomething [she] want[ed] to leave” on the Chair’s Facebook Page. J.A. 269. Randall\\n\\nthen “deleted the whole post,” including her original post regarding the town hall\\n\\nmeeting, Davison’s comment and replies thereto, and all other public comments. J.A.\\n\\n269. Randall also banned Davison’s Virginia SGP Page from the Chair’s Facebook Page,\\n\\nwhich precluded Davison from using his Virginia SGP Page from commenting on the\\n\\nChair’s Facebook Page. The next morning, about twelve hours later, Randall\\n\\nreconsidered her actions and unbanned Davison’s Virginia SGP Page.\\n\\n B.\\n\\n On November 3, 2016, Davison filed an amended complaint seeking declaratory\\n\\nand injunctive relief under 42 U.S.C. § 1983 against Randall, in both her official and\\n\\nindividual capacities, and the Loudoun Board alleging that the “banning of [Davison]\\n\\nfrom commenting on [the Chair’s Facebook Page] is viewpoint discrimination.” J.A. 31.\\n\\nDavison further alleged that the ban violated his procedural due process rights protected\\n\\nby the Fourteenth Amendment because “Randall blocked Davison’s constitutionally\\n\\nprotected speech on [the Chair’s Facebook Page], a limited public forum, without prior\\n\\nnotice and without providing an opportunity for appealing [her] decision.” J.A. 32.\\n\\nDavison did not challenge Randall’s deletion of his post.\\n\\n On March 6, 2017—four days before the close of discovery and approximately\\n\\ntwo months before trial—Davison moved for leave to amend his complaint a second time\\n\\n\\n 10\\n\\nto add claims under the Virginia Constitution that were materially indistinguishable from\\n\\nhis previously asserted First and Fourteenth Amendment claims premised on the ban, as\\n\\nwell as a separate First Amendment claim against the Loudoun Board. Davison’s\\n\\nproposed new First Amendment claim theorized that the County violated his free speech\\n\\nrights by choosing to use Facebook Pages as public forums, when Facebook allows\\n\\nprivate users to restrict access to their posts, including posts to any Page a municipality\\n\\ndesignates as a limited public forum. Pl.’s Mem. in Supp. of Mot. for Leave to File\\n\\nSecond Am. Compl. 3–9, Davison v. Loudoun County Bd. of Supervisors, 16-cv-932-\\n\\nJCC-IDD, ECF No. 68. The district court referred the motion to a magistrate judge, who\\n\\ngranted leave to amend regarding the claims under the Virginia Constitution but denied\\n\\nleave as to the new First Amendment claim against the Loudoun Board. Davison lodged\\n\\nobjections to the magistrate judge’s partial denial of leave to amend, which objections the\\n\\ndistrict court overruled.\\n\\n Around the same time, Randall and the Loudoun Board each moved for summary\\n\\njudgment. The Loudoun Board asserted that the municipality could not be held liable for\\n\\nRandall’s banning of Davison from the Chair’s Facebook Page because the Chair’s\\n\\nFacebook Page was not an official municipal page and because Randall, not the Loudoun\\n\\nBoard as a body, was solely responsible for creating and administering the Chair’s\\n\\nFacebook Page. The Loudoun Board and Randall further asserted that the Chair’s\\n\\nFacebook Page did not amount to a public forum, and therefore Randall’s ban of\\n\\nDavison’s Virginia SGP Page did not implicate his free speech or procedural due process\\n\\nrights. Finally, Randall asserted that she was entitled to qualified immunity.\\n\\n\\n 11\\n\\n On May 10, 2017, the district court granted summary judgment in favor of the\\n\\nLoudoun Board, dismissing it from the suit. But as to Randall, the district court\\n\\nconcluded that Davison’s evidence established a material dispute of fact as to whether the\\n\\nChair’s Facebook Page amounted to a limited public forum and whether Randall, in her\\n\\nindividual capacity, acted under color of state law in banning Davison from the Chair’s\\n\\nFacebook Page. Davison v. Loudoun Cty. Bd. of Supervisors, No. 1:16-cv-932, 2017 WL\\n\\n1929406, at *6–9 (E.D. Va. May 10, 2017). The district court also rejected Randall’s\\n\\nqualified immunity argument. Id. at *8.\\n\\n Following a one-day bench trial of Davison’s claims against Randall, the district\\n\\ncourt issued a memorandum opinion and order awarding judgment in Davison’s favor on\\n\\nhis claims under the First Amendment and the analogous free speech provision in the\\n\\nVirginia Constitution. See Davison v. Loudoun Cty. Bd. of Supervisors, 267 F. Supp. 3d\\n\\n702, 714–18 (E.D. Va. 2017). The district court further entered judgment in Randall’s\\n\\nfavor on Davison’s federal and state procedural due process claims. Id. at 719–22. As to\\n\\nremedy, the district court denied Davison’s request for injunctive relief but granted\\n\\nDavison’s request for a declaratory judgment to resolve the “uncertainty regarding the\\n\\nlegal status of [the Chair’s Facebook Page].” Id. at 723.\\n\\n Randall and Davison, respectively, filed this appeal and cross appeal.\\n\\n II.\\n\\n On appeal, Randall argues that (A) Davison failed to establish standing to obtain\\n\\nprospective declaratory relief based on Randall’s alleged First Amendment violation; (B)\\n\\nthe district court erred in concluding that Randall acted under “color of state law” when\\n\\n\\n 12\\n\\nshe banned Davison’s Virginia SGP Page from the Chair’s Facebook Page; and (C) the\\n\\ndistrict court erred in concluding that Randall’s banning of Davison’s Virginia SGP Page\\n\\nviolated the First Amendment.\\n\\n A.\\n\\n Notwithstanding that she did not challenge Davison’s standing below—and\\n\\ntherefore that the district court never squarely addressed his standing—Randall now\\n\\nargues that Davison failed to establish Article III standing to support the district court’s\\n\\naward of prospective declaratory relief. Even though Defendants did not challenge\\n\\nDavison’s standing below, “standing to sue is a jurisdictional issue of constitutional\\n\\ndimensions, and it may be raised and addressed for the first time on appeal.” Hodges v.\\n\\nAbraham, 300 F.3d 432, 443 (4th Cir. 2002). This Court reviews de novo “whether a\\n\\ndistrict court possessed jurisdiction in a declaratory judgment proceeding.” Volvo Const.\\n\\nEquip. N. Am., Inc. v. CLM Equip. Co., Inc., 386 F.3d 581, 591 (4th Cir. 2004).\\n\\n To establish Article III standing, a plaintiff must prove that: “1) he or she suffered\\n\\nan ‘injury in fact’ that is concrete and particularized, and is actual or imminent; 2) the\\n\\ninjury is fairly traceable to the challenged action of the defendant; and 3) the injury likely\\n\\nwill be redressed by a favorable decision.” Friends of the Earth, Inc. v. Gaston Copper\\n\\nRecycling Corp., 629 F.3d 387, 396 (4th Cir. 2011). Randall does not dispute that any\\n\\ninjury Davison suffered is fairly traceable to her decision to ban him from the Chair’s\\n\\nFacebook Page. Nor does Randall dispute that any such injury would be remedied by a\\n\\nfavorable decision. Rather, Randall claims that Davison failed to adduce evidence\\n\\n\\n\\n\\n 13\\n\\nestablishing that he suffered an “injury in fact” sufficient to support prospective\\n\\ndeclaratory relief.\\n\\n “Injury in fact is ‘an invasion of a legally protected interest’ that is ‘concrete and\\n\\nparticularized’ and ‘actual or imminent, not conjectural or hypothetical.’” Kenny v.\\n\\nWilson, 885 F.3d 280, 287 (4th Cir. 2018) (quoting Spokeo, Inc. v. Robins, 136 S. Ct.\\n\\n1540, 1548 (2016)). Because “‘[p]ast exposure to illegal conduct does not in itself show\\n\\na present case or controversy regarding injunctive relief . . . if unaccompanied by any\\n\\ncontinuing, present adverse effects,’” a plaintiff seeking “declaratory or injunctive relief .\\n\\n. . must establish an ongoing or future injury in fact.” Id. at 287–88 (quoting O’Shea v.\\n\\nLittleton, 414 U.S. 488, 495–96 (1974)). Significantly, this Court—along with several\\n\\nother circuits—has held that “standing requirements are somewhat relaxed in First\\n\\nAmendment cases,” particularly regarding the injury-in-fact requirement. Cooksey v.\\n\\nFutrell, 721 F.3d 226, 235 (4th Cir. 2013) (collecting cases).\\n\\n In Kenny v. Wilson, 885 F.3d 280 (4th Cir. 2018), this Court addressed what\\n\\nevidence a plaintiff seeking relief under the First Amendment, like Davison, must put\\n\\nforward to establish a future injury-in-fact adequate to confer Article III standing to\\n\\nobtain prospective declaratory relief. In Kenny, several high school students lodged First\\n\\nAmendment challenges to two South Carolina disorderly conduct statutes. Id. at 284.\\n\\nThis Court explained that “there is a sufficiently imminent injury in fact if plaintiffs\\n\\nallege [1] ‘an intention to engage in a course of conduct arguably affected with a\\n\\nconstitutional interest, but proscribed by a statute, and [2] there exists a credible threat of\\n\\nprosecution thereunder.’” Id. at 288 (quoting Babbitt v. Farm Workers Nat’l Union, 442\\n\\n\\n 14\\n\\nU.S. 289, 298 (1979)). The Kenny plaintiffs satisfied the first prong because they “attend\\n\\nschool” and “attending school inevitably involves expressive conduct” that implicates the\\n\\ndisorderly conduct statutes. Id. As to the second element—whether the students alleged\\n\\na “credible threat of future enforcement”—we held that such a threat exists so long as it\\n\\n“is not imaginary or wholly speculative, chimerical, or wholly conjectural.” Id. (internal\\n\\nquotation marks, citations, and alterations omitted). “[P]ast enforcement against the same\\n\\nconduct is good evidence that the threat of enforcement is not chimerical.” Id. (quoting\\n\\nSusan B. Anthony List v. Driehaus, 134 S. Ct. 2334, 2345 (2014)). “Threat of\\n\\nprosecution is especially credible when defendants have not ‘disavowed enforcement’ if\\n\\nplaintiffs engage in similar conduct in the future.” Id. (quoting Driehaus, 134 S. Ct. at\\n\\n2345). Applying this standard, we held that the plaintiffs alleged a credible threat of\\n\\nenforcement “because these three plaintiffs regularly attend schools where they allege\\n\\nthere may be future encounters with school resource officers or other law enforcement;\\n\\nthey have been prosecuted under the laws in the past; and the defendants have not\\n\\ndisavowed enforcement if plaintiffs engage in similar conduct in the future.” Id. at 289.\\n\\n Under Kenny, Davison’s evidence established his standing to obtain prospective\\n\\ndeclaratory relief. Relevant to the first prong—whether Davison intends to engage in a\\n\\ncourse of conduct “arguably” impacted by the challenged conduct, Babbitt, 442 U.S. at\\n\\n298—the district court found, in awarding Davison declaratory relief, that he “continues\\n\\nto avail himself” of the Chair’s Facebook Page and that Davison is “active in local\\n\\npolitics, and has a particular interest in what he believes to be corruption on the part of\\n\\nLoudoun County’s school board.” Davison, 267 F. Supp. 3d at 707, 723. Accordingly,\\n\\n\\n 15\\n\\nthe evidence establishes that Davison continues to engage in a course of conduct—\\n\\nnamely, posting about alleged municipal corruption on the Chair’s Facebook Page—\\n\\nlikely to be impacted by Randall’s allegedly unconstitutional approach to managing the\\n\\npage.\\n\\n Turning to the second prong—whether there is a credible threat of enforcement—\\n\\nRandall previously blocked Davison from the Chair’s Facebook Page based on the\\n\\ncontent of his posts, providing “good evidence that the threat of enforcement is not\\n\\nchimerical.” Driehaus, 134 S. Ct. at 2345 (internal quotation marks omitted).\\n\\nAdditionally, Randall testified that she continues to believe she can ban Davison and\\n\\nothers from the Chair’s Facebook Page based on their views without triggering the First\\n\\nAmendment at all. See J.A. 277 (Randall stating she would “be happy to” ban other\\n\\ncommenters on her “Chair’s Facebook” page); J.A. 250 (Randall testifying that\\n\\ncomments “attacking another person” would not be allowed on her “Chair’s Facebook”\\n\\npage). To that end, in awarding Davison declaratory relief, the district court found that\\n\\nRandall “maintains she is permitted to administer this Facebook page as a purely personal\\n\\npage.” Davison, 267 F. Supp. 3d at 723. Accordingly, Davison established that he has\\n\\nbeen subject to past enforcement and that Randall has not “disavowed” future\\n\\nenforcement, which, under Kenny, is sufficient to establish a credible threat of\\n\\nenforcement. Cf. City of Lakewood v. Plain Dealer Pub. Co., 486 U.S. 750, 757 (1988)\\n\\n(“[T]he mere existence of the licensor’s unfettered discretion, coupled with the power of\\n\\nprior restraint, intimidates parties into censoring their own speech, even if the discretion\\n\\nand power are never actually abused.”).\\n\\n\\n 16\\n\\n In sum, Davison’s evidence demonstrated—and the district court found—that\\n\\nDavison intends to continue to use the Chair’s Facebook Page and that Davison faces a\\n\\ncredible threat of future enforcement. See Davison, 267 F. Supp. 3d at 723.\\n\\nAccordingly, Davison adduced facts establishing an injury in fact sufficient to justify the\\n\\nprospective declaratory relief awarded by the district court.\\n\\n B.\\n\\n Next, Randall asserts that the district court erred in concluding, with regard to\\n\\nDavison’s individual capacity First Amendment claim, that Randall acted “under color of\\n\\nstate law,” as that phrase is used in Section 1983, in administering the Chair’s Facebook\\n\\nPage and banning Davison from that page. “This Court reviews judgments stemming\\n\\nfrom a bench trial under a mixed standard: factual findings are reviewed for clear error,\\n\\nwhereas conclusions of law are reviewed de novo.” Helton v. AT&T Inc., 709 F.3d 343,\\n\\n350 (4th Cir. 2013). Whether, under the undisputed facts, Randall acted under color of\\n\\nstate law is a legal question this Court reviews de novo. Rossignol v. Voorhaar, 316 F.3d\\n\\n516, 523 (4th Cir. 2003).\\n\\n To state a claim under Section 1983, a plaintiff must show that the alleged\\n\\nconstitutional deprivation at issue occurred because of action taken by the defendant\\n\\n“under color of . . . state law.” Philips v. Pitt Cty. Mem’l Hosp., 572 F.3d 176, 180 (4th\\n\\nCir. 2009). “The traditional definition of acting under color of state law requires that the\\n\\ndefendant in a § 1983 action have exercised power ‘possessed by virtue of state law and\\n\\nmade possible only because the wrongdoer is clothed with the authority of state law.’”\\n\\nWest v. Atkins, 487 U.S. 42, 49 (1988) (quoting United States v. Classic, 313 U.S. 299,\\n\\n\\n 17\\n\\n326 (1941)). Section 1983’s “color-of-law prerequisite is synonymous with the more\\n\\nfamiliar state-action requirement” applicable to Fourteenth Amendment claims, “and the\\n\\nanalysis for each is identical.” Pitt Cty. Mem’l Hosp., 572 F.3d at 180. Both inquiries\\n\\ndemand that “the conduct allegedly causing the deprivation of a federal right be fairly\\n\\nattributable to the State.” Holly v. Scott, 434 F.3d 287, 292 (4th Cir. 2006) (quoting\\n\\nLugar v. Edmondson Oil Co., Inc., 457 U.S. 922, 937 (1982)).\\n\\n “[T]here is no specific formula for determining whether state action is present.”\\n\\nId. at 292 (internal quotation marks omitted). Rather, “[w]hat is fairly attributable [to the\\n\\nstate]”—i.e., what constitutes action under color of state law—“is a matter of normative\\n\\njudgment, and the criteria lack rigid simplicity.” Id. (internal quotation marks omitted).\\n\\nCourts must examine the “totality of the circumstances,” id. (internal quotation marks\\n\\nomitted), to determine if the action at issue “bore a ‘sufficiently close nexus’ with the\\n\\nState to be ‘fairly treated as that of the State itself,’” Rossignol, 316 F.3d at 525 (quoting\\n\\nJackson v. Metro. Edison Co., 419 U.S. 345, 351 (1974)).\\n\\n Although no one factor is determinative, this Court has held that a defendant’s\\n\\npurportedly private actions bear a “sufficiently close nexus” with the State to satisfy\\n\\nSection 1983’s color-of-law requirement when the defendant’s challenged “actions are\\n\\nlinked to events which arose out of his official status.” Id. at 524. When a defendant’s\\n\\n“status” as a public official “enabled [her] to execute [a challenged action] in a manner\\n\\nthat private citizens never could have,” then the action also is more likely to be treated as\\n\\nattributable to the state. Id. at 526; see also Martinez v. Colon, 54 F.3d 980, 986 (1st Cir.\\n\\n1995) (“[S]ection 1983 is . . . implicated . . . [when] the conduct is such that the actor\\n\\n\\n 18\\n\\ncould not have behaved in that way but for the authority of his office.”); Goldstein v.\\n\\nChestnut Ridge Volunteer Fire Co., 218 F.3d 337, 343 (4th Cir. 2000) (holding that\\n\\nchallenged conduct is more likely to amount to state action when “the injury caused is\\n\\naggravated in a unique way by the incidents of governmental authority” (internal\\n\\nquotation marks omitted)). Likewise, an official’s conduct is more likely to amount to\\n\\nstate action when it “occurs in the course of performing an actual or apparent duty of his\\n\\noffice.” Martinez, 54 F.3d at 986. And the challenged action of a defendant\\n\\ngovernmental official is likely to be treated as taken under color of law when the official\\n\\n“use[d] the power and prestige of his state office to damage the plaintiff.” Harris v.\\n\\nHarvey, 605 F.2d 330, 337 (7th Cir. 1979). In the context of an alleged First Amendment\\n\\nviolation, in particular, this Court has found that a challenged action by a governmental\\n\\nofficial is fairly attributable to the state when “the sole intention” of the official in taking\\n\\nthe action was “to suppress speech critical of his conduct of official duties or fitness for\\n\\npublic office.” Rossignol, 316 F.3d at 524.\\n\\n Here, after thoroughly analyzing the totality of the circumstances surrounding\\n\\nRandall’s creation and administration of the Chair’s Facebook Page and banning of\\n\\nDavison from that page, the district court concluded that Randall acted under color of\\n\\nstate law. Davison, 267 F. Supp. 3d at 723. We agree.\\n\\n Randall created and administered the Chair’s Facebook Page to further her duties\\n\\nas a municipal official. She used the Chair’s Facebook Page “as a tool of governance,”\\n\\nid. at 713: through the Chair’s Facebook Page, Randall provides information to the public\\n\\n\\n\\n\\n 19\\n\\nabout her and the Loudoun Board’s official activities and solicits input from the public on\\n\\npolicy issues she and the Loudoun Board confront. See supra Part I.A.\\n\\n For instance, Randall used the Chair’s Facebook Page to inform the public about\\n\\nserious public safety events and to keep her constituents abreast of the County’s response\\n\\nto a snowstorm and to coordinate snow removal activities. And, as the district court\\n\\ncorrectly emphasized, Randall\\n\\n swathe[d] the [Chair’s Facebook Page] in the trappings of her office.\\n Among other things, (1) the title of the page includes [Randall]’s title; (2)\\n the page is categorized as that of a government official; (3) the page lists as\\n contact information [Randall]’s official County email address and the\\n telephone number of [Randall]’s County office; (4) the page includes the\\n web address of [Randall]’s official County website; (5) many—perhaps\\n most—of the posts are expressly addressed to “Loudoun,” [Randall]’s\\n constituents; (6) [Randall] has submitted posts on behalf of the [Loudoun\\n Board] as a whole; (7) [Randall] has asked her constituents to use the\\n [Chair‘s Facebook Page] as a channel for “back and forth constituent\\n conversations”; and (8) the content posted has a strong tendency toward\\n matters related to [Randall]’s office.\\n\\nDavison, 267 F. Supp. 3d at 714. A private citizen could not have created and used the\\n\\nChair’s Facebook Page in such a manner. Rossignol, 316 F.3d at 526. Put simply,\\n\\nRandall clothed the Chair’s Facebook Page in “the power and prestige of h[er] state\\n\\noffice,” Harris, 605 F.2d at 337, and created and administered the page to “perform[]\\n\\nactual or apparent dut[ies] of h[er] office,” Martinez, 54 F.3d at 986.\\n\\n Additionally, the specific actions giving rise to Davison’s claim—Randall’s\\n\\nbanning of Davison’s Virginia SGP Page—“are linked to events which arose out of h[er]\\n\\nofficial status.” Rossignol, 316 F.3d at 524. Randall’s post to the Chair’s Facebook Page\\n\\nthat prompted Davison’s comment informed the public about what happened at the\\n\\n\\n\\n 20\\n\\nLoudoun Board and Loudoun County School Board’s joint meeting. And Davison’s\\n\\ncomment also dealt with an issue related to that meeting and of significant public\\n\\ninterest—School Board members’ alleged conflicts of interest in approving financial\\n\\ntransactions. That Randall’s ban of Davison amounted to an effort “to suppress speech\\n\\ncritical of [such members’] conduct of [their] official duties or fitness for public office”\\n\\nfurther reinforces that the ban was taken under color of state law. Id. at 525. Considering\\n\\nthe totality of these circumstances, the district court correctly held that Randall acted\\n\\nunder color of state law in banning Davison from the Chair’s Facebook Page.\\n\\n C.\\n\\n Third, Randall argues that the district court erred in ruling in Davison’s favor on\\n\\nhis individual capacity First Amendment claim against Randall. Randall principally\\n\\nchallenges the district court’s conclusion that the Chair’s Facebook Page constitutes a\\n\\n“public forum” under traditional First Amendment law. We review this legal question de\\n\\nnovo. See Helton, 709 F.3d at 350.\\n\\n Under long-established First Amendment law, governmental entities are “strictly\\n\\nlimited” in their ability to regulate private speech in public fora. Pleasant Grove City,\\n\\nUtah v. Summum, 555 U.S. 460, 469 (2009). The Supreme Court has recognized two\\n\\ncategories of public fora: “traditional public forums” and “limited (or designated) public\\n\\nforums.” Am. Civil Liberties Union v. Mote, 423 F.3d 438, 443 (4th Cir. 2005).\\n\\n“Traditional” public forums—“such as streets, sidewalks, and parks”—“have the\\n\\ncharacteristics of a public thoroughfare, a purpose that is compatible with expressive\\n\\nconduct, as well as a tradition and history of being used for expressive public conduct.”\\n\\n\\n 21\\n\\nId. “Limited” or “designated” forums are forums that are “not traditionally public, but\\n\\n[that] the government has purposefully opened to the public, or some segment of the\\n\\npublic, for expressive activity.” Id. Accordingly, the hallmark of both types of public\\n\\nfora—what renders the fora “public”—is that the government has made the space\\n\\navailable—either by designation or long-standing custom—for “expressive public\\n\\nconduct” or “expressive activity,” and the space is compatible with such activity. Id.\\n\\n“Conversely, a non-public forum is one that has not traditionally been open to the public,\\n\\nwhere opening it to expressive conduct would ‘somehow interfere with the objective use\\n\\nand purpose to which the property has been dedicated.’” Id. (quoting Warren v. Fairfax\\n\\nCty., 196 F.3d 186, 190–91 (4th Cir. 1999)).\\n\\n Although neither the Supreme Court nor any Circuit has squarely addressed\\n\\nwhether, and in what circumstances, a governmental social media page—like the Chair’s\\n\\nFacebook Page—constitutes a public forum, 3 aspects of the Chair’s Facebook Page bear\\n\\nthe hallmarks of a public forum. Randall “intentionally open[ed the public comment\\n\\nsection of the Chair’s Facebook Page] for public discourse,” Cornelius v. NAACP Legal\\n\\nDefense & Educ. Fund, Inc., 473 U.S. 788, 802 (1985), inviting “ANY Loudoun citizen”\\n\\n 3\\n In addition to the court below, two other district courts have considered whether\\na government official’s social media page constituted a public forum. Those courts\\nreached conflicting results. Compare Morgan v. Bevin, 298 F. Supp. 3d 1003, 1010 (E.D.\\nKy. 2018) (holding that First Amendment forum analysis did not apply to restrictions on\\nspeech in the official Facebook and Twitter pages of the Governor of Kentucky), with\\nKnight First Amend. Inst. at Colum. Univ. v. Trump, 302 F. Supp. 3d 541, 573 (S.D.N.Y.\\n2018) (holding that the interactive component of the President’s Twitter account, as\\nopposed to the President’s tweets themselves, constituted a designated public forum),\\nappeal docketed, No. 18-1691 (2d Cir. Oct. 24, 2018).\\n\\n\\n\\n 22\\n\\nto make posts to the comments section of the Chair’s Facebook Page—the interactive\\n\\ncomponent of the page—“on ANY issues, request, criticism, complement or just your\\n\\nthoughts,” J.A. 455. Randall placed no restrictions on the public’s access to the page or\\n\\nuse of the interactive component of the Chair’s Facebook Page. And, in accordance with\\n\\nRandall’s invitation, the public made numerous posts on matters of public concern.\\n\\n The Chair’s Facebook Page also is “compatib[le] with expressive activity.”\\n\\nCornelius, 473 U.S. at 802. “Congress [has] recognized the internet and interactive\\n\\ncomputer services as offering ‘a forum for a true diversity of political discourse, unique\\n\\nopportunities for cultural development, and myriad avenues for intellectual activity.’”\\n\\nZeran v. Am. Online, Inc., 129 F.3d 327, 330 (4th Cir. 1997) (quoting 47 U.S.C. §\\n\\n230(a)(3)); cf. Bland, 730 F.3d at 386 (finding post to campaign Facebook page\\n\\n“constituted pure speech”). And the Supreme Court recently analogized social media\\n\\nsites, like the Chair’s Facebook Page, to “traditional” public forums, characterizing the\\n\\ninternet as “the most important place[] (in a spacial sense) for the exchange of views.”\\n\\nPackingham v. North Carolina, 137 S. Ct. 1730, 1735 (2017). An “exchange of views”\\n\\nis precisely what Randall sought—and what in fact transpired—when she expressly\\n\\ninvited “ANY Loudoun citizen” to visit the page and comment “on ANY issues,” and\\n\\nreceived numerous such posts and comments. J.A. 455.\\n\\n Randall nevertheless argues that traditional public forum analysis should not apply\\n\\nto the Chair’s Facebook Page for two reasons: (1) the Chair’s Facebook Page is “a private\\n\\nwebsite” and therefore does not constitute “public property” susceptible to forum\\n\\nanalysis, and (2) the Chair’s Facebook Page, in its entirety, constitutes “government\\n\\n\\n 23\\n\\nspeech” properly analyzed under the framework set forth in Pleasant Grove. Randall’s\\n\\nBr. at 19–21, 29–31. We disagree.\\n\\n Even assuming the intangible space at issue is “private property,” as Randall\\n\\nclaims—which is not at all clear from the record before us 4—the Supreme Court never\\n\\nhas circumscribed forum analysis solely to government-owned property. For example, in\\n\\nCornelius, the Court recognized that forum analysis applies “to private property\\n\\ndedicated to public use.” Cornelius, 473 U.S. at 801 (emphasis added); see also\\n\\nChristian Legal Soc’y Chapter of the Univ. of Cal. v. Martinez, 561 U.S. 661, 679 (2010)\\n\\n(“[T]his Court has employed forum analysis to determine when a governmental entity, in\\n\\nregulating property in its charge, may place limitations on speech.” (emphasis added)).\\n\\n 4\\n The Facebook “platform” and the “software” that underlies that platform is,\\naccording to Facebook’s Terms of Service, property of Facebook, Inc. Terms of Service,\\nFacebook, https://www.facebook.com/terms.php (last visited Jan. 4, 2019). Facebook’s\\nTerms of Service further provide that users “own the content [they] create and share on\\nFacebook and the other Facebook Products,” including Pages. Id. There would seem to\\nbe a good argument, therefore, that content created, and posted to Facebook, by\\ngovernment officials performing the functions and duties of their offices constitutes\\ngovernment property. Cf. Solomons v. United States, 137 U.S. 342, 346–48 (1890)\\n(holding that intellectual property created by government employee in the course of his\\nofficial duties constituted government property because “[i]f one is employed to devise or\\nperfect an instrument, or a means for accomplishing a prescribed result, he cannot, after\\nsuccessfully accomplishing the work for which he was employed, plead title thereto as\\nagainst his employer”). Likewise, under Facebook’s Terms of Service, the posts and\\ncomments by individual Facebook users—like Davison—to a Facebook Page—like the\\nChair’s Facebook Page—constitute property of those users. Accordingly, a single\\nFacebook Page—including the Chair’s Facebook Page—encompasses a web of property\\nrights, some of which may lie with the government. We need not—and thus do not—\\ndecide with whom these property rights lie in this particular case, however, because we\\nhold that even assuming the Chair’s Facebook Page constitutes private property, Randall,\\nacting under color of state law, exercised control over the aspects of that page giving rise\\nto Davison’s claim.\\n\\n\\n\\n 24\\n\\nAnd the Supreme Court and lower courts have held that private property, whether\\n\\ntangible or intangible, constituted a public forum when, for example, the government\\n\\nretained substantial control over the property under regulation or by contract. See, e.g.,\\n\\nSe. Promotions, Ltd. v. Conrad, 420 U.S. 546, 547, 555 (1975) (holding that “a privately\\n\\nowned Chattanooga theater under long-term lease to the city” was a “public forum[]\\n\\ndesigned for and dedicated to expressive activities”); Halleck v. Manhattan Community\\n\\nAccess Corp., 882 F.3d 300, 306–07 (2d Cir. 2018) (holding that public access television\\n\\nchannels operated by a private non-profit corporation constituted public forums), cert.\\n\\ngranted 139 S. Ct. 360 (2018) (mem.); First Unitarian Church of Salt Lake City v. Salt\\n\\nLake City Corp., 308 F.3d 1114, 1122 (10th Cir. 2002) (“[F]orum analysis does not\\n\\nrequire that the government have a possessory interest in or title to the underlying land.\\n\\nEither government ownership or regulation is sufficient for a First Amendment forum of\\n\\nsome kind to exist.”); Freedom from Religion Foundation, Inc. v. City of Marshfield,\\n\\nWis., 203 F.3d 487, 494 (7th Cir. 2000) (holding that private property abutted by public\\n\\npark constituted public forum).\\n\\n Significantly, even assuming the relevant aspects of the Chair’s Facebook Page\\n\\nconstitute private property—which, again, is not entirely clear from the record before\\n\\nus—Randall, acting under color of state law, retained and exercised significant control\\n\\nover the page. She created the Chair’s Facebook Page. She designated the page as\\n\\nbelonging to a “governmental official.” She clothed the page in the trappings of her\\n\\npublic office. She chose to list her official contact information on the page. And she\\n\\n\\n\\n\\n 25\\n\\ncurated the links in the left column of the page and the lists of Facebook Pages or profiles\\n\\n“liked” by the Chair’s Facebook Page in the right column.\\n\\n Of particular importance, Randall had complete control over the aspect of the\\n\\nChair’s Facebook Page giving rise to Davison’s challenge because, as administrator of\\n\\nthe page, Randall had authority to ban Facebook profiles or Pages from using the Chair’s\\n\\nFacebook Page—and, therefore, the interactive component of the page—authority she\\n\\nexercised in banning Davison’s Virginia SGP Page. Cf. Knight, 302 F. Supp. 3d at 566–\\n\\n67 (holding that the interactive component of the President’s Twitter account constituted\\n\\npublic forum because the President and his advisors “exercise control over various\\n\\naspects of the . . . account,” including the power to block other users from accessing the\\n\\naccount).\\n\\n The Second Circuit’s decision in Halleck dealing with privately operated public\\n\\naccess television channels is instructive. Federal law allows cable franchising authorities\\n\\nto require cable operators to designate channel capacity for public use. Halleck, 882 F.3d\\n\\nat 302. Likewise, New York regulations oblige cable operators to designate at least one\\n\\nchannel for full-time public use. Id. Pursuant to that authority, the City of New York\\n\\nentered into a cable franchise agreement with a cable company requiring the company to\\n\\nmake available four public access channels, which channels were operated by a private,\\n\\nnon-profit corporation, MNN. Id. Several producers of public access programming sued\\n\\nMNN, alleging that MNN violated the producers’ First Amendment rights by indefinitely\\n\\nsuspending them from using the public access channels “because of disapproval of the\\n\\ncontent of a TV program” they had submitted for airing. Id.\\n\\n\\n 26\\n\\n The Second Circuit concluded that the public access channels constituted a public\\n\\nforum, notwithstanding that they were operated by a private company. Id. at 306–08.\\n\\nThe court reached that conclusion for two reasons. First, it pointed to the similarities\\n\\nbetween public access channels and traditional public forums, like parks, describing “[a]\\n\\npublic access channel [a]s the electronic version of the public square.” Id. at 306.\\n\\nSecond, the court emphasized the extensive government involvement with, and control\\n\\nover, public access channels by virtue of the federal and state regulatory schemes. See id.\\n\\n(“[W]here, as here, federal law authorizes setting aside channels to be ‘the electronic\\n\\nmarketplace of ideas,’ state regulation requires cable operators to provide at least one\\n\\npublic access channel, a municipal contract requires a cable operator to provide four such\\n\\nchannels, and a municipal official has designated a private corporation to run those\\n\\nchannels, those channels are public forums.” (emphasis added)).\\n\\n Although not subject to the extensive federal and state regulatory regime\\n\\napplicable in Halleck, 5 the Chair’s Facebook Page is in many ways analogous to the\\n\\nprivately-operated public access channels considered by the Second Circuit. Just as the\\n\\nfederal government sought to establish an “electronic marketplace of ideas” by\\n\\nmandating provision of public access channels, Randall expressly sought to—and did, in\\n\\n\\n 5\\n The federal Communications Decency Act allows private online intermediaries,\\nlike Facebook, the ability to moderate content by providing such intermediaries with\\nbroad immunity from user-generated content posted on their sites. 47 U.S.C. § 230. This\\nCourt has recognized that an “important purpose of § 230 was to encourage service\\nproviders to self-regulate the dissemination of offensive material over their services.”\\nZeran, 129 F.3d at 331.\\n\\n\\n\\n 27\\n\\nfact—create an “electronic marketplace of ideas” by inviting “ANY” constituent to post\\n\\nto the Chair Page on “ANY issues.” J.A. 455. Likewise, just as the City of New York\\n\\nchose to have a private corporation operate the public access channels, Randall chose to\\n\\ncreate her electronic marketplace of ideas, the Chair’s Facebook Page, on a private\\n\\nplatform, Facebook. Indeed, the present case provides a stronger basis for treating the\\n\\ninteractive component of the Chair’s Facebook Page as a public forum because whereas\\n\\nthe private corporation in Halleck, MNN, exercised control over the aspect of the public\\n\\naccess channel giving rise to the First Amendment claim—banning the public access\\n\\nprogram producer—a public official, Randall exercised unconstrained control over the\\n\\naspect of the Chair’s Facebook Page giving rise to Davison’s claim—banning of other\\n\\nFacebook profiles and Pages. 6\\n\\n\\n 6\\n On October 12, 2018, the Supreme Court granted MNN’s petition for writ of\\ncertiorari in Halleck. 139 S. Ct. 360. MNN’s petition presented two questions: (1)\\n“[w]hether the Second Circuit erred in rejecting th[e Supreme] Court’s state actor tests\\nand instead creating a per se rule that private operators of public access channels are state\\nactors subject to constitutional liability” and (2) “[w]hether the Second Circuit erred in\\nholding—contrary to the Sixth and D.C. Circuits—that private entities operating public\\naccess televisions stations are state actors for constitutional purposes where the state has\\nno control over the private entity’s board or operations.” Petition for Writ of Certiorari i,\\nManhattan Community Access Corp. v. Halleck, --- S. Ct. --- (No. 17-1702). MNN’s\\nargument before the Supreme Court, therefore, focuses on the Second Circuit’s\\ndetermination that MNN constituted a state actor, not the court’s determination that the\\npublic access channels constituted a public forum.\\n\\n Although not identified as an issue on appeal, MNN’s petition also took issue with\\nthe Second Circuit’s determination that the public access channels operated by MNN\\nconstituted a public forum. But that contention was entirely derivative of its state action\\nargument. In particular, MNN objected to the Second Circuit’s public forum conclusion\\nonly because the public access channels were privately operated and because, in its\\nopinion, the Second Circuit’s purportedly “categorical” holding that public access\\n(Continued)\\n\\n 28\\n\\n Not only does case law contradict Randall’s argument that public forum analysis\\n\\nnever applies to private property, her argument also fails because it makes no legal sense\\n\\nto establish a bright-line rule that forum analysis applies only to government-owned\\n\\nproperty. Why, for example, should the First Amendment allow a municipality to engage\\n\\nin viewpoint discrimination in curating a public library branch in leased space but not\\n\\nallow the municipality to engage in such discrimination in a library branch on\\n\\nmunicipally owned property? Cf. Bd. of Educ., Island Trees Union Free Sch. Dist. No.\\n\\n26 v. Pico, 457 U.S. 853, 870–71 (1982) (plurality op.) (“If a Democratic school board,\\n\\nmotivated by partisan affiliation, ordered removal of all books written by or in favor of\\n\\nRepublicans, few would doubt that the order violated the constitutional rights of the\\n\\nstudents denied access to those books.”). Or why should a municipality be allowed to\\n\\nengage in viewpoint discrimination when holding a virtual public meeting hosted on a\\n\\nprivate website when such discrimination would be unconstitutional if the meeting was\\n\\nheld in a governmental building? Cf. Lyrissa Lidsky, Public Forum 2.0, 91 B.U. L. Rev.\\n\\n1975, 1996 (2011) (“Just as the government can rent a building to use as a forum for\\n\\npublic debate and discussion, so, too, can it ‘rent’ a social media page for the promotion\\n\\n\\n\\nchannels constitute public forums ignore[d] “the far more critical issue of whether (and to\\nwhat extent) there is government control over a public access channel.” Id. at 19–20.\\n\\n Here, a government official acting under color of state law, Randall, exercised\\nunconstrained control over the aspect of the Chair’s Facebook Page giving rise to\\nDavison’s claim.\\n\\n\\n\\n\\n 29\\n\\nof public discussion.”). We do not believe the First Amendment draws such arbitrary\\n\\nlines.\\n\\n Randall’s second argument—that the Chair’s Facebook Page amounts to\\n\\n“government speech”—fails to recognize the meaningful difference between Randall’s\\n\\nposts to the Chair’s Facebook Page and the public comments and posts she invited in the\\n\\npage’s interactive space. To be sure, Randall’s comments and curated references on the\\n\\nChair’s Facebook Page to other Pages, personal profiles, and websites amount to\\n\\ngovernmental speech. See Sutliffe v. Epping School Dist., 584 F.3d 314, 329–30 (1st Cir.\\n\\n2009) (holding that municipality’s refusal to place hyperlink on municipal website to\\n\\nwebsite of group opposed to municipal budget constituted government speech); Page v.\\n\\nLexington Cty. School Dist. One, 531 F.3d 275, 283–85 (4th Cir. 2008) (holding that\\n\\nSchool District’s refusal to place hyperlink on its website to website of group that\\n\\nopposed School District’s position on pending legislation constituted government speech\\n\\nbecause, in part, “the links to other websites were selected by the School District alone as\\n\\nones that supported its own message”); Knight, 302 F. Supp. 3d at 571 (“[T]he\\n\\nPresident’s tweets are [not] susceptible to forum analysis . . . because the content is\\n\\ngovernment speech.”).\\n\\n But the interactive component of the Chair’s Facebook Page—the portion of the\\n\\nmiddle column in which the public can post comments, reply to posts, and “like”\\n\\ncomments and posts—is materially different. See Knight, 302 F. Supp. 3d at 572\\n\\n(distinguishing a government official’s tweets and “the interactive space for replies and\\n\\nretweets”). Randall placed no formal limitations on the ability of Facebook personal\\n\\n\\n 30\\n\\nprofiles and Pages to access the Chair’s Facebook Page and make comments and posts to\\n\\nthe interactive component of the page. On the contrary, she expressly invited posts to the\\n\\npage “from ANY Loudon citizen on ANY issues, request, criticism, complement or just\\n\\nyour thoughts.” J.A. 455. And comments and posts by users cannot be mistaken for\\n\\nRandall’s own speech because they identify the posting or replying personal profile or\\n\\nPage, and thereby distinguish that user from Randall.\\n\\n Contrary to Randall’s argument that the Chair’s Facebook Page, in its entirety,\\n\\namounts to government speech, the present case also is meaningfully distinguishable\\n\\nfrom the government speech framework identified in Pleasant Grove. There, a\\n\\nmunicipality denied a private religious group’s request to allow it to erect a “monument\\n\\nin a city park in which other donated monuments were previously erected,” including a\\n\\nmonument depicting a prominent symbol of a different religion. 555 U.S. at 464. The\\n\\nplaintiff religious group sought relief under the First Amendment, arguing that the city\\n\\npark constituted a traditional public forum, and therefore that the city could not reject the\\n\\nreligious group’s proposed monument when it had previously allowed construction of a\\n\\nmonument associated with another religion. Id. at 466.\\n\\n The Supreme Court held that the city did not violate the First Amendment because\\n\\nthe government speech framework, rather than forum analysis, applied to the conduct at\\n\\nissue. In reaching that conclusion, the Court emphasized that the city never “opened up\\n\\nthe Park for the placement of whatever permanent monuments might be offered by\\n\\nprivate donors.” Id. at 472–73. “Rather, the City has ‘effectively controlled’ the\\n\\nmessages sent by the monuments in the Park by exercising ‘final approval authority’ over\\n\\n\\n 31\\n\\ntheir selection.” Id. at 473. The Court further emphasized that “[t]he forum doctrine has\\n\\nbeen applied in situations in which government-owned property or a government\\n\\nprogram was capable of accommodating a large number of public speakers without\\n\\ndefeating the essential function of the land or the program.” Id. at 478. A city park,\\n\\nhowever, “can accommodate only a limited number of permanent monuments,” and\\n\\ntherefore a municipality cannot—and need not—provide park space for all who wish to\\n\\nerect a monument. Id.\\n\\n Here, Randall “effectively controlled” certain aspects of the Chair’s Facebook\\n\\nPage: she curated the Chair’s Facebook Page’s left and right columns and made posts to\\n\\nthe middle column. Id. at 472. But Randall also expressly opened the Chair’s Facebook\\n\\nPage’s middle column—its interactive space—for “ANY” user to post on “ANY issues,”\\n\\nJ.A. 455, and therefore did not retain “final approval authority” over that aspect of the\\n\\nChair’s Facebook Page, Pleasant Grove, 555 U.S. at 473. Just as the parkland\\n\\nsurrounding monuments in Pleasant Grove continued to constitute a public forum, even\\n\\nthough the monuments themselves constituted government speech, so too the interactive\\n\\ncomponent of the Chair’s Facebook Page constitutes a public forum, even though\\n\\nRandall’s curation of and posts to the Chair’s Facebook Page amount to government\\n\\nspeech. Additionally, the interactive component of the Chair’s Facebook Page does not\\n\\nface the same spacial limitations as those of the park in Pleasant Grove, but instead is\\n\\n“capable of accommodating a large number of public speakers without defeating [its]\\n\\nessential function.” Id. at 578. Accordingly, Pleasant Grove supports, rather than\\n\\n\\n\\n\\n 32\\n\\nundermines, our conclusion that the interactive component of the Chair’s Facebook Page\\n\\nconstitutes a public forum.\\n\\n Upon concluding that interactive component of the Chair’s Facebook Page\\n\\namounts to a public forum, we would normally need to determine whether it constitutes a\\n\\ntraditional public forum or designated or limited public forum. In the present case,\\n\\nhowever, we need not decide that question because Randall’s ban of Davison amounted\\n\\nto “viewpoint discrimination,” which is “prohibited in all forums.” See Child Evangelism\\n\\nFellowship of S.C. v. Anderson Sch. Dist. Five, 470 F.3d 1062, 1067 n.2 (4th Cir. 2006).\\n\\n“Viewpoint discrimination . . . ‘targets not subject matter, but particular views taken by\\n\\nspeakers on a subject.’” Id. (quoting Rosenberger v. Rector & Visitors of Univ. of Va.,\\n\\n515 U.S. 819, 829 (1995)). Viewpoint discrimination is apparent, for example, if a\\n\\ngovernment official’s decision to take a challenged action was “impermissibly motivated\\n\\nby a desire to suppress a particular point of view.” Cornelius, 473 U.S. at 812–13.\\n\\n Here, the district court found—as the record amply supports—that Randall banned\\n\\nDavison’s Virginia SGP Page because Davison posted a comment using that page\\n\\nalleging “corruption on the part of Loudoun County’s School Board involving conflicts\\n\\nof interests among the School Board and their family members.” Davison, 267 F. Supp.\\n\\n3d at 711. Although Randall stated that she had “no idea” whether Davison’s allegations\\n\\nwere “correct,” she nonetheless banned him because she viewed the allegations as\\n\\n“slanderous” and she “didn’t want [the allegations] on the site.” Id. at 717. Randall’s\\n\\ndecision to ban Davison because of his allegation of governmental corruption constitutes\\n\\nblack-letter viewpoint discrimination.\\n\\n\\n 33\\n\\n Put simply, Randall unconstitutionally sought to “suppress” Davison’s opinion\\n\\nthat there was corruption on the School Board. Cornelius, 473 U.S. at 812–13; see also,\\n\\ne.g., Rossignol, 316 F.3d at 521 (holding that sheriff’s deputies engaged in viewpoint\\n\\ndiscrimination when they seized an issue of a newspaper that criticized the county\\n\\nsheriff’s and his deputies’ performance of their official duties); Putnam Pit, Inc. v. City of\\n\\nCookeville, Tenn., 221 F.3d 834, 846 (6th Cir. 2000) (holding that a municipality engages\\n\\nin viewpoint discrimination if it refuses to link newspaper webpage to the city’s website\\n\\nsolely because the newspaper sought to expose municipal corruption); Knight, 302 F.\\n\\nSupp. 3d at 575 (holding that the President engaged in viewpoint discrimination when he\\n\\nblocked individuals from his Twitter account because the individuals “posted tweets that\\n\\ncriticized the President or his policies”). 7 That Randall’s action targeted comments\\n\\ncritical of the School Board members’ official actions and fitness for office renders the\\n\\nbanning all the more problematic as such speech “occupies the core of the protection\\n\\nafforded by the First Amendment.” Rossignol, 316 F.3d at 521 (quoting McIntyre v.\\n\\nOhio Elections Comm’n, 514 U.S. 334, 346 (1995)).\\n\\n In sum, the interactive component of the Chair’s Facebook Page constituted a\\n\\npublic forum, and Randall engaged in unconstitutional viewpoint discrimination when\\n\\nshe banned Davison’s Virginia SGP Page from that forum.\\n\\n\\n 7\\n Randall also asserts that she did not violate Davison’s First Amendment rights\\nbecause she banned his “Virginia SGP” Page, not his “Brian Davison” profile. Davison\\nis the sole operator of the “Virginia SGP” Page, however, and therefore the ban\\nimplicated his First Amendment rights. Randall fails to identify any case supporting her\\nposition, nor have we found any. Accordingly, we reject this argument.\\n\\n\\n 34\\n\\n III.\\n\\n In his cross-appeal, Davison asserts that the district court reversibly erred in two\\n\\nways: (A) by dismissing his claim against Randall in her official capacity and (B) by\\n\\ndenying his motion to amend his complaint to add the new First Amendment claim\\n\\nagainst the Loudoun Board. 8 We disagree.\\n\\n A.\\n\\n Davison first argues that the district court erred in dismissing his claim against\\n\\nRandall in her official capacity. Whereas “[p]ersonal-capacity suits seek to impose\\n\\npersonal liability upon a government official for actions [she] takes under color of state\\n\\nlaw,” Kentucky v. Graham, 473 U.S. 159, 165 (1985), “official capacity suits are ‘treated\\n\\nas suits against the municipality,’” Santos v. Frederick Cty. Bd. of Comm’rs, 725 F.3d\\n\\n451, 469 (4th Cir. 2013) (quoting Hafer v. Melo, 502 U.S. 21, 25 (1991)). Because\\n\\n“municipal liability under Section 1983 does not amount to respondeat superior . . . a\\n\\n 8\\n Davison also argues that the district court erred in rejecting his procedural due\\nprocess claims under the Fourteenth Amendment and an analogous provision in the\\nVirginia Constitution. Before the district court, Davison “flatly asserted that due process\\nalways requires the government to provide a hearing before imposing a prior restraint on\\nspeech,” and therefore that Randall violated Davison’s First Amendment rights by failing\\nto conduct a pre-ban hearing. Davison, 267 F. Supp. 3d at 719. The district court\\ncorrectly rejected Davison’s proposed categorical rule. Id. (citing Cafeteria & Rest.\\nWorkers Union Local 473, AFL-CIO v. McElroy, 367 U.S. 886, 895 (1961). And\\nDavison has abandoned that asserted categorical rule on appeal, Davison’s Br. at 49–50\\nn.19 (“[I]t might be permissible in certain contexts to delete an individual comment\\nwithout providing full pre-deprivation process . . . .”), instead arguing he is entitled to\\nrelief under the balancing test set forth in Mathews v. Eldridge, 424 U.S. 319, 334–35\\n(1976). Because Davison did not make that argument before the district court, we decline\\nto consider it now. See CoreTel Va., LLC v. Verizon Va., LLC, 808 F.3d 978, 988 (4th\\nCir. 2015).\\n\\n\\n\\n 35\\n\\nmunicipality is subject to Section 1983 liability only when its ‘policy or custom, whether\\n\\nmade by its lawmakers or by those whose edicts or acts may fairly be said to represent\\n\\nofficial policy, inflicts the [plaintiff’s] injury.’” Id. at 469–70 (quoting Monell v. Dep’t of\\n\\nSoc. Servs. of the City of N.Y., 436 U.S. 658, 694 (1978)).\\n\\n Here, the district court dismissed Davison’s official capacity claim because it\\n\\nfound that “no policy—whether County-wide or specific to [Randall]’s office—played\\n\\nany role in [Randall]’s decision to ban [Davison] from her [Chair’s Facebook Page].”\\n\\nDavison, 267 F. Supp. 3d at 715. We review the district court’s factual findings bearing\\n\\non whether Randall acted pursuant to a municipal policy or custom for clear error and its\\n\\nlegal conclusions de novo. Helton, 709 F.3d at 350.\\n\\n On appeal, Davison does not dispute the district court’s finding—which the record\\n\\namply supports—that Loudoun County did not promulgate a policy governing individual\\n\\nLoudoun Board members’ Facebook pages. Rather, Davison principally 9 argues that “the\\n\\ncounty can be held liable for Randall’s actions because in banning Davison, Randall\\n\\nacted as a municipal policymaker.” Davison’s Br. at 47.\\n\\n\\n\\n\\n 9\\n Davison also argues the Loudoun Board’s failure to adopt a policy pertaining to\\nindividual board members’ Facebook pages gives rise to an official capacity claim\\nbecause it establishes that the Loudoun “Board was—and remains—deliberately\\nindifferent to the likelihood of unconstitutional censorship and viewpoint-based\\ndiscrimination on individual supervisors’ social media sites.” Davison’s Br. at 46. But\\nDavison never advanced a “deliberate indifference” theory of municipal liability before\\nthe district court. Again, we decline to consider an argument Davison raises for the first\\ntime on appeal. See CoreTel, LLC, 808 F.3d at 988.\\n\\n\\n\\n 36\\n\\n Davison is correct that “municipal liability may be imposed for a single decision\\n\\nby municipal policymakers under appropriate circumstances.” Hunter v. Town of\\n\\nMocksville, N.C., 897 F.3d 538, 554 (4th Cir. 2018) (quoting Pembaur v. City of\\n\\nCincinnati, 475 U.S. 469, 480 (1986)). “[I]n assessing whether a municipality may be\\n\\nheld liable for constitutional or statutory violations of their decisionmakers, the\\n\\ntouchstone inquiry is whether ‘the decisionmaker possesses final authority to establish\\n\\nmunicipal policy with respect to the action ordered.’” Id. at 554–55 (emphasis added)\\n\\n(quoting Liverman v. City of Petersburg, 844 F.3d 400, 413 (4th Cir. 2016)).\\n\\n Here, Davison failed to put forward evidence establishing that Randall was a final\\n\\nmunicipal policymaker with regard to her banning of Davison from the Chair’s Facebook\\n\\nPage. On the contrary, record evidence establishes that the Loudoun Board retained\\n\\nauthority to establish municipal policy with respect to social media pages, as it adopted a\\n\\nsocial media policy governing the County’s official social media pages. Davison\\n\\nconcedes as much, arguing that the Loudoun Board “neglected . . . to extend its written\\n\\nguidelines to Board members’ official pages.” Davison’s Br. at 46. But that argument\\n\\npresupposes that the Loudoun Board—not Randall—had authority to establish municipal\\n\\npolicy with respect “to Board members’ official pages.”\\n\\n Davison nevertheless argues that the Loudoun Board “implicitly” delegated its\\n\\nfinal policymaking authority to Randall by not addressing individual Loudoun Board\\n\\nmembers’ official pages in its social media policy. Davison is correct that delegation of\\n\\nfinal policy making authority may be “implied from a continued course of knowing\\n\\nacquiescence by the governing body in the exercise of policymaking authority by an\\n\\n\\n 37\\n\\nagency or official.” Id. at 48 (quoting Spell v. McDaniel, 824 F.2d 1380, 1387 (4th Cir.\\n\\n1987)). But Davison identifies no evidence that the Loudoun Board knew of the Chair’s\\n\\nFacebook Page, let alone that it “aquiesce[d]” in Randall’s administration of the page and\\n\\nbanning of Davison, in particular. On the contrary, the district court found that Randall\\n\\nmade a one-off, “unilateral decision to ban [Davison] in the heat of the moment, and\\n\\nreconsidered soon thereafter,” Davison, 267 F. Supp. 3d at 715—before the Loudoun\\n\\nBoard had a chance to learn of her action. In such circumstances, the district court did\\n\\nnot reversibly err in rejecting Davison’s official capacity claim.\\n\\n B.\\n\\n Next, Davison argues that the district court erred in denying him leave to amend\\n\\nhis complaint to add a claim that “the County violates the First Amendment by\\n\\nmaintaining a limited public forum on Facebook,” when policies imposed by Facebook,\\n\\nrather than the County, restrain, or have the potential to restrain, speech. J.A. 74. “A\\n\\ndistrict court may deny a motion to amend when the amendment would be prejudicial to\\n\\nthe opposing party, the moving party has acted in bad faith, or the amendment would be\\n\\nfutile.” Equal Rights Ctr. v. Niles Bolton Assocs., 602 F.3d 597, 603 (4th Cir. 2010).\\n\\nThe magistrate judge recommended—and the district court agreed—that Davison be\\n\\ndenied leave to amend on grounds of both futility and prejudice. We review for abuse of\\n\\ndiscretion a district court’s denial of leave to amend for prejudice, whereas we review de\\n\\nnovo a district court’s denial of leave to amend on the basis of futility. See U.S. ex rel.\\n\\nAhumada v. NISH, 756 F.3d 268, 274 (4th Cir. 2014).\\n\\n\\n\\n\\n 38\\n\\n Regarding prejudice, the district court determined that the amendment came “too\\n\\nlate in these proceedings” and would “add a new, novel legal theory to the case after the\\n\\nclose of discovery, after the existing claims against [the Loudoun Board] have been\\n\\nshown to be meritless, after the point at which Defendants could have addressed the\\n\\nclaim in briefing before trial, and on the eve of trial.” J.A. 74. The district court did not\\n\\nabuse its discretion in denying leave to amend in such circumstances. See, e.g., Equal\\n\\nRights Ctr., 602 F.3d at 603–04 (holding that district court did not abuse its discretion in\\n\\ndenying leave to amend on the basis of prejudice when amendment came after the close\\n\\nof discovery and “on the eve of the deadline for dispositive motions” and therefore\\n\\n“would [have] change[d] the nature of the litigation”); Deasy v. Hill, 833 F.2d 38, 41 (4th\\n\\nCir. 1987) (affirming denial of leave to amend on grounds of prejudice when “the motion\\n\\nto amend came right before trial and after discovery was complete”).\\n\\n Although we affirm the district court’s judgment on the basis of its finding of\\n\\nprejudice, we do not concur in its conclusion as to futility. “Futility is apparent if the\\n\\nproposed amended complaint fails to state a claim under the applicable rules and\\n\\naccompanying standards.” Katyle v. Penn Nat. Gaming, Inc., 637 F.3d 462, 471 (4th Cir.\\n\\n2011). Accordingly, Davison’s proposed amendment was futile if the new claim would\\n\\nnot have survived a motion to dismiss under Federal Rule of Civil Procedure 12(b)(6).\\n\\nSee Runnion ex rel. Runnion v. Girl Scouts of Greater Chicago & Nw. Ind., 786 F.3d 510,\\n\\n524 (7th Cir. 2015) (“[W]hen the basis for denial is futility, we apply the legal\\n\\nsufficiency standard of Rule 12(b)(6) to determine whether the proposed amended\\n\\ncomplaint fails to state a claim.”).\\n\\n\\n 39\\n\\n Davison’s proposed First Amendment claim deals not with the Chair’s Facebook\\n\\nPage—which the Loudoun Board did not authorize or attempt to regulate—but rather\\n\\nwith Loudoun County’s official Facebook Pages created and maintained pursuant to the\\n\\nLoudoun Board’s social media policy. As with his claims related to the Chair’s\\n\\nFacebook Page, Davison alleged that the Facebook Pages created and maintained by the\\n\\nLoudoun Board constituted public forums subject to the First Amendment. Davison\\n\\ntheorized that the Loudoun Board’s decision to use Facebook as its social media forum\\n\\nviolated his First Amendment rights because Facebook rules permit individual\\n\\n“requesting” users to ban other personal profiles and Pages such that the banned users can\\n\\nno longer see posts authored by the requesting users. In such circumstances, the banned\\n\\nusers “cannot see [the requesting user’s] comment[s] or participate in the discussion\\n\\nsurrounding the [requesting] party’s comment.” Davison’s Br. at 59. Davison’s\\n\\nproposed amended complaint asserted that “this scenario violates the First Amendment\\n\\nbecause Loudoun County has effectively enabled third parties to exclude discussion\\n\\nwithin a public forum—something a government body could not permissibly do in a\\n\\nphysical forum.” Id. at 59–60 (internal citation omitted). Put differently, Davison\\n\\ntheorized that Loudoun County violated the First Amendment by choosing to use\\n\\nFacebook as a public forum, when rules imposed by Facebook allow private users to\\n\\nrestrict access to their posts—and comments on and responses to those posts—including\\n\\nposts to any municipal Facebook Page.\\n\\n No court appears to have addressed that novel legal theory. And although the First\\n\\nAmendment constrains only government policies, not policies established by private\\n\\n\\n 40\\n\\nentities, one can conceive of a colorable legal argument that a governmental actor’s\\n\\ndecision to select a private social media website for use as a public forum—and therefore\\n\\nselect that website’s suite of rules and regulations—could violate the First Amendment, if\\n\\nthe private website included certain types of exclusionary rules. For example, if the\\n\\ngovernment chose as its electronic public forum a social media site that allowed only\\n\\nregistered members of one political party to post and comment, there would seem to be a\\n\\ncompelling argument that the government’s selection of that social media site violated the\\n\\nFirst Amendment rights of members of other political parties, even if the partisan\\n\\nrestriction was imposed by the private company, not the governmental body. Such a\\n\\nrestriction would be seem to be no different than a municipality choosing to hold a town\\n\\nhall meeting in a venue that refused admission to individuals associated with a disfavored\\n\\npolitical party or viewpoint. Cf. DeBoer v. Village of Oak Park, 267 F.3d 558, 571 (7th\\n\\nCir. 2001) (“[T]he government engages in viewpoint discrimination when it denies access\\n\\nto a speaker solely to suppress the point of view he espouses on an otherwise includible\\n\\nsubject.”).\\n\\n Given that Davison’s proposed claim asserted a novel and colorable legal theory\\n\\nand that “Rule 12(b)(6) dismissals are especially disfavored in cases where the complaint\\n\\nsets forth a novel legal theory that can best be assessed after factual development,”\\n\\nWright v. North Carolina, 787 F.3d 256, 263 (4th Cir. 2015) (internal quotation marks\\n\\nomitted), we affirm the district court’s denial of Davison’s motion for leave to amend his\\n\\ncomplaint on the basis of its finding of prejudice but not on the basis of futility.\\n\\n IV.\\n\\n\\n 41\\n\\nFor the foregoing reasons, we affirm the judgment of the district court.\\n\\n AFFIRMED\\n\\n\\n\\n\\n 42\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4356556/\", \"author_raw\": \"WYNN, Circuit Judge:\"}, {\"author\": \"BARBARA MILANO KEENAN, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"BARBARA MILANO KEENAN, Circuit Judge, concurring:\\n\\n I join the well-reasoned majority opinion in full. I agree that the central “aspects\\n\\nof the Chair’s Facebook Page bear the hallmarks of a public forum.” I am particularly\\n\\npersuaded by the facts concerning Randall’s conduct of impressing the Chair Facebook\\n\\nPage with the trappings of a “government official” Facebook Page and of inviting\\n\\ncitizens to comment, without restriction, on matters of public concern. Accordingly,\\n\\nunder our precedent, I agree that Randall’s conduct of banning Davison’s Virginia SGP\\n\\nPage based on the content of a comment is attributable to the government and violates the\\n\\nFirst Amendment. See Rossignol v. Voorhaar, 316 F.3d 516, 523-25 (4th Cir. 2003).\\n\\n I nonetheless write separately to call attention to two issues regarding\\n\\ngovernmental use of social media that do not fit neatly into our precedent. First, I\\n\\nquestion whether any and all public officials, regardless of their roles, should be treated\\n\\nequally in their ability to open a public forum on social media. The Supreme Court\\n\\nrecently cited a series of decisions in which “a unit of government” had created a public\\n\\nforum. Matal v. Tam, 137 S. Ct. 1744, 1763 (2017) (emphasis added) (citing cases); see\\n\\nalso Pleasant Grove City v. Summum, 555 U.S. 460, 470 (2009) (“a government entity\\n\\nmay create a forum” (emphasis added)). However, it appears to be an open question\\n\\nwhether an individual public official serving in a legislative capacity qualifies as a unit of\\n\\ngovernment or a government entity for purposes of her ability to open a public forum.\\n\\nInstead, our precedent merely directs us to consider whether the challenged action “bore a\\n\\nsufficiently close nexus” with the government to be “fairly treated” as that of the\\n\\n\\n\\n\\n 43\\n\\ngovernment itself. Rossignol, 316 F.3d at 525 (internal quotation marks and citation\\n\\nomitted).\\n\\n The nature and extent of a public official’s authority should have some bearing on\\n\\nthe official’s ability to open a public forum on social media. While the nine-member\\n\\nLoudoun County Board of Supervisors (the Board) serves to set policies, adopt\\n\\nordinances, and appropriate funds, the Chair simply is empowered individually to oversee\\n\\nmeetings and to set agendas. 1 The record before us is silent regarding the Chair’s\\n\\nauthority to take any official action on her own.\\n\\n In contrast, certain elected executive officials, under given circumstances, can\\n\\nconduct government business and set official policy unilaterally, including through the\\n\\nuse of social media. See, e.g., Knight First Amendment Inst. at Columbia Univ. v. Trump,\\n\\n302 F. Supp. 3d 541, 567 (S.D.N.Y. 2018) (discussing President Donald J. Trump’s use\\n\\nof his Twitter account to appoint and remove officers and conduct foreign policy), appeal\\n\\ndocketed, No. 18-1691 (2d Cir. Oct. 24, 2018); Schisler v. State, 907 A.2d 175, 218-20\\n\\n(Md. 2006) (describing the governor’s unilateral power to remove certain officers). The\\n\\nrelevance of such distinctions to a public official’s ability to create a public forum on\\n\\nsocial media is a matter that should be addressed by the Supreme Court. Because this is\\n\\nan open question, we are bound by current precedent and, for the reasons set forth in the\\n\\n\\n\\n 1\\n See Bd. of Supervisors Operations Manual, LOUDOUN CTY., VA chs. 2-3,\\nhttps://www.loudoun.gov/DocumentCenter/View/117084/Board-of-Supervisors-\\nOperations-Manual-2016-2020 (last visited Dec. 20, 2018) (saved as ECF opinion\\nattachment).\\n\\n\\n 44\\n\\nmajority opinion, Randall as a single board member acted under of color of law and\\n\\nopened a public forum on Facebook.\\n\\n Second, the Supreme Court should consider further the reach of the First\\n\\nAmendment in the context of social media. I acknowledge that the Supreme Court has\\n\\nreferred to social media as “the modern public square,” Packingham v. North Carolina,\\n\\n137 S. Ct. 1730, 1737 (2017), implying that First Amendment principles protecting\\n\\nspeech from government intrusion do extend to social media. However, the interplay\\n\\nbetween private companies hosting social media sites and government actors managing\\n\\nthose sites necessarily blurs the line regarding which party is responsible for burdens\\n\\nplaced on a participant’s speech.\\n\\n For example, hate speech is protected under the First Amendment. See Matal, 137\\n\\nS. Ct. at 1763-64 (holding that the disparagement clause of the Lanham Act violated the\\n\\nFirst Amendment free speech clause because it prohibited hate speech). But social media\\n\\ncompanies like Facebook and others have policies forbidding hate speech on their\\n\\nplatforms. 2 Thus, while a government official, who under color of law has opened a\\n\\npublic forum on a social media platform like Facebook, could not ban a user’s comment\\n\\ncontaining hate speech, that official could report the hate speech to Facebook. And\\n\\nFacebook personnel could ban the user’s comment, arguably circumventing First\\n\\nAmendment protections.\\n\\n\\n 2\\n See, e.g., Cmty. Standards, Hate Speech, FACEBOOK, https://www.facebook.com/\\ncommunitystandards/hate_speech (last visited Dec. 20, 2018) (saved as ECF opinion\\nattachment).\\n\\n\\n\\n 45\\n\\n Admittedly, this question is not directly presented in the present case, given that\\n\\nthe public official, not a Facebook employee, acted to restrict speech. Nonetheless, cases\\n\\nnecessarily will arise requiring courts to consider the nuances of social media and their\\n\\nvarious roles in hosting public forums established by government officials or entities.\\n\\nTherefore, in my view, courts must exercise great caution when examining these issues,\\n\\nas we await further guidance from the Supreme Court on the First Amendment’s reach\\n\\ninto social media.\\n\\n\\n\\n\\n 46\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4356556/\", \"author_raw\": \"BARBARA MILANO KEENAN, Circuit Judge, concurring\"}]}"},"judge1":{"kind":"string","value":"KEENAN"},"judge2":{"kind":"string","value":"WYNN"},"judge3":{"kind":"string","value":"HARRIS"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":2,"string":"2"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":1,"string":"1"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4579303/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Brian DAVISON, Plaintiff - Appellee, v. Phyllis RANDALL, in Her Official and Individual Capacity, Defendant - Appellant, and Loudoun County Board of Supervisors, in Their Official and Individual Capacities; Leo Rogers, in His Official Capacity; Tony Buffington, in His Official Capacity; Ron Meyer, in His Official Capacity; Geary Higgins, in His Official Capacity, Defendants. Local Government Attorneys of Virginia, Inc.; International Municipal Lawyers Association ; Virginia Association of Counties; Virginia Municipal League, Amici Supporting Appellant, American Civil Liberties Union; ACLU of Virginia ; ACLU of Maryland; ACLU of North Carolina; ACLU of South Carolina; ACLU of West Virginia, Amici Supporting Appellee. Brian C. Davison, Plaintiff - Appellant, v. Phyllis Randall, in Her Official and Individual Capacity; Loudoun County Board of Supervisors, in Their Official and Individual Capacities, Defendants - Appellees, and Leo Rogers, in His Official Capacity; Tony Buffington, in His Official Capacity; Ron Meyer, in His Official Capacity; Geary Higgins, in His Official Capacity, Defendants.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-07\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-2002\n\n\nBRIAN DAVISON,\n\n Plaintiff - Appellee,\n\n v.\n\nPHYLLIS RANDALL, In her official and individual capacity,\n\n Defendant - Appellant,\n\n and\n\nLOUDOUN COUNTY BOARD OF SUPERVISORS, In their official and\nindividual capacities; LEO ROGERS, In his official capacity; TONY\nBUFFINGTON, In his official capacity; RON MEYER, In his official capacity;\nGEARY HIGGINS, In his official capacity,\n\n Defendants.\n\n------------------------------\n\nLOCAL GOVERNMENT ATTORNEYS OF VIRGINIA, INC.;\nINTERNATIONAL MUNICIPAL LAWYERS ASSOCIATION; VIRGINIA\nASSOCIATION OF COUNTIES; VIRGINIA MUNICIPAL LEAGUE,\n\n Amici Supporting Appellant,\n\nAMERICAN CIVIL LIBERTIES UNION; ACLU OF VIRGINIA; ACLU OF\nMARYLAND; ACLU OF NORTH CAROLINA; ACLU OF SOUTH\nCAROLINA; ACLU OF WEST VIRGINIA,\n\n Amici Supporting Appellee.\n\n No. 17-2003\n\n\nBRIAN C. DAVISON,\n\n Plaintiff - Appellant,\n\n v.\n\nPHYLLIS RANDALL, In her official and individual capacity; LOUDOUN\nCOUNTY BOARD OF SUPERVISORS, In their official and individual\ncapacities,\n\n Defendants - Appellees,\n\n and\n\nLEO ROGERS, In his official capacity; TONY BUFFINGTON, In his official\ncapacity; RON MEYER, In his official capacity; GEARY HIGGINS, In his\nofficial capacity,\n\n Defendants.\n\n\nAppeals from the United States District Court for the Eastern District of Virginia, at\nAlexandria. James C. Cacheris, Senior District Judge. (1:16-cv-00932-JCC-IDD)\n\n\nArgued: September 26, 2018 Decided: January 7, 2019\n\n\nBefore KEENAN, WYNN, and HARRIS, Circuit Judges.\n\n\nAffirmed by published opinion. Judge Wynn wrote the opinion, in which Judge Keenan\nand Judge Harris concurred. Judge Keenan wrote a separate concurring opinion.\n\n\nARGUED: Scott E. Gant, BOIES SCHILLER FLEXNER, LLP, Washington, D.C.; Leo\nP. Rogers, LOUDON COUNTY ATTORNEY, Leesburg, Virginia, for Appellant/Cross-\nAppellee. Katherine A. Fallow, KNIGHT FIRST AMENDMENT INSTITUTE AT\n\n\n 2\n\nCOLUMBIA UNIVERSITY, New York, New York, for Appellee/Cross-Appellant. ON\nBRIEF: Aaron E. Nathan, BOIES SCHILLER FLEXNER LLP, Washington, D.C., for\nAppellant/Cross-Appellee. Jameel Jaffer, Carrie DeCell, KNIGHT FIRST\nAMENDMENT INSTITUTE AT COLUMBIA UNIVERSITY, New York, New York,\nfor Appellee/Cross-Appellant. Vishal Agraharkar, AMERICAN CIVIL LIBERTIES\nUNION FOUNDATION OF VIRGINIA, Richmond, Virginia; Esha Bhandari, Vera\nEidelman, AMERICAN CIVIL LIBERTIES UNION FOUNDATION, New York, New\nYork; Susan K. Dunn, ACLU OF SC FOUNDATION, INC., Charleston, South Carolina;\nChristopher Brook, AMERICAN CIVIL LIBERTIES UNION OF NORTH CAROLINA\nLEGAL FOUNDATION, Raleigh, North Carolina; Deborah A. Jeon, ACLU\nFOUNDATION OF MARYLAND, Baltimore, Maryland; Jennifer D. Oliva, ACLU OF\nWEST VIRGINIA FOUNDATION, Charleston, West Virginia, for Amici American\nCivil Liberties Union, ACLU of Virginia, ACLU of Maryland, ACLU of North Carolina,\nACLU of South Carolina, and ACLU of West Virginia. Joshua A. Geltzer, Douglas\nLetter, Amy L. Marshak, Mary B. McCord, INSTITUTE FOR CONSTITUTIONAL\nADVOCACY AND PROTECTION GEORGETOWN UNIVERSITY LAW CENTER,\nWashington, D.C.; Kwaku A. Akowuah, Christopher C. Fonzone, Kate Heinzelman,\nSIDLEY AUSTIN LLP, Washington, D.C., for Amici Curiae First Amendment Legal\nScholars.\n\n\n\n\n 3\n\nWYNN, Circuit Judge:\n\n Phyllis Randall, Chair of the Loudoun County, Virginia, Board of Supervisors (the\n\n“Loudoun Board”), brings this appeal, arguing that the district court erred in concluding\n\nthat she violated the First Amendment rights of one of her constituents, Brian Davison,\n\nwhen she banned Davison from the “Chair Phyllis J. Randall” Facebook page she\n\nadministered. In a cross appeal, Davison principally argues that the district court erred\n\nin dismissing his procedural due process claim premised on the ban. For the reasons that\n\nfollow, we affirm.\n\n I.\n\n A.\n\n Randall has chaired the Loudoun County Board of Supervisors since January 1,\n\n2016. The day before she was sworn in as chair, Randall created the “Chair Phyllis J.\n\nRandall” Facebook Page (the “Chair’s Facebook Page”). According to Facebook, Inc.,\n\nunlike personal Facebook profiles, which are for non-commercial use and represent\n\nindividual people, Facebook “Pages”—like the Chair’s Facebook Page—“help\n\nbusinesses, organizations, and brands share their stories and connect with people.” J.A.\n\n403. “Pages are managed by people who have personal profiles,” the company explains.\n\nJ.A. 403. In addition to the Chair’s Facebook Page, Randall created and maintained two\n\nother Facebook profiles: a personal profile and a Page devoted to her campaign. Randall\n\nclassified her campaign page as belonging to a “politician” and used no designation for\n\nher personal profile, but she designated the Chair’s Facebook Page as a “governmental\n\nofficial” page. J.A. 209–10.\n\n\n 4\n\n Randall and her Chief of Staff, Jeanine Arnett, share administrative control over\n\nthe Chair’s Facebook Page, although Randall almost exclusively controls the page’s\n\ncontent. On her campaign page, Randall characterized the Chair’s Facebook Page as her\n\n“county Facebook page” stating:\n\n I really want to hear from ANY Loudoun citizen on ANY issues, request,\n criticism, complement or just your thoughts. However, I really try to keep\n back and forth conversations (as opposed to one time information items\n such as road closures) on my county Facebook page (Chair Phyllis J.\n Randall) or County email (Phyllis.randall@loudoun.gov). Having back and\n forth constituent conversations are Foiable ([Freedom of Information Act])\n so if you could reach out to me on these mediums that would be\n appreciated.\n\nJ.A. 455 (emphasis added).\n\n The Chair’s Facebook Page includes three columns. The left column, which is\n\ntopped by a picture of Randall, includes several links to allow visitors to quickly navigate\n\nthe contents of the Chair’s Facebook Page.\n\n The middle column, which is organized in reverse chronological order similar to a\n\npersonal profile’s News Feed, is composed of posts by Randall and comments by\n\nFacebook users on those posts. Randall’s posts are almost always directed to “Loudoun,”\n\nsee, e.g., J.A. 408–10, and deal with numerous aspects of Randall’s official\n\nresponsibilities. For example, Randall used the Chair’s Facebook Page to notify the\n\npublic about upcoming Loudoun Board meetings, and the subjects to be discussed during\n\nthose meetings. Randall also used the page to inform Loudoun County residents about\n\nsignificant public safety issues. See, e.g., J.A. 412 (stating that Loudoun Board had\n\n“been informed by the Sheriff’s Office about the non-legitimate threat made on social\n\n\n\n 5\n\nmedia toward Dominion High School in Sterling”); J.A. 418 (reporting that she “ha[d]\n\nbeen briefed regarding the student falling from the water tower this morning” and\n\nadvising the public to “not make any assumptions but wait for information”). And\n\nRandall used the Chair’s Facebook Page to coordinate Loudoun County’s response to a\n\nlarge snow storm, including to communicate with constituents regarding which municipal\n\nstreets required plowing.\n\n Other posts by Randall to the Chair’s Facebook Page invited members of the\n\npublic to apply to participate on a public commission and to participate in public\n\nmeetings regarding key issues facing Loudoun County residents, such as revised flood\n\nplain zones and the Zika virus. Randall also authored posts regarding a variety of trips\n\nand meetings she had taken in furtherance of Loudoun County business. E.g., J.A. 408\n\n(reporting that Randall “address[ed] the (county) role in Treatment” at a “regional\n\nconference on Opioid and Substance Abuse Addiction”); J.A. 410 (stating that Randall\n\nrepresented Loudoun County at its “annual credit rating presentation” in New York); J.A.\n\n415 (informing public of trip to Loudoun’s “Sister City” in Germany); J.A. 426\n\n(reporting that Randall was “in Richmond lobbying for [Loudoun County’s] legislative\n\nprogram”). Finally, Randall used the page to advise the public regarding official actions\n\ntaken by the Loudoun Board. E.g., J.A. 433 (reporting that Loudoun Board “approved\n\nfunding for new breathing apparatus for our Loudoun Firefighters”); J.A. 442 (listing\n\nseveral “proclamations of note” by the Loudoun Board); J.A. 443 (informing public that\n\nLoudoun Board “adopted a budget for Fiscal Year 2017 totaling $2.46 billion for the\n\ngeneral county government and schools”). Although Randall’s posts on the Chair’s\n\n\n 6\n\nFacebook Page principally addressed her official responsibilities, a few posts addressed\n\ntopics less closely related to her official activities such as her affection for the German\n\nlanguage or pride in becoming an organ donor.\n\n Members of the public, including Davison, “liked” 1 or commented on several of\n\nRandall’s posts on the Chair’s Facebook Page. Each “like” or comment identified the\n\nname of the personal profile or Page of the authoring party. Many of the comments\n\nthanked Randall and the Loudoun Board for representing the public’s interests. Other\n\nposts by members of the public offered feedback on various issues faced by Randall and\n\nthe Loudoun Board. E.g., J.A. 427 (stating that “[p]utting recreation in a flood plain is\n\nnot a good idea”); J.A. 448 (stating that “more needs to be done with the explosion of\n\nLyme disease in Loudoun”). And other comments dealt with constituent-specific issues.\n\nE.g., J.A. 415 (constituent stating, in response to post by Randall regarding visit to\n\nLoudoun County’s “Sister City” in Germany, that constituent’s “daughter is interested in\n\nexchange programs”); J.A. 454 (stating that “there [we]re no [snow] plows to be seen” in\n\na particular neighborhood). Finally, several comments, including a number authored by\n\nDavison, criticized the Loudoun Board, generally, and Randall, in particular, for actions\n\ntaken in their official capacities. E.g., J.A. 429–30 (Davison criticizing public school\n\nsystem budget and expenditures); J.A. 438–39 (member of public criticizing\n\ngovernmental entity’s inspection of farm, claiming it failed to uncover animal abuse);\n\n\n 1\n “‘Liking’ on Facebook is a way for Facebook users to share information with\neach other.” Bland v. Roberts, 730 F.3d 368, 385 (4th Cir. 2013).\n\n\n\n 7\n\nJ.A. 449 (Davison characterizing question he posed at Loudoun Board and Loudoun\n\nSchool Board joint town hall). On some occasions, Randall responded to these\n\ncomments or criticisms.\n\n In the right column of the Chair’s Facebook Page, the page is identified as a\n\n“government official” page. It provides contact information for Randall’s county office,\n\nincluding her office telephone number, Randall’s official county email address, and the\n\ninternet address for the official county website. The column also identifies how many\n\nand which Facebook personal profiles and Pages “like” and “follow” the Chair’s\n\nFacebook Page. 2 And the column includes a list of personal profiles and Pages “liked”\n\nby the Chair’s Facebook Page.\n\n Randall publicized the Chair’s Facebook Page in her official “Chair Phyllis J.\n\nRandall” newsletter, which is prepared by County employees, hosted on the County’s\n\nwebsite, and distributed to Loudoun citizens using Randall’s official county email\n\naccount. The newsletter ends with the words “STAY CONNECTED” and a Facebook\n\nicon that hyperlinks to the Chair’s Facebook Page. Randall also highlighted the Chair’s\n\nFacebook Page in “Winter Storm Information” notices emailed from her official county\n\naccount to Loudoun County residents, advising recipients to “Visit [the Chair’s Facebook\n\nPage] for Updates.” J.A. 341–42, 344.\n\n 2\n According to Facebook, “[l]iking a Facebook Page means you are connecting to\nthat Page. When you connect to a Page, it will appear in [a user’s] timeline and [the user]\nwill appear on the page as a person who likes that Page. The Page will also be able to\npost content into [the user’s] News Feed.” Bland, 730 F.3d at 385 (internal quotation\nmarks omitted).\n\n\n\n 8\n\n Davison, an outspoken resident of Loudoun County, apparently largely focuses his\n\ncivic engagement and expression on “the funding and . . . management of public\n\nschools.” J.A. 95. To that end, he has repeatedly expressed concern about “School Board\n\nmembers failing to disclose personal conflicts as required by law before voting on\n\nfinancial transactions before the School Board.” J.A. 96.\n\n On February 3, 2016, Davison attended a Loudoun town hall meeting that\n\nincluded the Loudoun County School Board and Randall. At the meeting, Davison\n\nsubmitted a question implying that certain School Board members had acted unethically\n\nin approving financial transactions. Randall volunteered to answer the question but\n\ncharacterized it as a “set-up question” that she did not “appreciate.” J.A. 103. Shortly\n\nafter Randall answered the question—and while the town hall meeting was still\n\nongoing—Davison posted a message on Twitter in which he tagged Randall:\n\n“@ChairRandall ‘set up question’? You might want to strictly follow FOIA and the\n\nCOIA as well.” J.A. 470–71.\n\n Later that evening, Randall posted about the town hall meeting on the Chair’s\n\nFacebook Page, describing “what was generally discussed at the meeting.” J.A. 268. In\n\nresponse, Davison then used one of the Facebook Pages he manages through his personal\n\nFacebook profile—“Virginia SGP,” which Davison frequently uses to post political\n\ncommentary—to comment on Randall’s post about the town hall meeting. Although\n\nneither Davison nor Randall remember the precise content of Davison’s comment,\n\nRandall testified that it contained “accusations” regarding School Board members’ and\n\ntheir families’ putative conflicts of interest related to municipal financial transactions,\n\n\n 9\n\nsuggesting, in Randall’s opinion, that School Board members had been “taking kickback\n\nmoney.” See J.A. 268–69, 289–90. Randall stated that she “had no idea if any of th[e]\n\n[accusations] w[ere] correct,” but she determined that the post was “probably not\n\nsomething [she] want[ed] to leave” on the Chair’s Facebook Page. J.A. 269. Randall\n\nthen “deleted the whole post,” including her original post regarding the town hall\n\nmeeting, Davison’s comment and replies thereto, and all other public comments. J.A.\n\n269. Randall also banned Davison’s Virginia SGP Page from the Chair’s Facebook Page,\n\nwhich precluded Davison from using his Virginia SGP Page from commenting on the\n\nChair’s Facebook Page. The next morning, about twelve hours later, Randall\n\nreconsidered her actions and unbanned Davison’s Virginia SGP Page.\n\n B.\n\n On November 3, 2016, Davison filed an amended complaint seeking declaratory\n\nand injunctive relief under 42 U.S.C. § 1983 against Randall, in both her official and\n\nindividual capacities, and the Loudoun Board alleging that the “banning of [Davison]\n\nfrom commenting on [the Chair’s Facebook Page] is viewpoint discrimination.” J.A. 31.\n\nDavison further alleged that the ban violated his procedural due process rights protected\n\nby the Fourteenth Amendment because “Randall blocked Davison’s constitutionally\n\nprotected speech on [the Chair’s Facebook Page], a limited public forum, without prior\n\nnotice and without providing an opportunity for appealing [her] decision.” J.A. 32.\n\nDavison did not challenge Randall’s deletion of his post.\n\n On March 6, 2017—four days before the close of discovery and approximately\n\ntwo months before trial—Davison moved for leave to amend his complaint a second time\n\n\n 10\n\nto add claims under the Virginia Constitution that were materially indistinguishable from\n\nhis previously asserted First and Fourteenth Amendment claims premised on the ban, as\n\nwell as a separate First Amendment claim against the Loudoun Board. Davison’s\n\nproposed new First Amendment claim theorized that the County violated his free speech\n\nrights by choosing to use Facebook Pages as public forums, when Facebook allows\n\nprivate users to restrict access to their posts, including posts to any Page a municipality\n\ndesignates as a limited public forum. Pl.’s Mem. in Supp. of Mot. for Leave to File\n\nSecond Am. Compl. 3–9, Davison v. Loudoun County Bd. of Supervisors, 16-cv-932-\n\nJCC-IDD, ECF No. 68. The district court referred the motion to a magistrate judge, who\n\ngranted leave to amend regarding the claims under the Virginia Constitution but denied\n\nleave as to the new First Amendment claim against the Loudoun Board. Davison lodged\n\nobjections to the magistrate judge’s partial denial of leave to amend, which objections the\n\ndistrict court overruled.\n\n Around the same time, Randall and the Loudoun Board each moved for summary\n\njudgment. The Loudoun Board asserted that the municipality could not be held liable for\n\nRandall’s banning of Davison from the Chair’s Facebook Page because the Chair’s\n\nFacebook Page was not an official municipal page and because Randall, not the Loudoun\n\nBoard as a body, was solely responsible for creating and administering the Chair’s\n\nFacebook Page. The Loudoun Board and Randall further asserted that the Chair’s\n\nFacebook Page did not amount to a public forum, and therefore Randall’s ban of\n\nDavison’s Virginia SGP Page did not implicate his free speech or procedural due process\n\nrights. Finally, Randall asserted that she was entitled to qualified immunity.\n\n\n 11\n\n On May 10, 2017, the district court granted summary judgment in favor of the\n\nLoudoun Board, dismissing it from the suit. But as to Randall, the district court\n\nconcluded that Davison’s evidence established a material dispute of fact as to whether the\n\nChair’s Facebook Page amounted to a limited public forum and whether Randall, in her\n\nindividual capacity, acted under color of state law in banning Davison from the Chair’s\n\nFacebook Page. Davison v. Loudoun Cty. Bd. of Supervisors, No. 1:16-cv-932, 2017 WL\n\n1929406, at *6–9 (E.D. Va. May 10, 2017). The district court also rejected Randall’s\n\nqualified immunity argument. Id. at *8.\n\n Following a one-day bench trial of Davison’s claims against Randall, the district\n\ncourt issued a memorandum opinion and order awarding judgment in Davison’s favor on\n\nhis claims under the First Amendment and the analogous free speech provision in the\n\nVirginia Constitution. See Davison v. Loudoun Cty. Bd. of Supervisors, 267 F. Supp. 3d\n\n702, 714–18 (E.D. Va. 2017). The district court further entered judgment in Randall’s\n\nfavor on Davison’s federal and state procedural due process claims. Id. at 719–22. As to\n\nremedy, the district court denied Davison’s request for injunctive relief but granted\n\nDavison’s request for a declaratory judgment to resolve the “uncertainty regarding the\n\nlegal status of [the Chair’s Facebook Page].” Id. at 723.\n\n Randall and Davison, respectively, filed this appeal and cross appeal.\n\n II.\n\n On appeal, Randall argues that (A) Davison failed to establish standing to obtain\n\nprospective declaratory relief based on Randall’s alleged First Amendment violation; (B)\n\nthe district court erred in concluding that Randall acted under “color of state law” when\n\n\n 12\n\nshe banned Davison’s Virginia SGP Page from the Chair’s Facebook Page; and (C) the\n\ndistrict court erred in concluding that Randall’s banning of Davison’s Virginia SGP Page\n\nviolated the First Amendment.\n\n A.\n\n Notwithstanding that she did not challenge Davison’s standing below—and\n\ntherefore that the district court never squarely addressed his standing—Randall now\n\nargues that Davison failed to establish Article III standing to support the district court’s\n\naward of prospective declaratory relief. Even though Defendants did not challenge\n\nDavison’s standing below, “standing to sue is a jurisdictional issue of constitutional\n\ndimensions, and it may be raised and addressed for the first time on appeal.” Hodges v.\n\nAbraham, 300 F.3d 432, 443 (4th Cir. 2002). This Court reviews de novo “whether a\n\ndistrict court possessed jurisdiction in a declaratory judgment proceeding.” Volvo Const.\n\nEquip. N. Am., Inc. v. CLM Equip. Co., Inc., 386 F.3d 581, 591 (4th Cir. 2004).\n\n To establish Article III standing, a plaintiff must prove that: “1) he or she suffered\n\nan ‘injury in fact’ that is concrete and particularized, and is actual or imminent; 2) the\n\ninjury is fairly traceable to the challenged action of the defendant; and 3) the injury likely\n\nwill be redressed by a favorable decision.” Friends of the Earth, Inc. v. Gaston Copper\n\nRecycling Corp., 629 F.3d 387, 396 (4th Cir. 2011). Randall does not dispute that any\n\ninjury Davison suffered is fairly traceable to her decision to ban him from the Chair’s\n\nFacebook Page. Nor does Randall dispute that any such injury would be remedied by a\n\nfavorable decision. Rather, Randall claims that Davison failed to adduce evidence\n\n\n\n\n 13\n\nestablishing that he suffered an “injury in fact” sufficient to support prospective\n\ndeclaratory relief.\n\n “Injury in fact is ‘an invasion of a legally protected interest’ that is ‘concrete and\n\nparticularized’ and ‘actual or imminent, not conjectural or hypothetical.’” Kenny v.\n\nWilson, 885 F.3d 280, 287 (4th Cir. 2018) (quoting Spokeo, Inc. v. Robins, 136 S. Ct.\n\n1540, 1548 (2016)). Because “‘[p]ast exposure to illegal conduct does not in itself show\n\na present case or controversy regarding injunctive relief . . . if unaccompanied by any\n\ncontinuing, present adverse effects,’” a plaintiff seeking “declaratory or injunctive relief .\n\n. . must establish an ongoing or future injury in fact.” Id. at 287–88 (quoting O’Shea v.\n\nLittleton, 414 U.S. 488, 495–96 (1974)). Significantly, this Court—along with several\n\nother circuits—has held that “standing requirements are somewhat relaxed in First\n\nAmendment cases,” particularly regarding the injury-in-fact requirement. Cooksey v.\n\nFutrell, 721 F.3d 226, 235 (4th Cir. 2013) (collecting cases).\n\n In Kenny v. Wilson, 885 F.3d 280 (4th Cir. 2018), this Court addressed what\n\nevidence a plaintiff seeking relief under the First Amendment, like Davison, must put\n\nforward to establish a future injury-in-fact adequate to confer Article III standing to\n\nobtain prospective declaratory relief. In Kenny, several high school students lodged First\n\nAmendment challenges to two South Carolina disorderly conduct statutes. Id. at 284.\n\nThis Court explained that “there is a sufficiently imminent injury in fact if plaintiffs\n\nallege [1] ‘an intention to engage in a course of conduct arguably affected with a\n\nconstitutional interest, but proscribed by a statute, and [2] there exists a credible threat of\n\nprosecution thereunder.’” Id. at 288 (quoting Babbitt v. Farm Workers Nat’l Union, 442\n\n\n 14\n\nU.S. 289, 298 (1979)). The Kenny plaintiffs satisfied the first prong because they “attend\n\nschool” and “attending school inevitably involves expressive conduct” that implicates the\n\ndisorderly conduct statutes. Id. As to the second element—whether the students alleged\n\na “credible threat of future enforcement”—we held that such a threat exists so long as it\n\n“is not imaginary or wholly speculative, chimerical, or wholly conjectural.” Id. (internal\n\nquotation marks, citations, and alterations omitted). “[P]ast enforcement against the same\n\nconduct is good evidence that the threat of enforcement is not chimerical.” Id. (quoting\n\nSusan B. Anthony List v. Driehaus, 134 S. Ct. 2334, 2345 (2014)). “Threat of\n\nprosecution is especially credible when defendants have not ‘disavowed enforcement’ if\n\nplaintiffs engage in similar conduct in the future.” Id. (quoting Driehaus, 134 S. Ct. at\n\n2345). Applying this standard, we held that the plaintiffs alleged a credible threat of\n\nenforcement “because these three plaintiffs regularly attend schools where they allege\n\nthere may be future encounters with school resource officers or other law enforcement;\n\nthey have been prosecuted under the laws in the past; and the defendants have not\n\ndisavowed enforcement if plaintiffs engage in similar conduct in the future.” Id. at 289.\n\n Under Kenny, Davison’s evidence established his standing to obtain prospective\n\ndeclaratory relief. Relevant to the first prong—whether Davison intends to engage in a\n\ncourse of conduct “arguably” impacted by the challenged conduct, Babbitt, 442 U.S. at\n\n298—the district court found, in awarding Davison declaratory relief, that he “continues\n\nto avail himself” of the Chair’s Facebook Page and that Davison is “active in local\n\npolitics, and has a particular interest in what he believes to be corruption on the part of\n\nLoudoun County’s school board.” Davison, 267 F. Supp. 3d at 707, 723. Accordingly,\n\n\n 15\n\nthe evidence establishes that Davison continues to engage in a course of conduct—\n\nnamely, posting about alleged municipal corruption on the Chair’s Facebook Page—\n\nlikely to be impacted by Randall’s allegedly unconstitutional approach to managing the\n\npage.\n\n Turning to the second prong—whether there is a credible threat of enforcement—\n\nRandall previously blocked Davison from the Chair’s Facebook Page based on the\n\ncontent of his posts, providing “good evidence that the threat of enforcement is not\n\nchimerical.” Driehaus, 134 S. Ct. at 2345 (internal quotation marks omitted).\n\nAdditionally, Randall testified that she continues to believe she can ban Davison and\n\nothers from the Chair’s Facebook Page based on their views without triggering the First\n\nAmendment at all. See J.A. 277 (Randall stating she would “be happy to” ban other\n\ncommenters on her “Chair’s Facebook” page); J.A. 250 (Randall testifying that\n\ncomments “attacking another person” would not be allowed on her “Chair’s Facebook”\n\npage). To that end, in awarding Davison declaratory relief, the district court found that\n\nRandall “maintains she is permitted to administer this Facebook page as a purely personal\n\npage.” Davison, 267 F. Supp. 3d at 723. Accordingly, Davison established that he has\n\nbeen subject to past enforcement and that Randall has not “disavowed” future\n\nenforcement, which, under Kenny, is sufficient to establish a credible threat of\n\nenforcement. Cf. City of Lakewood v. Plain Dealer Pub. Co., 486 U.S. 750, 757 (1988)\n\n(“[T]he mere existence of the licensor’s unfettered discretion, coupled with the power of\n\nprior restraint, intimidates parties into censoring their own speech, even if the discretion\n\nand power are never actually abused.”).\n\n\n 16\n\n In sum, Davison’s evidence demonstrated—and the district court found—that\n\nDavison intends to continue to use the Chair’s Facebook Page and that Davison faces a\n\ncredible threat of future enforcement. See Davison, 267 F. Supp. 3d at 723.\n\nAccordingly, Davison adduced facts establishing an injury in fact sufficient to justify the\n\nprospective declaratory relief awarded by the district court.\n\n B.\n\n Next, Randall asserts that the district court erred in concluding, with regard to\n\nDavison’s individual capacity First Amendment claim, that Randall acted “under color of\n\nstate law,” as that phrase is used in Section 1983, in administering the Chair’s Facebook\n\nPage and banning Davison from that page. “This Court reviews judgments stemming\n\nfrom a bench trial under a mixed standard: factual findings are reviewed for clear error,\n\nwhereas conclusions of law are reviewed de novo.” Helton v. AT&T Inc., 709 F.3d 343,\n\n350 (4th Cir. 2013). Whether, under the undisputed facts, Randall acted under color of\n\nstate law is a legal question this Court reviews de novo. Rossignol v. Voorhaar, 316 F.3d\n\n516, 523 (4th Cir. 2003).\n\n To state a claim under Section 1983, a plaintiff must show that the alleged\n\nconstitutional deprivation at issue occurred because of action taken by the defendant\n\n“under color of . . . state law.” Philips v. Pitt Cty. Mem’l Hosp., 572 F.3d 176, 180 (4th\n\nCir. 2009). “The traditional definition of acting under color of state law requires that the\n\ndefendant in a § 1983 action have exercised power ‘possessed by virtue of state law and\n\nmade possible only because the wrongdoer is clothed with the authority of state law.’”\n\nWest v. Atkins, 487 U.S. 42, 49 (1988) (quoting United States v. Classic, 313 U.S. 299,\n\n\n 17\n\n326 (1941)). Section 1983’s “color-of-law prerequisite is synonymous with the more\n\nfamiliar state-action requirement” applicable to Fourteenth Amendment claims, “and the\n\nanalysis for each is identical.” Pitt Cty. Mem’l Hosp., 572 F.3d at 180. Both inquiries\n\ndemand that “the conduct allegedly causing the deprivation of a federal right be fairly\n\nattributable to the State.” Holly v. Scott, 434 F.3d 287, 292 (4th Cir. 2006) (quoting\n\nLugar v. Edmondson Oil Co., Inc., 457 U.S. 922, 937 (1982)).\n\n “[T]here is no specific formula for determining whether state action is present.”\n\nId. at 292 (internal quotation marks omitted). Rather, “[w]hat is fairly attributable [to the\n\nstate]”—i.e., what constitutes action under color of state law—“is a matter of normative\n\njudgment, and the criteria lack rigid simplicity.” Id. (internal quotation marks omitted).\n\nCourts must examine the “totality of the circumstances,” id. (internal quotation marks\n\nomitted), to determine if the action at issue “bore a ‘sufficiently close nexus’ with the\n\nState to be ‘fairly treated as that of the State itself,’” Rossignol, 316 F.3d at 525 (quoting\n\nJackson v. Metro. Edison Co., 419 U.S. 345, 351 (1974)).\n\n Although no one factor is determinative, this Court has held that a defendant’s\n\npurportedly private actions bear a “sufficiently close nexus” with the State to satisfy\n\nSection 1983’s color-of-law requirement when the defendant’s challenged “actions are\n\nlinked to events which arose out of his official status.” Id. at 524. When a defendant’s\n\n“status” as a public official “enabled [her] to execute [a challenged action] in a manner\n\nthat private citizens never could have,” then the action also is more likely to be treated as\n\nattributable to the state. Id. at 526; see also Martinez v. Colon, 54 F.3d 980, 986 (1st Cir.\n\n1995) (“[S]ection 1983 is . . . implicated . . . [when] the conduct is such that the actor\n\n\n 18\n\ncould not have behaved in that way but for the authority of his office.”); Goldstein v.\n\nChestnut Ridge Volunteer Fire Co., 218 F.3d 337, 343 (4th Cir. 2000) (holding that\n\nchallenged conduct is more likely to amount to state action when “the injury caused is\n\naggravated in a unique way by the incidents of governmental authority” (internal\n\nquotation marks omitted)). Likewise, an official’s conduct is more likely to amount to\n\nstate action when it “occurs in the course of performing an actual or apparent duty of his\n\noffice.” Martinez, 54 F.3d at 986. And the challenged action of a defendant\n\ngovernmental official is likely to be treated as taken under color of law when the official\n\n“use[d] the power and prestige of his state office to damage the plaintiff.” Harris v.\n\nHarvey, 605 F.2d 330, 337 (7th Cir. 1979). In the context of an alleged First Amendment\n\nviolation, in particular, this Court has found that a challenged action by a governmental\n\nofficial is fairly attributable to the state when “the sole intention” of the official in taking\n\nthe action was “to suppress speech critical of his conduct of official duties or fitness for\n\npublic office.” Rossignol, 316 F.3d at 524.\n\n Here, after thoroughly analyzing the totality of the circumstances surrounding\n\nRandall’s creation and administration of the Chair’s Facebook Page and banning of\n\nDavison from that page, the district court concluded that Randall acted under color of\n\nstate law. Davison, 267 F. Supp. 3d at 723. We agree.\n\n Randall created and administered the Chair’s Facebook Page to further her duties\n\nas a municipal official. She used the Chair’s Facebook Page “as a tool of governance,”\n\nid. at 713: through the Chair’s Facebook Page, Randall provides information to the public\n\n\n\n\n 19\n\nabout her and the Loudoun Board’s official activities and solicits input from the public on\n\npolicy issues she and the Loudoun Board confront. See supra Part I.A.\n\n For instance, Randall used the Chair’s Facebook Page to inform the public about\n\nserious public safety events and to keep her constituents abreast of the County’s response\n\nto a snowstorm and to coordinate snow removal activities. And, as the district court\n\ncorrectly emphasized, Randall\n\n swathe[d] the [Chair’s Facebook Page] in the trappings of her office.\n Among other things, (1) the title of the page includes [Randall]’s title; (2)\n the page is categorized as that of a government official; (3) the page lists as\n contact information [Randall]’s official County email address and the\n telephone number of [Randall]’s County office; (4) the page includes the\n web address of [Randall]’s official County website; (5) many—perhaps\n most—of the posts are expressly addressed to “Loudoun,” [Randall]’s\n constituents; (6) [Randall] has submitted posts on behalf of the [Loudoun\n Board] as a whole; (7) [Randall] has asked her constituents to use the\n [Chair‘s Facebook Page] as a channel for “back and forth constituent\n conversations”; and (8) the content posted has a strong tendency toward\n matters related to [Randall]’s office.\n\nDavison, 267 F. Supp. 3d at 714. A private citizen could not have created and used the\n\nChair’s Facebook Page in such a manner. Rossignol, 316 F.3d at 526. Put simply,\n\nRandall clothed the Chair’s Facebook Page in “the power and prestige of h[er] state\n\noffice,” Harris, 605 F.2d at 337, and created and administered the page to “perform[]\n\nactual or apparent dut[ies] of h[er] office,” Martinez, 54 F.3d at 986.\n\n Additionally, the specific actions giving rise to Davison’s claim—Randall’s\n\nbanning of Davison’s Virginia SGP Page—“are linked to events which arose out of h[er]\n\nofficial status.” Rossignol, 316 F.3d at 524. Randall’s post to the Chair’s Facebook Page\n\nthat prompted Davison’s comment informed the public about what happened at the\n\n\n\n 20\n\nLoudoun Board and Loudoun County School Board’s joint meeting. And Davison’s\n\ncomment also dealt with an issue related to that meeting and of significant public\n\ninterest—School Board members’ alleged conflicts of interest in approving financial\n\ntransactions. That Randall’s ban of Davison amounted to an effort “to suppress speech\n\ncritical of [such members’] conduct of [their] official duties or fitness for public office”\n\nfurther reinforces that the ban was taken under color of state law. Id. at 525. Considering\n\nthe totality of these circumstances, the district court correctly held that Randall acted\n\nunder color of state law in banning Davison from the Chair’s Facebook Page.\n\n C.\n\n Third, Randall argues that the district court erred in ruling in Davison’s favor on\n\nhis individual capacity First Amendment claim against Randall. Randall principally\n\nchallenges the district court’s conclusion that the Chair’s Facebook Page constitutes a\n\n“public forum” under traditional First Amendment law. We review this legal question de\n\nnovo. See Helton, 709 F.3d at 350.\n\n Under long-established First Amendment law, governmental entities are “strictly\n\nlimited” in their ability to regulate private speech in public fora. Pleasant Grove City,\n\nUtah v. Summum, 555 U.S. 460, 469 (2009). The Supreme Court has recognized two\n\ncategories of public fora: “traditional public forums” and “limited (or designated) public\n\nforums.” Am. Civil Liberties Union v. Mote, 423 F.3d 438, 443 (4th Cir. 2005).\n\n“Traditional” public forums—“such as streets, sidewalks, and parks”—“have the\n\ncharacteristics of a public thoroughfare, a purpose that is compatible with expressive\n\nconduct, as well as a tradition and history of being used for expressive public conduct.”\n\n\n 21\n\nId. “Limited” or “designated” forums are forums that are “not traditionally public, but\n\n[that] the government has purposefully opened to the public, or some segment of the\n\npublic, for expressive activity.” Id. Accordingly, the hallmark of both types of public\n\nfora—what renders the fora “public”—is that the government has made the space\n\navailable—either by designation or long-standing custom—for “expressive public\n\nconduct” or “expressive activity,” and the space is compatible with such activity. Id.\n\n“Conversely, a non-public forum is one that has not traditionally been open to the public,\n\nwhere opening it to expressive conduct would ‘somehow interfere with the objective use\n\nand purpose to which the property has been dedicated.’” Id. (quoting Warren v. Fairfax\n\nCty., 196 F.3d 186, 190–91 (4th Cir. 1999)).\n\n Although neither the Supreme Court nor any Circuit has squarely addressed\n\nwhether, and in what circumstances, a governmental social media page—like the Chair’s\n\nFacebook Page—constitutes a public forum, 3 aspects of the Chair’s Facebook Page bear\n\nthe hallmarks of a public forum. Randall “intentionally open[ed the public comment\n\nsection of the Chair’s Facebook Page] for public discourse,” Cornelius v. NAACP Legal\n\nDefense & Educ. Fund, Inc., 473 U.S. 788, 802 (1985), inviting “ANY Loudoun citizen”\n\n 3\n In addition to the court below, two other district courts have considered whether\na government official’s social media page constituted a public forum. Those courts\nreached conflicting results. Compare Morgan v. Bevin, 298 F. Supp. 3d 1003, 1010 (E.D.\nKy. 2018) (holding that First Amendment forum analysis did not apply to restrictions on\nspeech in the official Facebook and Twitter pages of the Governor of Kentucky), with\nKnight First Amend. Inst. at Colum. Univ. v. Trump, 302 F. Supp. 3d 541, 573 (S.D.N.Y.\n2018) (holding that the interactive component of the President’s Twitter account, as\nopposed to the President’s tweets themselves, constituted a designated public forum),\nappeal docketed, No. 18-1691 (2d Cir. Oct. 24, 2018).\n\n\n\n 22\n\nto make posts to the comments section of the Chair’s Facebook Page—the interactive\n\ncomponent of the page—“on ANY issues, request, criticism, complement or just your\n\nthoughts,” J.A. 455. Randall placed no restrictions on the public’s access to the page or\n\nuse of the interactive component of the Chair’s Facebook Page. And, in accordance with\n\nRandall’s invitation, the public made numerous posts on matters of public concern.\n\n The Chair’s Facebook Page also is “compatib[le] with expressive activity.”\n\nCornelius, 473 U.S. at 802. “Congress [has] recognized the internet and interactive\n\ncomputer services as offering ‘a forum for a true diversity of political discourse, unique\n\nopportunities for cultural development, and myriad avenues for intellectual activity.’”\n\nZeran v. Am. Online, Inc., 129 F.3d 327, 330 (4th Cir. 1997) (quoting 47 U.S.C. §\n\n230(a)(3)); cf. Bland, 730 F.3d at 386 (finding post to campaign Facebook page\n\n“constituted pure speech”). And the Supreme Court recently analogized social media\n\nsites, like the Chair’s Facebook Page, to “traditional” public forums, characterizing the\n\ninternet as “the most important place[] (in a spacial sense) for the exchange of views.”\n\nPackingham v. North Carolina, 137 S. Ct. 1730, 1735 (2017). An “exchange of views”\n\nis precisely what Randall sought—and what in fact transpired—when she expressly\n\ninvited “ANY Loudoun citizen” to visit the page and comment “on ANY issues,” and\n\nreceived numerous such posts and comments. J.A. 455.\n\n Randall nevertheless argues that traditional public forum analysis should not apply\n\nto the Chair’s Facebook Page for two reasons: (1) the Chair’s Facebook Page is “a private\n\nwebsite” and therefore does not constitute “public property” susceptible to forum\n\nanalysis, and (2) the Chair’s Facebook Page, in its entirety, constitutes “government\n\n\n 23\n\nspeech” properly analyzed under the framework set forth in Pleasant Grove. Randall’s\n\nBr. at 19–21, 29–31. We disagree.\n\n Even assuming the intangible space at issue is “private property,” as Randall\n\nclaims—which is not at all clear from the record before us 4—the Supreme Court never\n\nhas circumscribed forum analysis solely to government-owned property. For example, in\n\nCornelius, the Court recognized that forum analysis applies “to private property\n\ndedicated to public use.” Cornelius, 473 U.S. at 801 (emphasis added); see also\n\nChristian Legal Soc’y Chapter of the Univ. of Cal. v. Martinez, 561 U.S. 661, 679 (2010)\n\n(“[T]his Court has employed forum analysis to determine when a governmental entity, in\n\nregulating property in its charge, may place limitations on speech.” (emphasis added)).\n\n 4\n The Facebook “platform” and the “software” that underlies that platform is,\naccording to Facebook’s Terms of Service, property of Facebook, Inc. Terms of Service,\nFacebook, https://www.facebook.com/terms.php (last visited Jan. 4, 2019). Facebook’s\nTerms of Service further provide that users “own the content [they] create and share on\nFacebook and the other Facebook Products,” including Pages. Id. There would seem to\nbe a good argument, therefore, that content created, and posted to Facebook, by\ngovernment officials performing the functions and duties of their offices constitutes\ngovernment property. Cf. Solomons v. United States, 137 U.S. 342, 346–48 (1890)\n(holding that intellectual property created by government employee in the course of his\nofficial duties constituted government property because “[i]f one is employed to devise or\nperfect an instrument, or a means for accomplishing a prescribed result, he cannot, after\nsuccessfully accomplishing the work for which he was employed, plead title thereto as\nagainst his employer”). Likewise, under Facebook’s Terms of Service, the posts and\ncomments by individual Facebook users—like Davison—to a Facebook Page—like the\nChair’s Facebook Page—constitute property of those users. Accordingly, a single\nFacebook Page—including the Chair’s Facebook Page—encompasses a web of property\nrights, some of which may lie with the government. We need not—and thus do not—\ndecide with whom these property rights lie in this particular case, however, because we\nhold that even assuming the Chair’s Facebook Page constitutes private property, Randall,\nacting under color of state law, exercised control over the aspects of that page giving rise\nto Davison’s claim.\n\n\n\n 24\n\nAnd the Supreme Court and lower courts have held that private property, whether\n\ntangible or intangible, constituted a public forum when, for example, the government\n\nretained substantial control over the property under regulation or by contract. See, e.g.,\n\nSe. Promotions, Ltd. v. Conrad, 420 U.S. 546, 547, 555 (1975) (holding that “a privately\n\nowned Chattanooga theater under long-term lease to the city” was a “public forum[]\n\ndesigned for and dedicated to expressive activities”); Halleck v. Manhattan Community\n\nAccess Corp., 882 F.3d 300, 306–07 (2d Cir. 2018) (holding that public access television\n\nchannels operated by a private non-profit corporation constituted public forums), cert.\n\ngranted 139 S. Ct. 360 (2018) (mem.); First Unitarian Church of Salt Lake City v. Salt\n\nLake City Corp., 308 F.3d 1114, 1122 (10th Cir. 2002) (“[F]orum analysis does not\n\nrequire that the government have a possessory interest in or title to the underlying land.\n\nEither government ownership or regulation is sufficient for a First Amendment forum of\n\nsome kind to exist.”); Freedom from Religion Foundation, Inc. v. City of Marshfield,\n\nWis., 203 F.3d 487, 494 (7th Cir. 2000) (holding that private property abutted by public\n\npark constituted public forum).\n\n Significantly, even assuming the relevant aspects of the Chair’s Facebook Page\n\nconstitute private property—which, again, is not entirely clear from the record before\n\nus—Randall, acting under color of state law, retained and exercised significant control\n\nover the page. She created the Chair’s Facebook Page. She designated the page as\n\nbelonging to a “governmental official.” She clothed the page in the trappings of her\n\npublic office. She chose to list her official contact information on the page. And she\n\n\n\n\n 25\n\ncurated the links in the left column of the page and the lists of Facebook Pages or profiles\n\n“liked” by the Chair’s Facebook Page in the right column.\n\n Of particular importance, Randall had complete control over the aspect of the\n\nChair’s Facebook Page giving rise to Davison’s challenge because, as administrator of\n\nthe page, Randall had authority to ban Facebook profiles or Pages from using the Chair’s\n\nFacebook Page—and, therefore, the interactive component of the page—authority she\n\nexercised in banning Davison’s Virginia SGP Page. Cf. Knight, 302 F. Supp. 3d at 566–\n\n67 (holding that the interactive component of the President’s Twitter account constituted\n\npublic forum because the President and his advisors “exercise control over various\n\naspects of the . . . account,” including the power to block other users from accessing the\n\naccount).\n\n The Second Circuit’s decision in Halleck dealing with privately operated public\n\naccess television channels is instructive. Federal law allows cable franchising authorities\n\nto require cable operators to designate channel capacity for public use. Halleck, 882 F.3d\n\nat 302. Likewise, New York regulations oblige cable operators to designate at least one\n\nchannel for full-time public use. Id. Pursuant to that authority, the City of New York\n\nentered into a cable franchise agreement with a cable company requiring the company to\n\nmake available four public access channels, which channels were operated by a private,\n\nnon-profit corporation, MNN. Id. Several producers of public access programming sued\n\nMNN, alleging that MNN violated the producers’ First Amendment rights by indefinitely\n\nsuspending them from using the public access channels “because of disapproval of the\n\ncontent of a TV program” they had submitted for airing. Id.\n\n\n 26\n\n The Second Circuit concluded that the public access channels constituted a public\n\nforum, notwithstanding that they were operated by a private company. Id. at 306–08.\n\nThe court reached that conclusion for two reasons. First, it pointed to the similarities\n\nbetween public access channels and traditional public forums, like parks, describing “[a]\n\npublic access channel [a]s the electronic version of the public square.” Id. at 306.\n\nSecond, the court emphasized the extensive government involvement with, and control\n\nover, public access channels by virtue of the federal and state regulatory schemes. See id.\n\n(“[W]here, as here, federal law authorizes setting aside channels to be ‘the electronic\n\nmarketplace of ideas,’ state regulation requires cable operators to provide at least one\n\npublic access channel, a municipal contract requires a cable operator to provide four such\n\nchannels, and a municipal official has designated a private corporation to run those\n\nchannels, those channels are public forums.” (emphasis added)).\n\n Although not subject to the extensive federal and state regulatory regime\n\napplicable in Halleck, 5 the Chair’s Facebook Page is in many ways analogous to the\n\nprivately-operated public access channels considered by the Second Circuit. Just as the\n\nfederal government sought to establish an “electronic marketplace of ideas” by\n\nmandating provision of public access channels, Randall expressly sought to—and did, in\n\n\n 5\n The federal Communications Decency Act allows private online intermediaries,\nlike Facebook, the ability to moderate content by providing such intermediaries with\nbroad immunity from user-generated content posted on their sites. 47 U.S.C. § 230. This\nCourt has recognized that an “important purpose of § 230 was to encourage service\nproviders to self-regulate the dissemination of offensive material over their services.”\nZeran, 129 F.3d at 331.\n\n\n\n 27\n\nfact—create an “electronic marketplace of ideas” by inviting “ANY” constituent to post\n\nto the Chair Page on “ANY issues.” J.A. 455. Likewise, just as the City of New York\n\nchose to have a private corporation operate the public access channels, Randall chose to\n\ncreate her electronic marketplace of ideas, the Chair’s Facebook Page, on a private\n\nplatform, Facebook. Indeed, the present case provides a stronger basis for treating the\n\ninteractive component of the Chair’s Facebook Page as a public forum because whereas\n\nthe private corporation in Halleck, MNN, exercised control over the aspect of the public\n\naccess channel giving rise to the First Amendment claim—banning the public access\n\nprogram producer—a public official, Randall exercised unconstrained control over the\n\naspect of the Chair’s Facebook Page giving rise to Davison’s claim—banning of other\n\nFacebook profiles and Pages. 6\n\n\n 6\n On October 12, 2018, the Supreme Court granted MNN’s petition for writ of\ncertiorari in Halleck. 139 S. Ct. 360. MNN’s petition presented two questions: (1)\n“[w]hether the Second Circuit erred in rejecting th[e Supreme] Court’s state actor tests\nand instead creating a per se rule that private operators of public access channels are state\nactors subject to constitutional liability” and (2) “[w]hether the Second Circuit erred in\nholding—contrary to the Sixth and D.C. Circuits—that private entities operating public\naccess televisions stations are state actors for constitutional purposes where the state has\nno control over the private entity’s board or operations.” Petition for Writ of Certiorari i,\nManhattan Community Access Corp. v. Halleck, --- S. Ct. --- (No. 17-1702). MNN’s\nargument before the Supreme Court, therefore, focuses on the Second Circuit’s\ndetermination that MNN constituted a state actor, not the court’s determination that the\npublic access channels constituted a public forum.\n\n Although not identified as an issue on appeal, MNN’s petition also took issue with\nthe Second Circuit’s determination that the public access channels operated by MNN\nconstituted a public forum. But that contention was entirely derivative of its state action\nargument. In particular, MNN objected to the Second Circuit’s public forum conclusion\nonly because the public access channels were privately operated and because, in its\nopinion, the Second Circuit’s purportedly “categorical” holding that public access\n(Continued)\n\n 28\n\n Not only does case law contradict Randall’s argument that public forum analysis\n\nnever applies to private property, her argument also fails because it makes no legal sense\n\nto establish a bright-line rule that forum analysis applies only to government-owned\n\nproperty. Why, for example, should the First Amendment allow a municipality to engage\n\nin viewpoint discrimination in curating a public library branch in leased space but not\n\nallow the municipality to engage in such discrimination in a library branch on\n\nmunicipally owned property? Cf. Bd. of Educ., Island Trees Union Free Sch. Dist. No.\n\n26 v. Pico, 457 U.S. 853, 870–71 (1982) (plurality op.) (“If a Democratic school board,\n\nmotivated by partisan affiliation, ordered removal of all books written by or in favor of\n\nRepublicans, few would doubt that the order violated the constitutional rights of the\n\nstudents denied access to those books.”). Or why should a municipality be allowed to\n\nengage in viewpoint discrimination when holding a virtual public meeting hosted on a\n\nprivate website when such discrimination would be unconstitutional if the meeting was\n\nheld in a governmental building? Cf. Lyrissa Lidsky, Public Forum 2.0, 91 B.U. L. Rev.\n\n1975, 1996 (2011) (“Just as the government can rent a building to use as a forum for\n\npublic debate and discussion, so, too, can it ‘rent’ a social media page for the promotion\n\n\n\nchannels constitute public forums ignore[d] “the far more critical issue of whether (and to\nwhat extent) there is government control over a public access channel.” Id. at 19–20.\n\n Here, a government official acting under color of state law, Randall, exercised\nunconstrained control over the aspect of the Chair’s Facebook Page giving rise to\nDavison’s claim.\n\n\n\n\n 29\n\nof public discussion.”). We do not believe the First Amendment draws such arbitrary\n\nlines.\n\n Randall’s second argument—that the Chair’s Facebook Page amounts to\n\n“government speech”—fails to recognize the meaningful difference between Randall’s\n\nposts to the Chair’s Facebook Page and the public comments and posts she invited in the\n\npage’s interactive space. To be sure, Randall’s comments and curated references on the\n\nChair’s Facebook Page to other Pages, personal profiles, and websites amount to\n\ngovernmental speech. See Sutliffe v. Epping School Dist., 584 F.3d 314, 329–30 (1st Cir.\n\n2009) (holding that municipality’s refusal to place hyperlink on municipal website to\n\nwebsite of group opposed to municipal budget constituted government speech); Page v.\n\nLexington Cty. School Dist. One, 531 F.3d 275, 283–85 (4th Cir. 2008) (holding that\n\nSchool District’s refusal to place hyperlink on its website to website of group that\n\nopposed School District’s position on pending legislation constituted government speech\n\nbecause, in part, “the links to other websites were selected by the School District alone as\n\nones that supported its own message”); Knight, 302 F. Supp. 3d at 571 (“[T]he\n\nPresident’s tweets are [not] susceptible to forum analysis . . . because the content is\n\ngovernment speech.”).\n\n But the interactive component of the Chair’s Facebook Page—the portion of the\n\nmiddle column in which the public can post comments, reply to posts, and “like”\n\ncomments and posts—is materially different. See Knight, 302 F. Supp. 3d at 572\n\n(distinguishing a government official’s tweets and “the interactive space for replies and\n\nretweets”). Randall placed no formal limitations on the ability of Facebook personal\n\n\n 30\n\nprofiles and Pages to access the Chair’s Facebook Page and make comments and posts to\n\nthe interactive component of the page. On the contrary, she expressly invited posts to the\n\npage “from ANY Loudon citizen on ANY issues, request, criticism, complement or just\n\nyour thoughts.” J.A. 455. And comments and posts by users cannot be mistaken for\n\nRandall’s own speech because they identify the posting or replying personal profile or\n\nPage, and thereby distinguish that user from Randall.\n\n Contrary to Randall’s argument that the Chair’s Facebook Page, in its entirety,\n\namounts to government speech, the present case also is meaningfully distinguishable\n\nfrom the government speech framework identified in Pleasant Grove. There, a\n\nmunicipality denied a private religious group’s request to allow it to erect a “monument\n\nin a city park in which other donated monuments were previously erected,” including a\n\nmonument depicting a prominent symbol of a different religion. 555 U.S. at 464. The\n\nplaintiff religious group sought relief under the First Amendment, arguing that the city\n\npark constituted a traditional public forum, and therefore that the city could not reject the\n\nreligious group’s proposed monument when it had previously allowed construction of a\n\nmonument associated with another religion. Id. at 466.\n\n The Supreme Court held that the city did not violate the First Amendment because\n\nthe government speech framework, rather than forum analysis, applied to the conduct at\n\nissue. In reaching that conclusion, the Court emphasized that the city never “opened up\n\nthe Park for the placement of whatever permanent monuments might be offered by\n\nprivate donors.” Id. at 472–73. “Rather, the City has ‘effectively controlled’ the\n\nmessages sent by the monuments in the Park by exercising ‘final approval authority’ over\n\n\n 31\n\ntheir selection.” Id. at 473. The Court further emphasized that “[t]he forum doctrine has\n\nbeen applied in situations in which government-owned property or a government\n\nprogram was capable of accommodating a large number of public speakers without\n\ndefeating the essential function of the land or the program.” Id. at 478. A city park,\n\nhowever, “can accommodate only a limited number of permanent monuments,” and\n\ntherefore a municipality cannot—and need not—provide park space for all who wish to\n\nerect a monument. Id.\n\n Here, Randall “effectively controlled” certain aspects of the Chair’s Facebook\n\nPage: she curated the Chair’s Facebook Page’s left and right columns and made posts to\n\nthe middle column. Id. at 472. But Randall also expressly opened the Chair’s Facebook\n\nPage’s middle column—its interactive space—for “ANY” user to post on “ANY issues,”\n\nJ.A. 455, and therefore did not retain “final approval authority” over that aspect of the\n\nChair’s Facebook Page, Pleasant Grove, 555 U.S. at 473. Just as the parkland\n\nsurrounding monuments in Pleasant Grove continued to constitute a public forum, even\n\nthough the monuments themselves constituted government speech, so too the interactive\n\ncomponent of the Chair’s Facebook Page constitutes a public forum, even though\n\nRandall’s curation of and posts to the Chair’s Facebook Page amount to government\n\nspeech. Additionally, the interactive component of the Chair’s Facebook Page does not\n\nface the same spacial limitations as those of the park in Pleasant Grove, but instead is\n\n“capable of accommodating a large number of public speakers without defeating [its]\n\nessential function.” Id. at 578. Accordingly, Pleasant Grove supports, rather than\n\n\n\n\n 32\n\nundermines, our conclusion that the interactive component of the Chair’s Facebook Page\n\nconstitutes a public forum.\n\n Upon concluding that interactive component of the Chair’s Facebook Page\n\namounts to a public forum, we would normally need to determine whether it constitutes a\n\ntraditional public forum or designated or limited public forum. In the present case,\n\nhowever, we need not decide that question because Randall’s ban of Davison amounted\n\nto “viewpoint discrimination,” which is “prohibited in all forums.” See Child Evangelism\n\nFellowship of S.C. v. Anderson Sch. Dist. Five, 470 F.3d 1062, 1067 n.2 (4th Cir. 2006).\n\n“Viewpoint discrimination . . . ‘targets not subject matter, but particular views taken by\n\nspeakers on a subject.’” Id. (quoting Rosenberger v. Rector & Visitors of Univ. of Va.,\n\n515 U.S. 819, 829 (1995)). Viewpoint discrimination is apparent, for example, if a\n\ngovernment official’s decision to take a challenged action was “impermissibly motivated\n\nby a desire to suppress a particular point of view.” Cornelius, 473 U.S. at 812–13.\n\n Here, the district court found—as the record amply supports—that Randall banned\n\nDavison’s Virginia SGP Page because Davison posted a comment using that page\n\nalleging “corruption on the part of Loudoun County’s School Board involving conflicts\n\nof interests among the School Board and their family members.” Davison, 267 F. Supp.\n\n3d at 711. Although Randall stated that she had “no idea” whether Davison’s allegations\n\nwere “correct,” she nonetheless banned him because she viewed the allegations as\n\n“slanderous” and she “didn’t want [the allegations] on the site.” Id. at 717. Randall’s\n\ndecision to ban Davison because of his allegation of governmental corruption constitutes\n\nblack-letter viewpoint discrimination.\n\n\n 33\n\n Put simply, Randall unconstitutionally sought to “suppress” Davison’s opinion\n\nthat there was corruption on the School Board. Cornelius, 473 U.S. at 812–13; see also,\n\ne.g., Rossignol, 316 F.3d at 521 (holding that sheriff’s deputies engaged in viewpoint\n\ndiscrimination when they seized an issue of a newspaper that criticized the county\n\nsheriff’s and his deputies’ performance of their official duties); Putnam Pit, Inc. v. City of\n\nCookeville, Tenn., 221 F.3d 834, 846 (6th Cir. 2000) (holding that a municipality engages\n\nin viewpoint discrimination if it refuses to link newspaper webpage to the city’s website\n\nsolely because the newspaper sought to expose municipal corruption); Knight, 302 F.\n\nSupp. 3d at 575 (holding that the President engaged in viewpoint discrimination when he\n\nblocked individuals from his Twitter account because the individuals “posted tweets that\n\ncriticized the President or his policies”). 7 That Randall’s action targeted comments\n\ncritical of the School Board members’ official actions and fitness for office renders the\n\nbanning all the more problematic as such speech “occupies the core of the protection\n\nafforded by the First Amendment.” Rossignol, 316 F.3d at 521 (quoting McIntyre v.\n\nOhio Elections Comm’n, 514 U.S. 334, 346 (1995)).\n\n In sum, the interactive component of the Chair’s Facebook Page constituted a\n\npublic forum, and Randall engaged in unconstitutional viewpoint discrimination when\n\nshe banned Davison’s Virginia SGP Page from that forum.\n\n\n 7\n Randall also asserts that she did not violate Davison’s First Amendment rights\nbecause she banned his “Virginia SGP” Page, not his “Brian Davison” profile. Davison\nis the sole operator of the “Virginia SGP” Page, however, and therefore the ban\nimplicated his First Amendment rights. Randall fails to identify any case supporting her\nposition, nor have we found any. Accordingly, we reject this argument.\n\n\n 34\n\n III.\n\n In his cross-appeal, Davison asserts that the district court reversibly erred in two\n\nways: (A) by dismissing his claim against Randall in her official capacity and (B) by\n\ndenying his motion to amend his complaint to add the new First Amendment claim\n\nagainst the Loudoun Board. 8 We disagree.\n\n A.\n\n Davison first argues that the district court erred in dismissing his claim against\n\nRandall in her official capacity. Whereas “[p]ersonal-capacity suits seek to impose\n\npersonal liability upon a government official for actions [she] takes under color of state\n\nlaw,” Kentucky v. Graham, 473 U.S. 159, 165 (1985), “official capacity suits are ‘treated\n\nas suits against the municipality,’” Santos v. Frederick Cty. Bd. of Comm’rs, 725 F.3d\n\n451, 469 (4th Cir. 2013) (quoting Hafer v. Melo, 502 U.S. 21, 25 (1991)). Because\n\n“municipal liability under Section 1983 does not amount to respondeat superior . . . a\n\n 8\n Davison also argues that the district court erred in rejecting his procedural due\nprocess claims under the Fourteenth Amendment and an analogous provision in the\nVirginia Constitution. Before the district court, Davison “flatly asserted that due process\nalways requires the government to provide a hearing before imposing a prior restraint on\nspeech,” and therefore that Randall violated Davison’s First Amendment rights by failing\nto conduct a pre-ban hearing. Davison, 267 F. Supp. 3d at 719. The district court\ncorrectly rejected Davison’s proposed categorical rule. Id. (citing Cafeteria & Rest.\nWorkers Union Local 473, AFL-CIO v. McElroy, 367 U.S. 886, 895 (1961). And\nDavison has abandoned that asserted categorical rule on appeal, Davison’s Br. at 49–50\nn.19 (“[I]t might be permissible in certain contexts to delete an individual comment\nwithout providing full pre-deprivation process . . . .”), instead arguing he is entitled to\nrelief under the balancing test set forth in Mathews v. Eldridge, 424 U.S. 319, 334–35\n(1976). Because Davison did not make that argument before the district court, we decline\nto consider it now. See CoreTel Va., LLC v. Verizon Va., LLC, 808 F.3d 978, 988 (4th\nCir. 2015).\n\n\n\n 35\n\nmunicipality is subject to Section 1983 liability only when its ‘policy or custom, whether\n\nmade by its lawmakers or by those whose edicts or acts may fairly be said to represent\n\nofficial policy, inflicts the [plaintiff’s] injury.’” Id. at 469–70 (quoting Monell v. Dep’t of\n\nSoc. Servs. of the City of N.Y., 436 U.S. 658, 694 (1978)).\n\n Here, the district court dismissed Davison’s official capacity claim because it\n\nfound that “no policy—whether County-wide or specific to [Randall]’s office—played\n\nany role in [Randall]’s decision to ban [Davison] from her [Chair’s Facebook Page].”\n\nDavison, 267 F. Supp. 3d at 715. We review the district court’s factual findings bearing\n\non whether Randall acted pursuant to a municipal policy or custom for clear error and its\n\nlegal conclusions de novo. Helton, 709 F.3d at 350.\n\n On appeal, Davison does not dispute the district court’s finding—which the record\n\namply supports—that Loudoun County did not promulgate a policy governing individual\n\nLoudoun Board members’ Facebook pages. Rather, Davison principally 9 argues that “the\n\ncounty can be held liable for Randall’s actions because in banning Davison, Randall\n\nacted as a municipal policymaker.” Davison’s Br. at 47.\n\n\n\n\n 9\n Davison also argues the Loudoun Board’s failure to adopt a policy pertaining to\nindividual board members’ Facebook pages gives rise to an official capacity claim\nbecause it establishes that the Loudoun “Board was—and remains—deliberately\nindifferent to the likelihood of unconstitutional censorship and viewpoint-based\ndiscrimination on individual supervisors’ social media sites.” Davison’s Br. at 46. But\nDavison never advanced a “deliberate indifference” theory of municipal liability before\nthe district court. Again, we decline to consider an argument Davison raises for the first\ntime on appeal. See CoreTel, LLC, 808 F.3d at 988.\n\n\n\n 36\n\n Davison is correct that “municipal liability may be imposed for a single decision\n\nby municipal policymakers under appropriate circumstances.” Hunter v. Town of\n\nMocksville, N.C., 897 F.3d 538, 554 (4th Cir. 2018) (quoting Pembaur v. City of\n\nCincinnati, 475 U.S. 469, 480 (1986)). “[I]n assessing whether a municipality may be\n\nheld liable for constitutional or statutory violations of their decisionmakers, the\n\ntouchstone inquiry is whether ‘the decisionmaker possesses final authority to establish\n\nmunicipal policy with respect to the action ordered.’” Id. at 554–55 (emphasis added)\n\n(quoting Liverman v. City of Petersburg, 844 F.3d 400, 413 (4th Cir. 2016)).\n\n Here, Davison failed to put forward evidence establishing that Randall was a final\n\nmunicipal policymaker with regard to her banning of Davison from the Chair’s Facebook\n\nPage. On the contrary, record evidence establishes that the Loudoun Board retained\n\nauthority to establish municipal policy with respect to social media pages, as it adopted a\n\nsocial media policy governing the County’s official social media pages. Davison\n\nconcedes as much, arguing that the Loudoun Board “neglected . . . to extend its written\n\nguidelines to Board members’ official pages.” Davison’s Br. at 46. But that argument\n\npresupposes that the Loudoun Board—not Randall—had authority to establish municipal\n\npolicy with respect “to Board members’ official pages.”\n\n Davison nevertheless argues that the Loudoun Board “implicitly” delegated its\n\nfinal policymaking authority to Randall by not addressing individual Loudoun Board\n\nmembers’ official pages in its social media policy. Davison is correct that delegation of\n\nfinal policy making authority may be “implied from a continued course of knowing\n\nacquiescence by the governing body in the exercise of policymaking authority by an\n\n\n 37\n\nagency or official.” Id. at 48 (quoting Spell v. McDaniel, 824 F.2d 1380, 1387 (4th Cir.\n\n1987)). But Davison identifies no evidence that the Loudoun Board knew of the Chair’s\n\nFacebook Page, let alone that it “aquiesce[d]” in Randall’s administration of the page and\n\nbanning of Davison, in particular. On the contrary, the district court found that Randall\n\nmade a one-off, “unilateral decision to ban [Davison] in the heat of the moment, and\n\nreconsidered soon thereafter,” Davison, 267 F. Supp. 3d at 715—before the Loudoun\n\nBoard had a chance to learn of her action. In such circumstances, the district court did\n\nnot reversibly err in rejecting Davison’s official capacity claim.\n\n B.\n\n Next, Davison argues that the district court erred in denying him leave to amend\n\nhis complaint to add a claim that “the County violates the First Amendment by\n\nmaintaining a limited public forum on Facebook,” when policies imposed by Facebook,\n\nrather than the County, restrain, or have the potential to restrain, speech. J.A. 74. “A\n\ndistrict court may deny a motion to amend when the amendment would be prejudicial to\n\nthe opposing party, the moving party has acted in bad faith, or the amendment would be\n\nfutile.” Equal Rights Ctr. v. Niles Bolton Assocs., 602 F.3d 597, 603 (4th Cir. 2010).\n\nThe magistrate judge recommended—and the district court agreed—that Davison be\n\ndenied leave to amend on grounds of both futility and prejudice. We review for abuse of\n\ndiscretion a district court’s denial of leave to amend for prejudice, whereas we review de\n\nnovo a district court’s denial of leave to amend on the basis of futility. See U.S. ex rel.\n\nAhumada v. NISH, 756 F.3d 268, 274 (4th Cir. 2014).\n\n\n\n\n 38\n\n Regarding prejudice, the district court determined that the amendment came “too\n\nlate in these proceedings” and would “add a new, novel legal theory to the case after the\n\nclose of discovery, after the existing claims against [the Loudoun Board] have been\n\nshown to be meritless, after the point at which Defendants could have addressed the\n\nclaim in briefing before trial, and on the eve of trial.” J.A. 74. The district court did not\n\nabuse its discretion in denying leave to amend in such circumstances. See, e.g., Equal\n\nRights Ctr., 602 F.3d at 603–04 (holding that district court did not abuse its discretion in\n\ndenying leave to amend on the basis of prejudice when amendment came after the close\n\nof discovery and “on the eve of the deadline for dispositive motions” and therefore\n\n“would [have] change[d] the nature of the litigation”); Deasy v. Hill, 833 F.2d 38, 41 (4th\n\nCir. 1987) (affirming denial of leave to amend on grounds of prejudice when “the motion\n\nto amend came right before trial and after discovery was complete”).\n\n Although we affirm the district court’s judgment on the basis of its finding of\n\nprejudice, we do not concur in its conclusion as to futility. “Futility is apparent if the\n\nproposed amended complaint fails to state a claim under the applicable rules and\n\naccompanying standards.” Katyle v. Penn Nat. Gaming, Inc., 637 F.3d 462, 471 (4th Cir.\n\n2011). Accordingly, Davison’s proposed amendment was futile if the new claim would\n\nnot have survived a motion to dismiss under Federal Rule of Civil Procedure 12(b)(6).\n\nSee Runnion ex rel. Runnion v. Girl Scouts of Greater Chicago & Nw. Ind., 786 F.3d 510,\n\n524 (7th Cir. 2015) (“[W]hen the basis for denial is futility, we apply the legal\n\nsufficiency standard of Rule 12(b)(6) to determine whether the proposed amended\n\ncomplaint fails to state a claim.”).\n\n\n 39\n\n Davison’s proposed First Amendment claim deals not with the Chair’s Facebook\n\nPage—which the Loudoun Board did not authorize or attempt to regulate—but rather\n\nwith Loudoun County’s official Facebook Pages created and maintained pursuant to the\n\nLoudoun Board’s social media policy. As with his claims related to the Chair’s\n\nFacebook Page, Davison alleged that the Facebook Pages created and maintained by the\n\nLoudoun Board constituted public forums subject to the First Amendment. Davison\n\ntheorized that the Loudoun Board’s decision to use Facebook as its social media forum\n\nviolated his First Amendment rights because Facebook rules permit individual\n\n“requesting” users to ban other personal profiles and Pages such that the banned users can\n\nno longer see posts authored by the requesting users. In such circumstances, the banned\n\nusers “cannot see [the requesting user’s] comment[s] or participate in the discussion\n\nsurrounding the [requesting] party’s comment.” Davison’s Br. at 59. Davison’s\n\nproposed amended complaint asserted that “this scenario violates the First Amendment\n\nbecause Loudoun County has effectively enabled third parties to exclude discussion\n\nwithin a public forum—something a government body could not permissibly do in a\n\nphysical forum.” Id. at 59–60 (internal citation omitted). Put differently, Davison\n\ntheorized that Loudoun County violated the First Amendment by choosing to use\n\nFacebook as a public forum, when rules imposed by Facebook allow private users to\n\nrestrict access to their posts—and comments on and responses to those posts—including\n\nposts to any municipal Facebook Page.\n\n No court appears to have addressed that novel legal theory. And although the First\n\nAmendment constrains only government policies, not policies established by private\n\n\n 40\n\nentities, one can conceive of a colorable legal argument that a governmental actor’s\n\ndecision to select a private social media website for use as a public forum—and therefore\n\nselect that website’s suite of rules and regulations—could violate the First Amendment, if\n\nthe private website included certain types of exclusionary rules. For example, if the\n\ngovernment chose as its electronic public forum a social media site that allowed only\n\nregistered members of one political party to post and comment, there would seem to be a\n\ncompelling argument that the government’s selection of that social media site violated the\n\nFirst Amendment rights of members of other political parties, even if the partisan\n\nrestriction was imposed by the private company, not the governmental body. Such a\n\nrestriction would be seem to be no different than a municipality choosing to hold a town\n\nhall meeting in a venue that refused admission to individuals associated with a disfavored\n\npolitical party or viewpoint. Cf. DeBoer v. Village of Oak Park, 267 F.3d 558, 571 (7th\n\nCir. 2001) (“[T]he government engages in viewpoint discrimination when it denies access\n\nto a speaker solely to suppress the point of view he espouses on an otherwise includible\n\nsubject.”).\n\n Given that Davison’s proposed claim asserted a novel and colorable legal theory\n\nand that “Rule 12(b)(6) dismissals are especially disfavored in cases where the complaint\n\nsets forth a novel legal theory that can best be assessed after factual development,”\n\nWright v. North Carolina, 787 F.3d 256, 263 (4th Cir. 2015) (internal quotation marks\n\nomitted), we affirm the district court’s denial of Davison’s motion for leave to amend his\n\ncomplaint on the basis of its finding of prejudice but not on the basis of futility.\n\n IV.\n\n\n 41\n\nFor the foregoing reasons, we affirm the judgment of the district court.\n\n AFFIRMED\n\n\n\n\n 42\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Brian DAVISON, Plaintiff - Appellee, v. Phyllis RANDALL, in Her Official and Individual Capacity, Defendant - Appellant, and Loudoun County Board of Supervisors, in Their Official and Individual Capacities; Leo Rogers, in His Official Capacity; Tony Buffington, in His Official Capacity; Ron Meyer, in His Official Capacity; Geary Higgins, in His Official Capacity, Defendants. Local Government Attorneys of Virginia, Inc.; International Municipal Lawyers Association ; Virginia Association of Counties; Virginia Municipal League, Amici Supporting Appellant, American Civil Liberties Union; ACLU of Virginia ; ACLU of Maryland; ACLU of North Carolina; ACLU of South Carolina; ACLU of West Virginia, Amici Supporting Appellee. Brian C. Davison, Plaintiff - Appellant, v. Phyllis Randall, in Her Official and Individual Capacity; Loudoun County Board of Supervisors, in Their Official and Individual Capacities, Defendants - Appellees, and Leo Rogers, in His Official Capacity; Tony Buffington, in His Official Capacity; Ron Meyer, in His Official Capacity; Geary Higgins, in His Official Capacity, Defendants.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-07\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-2002\\n\\n\\nBRIAN DAVISON,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nPHYLLIS RANDALL, In her official and individual capacity,\\n\\n Defendant - Appellant,\\n\\n and\\n\\nLOUDOUN COUNTY BOARD OF SUPERVISORS, In their official and\\nindividual capacities; LEO ROGERS, In his official capacity; TONY\\nBUFFINGTON, In his official capacity; RON MEYER, In his official capacity;\\nGEARY HIGGINS, In his official capacity,\\n\\n Defendants.\\n\\n------------------------------\\n\\nLOCAL GOVERNMENT ATTORNEYS OF VIRGINIA, INC.;\\nINTERNATIONAL MUNICIPAL LAWYERS ASSOCIATION; VIRGINIA\\nASSOCIATION OF COUNTIES; VIRGINIA MUNICIPAL LEAGUE,\\n\\n Amici Supporting Appellant,\\n\\nAMERICAN CIVIL LIBERTIES UNION; ACLU OF VIRGINIA; ACLU OF\\nMARYLAND; ACLU OF NORTH CAROLINA; ACLU OF SOUTH\\nCAROLINA; ACLU OF WEST VIRGINIA,\\n\\n Amici Supporting Appellee.\\n\\n No. 17-2003\\n\\n\\nBRIAN C. DAVISON,\\n\\n Plaintiff - Appellant,\\n\\n v.\\n\\nPHYLLIS RANDALL, In her official and individual capacity; LOUDOUN\\nCOUNTY BOARD OF SUPERVISORS, In their official and individual\\ncapacities,\\n\\n Defendants - Appellees,\\n\\n and\\n\\nLEO ROGERS, In his official capacity; TONY BUFFINGTON, In his official\\ncapacity; RON MEYER, In his official capacity; GEARY HIGGINS, In his\\nofficial capacity,\\n\\n Defendants.\\n\\n\\nAppeals from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. James C. Cacheris, Senior District Judge. (1:16-cv-00932-JCC-IDD)\\n\\n\\nArgued: September 26, 2018 Decided: January 7, 2019\\n\\n\\nBefore KEENAN, WYNN, and HARRIS, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Wynn wrote the opinion, in which Judge Keenan\\nand Judge Harris concurred. Judge Keenan wrote a separate concurring opinion.\\n\\n\\nARGUED: Scott E. Gant, BOIES SCHILLER FLEXNER, LLP, Washington, D.C.; Leo\\nP. Rogers, LOUDON COUNTY ATTORNEY, Leesburg, Virginia, for Appellant/Cross-\\nAppellee. Katherine A. Fallow, KNIGHT FIRST AMENDMENT INSTITUTE AT\\n\\n\\n 2\\n\\nCOLUMBIA UNIVERSITY, New York, New York, for Appellee/Cross-Appellant. ON\\nBRIEF: Aaron E. Nathan, BOIES SCHILLER FLEXNER LLP, Washington, D.C., for\\nAppellant/Cross-Appellee. Jameel Jaffer, Carrie DeCell, KNIGHT FIRST\\nAMENDMENT INSTITUTE AT COLUMBIA UNIVERSITY, New York, New York,\\nfor Appellee/Cross-Appellant. Vishal Agraharkar, AMERICAN CIVIL LIBERTIES\\nUNION FOUNDATION OF VIRGINIA, Richmond, Virginia; Esha Bhandari, Vera\\nEidelman, AMERICAN CIVIL LIBERTIES UNION FOUNDATION, New York, New\\nYork; Susan K. Dunn, ACLU OF SC FOUNDATION, INC., Charleston, South Carolina;\\nChristopher Brook, AMERICAN CIVIL LIBERTIES UNION OF NORTH CAROLINA\\nLEGAL FOUNDATION, Raleigh, North Carolina; Deborah A. Jeon, ACLU\\nFOUNDATION OF MARYLAND, Baltimore, Maryland; Jennifer D. Oliva, ACLU OF\\nWEST VIRGINIA FOUNDATION, Charleston, West Virginia, for Amici American\\nCivil Liberties Union, ACLU of Virginia, ACLU of Maryland, ACLU of North Carolina,\\nACLU of South Carolina, and ACLU of West Virginia. Joshua A. Geltzer, Douglas\\nLetter, Amy L. Marshak, Mary B. McCord, INSTITUTE FOR CONSTITUTIONAL\\nADVOCACY AND PROTECTION GEORGETOWN UNIVERSITY LAW CENTER,\\nWashington, D.C.; Kwaku A. Akowuah, Christopher C. Fonzone, Kate Heinzelman,\\nSIDLEY AUSTIN LLP, Washington, D.C., for Amici Curiae First Amendment Legal\\nScholars.\\n\\n\\n\\n\\n 3\\n\\nWYNN, Circuit Judge:\\n\\n Phyllis Randall, Chair of the Loudoun County, Virginia, Board of Supervisors (the\\n\\n“Loudoun Board”), brings this appeal, arguing that the district court erred in concluding\\n\\nthat she violated the First Amendment rights of one of her constituents, Brian Davison,\\n\\nwhen she banned Davison from the “Chair Phyllis J. Randall” Facebook page she\\n\\nadministered. In a cross appeal, Davison principally argues that the district court erred\\n\\nin dismissing his procedural due process claim premised on the ban. For the reasons that\\n\\nfollow, we affirm.\\n\\n I.\\n\\n A.\\n\\n Randall has chaired the Loudoun County Board of Supervisors since January 1,\\n\\n2016. The day before she was sworn in as chair, Randall created the “Chair Phyllis J.\\n\\nRandall” Facebook Page (the “Chair’s Facebook Page”). According to Facebook, Inc.,\\n\\nunlike personal Facebook profiles, which are for non-commercial use and represent\\n\\nindividual people, Facebook “Pages”—like the Chair’s Facebook Page—“help\\n\\nbusinesses, organizations, and brands share their stories and connect with people.” J.A.\\n\\n403. “Pages are managed by people who have personal profiles,” the company explains.\\n\\nJ.A. 403. In addition to the Chair’s Facebook Page, Randall created and maintained two\\n\\nother Facebook profiles: a personal profile and a Page devoted to her campaign. Randall\\n\\nclassified her campaign page as belonging to a “politician” and used no designation for\\n\\nher personal profile, but she designated the Chair’s Facebook Page as a “governmental\\n\\nofficial” page. J.A. 209–10.\\n\\n\\n 4\\n\\n Randall and her Chief of Staff, Jeanine Arnett, share administrative control over\\n\\nthe Chair’s Facebook Page, although Randall almost exclusively controls the page’s\\n\\ncontent. On her campaign page, Randall characterized the Chair’s Facebook Page as her\\n\\n“county Facebook page” stating:\\n\\n I really want to hear from ANY Loudoun citizen on ANY issues, request,\\n criticism, complement or just your thoughts. However, I really try to keep\\n back and forth conversations (as opposed to one time information items\\n such as road closures) on my county Facebook page (Chair Phyllis J.\\n Randall) or County email (Phyllis.randall@loudoun.gov). Having back and\\n forth constituent conversations are Foiable ([Freedom of Information Act])\\n so if you could reach out to me on these mediums that would be\\n appreciated.\\n\\nJ.A. 455 (emphasis added).\\n\\n The Chair’s Facebook Page includes three columns. The left column, which is\\n\\ntopped by a picture of Randall, includes several links to allow visitors to quickly navigate\\n\\nthe contents of the Chair’s Facebook Page.\\n\\n The middle column, which is organized in reverse chronological order similar to a\\n\\npersonal profile’s News Feed, is composed of posts by Randall and comments by\\n\\nFacebook users on those posts. Randall’s posts are almost always directed to “Loudoun,”\\n\\nsee, e.g., J.A. 408–10, and deal with numerous aspects of Randall’s official\\n\\nresponsibilities. For example, Randall used the Chair’s Facebook Page to notify the\\n\\npublic about upcoming Loudoun Board meetings, and the subjects to be discussed during\\n\\nthose meetings. Randall also used the page to inform Loudoun County residents about\\n\\nsignificant public safety issues. See, e.g., J.A. 412 (stating that Loudoun Board had\\n\\n“been informed by the Sheriff’s Office about the non-legitimate threat made on social\\n\\n\\n\\n 5\\n\\nmedia toward Dominion High School in Sterling”); J.A. 418 (reporting that she “ha[d]\\n\\nbeen briefed regarding the student falling from the water tower this morning” and\\n\\nadvising the public to “not make any assumptions but wait for information”). And\\n\\nRandall used the Chair’s Facebook Page to coordinate Loudoun County’s response to a\\n\\nlarge snow storm, including to communicate with constituents regarding which municipal\\n\\nstreets required plowing.\\n\\n Other posts by Randall to the Chair’s Facebook Page invited members of the\\n\\npublic to apply to participate on a public commission and to participate in public\\n\\nmeetings regarding key issues facing Loudoun County residents, such as revised flood\\n\\nplain zones and the Zika virus. Randall also authored posts regarding a variety of trips\\n\\nand meetings she had taken in furtherance of Loudoun County business. E.g., J.A. 408\\n\\n(reporting that Randall “address[ed] the (county) role in Treatment” at a “regional\\n\\nconference on Opioid and Substance Abuse Addiction”); J.A. 410 (stating that Randall\\n\\nrepresented Loudoun County at its “annual credit rating presentation” in New York); J.A.\\n\\n415 (informing public of trip to Loudoun’s “Sister City” in Germany); J.A. 426\\n\\n(reporting that Randall was “in Richmond lobbying for [Loudoun County’s] legislative\\n\\nprogram”). Finally, Randall used the page to advise the public regarding official actions\\n\\ntaken by the Loudoun Board. E.g., J.A. 433 (reporting that Loudoun Board “approved\\n\\nfunding for new breathing apparatus for our Loudoun Firefighters”); J.A. 442 (listing\\n\\nseveral “proclamations of note” by the Loudoun Board); J.A. 443 (informing public that\\n\\nLoudoun Board “adopted a budget for Fiscal Year 2017 totaling $2.46 billion for the\\n\\ngeneral county government and schools”). Although Randall’s posts on the Chair’s\\n\\n\\n 6\\n\\nFacebook Page principally addressed her official responsibilities, a few posts addressed\\n\\ntopics less closely related to her official activities such as her affection for the German\\n\\nlanguage or pride in becoming an organ donor.\\n\\n Members of the public, including Davison, “liked” 1 or commented on several of\\n\\nRandall’s posts on the Chair’s Facebook Page. Each “like” or comment identified the\\n\\nname of the personal profile or Page of the authoring party. Many of the comments\\n\\nthanked Randall and the Loudoun Board for representing the public’s interests. Other\\n\\nposts by members of the public offered feedback on various issues faced by Randall and\\n\\nthe Loudoun Board. E.g., J.A. 427 (stating that “[p]utting recreation in a flood plain is\\n\\nnot a good idea”); J.A. 448 (stating that “more needs to be done with the explosion of\\n\\nLyme disease in Loudoun”). And other comments dealt with constituent-specific issues.\\n\\nE.g., J.A. 415 (constituent stating, in response to post by Randall regarding visit to\\n\\nLoudoun County’s “Sister City” in Germany, that constituent’s “daughter is interested in\\n\\nexchange programs”); J.A. 454 (stating that “there [we]re no [snow] plows to be seen” in\\n\\na particular neighborhood). Finally, several comments, including a number authored by\\n\\nDavison, criticized the Loudoun Board, generally, and Randall, in particular, for actions\\n\\ntaken in their official capacities. E.g., J.A. 429–30 (Davison criticizing public school\\n\\nsystem budget and expenditures); J.A. 438–39 (member of public criticizing\\n\\ngovernmental entity’s inspection of farm, claiming it failed to uncover animal abuse);\\n\\n\\n 1\\n “‘Liking’ on Facebook is a way for Facebook users to share information with\\neach other.” Bland v. Roberts, 730 F.3d 368, 385 (4th Cir. 2013).\\n\\n\\n\\n 7\\n\\nJ.A. 449 (Davison characterizing question he posed at Loudoun Board and Loudoun\\n\\nSchool Board joint town hall). On some occasions, Randall responded to these\\n\\ncomments or criticisms.\\n\\n In the right column of the Chair’s Facebook Page, the page is identified as a\\n\\n“government official” page. It provides contact information for Randall’s county office,\\n\\nincluding her office telephone number, Randall’s official county email address, and the\\n\\ninternet address for the official county website. The column also identifies how many\\n\\nand which Facebook personal profiles and Pages “like” and “follow” the Chair’s\\n\\nFacebook Page. 2 And the column includes a list of personal profiles and Pages “liked”\\n\\nby the Chair’s Facebook Page.\\n\\n Randall publicized the Chair’s Facebook Page in her official “Chair Phyllis J.\\n\\nRandall” newsletter, which is prepared by County employees, hosted on the County’s\\n\\nwebsite, and distributed to Loudoun citizens using Randall’s official county email\\n\\naccount. The newsletter ends with the words “STAY CONNECTED” and a Facebook\\n\\nicon that hyperlinks to the Chair’s Facebook Page. Randall also highlighted the Chair’s\\n\\nFacebook Page in “Winter Storm Information” notices emailed from her official county\\n\\naccount to Loudoun County residents, advising recipients to “Visit [the Chair’s Facebook\\n\\nPage] for Updates.” J.A. 341–42, 344.\\n\\n 2\\n According to Facebook, “[l]iking a Facebook Page means you are connecting to\\nthat Page. When you connect to a Page, it will appear in [a user’s] timeline and [the user]\\nwill appear on the page as a person who likes that Page. The Page will also be able to\\npost content into [the user’s] News Feed.” Bland, 730 F.3d at 385 (internal quotation\\nmarks omitted).\\n\\n\\n\\n 8\\n\\n Davison, an outspoken resident of Loudoun County, apparently largely focuses his\\n\\ncivic engagement and expression on “the funding and . . . management of public\\n\\nschools.” J.A. 95. To that end, he has repeatedly expressed concern about “School Board\\n\\nmembers failing to disclose personal conflicts as required by law before voting on\\n\\nfinancial transactions before the School Board.” J.A. 96.\\n\\n On February 3, 2016, Davison attended a Loudoun town hall meeting that\\n\\nincluded the Loudoun County School Board and Randall. At the meeting, Davison\\n\\nsubmitted a question implying that certain School Board members had acted unethically\\n\\nin approving financial transactions. Randall volunteered to answer the question but\\n\\ncharacterized it as a “set-up question” that she did not “appreciate.” J.A. 103. Shortly\\n\\nafter Randall answered the question—and while the town hall meeting was still\\n\\nongoing—Davison posted a message on Twitter in which he tagged Randall:\\n\\n“@ChairRandall ‘set up question’? You might want to strictly follow FOIA and the\\n\\nCOIA as well.” J.A. 470–71.\\n\\n Later that evening, Randall posted about the town hall meeting on the Chair’s\\n\\nFacebook Page, describing “what was generally discussed at the meeting.” J.A. 268. In\\n\\nresponse, Davison then used one of the Facebook Pages he manages through his personal\\n\\nFacebook profile—“Virginia SGP,” which Davison frequently uses to post political\\n\\ncommentary—to comment on Randall’s post about the town hall meeting. Although\\n\\nneither Davison nor Randall remember the precise content of Davison’s comment,\\n\\nRandall testified that it contained “accusations” regarding School Board members’ and\\n\\ntheir families’ putative conflicts of interest related to municipal financial transactions,\\n\\n\\n 9\\n\\nsuggesting, in Randall’s opinion, that School Board members had been “taking kickback\\n\\nmoney.” See J.A. 268–69, 289–90. Randall stated that she “had no idea if any of th[e]\\n\\n[accusations] w[ere] correct,” but she determined that the post was “probably not\\n\\nsomething [she] want[ed] to leave” on the Chair’s Facebook Page. J.A. 269. Randall\\n\\nthen “deleted the whole post,” including her original post regarding the town hall\\n\\nmeeting, Davison’s comment and replies thereto, and all other public comments. J.A.\\n\\n269. Randall also banned Davison’s Virginia SGP Page from the Chair’s Facebook Page,\\n\\nwhich precluded Davison from using his Virginia SGP Page from commenting on the\\n\\nChair’s Facebook Page. The next morning, about twelve hours later, Randall\\n\\nreconsidered her actions and unbanned Davison’s Virginia SGP Page.\\n\\n B.\\n\\n On November 3, 2016, Davison filed an amended complaint seeking declaratory\\n\\nand injunctive relief under 42 U.S.C. § 1983 against Randall, in both her official and\\n\\nindividual capacities, and the Loudoun Board alleging that the “banning of [Davison]\\n\\nfrom commenting on [the Chair’s Facebook Page] is viewpoint discrimination.” J.A. 31.\\n\\nDavison further alleged that the ban violated his procedural due process rights protected\\n\\nby the Fourteenth Amendment because “Randall blocked Davison’s constitutionally\\n\\nprotected speech on [the Chair’s Facebook Page], a limited public forum, without prior\\n\\nnotice and without providing an opportunity for appealing [her] decision.” J.A. 32.\\n\\nDavison did not challenge Randall’s deletion of his post.\\n\\n On March 6, 2017—four days before the close of discovery and approximately\\n\\ntwo months before trial—Davison moved for leave to amend his complaint a second time\\n\\n\\n 10\\n\\nto add claims under the Virginia Constitution that were materially indistinguishable from\\n\\nhis previously asserted First and Fourteenth Amendment claims premised on the ban, as\\n\\nwell as a separate First Amendment claim against the Loudoun Board. Davison’s\\n\\nproposed new First Amendment claim theorized that the County violated his free speech\\n\\nrights by choosing to use Facebook Pages as public forums, when Facebook allows\\n\\nprivate users to restrict access to their posts, including posts to any Page a municipality\\n\\ndesignates as a limited public forum. Pl.’s Mem. in Supp. of Mot. for Leave to File\\n\\nSecond Am. Compl. 3–9, Davison v. Loudoun County Bd. of Supervisors, 16-cv-932-\\n\\nJCC-IDD, ECF No. 68. The district court referred the motion to a magistrate judge, who\\n\\ngranted leave to amend regarding the claims under the Virginia Constitution but denied\\n\\nleave as to the new First Amendment claim against the Loudoun Board. Davison lodged\\n\\nobjections to the magistrate judge’s partial denial of leave to amend, which objections the\\n\\ndistrict court overruled.\\n\\n Around the same time, Randall and the Loudoun Board each moved for summary\\n\\njudgment. The Loudoun Board asserted that the municipality could not be held liable for\\n\\nRandall’s banning of Davison from the Chair’s Facebook Page because the Chair’s\\n\\nFacebook Page was not an official municipal page and because Randall, not the Loudoun\\n\\nBoard as a body, was solely responsible for creating and administering the Chair’s\\n\\nFacebook Page. The Loudoun Board and Randall further asserted that the Chair’s\\n\\nFacebook Page did not amount to a public forum, and therefore Randall’s ban of\\n\\nDavison’s Virginia SGP Page did not implicate his free speech or procedural due process\\n\\nrights. Finally, Randall asserted that she was entitled to qualified immunity.\\n\\n\\n 11\\n\\n On May 10, 2017, the district court granted summary judgment in favor of the\\n\\nLoudoun Board, dismissing it from the suit. But as to Randall, the district court\\n\\nconcluded that Davison’s evidence established a material dispute of fact as to whether the\\n\\nChair’s Facebook Page amounted to a limited public forum and whether Randall, in her\\n\\nindividual capacity, acted under color of state law in banning Davison from the Chair’s\\n\\nFacebook Page. Davison v. Loudoun Cty. Bd. of Supervisors, No. 1:16-cv-932, 2017 WL\\n\\n1929406, at *6–9 (E.D. Va. May 10, 2017). The district court also rejected Randall’s\\n\\nqualified immunity argument. Id. at *8.\\n\\n Following a one-day bench trial of Davison’s claims against Randall, the district\\n\\ncourt issued a memorandum opinion and order awarding judgment in Davison’s favor on\\n\\nhis claims under the First Amendment and the analogous free speech provision in the\\n\\nVirginia Constitution. See Davison v. Loudoun Cty. Bd. of Supervisors, 267 F. Supp. 3d\\n\\n702, 714–18 (E.D. Va. 2017). The district court further entered judgment in Randall’s\\n\\nfavor on Davison’s federal and state procedural due process claims. Id. at 719–22. As to\\n\\nremedy, the district court denied Davison’s request for injunctive relief but granted\\n\\nDavison’s request for a declaratory judgment to resolve the “uncertainty regarding the\\n\\nlegal status of [the Chair’s Facebook Page].” Id. at 723.\\n\\n Randall and Davison, respectively, filed this appeal and cross appeal.\\n\\n II.\\n\\n On appeal, Randall argues that (A) Davison failed to establish standing to obtain\\n\\nprospective declaratory relief based on Randall’s alleged First Amendment violation; (B)\\n\\nthe district court erred in concluding that Randall acted under “color of state law” when\\n\\n\\n 12\\n\\nshe banned Davison’s Virginia SGP Page from the Chair’s Facebook Page; and (C) the\\n\\ndistrict court erred in concluding that Randall’s banning of Davison’s Virginia SGP Page\\n\\nviolated the First Amendment.\\n\\n A.\\n\\n Notwithstanding that she did not challenge Davison’s standing below—and\\n\\ntherefore that the district court never squarely addressed his standing—Randall now\\n\\nargues that Davison failed to establish Article III standing to support the district court’s\\n\\naward of prospective declaratory relief. Even though Defendants did not challenge\\n\\nDavison’s standing below, “standing to sue is a jurisdictional issue of constitutional\\n\\ndimensions, and it may be raised and addressed for the first time on appeal.” Hodges v.\\n\\nAbraham, 300 F.3d 432, 443 (4th Cir. 2002). This Court reviews de novo “whether a\\n\\ndistrict court possessed jurisdiction in a declaratory judgment proceeding.” Volvo Const.\\n\\nEquip. N. Am., Inc. v. CLM Equip. Co., Inc., 386 F.3d 581, 591 (4th Cir. 2004).\\n\\n To establish Article III standing, a plaintiff must prove that: “1) he or she suffered\\n\\nan ‘injury in fact’ that is concrete and particularized, and is actual or imminent; 2) the\\n\\ninjury is fairly traceable to the challenged action of the defendant; and 3) the injury likely\\n\\nwill be redressed by a favorable decision.” Friends of the Earth, Inc. v. Gaston Copper\\n\\nRecycling Corp., 629 F.3d 387, 396 (4th Cir. 2011). Randall does not dispute that any\\n\\ninjury Davison suffered is fairly traceable to her decision to ban him from the Chair’s\\n\\nFacebook Page. Nor does Randall dispute that any such injury would be remedied by a\\n\\nfavorable decision. Rather, Randall claims that Davison failed to adduce evidence\\n\\n\\n\\n\\n 13\\n\\nestablishing that he suffered an “injury in fact” sufficient to support prospective\\n\\ndeclaratory relief.\\n\\n “Injury in fact is ‘an invasion of a legally protected interest’ that is ‘concrete and\\n\\nparticularized’ and ‘actual or imminent, not conjectural or hypothetical.’” Kenny v.\\n\\nWilson, 885 F.3d 280, 287 (4th Cir. 2018) (quoting Spokeo, Inc. v. Robins, 136 S. Ct.\\n\\n1540, 1548 (2016)). Because “‘[p]ast exposure to illegal conduct does not in itself show\\n\\na present case or controversy regarding injunctive relief . . . if unaccompanied by any\\n\\ncontinuing, present adverse effects,’” a plaintiff seeking “declaratory or injunctive relief .\\n\\n. . must establish an ongoing or future injury in fact.” Id. at 287–88 (quoting O’Shea v.\\n\\nLittleton, 414 U.S. 488, 495–96 (1974)). Significantly, this Court—along with several\\n\\nother circuits—has held that “standing requirements are somewhat relaxed in First\\n\\nAmendment cases,” particularly regarding the injury-in-fact requirement. Cooksey v.\\n\\nFutrell, 721 F.3d 226, 235 (4th Cir. 2013) (collecting cases).\\n\\n In Kenny v. Wilson, 885 F.3d 280 (4th Cir. 2018), this Court addressed what\\n\\nevidence a plaintiff seeking relief under the First Amendment, like Davison, must put\\n\\nforward to establish a future injury-in-fact adequate to confer Article III standing to\\n\\nobtain prospective declaratory relief. In Kenny, several high school students lodged First\\n\\nAmendment challenges to two South Carolina disorderly conduct statutes. Id. at 284.\\n\\nThis Court explained that “there is a sufficiently imminent injury in fact if plaintiffs\\n\\nallege [1] ‘an intention to engage in a course of conduct arguably affected with a\\n\\nconstitutional interest, but proscribed by a statute, and [2] there exists a credible threat of\\n\\nprosecution thereunder.’” Id. at 288 (quoting Babbitt v. Farm Workers Nat’l Union, 442\\n\\n\\n 14\\n\\nU.S. 289, 298 (1979)). The Kenny plaintiffs satisfied the first prong because they “attend\\n\\nschool” and “attending school inevitably involves expressive conduct” that implicates the\\n\\ndisorderly conduct statutes. Id. As to the second element—whether the students alleged\\n\\na “credible threat of future enforcement”—we held that such a threat exists so long as it\\n\\n“is not imaginary or wholly speculative, chimerical, or wholly conjectural.” Id. (internal\\n\\nquotation marks, citations, and alterations omitted). “[P]ast enforcement against the same\\n\\nconduct is good evidence that the threat of enforcement is not chimerical.” Id. (quoting\\n\\nSusan B. Anthony List v. Driehaus, 134 S. Ct. 2334, 2345 (2014)). “Threat of\\n\\nprosecution is especially credible when defendants have not ‘disavowed enforcement’ if\\n\\nplaintiffs engage in similar conduct in the future.” Id. (quoting Driehaus, 134 S. Ct. at\\n\\n2345). Applying this standard, we held that the plaintiffs alleged a credible threat of\\n\\nenforcement “because these three plaintiffs regularly attend schools where they allege\\n\\nthere may be future encounters with school resource officers or other law enforcement;\\n\\nthey have been prosecuted under the laws in the past; and the defendants have not\\n\\ndisavowed enforcement if plaintiffs engage in similar conduct in the future.” Id. at 289.\\n\\n Under Kenny, Davison’s evidence established his standing to obtain prospective\\n\\ndeclaratory relief. Relevant to the first prong—whether Davison intends to engage in a\\n\\ncourse of conduct “arguably” impacted by the challenged conduct, Babbitt, 442 U.S. at\\n\\n298—the district court found, in awarding Davison declaratory relief, that he “continues\\n\\nto avail himself” of the Chair’s Facebook Page and that Davison is “active in local\\n\\npolitics, and has a particular interest in what he believes to be corruption on the part of\\n\\nLoudoun County’s school board.” Davison, 267 F. Supp. 3d at 707, 723. Accordingly,\\n\\n\\n 15\\n\\nthe evidence establishes that Davison continues to engage in a course of conduct—\\n\\nnamely, posting about alleged municipal corruption on the Chair’s Facebook Page—\\n\\nlikely to be impacted by Randall’s allegedly unconstitutional approach to managing the\\n\\npage.\\n\\n Turning to the second prong—whether there is a credible threat of enforcement—\\n\\nRandall previously blocked Davison from the Chair’s Facebook Page based on the\\n\\ncontent of his posts, providing “good evidence that the threat of enforcement is not\\n\\nchimerical.” Driehaus, 134 S. Ct. at 2345 (internal quotation marks omitted).\\n\\nAdditionally, Randall testified that she continues to believe she can ban Davison and\\n\\nothers from the Chair’s Facebook Page based on their views without triggering the First\\n\\nAmendment at all. See J.A. 277 (Randall stating she would “be happy to” ban other\\n\\ncommenters on her “Chair’s Facebook” page); J.A. 250 (Randall testifying that\\n\\ncomments “attacking another person” would not be allowed on her “Chair’s Facebook”\\n\\npage). To that end, in awarding Davison declaratory relief, the district court found that\\n\\nRandall “maintains she is permitted to administer this Facebook page as a purely personal\\n\\npage.” Davison, 267 F. Supp. 3d at 723. Accordingly, Davison established that he has\\n\\nbeen subject to past enforcement and that Randall has not “disavowed” future\\n\\nenforcement, which, under Kenny, is sufficient to establish a credible threat of\\n\\nenforcement. Cf. City of Lakewood v. Plain Dealer Pub. Co., 486 U.S. 750, 757 (1988)\\n\\n(“[T]he mere existence of the licensor’s unfettered discretion, coupled with the power of\\n\\nprior restraint, intimidates parties into censoring their own speech, even if the discretion\\n\\nand power are never actually abused.”).\\n\\n\\n 16\\n\\n In sum, Davison’s evidence demonstrated—and the district court found—that\\n\\nDavison intends to continue to use the Chair’s Facebook Page and that Davison faces a\\n\\ncredible threat of future enforcement. See Davison, 267 F. Supp. 3d at 723.\\n\\nAccordingly, Davison adduced facts establishing an injury in fact sufficient to justify the\\n\\nprospective declaratory relief awarded by the district court.\\n\\n B.\\n\\n Next, Randall asserts that the district court erred in concluding, with regard to\\n\\nDavison’s individual capacity First Amendment claim, that Randall acted “under color of\\n\\nstate law,” as that phrase is used in Section 1983, in administering the Chair’s Facebook\\n\\nPage and banning Davison from that page. “This Court reviews judgments stemming\\n\\nfrom a bench trial under a mixed standard: factual findings are reviewed for clear error,\\n\\nwhereas conclusions of law are reviewed de novo.” Helton v. AT&T Inc., 709 F.3d 343,\\n\\n350 (4th Cir. 2013). Whether, under the undisputed facts, Randall acted under color of\\n\\nstate law is a legal question this Court reviews de novo. Rossignol v. Voorhaar, 316 F.3d\\n\\n516, 523 (4th Cir. 2003).\\n\\n To state a claim under Section 1983, a plaintiff must show that the alleged\\n\\nconstitutional deprivation at issue occurred because of action taken by the defendant\\n\\n“under color of . . . state law.” Philips v. Pitt Cty. Mem’l Hosp., 572 F.3d 176, 180 (4th\\n\\nCir. 2009). “The traditional definition of acting under color of state law requires that the\\n\\ndefendant in a § 1983 action have exercised power ‘possessed by virtue of state law and\\n\\nmade possible only because the wrongdoer is clothed with the authority of state law.’”\\n\\nWest v. Atkins, 487 U.S. 42, 49 (1988) (quoting United States v. Classic, 313 U.S. 299,\\n\\n\\n 17\\n\\n326 (1941)). Section 1983’s “color-of-law prerequisite is synonymous with the more\\n\\nfamiliar state-action requirement” applicable to Fourteenth Amendment claims, “and the\\n\\nanalysis for each is identical.” Pitt Cty. Mem’l Hosp., 572 F.3d at 180. Both inquiries\\n\\ndemand that “the conduct allegedly causing the deprivation of a federal right be fairly\\n\\nattributable to the State.” Holly v. Scott, 434 F.3d 287, 292 (4th Cir. 2006) (quoting\\n\\nLugar v. Edmondson Oil Co., Inc., 457 U.S. 922, 937 (1982)).\\n\\n “[T]here is no specific formula for determining whether state action is present.”\\n\\nId. at 292 (internal quotation marks omitted). Rather, “[w]hat is fairly attributable [to the\\n\\nstate]”—i.e., what constitutes action under color of state law—“is a matter of normative\\n\\njudgment, and the criteria lack rigid simplicity.” Id. (internal quotation marks omitted).\\n\\nCourts must examine the “totality of the circumstances,” id. (internal quotation marks\\n\\nomitted), to determine if the action at issue “bore a ‘sufficiently close nexus’ with the\\n\\nState to be ‘fairly treated as that of the State itself,’” Rossignol, 316 F.3d at 525 (quoting\\n\\nJackson v. Metro. Edison Co., 419 U.S. 345, 351 (1974)).\\n\\n Although no one factor is determinative, this Court has held that a defendant’s\\n\\npurportedly private actions bear a “sufficiently close nexus” with the State to satisfy\\n\\nSection 1983’s color-of-law requirement when the defendant’s challenged “actions are\\n\\nlinked to events which arose out of his official status.” Id. at 524. When a defendant’s\\n\\n“status” as a public official “enabled [her] to execute [a challenged action] in a manner\\n\\nthat private citizens never could have,” then the action also is more likely to be treated as\\n\\nattributable to the state. Id. at 526; see also Martinez v. Colon, 54 F.3d 980, 986 (1st Cir.\\n\\n1995) (“[S]ection 1983 is . . . implicated . . . [when] the conduct is such that the actor\\n\\n\\n 18\\n\\ncould not have behaved in that way but for the authority of his office.”); Goldstein v.\\n\\nChestnut Ridge Volunteer Fire Co., 218 F.3d 337, 343 (4th Cir. 2000) (holding that\\n\\nchallenged conduct is more likely to amount to state action when “the injury caused is\\n\\naggravated in a unique way by the incidents of governmental authority” (internal\\n\\nquotation marks omitted)). Likewise, an official’s conduct is more likely to amount to\\n\\nstate action when it “occurs in the course of performing an actual or apparent duty of his\\n\\noffice.” Martinez, 54 F.3d at 986. And the challenged action of a defendant\\n\\ngovernmental official is likely to be treated as taken under color of law when the official\\n\\n“use[d] the power and prestige of his state office to damage the plaintiff.” Harris v.\\n\\nHarvey, 605 F.2d 330, 337 (7th Cir. 1979). In the context of an alleged First Amendment\\n\\nviolation, in particular, this Court has found that a challenged action by a governmental\\n\\nofficial is fairly attributable to the state when “the sole intention” of the official in taking\\n\\nthe action was “to suppress speech critical of his conduct of official duties or fitness for\\n\\npublic office.” Rossignol, 316 F.3d at 524.\\n\\n Here, after thoroughly analyzing the totality of the circumstances surrounding\\n\\nRandall’s creation and administration of the Chair’s Facebook Page and banning of\\n\\nDavison from that page, the district court concluded that Randall acted under color of\\n\\nstate law. Davison, 267 F. Supp. 3d at 723. We agree.\\n\\n Randall created and administered the Chair’s Facebook Page to further her duties\\n\\nas a municipal official. She used the Chair’s Facebook Page “as a tool of governance,”\\n\\nid. at 713: through the Chair’s Facebook Page, Randall provides information to the public\\n\\n\\n\\n\\n 19\\n\\nabout her and the Loudoun Board’s official activities and solicits input from the public on\\n\\npolicy issues she and the Loudoun Board confront. See supra Part I.A.\\n\\n For instance, Randall used the Chair’s Facebook Page to inform the public about\\n\\nserious public safety events and to keep her constituents abreast of the County’s response\\n\\nto a snowstorm and to coordinate snow removal activities. And, as the district court\\n\\ncorrectly emphasized, Randall\\n\\n swathe[d] the [Chair’s Facebook Page] in the trappings of her office.\\n Among other things, (1) the title of the page includes [Randall]’s title; (2)\\n the page is categorized as that of a government official; (3) the page lists as\\n contact information [Randall]’s official County email address and the\\n telephone number of [Randall]’s County office; (4) the page includes the\\n web address of [Randall]’s official County website; (5) many—perhaps\\n most—of the posts are expressly addressed to “Loudoun,” [Randall]’s\\n constituents; (6) [Randall] has submitted posts on behalf of the [Loudoun\\n Board] as a whole; (7) [Randall] has asked her constituents to use the\\n [Chair‘s Facebook Page] as a channel for “back and forth constituent\\n conversations”; and (8) the content posted has a strong tendency toward\\n matters related to [Randall]’s office.\\n\\nDavison, 267 F. Supp. 3d at 714. A private citizen could not have created and used the\\n\\nChair’s Facebook Page in such a manner. Rossignol, 316 F.3d at 526. Put simply,\\n\\nRandall clothed the Chair’s Facebook Page in “the power and prestige of h[er] state\\n\\noffice,” Harris, 605 F.2d at 337, and created and administered the page to “perform[]\\n\\nactual or apparent dut[ies] of h[er] office,” Martinez, 54 F.3d at 986.\\n\\n Additionally, the specific actions giving rise to Davison’s claim—Randall’s\\n\\nbanning of Davison’s Virginia SGP Page—“are linked to events which arose out of h[er]\\n\\nofficial status.” Rossignol, 316 F.3d at 524. Randall’s post to the Chair’s Facebook Page\\n\\nthat prompted Davison’s comment informed the public about what happened at the\\n\\n\\n\\n 20\\n\\nLoudoun Board and Loudoun County School Board’s joint meeting. And Davison’s\\n\\ncomment also dealt with an issue related to that meeting and of significant public\\n\\ninterest—School Board members’ alleged conflicts of interest in approving financial\\n\\ntransactions. That Randall’s ban of Davison amounted to an effort “to suppress speech\\n\\ncritical of [such members’] conduct of [their] official duties or fitness for public office”\\n\\nfurther reinforces that the ban was taken under color of state law. Id. at 525. Considering\\n\\nthe totality of these circumstances, the district court correctly held that Randall acted\\n\\nunder color of state law in banning Davison from the Chair’s Facebook Page.\\n\\n C.\\n\\n Third, Randall argues that the district court erred in ruling in Davison’s favor on\\n\\nhis individual capacity First Amendment claim against Randall. Randall principally\\n\\nchallenges the district court’s conclusion that the Chair’s Facebook Page constitutes a\\n\\n“public forum” under traditional First Amendment law. We review this legal question de\\n\\nnovo. See Helton, 709 F.3d at 350.\\n\\n Under long-established First Amendment law, governmental entities are “strictly\\n\\nlimited” in their ability to regulate private speech in public fora. Pleasant Grove City,\\n\\nUtah v. Summum, 555 U.S. 460, 469 (2009). The Supreme Court has recognized two\\n\\ncategories of public fora: “traditional public forums” and “limited (or designated) public\\n\\nforums.” Am. Civil Liberties Union v. Mote, 423 F.3d 438, 443 (4th Cir. 2005).\\n\\n“Traditional” public forums—“such as streets, sidewalks, and parks”—“have the\\n\\ncharacteristics of a public thoroughfare, a purpose that is compatible with expressive\\n\\nconduct, as well as a tradition and history of being used for expressive public conduct.”\\n\\n\\n 21\\n\\nId. “Limited” or “designated” forums are forums that are “not traditionally public, but\\n\\n[that] the government has purposefully opened to the public, or some segment of the\\n\\npublic, for expressive activity.” Id. Accordingly, the hallmark of both types of public\\n\\nfora—what renders the fora “public”—is that the government has made the space\\n\\navailable—either by designation or long-standing custom—for “expressive public\\n\\nconduct” or “expressive activity,” and the space is compatible with such activity. Id.\\n\\n“Conversely, a non-public forum is one that has not traditionally been open to the public,\\n\\nwhere opening it to expressive conduct would ‘somehow interfere with the objective use\\n\\nand purpose to which the property has been dedicated.’” Id. (quoting Warren v. Fairfax\\n\\nCty., 196 F.3d 186, 190–91 (4th Cir. 1999)).\\n\\n Although neither the Supreme Court nor any Circuit has squarely addressed\\n\\nwhether, and in what circumstances, a governmental social media page—like the Chair’s\\n\\nFacebook Page—constitutes a public forum, 3 aspects of the Chair’s Facebook Page bear\\n\\nthe hallmarks of a public forum. Randall “intentionally open[ed the public comment\\n\\nsection of the Chair’s Facebook Page] for public discourse,” Cornelius v. NAACP Legal\\n\\nDefense & Educ. Fund, Inc., 473 U.S. 788, 802 (1985), inviting “ANY Loudoun citizen”\\n\\n 3\\n In addition to the court below, two other district courts have considered whether\\na government official’s social media page constituted a public forum. Those courts\\nreached conflicting results. Compare Morgan v. Bevin, 298 F. Supp. 3d 1003, 1010 (E.D.\\nKy. 2018) (holding that First Amendment forum analysis did not apply to restrictions on\\nspeech in the official Facebook and Twitter pages of the Governor of Kentucky), with\\nKnight First Amend. Inst. at Colum. Univ. v. Trump, 302 F. Supp. 3d 541, 573 (S.D.N.Y.\\n2018) (holding that the interactive component of the President’s Twitter account, as\\nopposed to the President’s tweets themselves, constituted a designated public forum),\\nappeal docketed, No. 18-1691 (2d Cir. Oct. 24, 2018).\\n\\n\\n\\n 22\\n\\nto make posts to the comments section of the Chair’s Facebook Page—the interactive\\n\\ncomponent of the page—“on ANY issues, request, criticism, complement or just your\\n\\nthoughts,” J.A. 455. Randall placed no restrictions on the public’s access to the page or\\n\\nuse of the interactive component of the Chair’s Facebook Page. And, in accordance with\\n\\nRandall’s invitation, the public made numerous posts on matters of public concern.\\n\\n The Chair’s Facebook Page also is “compatib[le] with expressive activity.”\\n\\nCornelius, 473 U.S. at 802. “Congress [has] recognized the internet and interactive\\n\\ncomputer services as offering ‘a forum for a true diversity of political discourse, unique\\n\\nopportunities for cultural development, and myriad avenues for intellectual activity.’”\\n\\nZeran v. Am. Online, Inc., 129 F.3d 327, 330 (4th Cir. 1997) (quoting 47 U.S.C. §\\n\\n230(a)(3)); cf. Bland, 730 F.3d at 386 (finding post to campaign Facebook page\\n\\n“constituted pure speech”). And the Supreme Court recently analogized social media\\n\\nsites, like the Chair’s Facebook Page, to “traditional” public forums, characterizing the\\n\\ninternet as “the most important place[] (in a spacial sense) for the exchange of views.”\\n\\nPackingham v. North Carolina, 137 S. Ct. 1730, 1735 (2017). An “exchange of views”\\n\\nis precisely what Randall sought—and what in fact transpired—when she expressly\\n\\ninvited “ANY Loudoun citizen” to visit the page and comment “on ANY issues,” and\\n\\nreceived numerous such posts and comments. J.A. 455.\\n\\n Randall nevertheless argues that traditional public forum analysis should not apply\\n\\nto the Chair’s Facebook Page for two reasons: (1) the Chair’s Facebook Page is “a private\\n\\nwebsite” and therefore does not constitute “public property” susceptible to forum\\n\\nanalysis, and (2) the Chair’s Facebook Page, in its entirety, constitutes “government\\n\\n\\n 23\\n\\nspeech” properly analyzed under the framework set forth in Pleasant Grove. Randall’s\\n\\nBr. at 19–21, 29–31. We disagree.\\n\\n Even assuming the intangible space at issue is “private property,” as Randall\\n\\nclaims—which is not at all clear from the record before us 4—the Supreme Court never\\n\\nhas circumscribed forum analysis solely to government-owned property. For example, in\\n\\nCornelius, the Court recognized that forum analysis applies “to private property\\n\\ndedicated to public use.” Cornelius, 473 U.S. at 801 (emphasis added); see also\\n\\nChristian Legal Soc’y Chapter of the Univ. of Cal. v. Martinez, 561 U.S. 661, 679 (2010)\\n\\n(“[T]his Court has employed forum analysis to determine when a governmental entity, in\\n\\nregulating property in its charge, may place limitations on speech.” (emphasis added)).\\n\\n 4\\n The Facebook “platform” and the “software” that underlies that platform is,\\naccording to Facebook’s Terms of Service, property of Facebook, Inc. Terms of Service,\\nFacebook, https://www.facebook.com/terms.php (last visited Jan. 4, 2019). Facebook’s\\nTerms of Service further provide that users “own the content [they] create and share on\\nFacebook and the other Facebook Products,” including Pages. Id. There would seem to\\nbe a good argument, therefore, that content created, and posted to Facebook, by\\ngovernment officials performing the functions and duties of their offices constitutes\\ngovernment property. Cf. Solomons v. United States, 137 U.S. 342, 346–48 (1890)\\n(holding that intellectual property created by government employee in the course of his\\nofficial duties constituted government property because “[i]f one is employed to devise or\\nperfect an instrument, or a means for accomplishing a prescribed result, he cannot, after\\nsuccessfully accomplishing the work for which he was employed, plead title thereto as\\nagainst his employer”). Likewise, under Facebook’s Terms of Service, the posts and\\ncomments by individual Facebook users—like Davison—to a Facebook Page—like the\\nChair’s Facebook Page—constitute property of those users. Accordingly, a single\\nFacebook Page—including the Chair’s Facebook Page—encompasses a web of property\\nrights, some of which may lie with the government. We need not—and thus do not—\\ndecide with whom these property rights lie in this particular case, however, because we\\nhold that even assuming the Chair’s Facebook Page constitutes private property, Randall,\\nacting under color of state law, exercised control over the aspects of that page giving rise\\nto Davison’s claim.\\n\\n\\n\\n 24\\n\\nAnd the Supreme Court and lower courts have held that private property, whether\\n\\ntangible or intangible, constituted a public forum when, for example, the government\\n\\nretained substantial control over the property under regulation or by contract. See, e.g.,\\n\\nSe. Promotions, Ltd. v. Conrad, 420 U.S. 546, 547, 555 (1975) (holding that “a privately\\n\\nowned Chattanooga theater under long-term lease to the city” was a “public forum[]\\n\\ndesigned for and dedicated to expressive activities”); Halleck v. Manhattan Community\\n\\nAccess Corp., 882 F.3d 300, 306–07 (2d Cir. 2018) (holding that public access television\\n\\nchannels operated by a private non-profit corporation constituted public forums), cert.\\n\\ngranted 139 S. Ct. 360 (2018) (mem.); First Unitarian Church of Salt Lake City v. Salt\\n\\nLake City Corp., 308 F.3d 1114, 1122 (10th Cir. 2002) (“[F]orum analysis does not\\n\\nrequire that the government have a possessory interest in or title to the underlying land.\\n\\nEither government ownership or regulation is sufficient for a First Amendment forum of\\n\\nsome kind to exist.”); Freedom from Religion Foundation, Inc. v. City of Marshfield,\\n\\nWis., 203 F.3d 487, 494 (7th Cir. 2000) (holding that private property abutted by public\\n\\npark constituted public forum).\\n\\n Significantly, even assuming the relevant aspects of the Chair’s Facebook Page\\n\\nconstitute private property—which, again, is not entirely clear from the record before\\n\\nus—Randall, acting under color of state law, retained and exercised significant control\\n\\nover the page. She created the Chair’s Facebook Page. She designated the page as\\n\\nbelonging to a “governmental official.” She clothed the page in the trappings of her\\n\\npublic office. She chose to list her official contact information on the page. And she\\n\\n\\n\\n\\n 25\\n\\ncurated the links in the left column of the page and the lists of Facebook Pages or profiles\\n\\n“liked” by the Chair’s Facebook Page in the right column.\\n\\n Of particular importance, Randall had complete control over the aspect of the\\n\\nChair’s Facebook Page giving rise to Davison’s challenge because, as administrator of\\n\\nthe page, Randall had authority to ban Facebook profiles or Pages from using the Chair’s\\n\\nFacebook Page—and, therefore, the interactive component of the page—authority she\\n\\nexercised in banning Davison’s Virginia SGP Page. Cf. Knight, 302 F. Supp. 3d at 566–\\n\\n67 (holding that the interactive component of the President’s Twitter account constituted\\n\\npublic forum because the President and his advisors “exercise control over various\\n\\naspects of the . . . account,” including the power to block other users from accessing the\\n\\naccount).\\n\\n The Second Circuit’s decision in Halleck dealing with privately operated public\\n\\naccess television channels is instructive. Federal law allows cable franchising authorities\\n\\nto require cable operators to designate channel capacity for public use. Halleck, 882 F.3d\\n\\nat 302. Likewise, New York regulations oblige cable operators to designate at least one\\n\\nchannel for full-time public use. Id. Pursuant to that authority, the City of New York\\n\\nentered into a cable franchise agreement with a cable company requiring the company to\\n\\nmake available four public access channels, which channels were operated by a private,\\n\\nnon-profit corporation, MNN. Id. Several producers of public access programming sued\\n\\nMNN, alleging that MNN violated the producers’ First Amendment rights by indefinitely\\n\\nsuspending them from using the public access channels “because of disapproval of the\\n\\ncontent of a TV program” they had submitted for airing. Id.\\n\\n\\n 26\\n\\n The Second Circuit concluded that the public access channels constituted a public\\n\\nforum, notwithstanding that they were operated by a private company. Id. at 306–08.\\n\\nThe court reached that conclusion for two reasons. First, it pointed to the similarities\\n\\nbetween public access channels and traditional public forums, like parks, describing “[a]\\n\\npublic access channel [a]s the electronic version of the public square.” Id. at 306.\\n\\nSecond, the court emphasized the extensive government involvement with, and control\\n\\nover, public access channels by virtue of the federal and state regulatory schemes. See id.\\n\\n(“[W]here, as here, federal law authorizes setting aside channels to be ‘the electronic\\n\\nmarketplace of ideas,’ state regulation requires cable operators to provide at least one\\n\\npublic access channel, a municipal contract requires a cable operator to provide four such\\n\\nchannels, and a municipal official has designated a private corporation to run those\\n\\nchannels, those channels are public forums.” (emphasis added)).\\n\\n Although not subject to the extensive federal and state regulatory regime\\n\\napplicable in Halleck, 5 the Chair’s Facebook Page is in many ways analogous to the\\n\\nprivately-operated public access channels considered by the Second Circuit. Just as the\\n\\nfederal government sought to establish an “electronic marketplace of ideas” by\\n\\nmandating provision of public access channels, Randall expressly sought to—and did, in\\n\\n\\n 5\\n The federal Communications Decency Act allows private online intermediaries,\\nlike Facebook, the ability to moderate content by providing such intermediaries with\\nbroad immunity from user-generated content posted on their sites. 47 U.S.C. § 230. This\\nCourt has recognized that an “important purpose of § 230 was to encourage service\\nproviders to self-regulate the dissemination of offensive material over their services.”\\nZeran, 129 F.3d at 331.\\n\\n\\n\\n 27\\n\\nfact—create an “electronic marketplace of ideas” by inviting “ANY” constituent to post\\n\\nto the Chair Page on “ANY issues.” J.A. 455. Likewise, just as the City of New York\\n\\nchose to have a private corporation operate the public access channels, Randall chose to\\n\\ncreate her electronic marketplace of ideas, the Chair’s Facebook Page, on a private\\n\\nplatform, Facebook. Indeed, the present case provides a stronger basis for treating the\\n\\ninteractive component of the Chair’s Facebook Page as a public forum because whereas\\n\\nthe private corporation in Halleck, MNN, exercised control over the aspect of the public\\n\\naccess channel giving rise to the First Amendment claim—banning the public access\\n\\nprogram producer—a public official, Randall exercised unconstrained control over the\\n\\naspect of the Chair’s Facebook Page giving rise to Davison’s claim—banning of other\\n\\nFacebook profiles and Pages. 6\\n\\n\\n 6\\n On October 12, 2018, the Supreme Court granted MNN’s petition for writ of\\ncertiorari in Halleck. 139 S. Ct. 360. MNN’s petition presented two questions: (1)\\n“[w]hether the Second Circuit erred in rejecting th[e Supreme] Court’s state actor tests\\nand instead creating a per se rule that private operators of public access channels are state\\nactors subject to constitutional liability” and (2) “[w]hether the Second Circuit erred in\\nholding—contrary to the Sixth and D.C. Circuits—that private entities operating public\\naccess televisions stations are state actors for constitutional purposes where the state has\\nno control over the private entity’s board or operations.” Petition for Writ of Certiorari i,\\nManhattan Community Access Corp. v. Halleck, --- S. Ct. --- (No. 17-1702). MNN’s\\nargument before the Supreme Court, therefore, focuses on the Second Circuit’s\\ndetermination that MNN constituted a state actor, not the court’s determination that the\\npublic access channels constituted a public forum.\\n\\n Although not identified as an issue on appeal, MNN’s petition also took issue with\\nthe Second Circuit’s determination that the public access channels operated by MNN\\nconstituted a public forum. But that contention was entirely derivative of its state action\\nargument. In particular, MNN objected to the Second Circuit’s public forum conclusion\\nonly because the public access channels were privately operated and because, in its\\nopinion, the Second Circuit’s purportedly “categorical” holding that public access\\n(Continued)\\n\\n 28\\n\\n Not only does case law contradict Randall’s argument that public forum analysis\\n\\nnever applies to private property, her argument also fails because it makes no legal sense\\n\\nto establish a bright-line rule that forum analysis applies only to government-owned\\n\\nproperty. Why, for example, should the First Amendment allow a municipality to engage\\n\\nin viewpoint discrimination in curating a public library branch in leased space but not\\n\\nallow the municipality to engage in such discrimination in a library branch on\\n\\nmunicipally owned property? Cf. Bd. of Educ., Island Trees Union Free Sch. Dist. No.\\n\\n26 v. Pico, 457 U.S. 853, 870–71 (1982) (plurality op.) (“If a Democratic school board,\\n\\nmotivated by partisan affiliation, ordered removal of all books written by or in favor of\\n\\nRepublicans, few would doubt that the order violated the constitutional rights of the\\n\\nstudents denied access to those books.”). Or why should a municipality be allowed to\\n\\nengage in viewpoint discrimination when holding a virtual public meeting hosted on a\\n\\nprivate website when such discrimination would be unconstitutional if the meeting was\\n\\nheld in a governmental building? Cf. Lyrissa Lidsky, Public Forum 2.0, 91 B.U. L. Rev.\\n\\n1975, 1996 (2011) (“Just as the government can rent a building to use as a forum for\\n\\npublic debate and discussion, so, too, can it ‘rent’ a social media page for the promotion\\n\\n\\n\\nchannels constitute public forums ignore[d] “the far more critical issue of whether (and to\\nwhat extent) there is government control over a public access channel.” Id. at 19–20.\\n\\n Here, a government official acting under color of state law, Randall, exercised\\nunconstrained control over the aspect of the Chair’s Facebook Page giving rise to\\nDavison’s claim.\\n\\n\\n\\n\\n 29\\n\\nof public discussion.”). We do not believe the First Amendment draws such arbitrary\\n\\nlines.\\n\\n Randall’s second argument—that the Chair’s Facebook Page amounts to\\n\\n“government speech”—fails to recognize the meaningful difference between Randall’s\\n\\nposts to the Chair’s Facebook Page and the public comments and posts she invited in the\\n\\npage’s interactive space. To be sure, Randall’s comments and curated references on the\\n\\nChair’s Facebook Page to other Pages, personal profiles, and websites amount to\\n\\ngovernmental speech. See Sutliffe v. Epping School Dist., 584 F.3d 314, 329–30 (1st Cir.\\n\\n2009) (holding that municipality’s refusal to place hyperlink on municipal website to\\n\\nwebsite of group opposed to municipal budget constituted government speech); Page v.\\n\\nLexington Cty. School Dist. One, 531 F.3d 275, 283–85 (4th Cir. 2008) (holding that\\n\\nSchool District’s refusal to place hyperlink on its website to website of group that\\n\\nopposed School District’s position on pending legislation constituted government speech\\n\\nbecause, in part, “the links to other websites were selected by the School District alone as\\n\\nones that supported its own message”); Knight, 302 F. Supp. 3d at 571 (“[T]he\\n\\nPresident’s tweets are [not] susceptible to forum analysis . . . because the content is\\n\\ngovernment speech.”).\\n\\n But the interactive component of the Chair’s Facebook Page—the portion of the\\n\\nmiddle column in which the public can post comments, reply to posts, and “like”\\n\\ncomments and posts—is materially different. See Knight, 302 F. Supp. 3d at 572\\n\\n(distinguishing a government official’s tweets and “the interactive space for replies and\\n\\nretweets”). Randall placed no formal limitations on the ability of Facebook personal\\n\\n\\n 30\\n\\nprofiles and Pages to access the Chair’s Facebook Page and make comments and posts to\\n\\nthe interactive component of the page. On the contrary, she expressly invited posts to the\\n\\npage “from ANY Loudon citizen on ANY issues, request, criticism, complement or just\\n\\nyour thoughts.” J.A. 455. And comments and posts by users cannot be mistaken for\\n\\nRandall’s own speech because they identify the posting or replying personal profile or\\n\\nPage, and thereby distinguish that user from Randall.\\n\\n Contrary to Randall’s argument that the Chair’s Facebook Page, in its entirety,\\n\\namounts to government speech, the present case also is meaningfully distinguishable\\n\\nfrom the government speech framework identified in Pleasant Grove. There, a\\n\\nmunicipality denied a private religious group’s request to allow it to erect a “monument\\n\\nin a city park in which other donated monuments were previously erected,” including a\\n\\nmonument depicting a prominent symbol of a different religion. 555 U.S. at 464. The\\n\\nplaintiff religious group sought relief under the First Amendment, arguing that the city\\n\\npark constituted a traditional public forum, and therefore that the city could not reject the\\n\\nreligious group’s proposed monument when it had previously allowed construction of a\\n\\nmonument associated with another religion. Id. at 466.\\n\\n The Supreme Court held that the city did not violate the First Amendment because\\n\\nthe government speech framework, rather than forum analysis, applied to the conduct at\\n\\nissue. In reaching that conclusion, the Court emphasized that the city never “opened up\\n\\nthe Park for the placement of whatever permanent monuments might be offered by\\n\\nprivate donors.” Id. at 472–73. “Rather, the City has ‘effectively controlled’ the\\n\\nmessages sent by the monuments in the Park by exercising ‘final approval authority’ over\\n\\n\\n 31\\n\\ntheir selection.” Id. at 473. The Court further emphasized that “[t]he forum doctrine has\\n\\nbeen applied in situations in which government-owned property or a government\\n\\nprogram was capable of accommodating a large number of public speakers without\\n\\ndefeating the essential function of the land or the program.” Id. at 478. A city park,\\n\\nhowever, “can accommodate only a limited number of permanent monuments,” and\\n\\ntherefore a municipality cannot—and need not—provide park space for all who wish to\\n\\nerect a monument. Id.\\n\\n Here, Randall “effectively controlled” certain aspects of the Chair’s Facebook\\n\\nPage: she curated the Chair’s Facebook Page’s left and right columns and made posts to\\n\\nthe middle column. Id. at 472. But Randall also expressly opened the Chair’s Facebook\\n\\nPage’s middle column—its interactive space—for “ANY” user to post on “ANY issues,”\\n\\nJ.A. 455, and therefore did not retain “final approval authority” over that aspect of the\\n\\nChair’s Facebook Page, Pleasant Grove, 555 U.S. at 473. Just as the parkland\\n\\nsurrounding monuments in Pleasant Grove continued to constitute a public forum, even\\n\\nthough the monuments themselves constituted government speech, so too the interactive\\n\\ncomponent of the Chair’s Facebook Page constitutes a public forum, even though\\n\\nRandall’s curation of and posts to the Chair’s Facebook Page amount to government\\n\\nspeech. Additionally, the interactive component of the Chair’s Facebook Page does not\\n\\nface the same spacial limitations as those of the park in Pleasant Grove, but instead is\\n\\n“capable of accommodating a large number of public speakers without defeating [its]\\n\\nessential function.” Id. at 578. Accordingly, Pleasant Grove supports, rather than\\n\\n\\n\\n\\n 32\\n\\nundermines, our conclusion that the interactive component of the Chair’s Facebook Page\\n\\nconstitutes a public forum.\\n\\n Upon concluding that interactive component of the Chair’s Facebook Page\\n\\namounts to a public forum, we would normally need to determine whether it constitutes a\\n\\ntraditional public forum or designated or limited public forum. In the present case,\\n\\nhowever, we need not decide that question because Randall’s ban of Davison amounted\\n\\nto “viewpoint discrimination,” which is “prohibited in all forums.” See Child Evangelism\\n\\nFellowship of S.C. v. Anderson Sch. Dist. Five, 470 F.3d 1062, 1067 n.2 (4th Cir. 2006).\\n\\n“Viewpoint discrimination . . . ‘targets not subject matter, but particular views taken by\\n\\nspeakers on a subject.’” Id. (quoting Rosenberger v. Rector & Visitors of Univ. of Va.,\\n\\n515 U.S. 819, 829 (1995)). Viewpoint discrimination is apparent, for example, if a\\n\\ngovernment official’s decision to take a challenged action was “impermissibly motivated\\n\\nby a desire to suppress a particular point of view.” Cornelius, 473 U.S. at 812–13.\\n\\n Here, the district court found—as the record amply supports—that Randall banned\\n\\nDavison’s Virginia SGP Page because Davison posted a comment using that page\\n\\nalleging “corruption on the part of Loudoun County’s School Board involving conflicts\\n\\nof interests among the School Board and their family members.” Davison, 267 F. Supp.\\n\\n3d at 711. Although Randall stated that she had “no idea” whether Davison’s allegations\\n\\nwere “correct,” she nonetheless banned him because she viewed the allegations as\\n\\n“slanderous” and she “didn’t want [the allegations] on the site.” Id. at 717. Randall’s\\n\\ndecision to ban Davison because of his allegation of governmental corruption constitutes\\n\\nblack-letter viewpoint discrimination.\\n\\n\\n 33\\n\\n Put simply, Randall unconstitutionally sought to “suppress” Davison’s opinion\\n\\nthat there was corruption on the School Board. Cornelius, 473 U.S. at 812–13; see also,\\n\\ne.g., Rossignol, 316 F.3d at 521 (holding that sheriff’s deputies engaged in viewpoint\\n\\ndiscrimination when they seized an issue of a newspaper that criticized the county\\n\\nsheriff’s and his deputies’ performance of their official duties); Putnam Pit, Inc. v. City of\\n\\nCookeville, Tenn., 221 F.3d 834, 846 (6th Cir. 2000) (holding that a municipality engages\\n\\nin viewpoint discrimination if it refuses to link newspaper webpage to the city’s website\\n\\nsolely because the newspaper sought to expose municipal corruption); Knight, 302 F.\\n\\nSupp. 3d at 575 (holding that the President engaged in viewpoint discrimination when he\\n\\nblocked individuals from his Twitter account because the individuals “posted tweets that\\n\\ncriticized the President or his policies”). 7 That Randall’s action targeted comments\\n\\ncritical of the School Board members’ official actions and fitness for office renders the\\n\\nbanning all the more problematic as such speech “occupies the core of the protection\\n\\nafforded by the First Amendment.” Rossignol, 316 F.3d at 521 (quoting McIntyre v.\\n\\nOhio Elections Comm’n, 514 U.S. 334, 346 (1995)).\\n\\n In sum, the interactive component of the Chair’s Facebook Page constituted a\\n\\npublic forum, and Randall engaged in unconstitutional viewpoint discrimination when\\n\\nshe banned Davison’s Virginia SGP Page from that forum.\\n\\n\\n 7\\n Randall also asserts that she did not violate Davison’s First Amendment rights\\nbecause she banned his “Virginia SGP” Page, not his “Brian Davison” profile. Davison\\nis the sole operator of the “Virginia SGP” Page, however, and therefore the ban\\nimplicated his First Amendment rights. Randall fails to identify any case supporting her\\nposition, nor have we found any. Accordingly, we reject this argument.\\n\\n\\n 34\\n\\n III.\\n\\n In his cross-appeal, Davison asserts that the district court reversibly erred in two\\n\\nways: (A) by dismissing his claim against Randall in her official capacity and (B) by\\n\\ndenying his motion to amend his complaint to add the new First Amendment claim\\n\\nagainst the Loudoun Board. 8 We disagree.\\n\\n A.\\n\\n Davison first argues that the district court erred in dismissing his claim against\\n\\nRandall in her official capacity. Whereas “[p]ersonal-capacity suits seek to impose\\n\\npersonal liability upon a government official for actions [she] takes under color of state\\n\\nlaw,” Kentucky v. Graham, 473 U.S. 159, 165 (1985), “official capacity suits are ‘treated\\n\\nas suits against the municipality,’” Santos v. Frederick Cty. Bd. of Comm’rs, 725 F.3d\\n\\n451, 469 (4th Cir. 2013) (quoting Hafer v. Melo, 502 U.S. 21, 25 (1991)). Because\\n\\n“municipal liability under Section 1983 does not amount to respondeat superior . . . a\\n\\n 8\\n Davison also argues that the district court erred in rejecting his procedural due\\nprocess claims under the Fourteenth Amendment and an analogous provision in the\\nVirginia Constitution. Before the district court, Davison “flatly asserted that due process\\nalways requires the government to provide a hearing before imposing a prior restraint on\\nspeech,” and therefore that Randall violated Davison’s First Amendment rights by failing\\nto conduct a pre-ban hearing. Davison, 267 F. Supp. 3d at 719. The district court\\ncorrectly rejected Davison’s proposed categorical rule. Id. (citing Cafeteria & Rest.\\nWorkers Union Local 473, AFL-CIO v. McElroy, 367 U.S. 886, 895 (1961). And\\nDavison has abandoned that asserted categorical rule on appeal, Davison’s Br. at 49–50\\nn.19 (“[I]t might be permissible in certain contexts to delete an individual comment\\nwithout providing full pre-deprivation process . . . .”), instead arguing he is entitled to\\nrelief under the balancing test set forth in Mathews v. Eldridge, 424 U.S. 319, 334–35\\n(1976). Because Davison did not make that argument before the district court, we decline\\nto consider it now. See CoreTel Va., LLC v. Verizon Va., LLC, 808 F.3d 978, 988 (4th\\nCir. 2015).\\n\\n\\n\\n 35\\n\\nmunicipality is subject to Section 1983 liability only when its ‘policy or custom, whether\\n\\nmade by its lawmakers or by those whose edicts or acts may fairly be said to represent\\n\\nofficial policy, inflicts the [plaintiff’s] injury.’” Id. at 469–70 (quoting Monell v. Dep’t of\\n\\nSoc. Servs. of the City of N.Y., 436 U.S. 658, 694 (1978)).\\n\\n Here, the district court dismissed Davison’s official capacity claim because it\\n\\nfound that “no policy—whether County-wide or specific to [Randall]’s office—played\\n\\nany role in [Randall]’s decision to ban [Davison] from her [Chair’s Facebook Page].”\\n\\nDavison, 267 F. Supp. 3d at 715. We review the district court’s factual findings bearing\\n\\non whether Randall acted pursuant to a municipal policy or custom for clear error and its\\n\\nlegal conclusions de novo. Helton, 709 F.3d at 350.\\n\\n On appeal, Davison does not dispute the district court’s finding—which the record\\n\\namply supports—that Loudoun County did not promulgate a policy governing individual\\n\\nLoudoun Board members’ Facebook pages. Rather, Davison principally 9 argues that “the\\n\\ncounty can be held liable for Randall’s actions because in banning Davison, Randall\\n\\nacted as a municipal policymaker.” Davison’s Br. at 47.\\n\\n\\n\\n\\n 9\\n Davison also argues the Loudoun Board’s failure to adopt a policy pertaining to\\nindividual board members’ Facebook pages gives rise to an official capacity claim\\nbecause it establishes that the Loudoun “Board was—and remains—deliberately\\nindifferent to the likelihood of unconstitutional censorship and viewpoint-based\\ndiscrimination on individual supervisors’ social media sites.” Davison’s Br. at 46. But\\nDavison never advanced a “deliberate indifference” theory of municipal liability before\\nthe district court. Again, we decline to consider an argument Davison raises for the first\\ntime on appeal. See CoreTel, LLC, 808 F.3d at 988.\\n\\n\\n\\n 36\\n\\n Davison is correct that “municipal liability may be imposed for a single decision\\n\\nby municipal policymakers under appropriate circumstances.” Hunter v. Town of\\n\\nMocksville, N.C., 897 F.3d 538, 554 (4th Cir. 2018) (quoting Pembaur v. City of\\n\\nCincinnati, 475 U.S. 469, 480 (1986)). “[I]n assessing whether a municipality may be\\n\\nheld liable for constitutional or statutory violations of their decisionmakers, the\\n\\ntouchstone inquiry is whether ‘the decisionmaker possesses final authority to establish\\n\\nmunicipal policy with respect to the action ordered.’” Id. at 554–55 (emphasis added)\\n\\n(quoting Liverman v. City of Petersburg, 844 F.3d 400, 413 (4th Cir. 2016)).\\n\\n Here, Davison failed to put forward evidence establishing that Randall was a final\\n\\nmunicipal policymaker with regard to her banning of Davison from the Chair’s Facebook\\n\\nPage. On the contrary, record evidence establishes that the Loudoun Board retained\\n\\nauthority to establish municipal policy with respect to social media pages, as it adopted a\\n\\nsocial media policy governing the County’s official social media pages. Davison\\n\\nconcedes as much, arguing that the Loudoun Board “neglected . . . to extend its written\\n\\nguidelines to Board members’ official pages.” Davison’s Br. at 46. But that argument\\n\\npresupposes that the Loudoun Board—not Randall—had authority to establish municipal\\n\\npolicy with respect “to Board members’ official pages.”\\n\\n Davison nevertheless argues that the Loudoun Board “implicitly” delegated its\\n\\nfinal policymaking authority to Randall by not addressing individual Loudoun Board\\n\\nmembers’ official pages in its social media policy. Davison is correct that delegation of\\n\\nfinal policy making authority may be “implied from a continued course of knowing\\n\\nacquiescence by the governing body in the exercise of policymaking authority by an\\n\\n\\n 37\\n\\nagency or official.” Id. at 48 (quoting Spell v. McDaniel, 824 F.2d 1380, 1387 (4th Cir.\\n\\n1987)). But Davison identifies no evidence that the Loudoun Board knew of the Chair’s\\n\\nFacebook Page, let alone that it “aquiesce[d]” in Randall’s administration of the page and\\n\\nbanning of Davison, in particular. On the contrary, the district court found that Randall\\n\\nmade a one-off, “unilateral decision to ban [Davison] in the heat of the moment, and\\n\\nreconsidered soon thereafter,” Davison, 267 F. Supp. 3d at 715—before the Loudoun\\n\\nBoard had a chance to learn of her action. In such circumstances, the district court did\\n\\nnot reversibly err in rejecting Davison’s official capacity claim.\\n\\n B.\\n\\n Next, Davison argues that the district court erred in denying him leave to amend\\n\\nhis complaint to add a claim that “the County violates the First Amendment by\\n\\nmaintaining a limited public forum on Facebook,” when policies imposed by Facebook,\\n\\nrather than the County, restrain, or have the potential to restrain, speech. J.A. 74. “A\\n\\ndistrict court may deny a motion to amend when the amendment would be prejudicial to\\n\\nthe opposing party, the moving party has acted in bad faith, or the amendment would be\\n\\nfutile.” Equal Rights Ctr. v. Niles Bolton Assocs., 602 F.3d 597, 603 (4th Cir. 2010).\\n\\nThe magistrate judge recommended—and the district court agreed—that Davison be\\n\\ndenied leave to amend on grounds of both futility and prejudice. We review for abuse of\\n\\ndiscretion a district court’s denial of leave to amend for prejudice, whereas we review de\\n\\nnovo a district court’s denial of leave to amend on the basis of futility. See U.S. ex rel.\\n\\nAhumada v. NISH, 756 F.3d 268, 274 (4th Cir. 2014).\\n\\n\\n\\n\\n 38\\n\\n Regarding prejudice, the district court determined that the amendment came “too\\n\\nlate in these proceedings” and would “add a new, novel legal theory to the case after the\\n\\nclose of discovery, after the existing claims against [the Loudoun Board] have been\\n\\nshown to be meritless, after the point at which Defendants could have addressed the\\n\\nclaim in briefing before trial, and on the eve of trial.” J.A. 74. The district court did not\\n\\nabuse its discretion in denying leave to amend in such circumstances. See, e.g., Equal\\n\\nRights Ctr., 602 F.3d at 603–04 (holding that district court did not abuse its discretion in\\n\\ndenying leave to amend on the basis of prejudice when amendment came after the close\\n\\nof discovery and “on the eve of the deadline for dispositive motions” and therefore\\n\\n“would [have] change[d] the nature of the litigation”); Deasy v. Hill, 833 F.2d 38, 41 (4th\\n\\nCir. 1987) (affirming denial of leave to amend on grounds of prejudice when “the motion\\n\\nto amend came right before trial and after discovery was complete”).\\n\\n Although we affirm the district court’s judgment on the basis of its finding of\\n\\nprejudice, we do not concur in its conclusion as to futility. “Futility is apparent if the\\n\\nproposed amended complaint fails to state a claim under the applicable rules and\\n\\naccompanying standards.” Katyle v. Penn Nat. Gaming, Inc., 637 F.3d 462, 471 (4th Cir.\\n\\n2011). Accordingly, Davison’s proposed amendment was futile if the new claim would\\n\\nnot have survived a motion to dismiss under Federal Rule of Civil Procedure 12(b)(6).\\n\\nSee Runnion ex rel. Runnion v. Girl Scouts of Greater Chicago & Nw. Ind., 786 F.3d 510,\\n\\n524 (7th Cir. 2015) (“[W]hen the basis for denial is futility, we apply the legal\\n\\nsufficiency standard of Rule 12(b)(6) to determine whether the proposed amended\\n\\ncomplaint fails to state a claim.”).\\n\\n\\n 39\\n\\n Davison’s proposed First Amendment claim deals not with the Chair’s Facebook\\n\\nPage—which the Loudoun Board did not authorize or attempt to regulate—but rather\\n\\nwith Loudoun County’s official Facebook Pages created and maintained pursuant to the\\n\\nLoudoun Board’s social media policy. As with his claims related to the Chair’s\\n\\nFacebook Page, Davison alleged that the Facebook Pages created and maintained by the\\n\\nLoudoun Board constituted public forums subject to the First Amendment. Davison\\n\\ntheorized that the Loudoun Board’s decision to use Facebook as its social media forum\\n\\nviolated his First Amendment rights because Facebook rules permit individual\\n\\n“requesting” users to ban other personal profiles and Pages such that the banned users can\\n\\nno longer see posts authored by the requesting users. In such circumstances, the banned\\n\\nusers “cannot see [the requesting user’s] comment[s] or participate in the discussion\\n\\nsurrounding the [requesting] party’s comment.” Davison’s Br. at 59. Davison’s\\n\\nproposed amended complaint asserted that “this scenario violates the First Amendment\\n\\nbecause Loudoun County has effectively enabled third parties to exclude discussion\\n\\nwithin a public forum—something a government body could not permissibly do in a\\n\\nphysical forum.” Id. at 59–60 (internal citation omitted). Put differently, Davison\\n\\ntheorized that Loudoun County violated the First Amendment by choosing to use\\n\\nFacebook as a public forum, when rules imposed by Facebook allow private users to\\n\\nrestrict access to their posts—and comments on and responses to those posts—including\\n\\nposts to any municipal Facebook Page.\\n\\n No court appears to have addressed that novel legal theory. And although the First\\n\\nAmendment constrains only government policies, not policies established by private\\n\\n\\n 40\\n\\nentities, one can conceive of a colorable legal argument that a governmental actor’s\\n\\ndecision to select a private social media website for use as a public forum—and therefore\\n\\nselect that website’s suite of rules and regulations—could violate the First Amendment, if\\n\\nthe private website included certain types of exclusionary rules. For example, if the\\n\\ngovernment chose as its electronic public forum a social media site that allowed only\\n\\nregistered members of one political party to post and comment, there would seem to be a\\n\\ncompelling argument that the government’s selection of that social media site violated the\\n\\nFirst Amendment rights of members of other political parties, even if the partisan\\n\\nrestriction was imposed by the private company, not the governmental body. Such a\\n\\nrestriction would be seem to be no different than a municipality choosing to hold a town\\n\\nhall meeting in a venue that refused admission to individuals associated with a disfavored\\n\\npolitical party or viewpoint. Cf. DeBoer v. Village of Oak Park, 267 F.3d 558, 571 (7th\\n\\nCir. 2001) (“[T]he government engages in viewpoint discrimination when it denies access\\n\\nto a speaker solely to suppress the point of view he espouses on an otherwise includible\\n\\nsubject.”).\\n\\n Given that Davison’s proposed claim asserted a novel and colorable legal theory\\n\\nand that “Rule 12(b)(6) dismissals are especially disfavored in cases where the complaint\\n\\nsets forth a novel legal theory that can best be assessed after factual development,”\\n\\nWright v. North Carolina, 787 F.3d 256, 263 (4th Cir. 2015) (internal quotation marks\\n\\nomitted), we affirm the district court’s denial of Davison’s motion for leave to amend his\\n\\ncomplaint on the basis of its finding of prejudice but not on the basis of futility.\\n\\n IV.\\n\\n\\n 41\\n\\nFor the foregoing reasons, we affirm the judgment of the district court.\\n\\n AFFIRMED\\n\\n\\n\\n\\n 42\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":85,"cells":{"id":{"kind":"number","value":4579688,"string":"4,579,688"},"name":{"kind":"string","value":"William D. BATTLE, III, Plaintiff - Appellant, v. J. LEDFORD, Correctional Officer; R. Edwards, Correctional Officer; Gregory Holloway, Warden of Wallens Ridge State Prison; George Hinkle, Regional Administrator for Virginia Department of Corrections, Defendants - Appellees."},"name_abbreviation":{"kind":"string","value":"William Battle, III v. J. Ledford"},"decision_date":{"kind":"string","value":"2019-01-08"},"docket_number":{"kind":"string","value":"17-6287"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Motz, Duncan, Thacker\", \"parties\": \"\", \"opinions\": [{\"author\": \"DIANA GRIBBON MOTZ, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-6287\\n\\n\\nWILLIAM D. BATTLE, III,\\n\\n Plaintiff - Appellant,\\n\\n v.\\n\\nJ. LEDFORD, Correctional Officer; R. EDWARDS, Correctional Officer;\\nGREGORY HOLLOWAY, Warden of Wallens Ridge State Prison; GEORGE\\nHINKLE, Regional Administrator for Virginia Department of Corrections,\\n\\n Defendants - Appellees.\\n\\n\\nAppeal from the United States District Court for the Western District of Virginia, at\\nRoanoke. Elizabeth Kay Dillon, District Judge. (7:16-cv-00020-EKD-RSB)\\n\\n\\nArgued: September 25, 2018 Decided: January 8, 2019\\n\\n\\nBefore MOTZ, DUNCAN, and THACKER, Circuit Judges.\\n\\n\\nVacated and remanded by published opinion. Judge Motz wrote the opinion, in which\\nJudge Duncan and Judge Thacker joined.\\n\\n\\nARGUED: Sarah Crandall, Elizabeth Joynes, UNIVERSITY OF VIRGINIA SCHOOL\\nOF LAW, Charlottesville, Virginia, for Appellant. Michelle Shane Kallen, OFFICE OF\\nTHE ATTORNEY GENERAL OF VIRGINIA, Richmond, Virginia, for Appellees. ON\\nBRIEF: Joseph Charlet, Third Year Law Student, Megan Keenan, Third Year Law\\nStudent, Evan Ward, Third Year Law Student, Appellate Litigation Clinic,\\nUNIVERSITY OF VIRGINIA SCHOOL OF LAW, Charlottesville, Virginia, for\\nAppellant. Mark R. Herring, Attorney General, Trevor S. Cox, Acting Solicitor General,\\n\\fLaura H. Cahill, Assistant Attorney General, Matthew R. McGuire, Deputy Solicitor\\nGeneral, OFFICE OF THE ATTORNEY GENERAL OF VIRGINIA, Richmond,\\nVirginia, for Appellees.\\n\\n\\n\\n\\n 2\\n\\fDIANA GRIBBON MOTZ, Circuit Judge:\\n\\n The Prison Litigation Reform Act requires a prisoner to exhaust administrative\\n\\nremedies before filing suit. When a prisoner filed this action under 42 U.S.C. § 1983\\n\\nafter exhausting those remedies, the district court held the statute of limitations barred his\\n\\nsuit. For the reasons that follow, we vacate and remand for further proceedings\\n\\nconsistent with this opinion.\\n\\n\\n\\n I.\\n\\n William D. Battle, III, entered Wallens Ridge State Prison in Roanoke, Virginia,\\n\\non December 6, 2013. After Battle completed the inmate intake process, corrections\\n\\nofficers J. Ledford and R. Edwards (collectively, “the officers”) escorted him to his\\n\\nassigned housing unit. A physical altercation between Battle and the officers occurred\\n\\nalong the way.\\n\\n The officers subsequently filed a disciplinary report against Battle. They charged\\n\\nthat Battle, who was restrained in handcuffs and leg irons during the transfer, used his\\n\\nbody to push one of the officers into a food cart. According to the officers, they subdued\\n\\nBattle by “plac[ing]” him on the ground. Battle disputed this account before a prison\\n\\nhearing administrator. He denied shoving any officer and instead claimed that a pain in\\n\\nhis ankle caused him to trip. He stated that the officers responded with unnecessary\\n\\nviolence: pulling his hair and slamming his head into the concrete floor, causing\\n\\n“bruising, lacerations, [and] swelling of the face.” Battle requested that the hearing\\n\\nadministrator examine video footage of the incident to corroborate his account.\\n\\n 3\\n\\f The hearing administrator declined to do so; instead, he simply credited the\\n\\nofficers’ version of the incident. After unsuccessfully appealing this decision to the\\n\\nprison’s chief warden, Battle submitted a second appeal to the regional corrections\\n\\nadministrator. On February 27, 2014, the regional administrator rejected Battle’s claim\\n\\nand issued a form confirming that Battle had reached the “last level of appeal for this\\n\\ngrievance.” A total of 83 days had passed since the altercation.\\n\\n On January 11, 2016 — two years and 36 days after the altercation — Battle\\n\\ncompleted a postage request for a pro se § 1983 complaint alleging the officers used\\n\\nexcessive force against him, in violation of the Eighth and Fourteenth Amendments. 1\\n\\nThe parties accept that this postage request establishes the filing date.\\n\\n The officers moved for summary judgment, arguing that Battle filed outside\\n\\nVirginia’s two-year statute of limitations applicable to § 1983 claims filed within the\\n\\njurisdiction. See Va. Code Ann. § 8.01-243(A) (setting limitations for personal injury\\n\\nactions). Battle countered that his complaint was timely because 42 U.S.C. § 1997e(a) of\\n\\nthe Prison Litigation Reform Act (“PLRA”) required him to exhaust available\\n\\nadministrative remedies before bringing a § 1983 claim. He argued that the 83 days\\n\\nduring which he participated in the required exhaustion should be tolled under two\\n\\n\\n\\n\\n 1\\n Battle’s complaint also named corrections administrators Gregory Holloway and\\nGeorge Hinkle as defendants. The district court held that Battle failed to state a claim\\nagainst these two officials. Battle does not appeal their dismissal.\\n\\n 4\\n\\fVirginia statutes and federal law, thus extending his filing deadline to February 27,\\n\\n2016. 2\\n\\n The first state statute on which Battle relied, Va. Code § 8.01-229(K), suspends\\n\\nthe statute of limitations for personal injury actions during criminal proceedings. The\\n\\nsecond, Va. Code § 8.01-195.3(7), governs actions brought under the Virginia Tort\\n\\nClaims Act (“VTCA”) and tolls the time for filing a claim notice during the pendency of\\n\\na prison grievance process. Additionally, Battle relied on federal equitable tolling law.\\n\\n The district court considered only Battle’s argument as to Va. Code § 8.01-\\n\\n229(K). It held that statute could not be used to toll Battle’s limitations period because a\\n\\n“prison disciplinary proceeding is not a criminal prosecution.” Battle v. Ledford, No.\\n\\n7:16CV00020, 2017 WL 432822, at *3 n.5 (W.D. Va. Jan. 30, 2017) (citing Wolff v.\\n\\nMcDonnell, 418 U.S. 539, 556 (1974)). The court then granted the officers’ motion for\\n\\nsummary judgment, concluding that Battle filed his complaint 36 days too late.\\n\\n On appeal, Battle concedes that the district court properly rejected his claim under\\n\\nVa. Code Ann. § 8.01-229(K). He maintains, however, that the court overlooked his\\n\\nclaims of state statutory tolling under the VTCA and federal equitable tolling, and so\\n\\nerred in deeming his complaint time-barred.\\n\\n We review a district court’s grant of summary judgment de novo. Henry v.\\n\\nPurnell, 652 F.3d 524, 531 (4th Cir. 2011) (en banc). Summary judgment is appropriate\\n\\n 2\\n Battle explained in a related affidavit that he understood from a prisoners’ rights\\npamphlet that the exhaustion of administrative remedies required by the Prison Litigation\\nReform Act mandated tolling, but could not easily verify the proposition because he had\\nlimited access to the law library.\\n\\n 5\\n\\fonly when “there is no genuine dispute as to any material fact and the movant is entitled\\n\\nto judgment as a matter of law.” Fed. R. Civ. P. 56(a).\\n\\n\\n\\n II.\\n\\n Congress did not provide fixed timing rules in § 1983 or its companion provision,\\n\\n§ 1988. 3 Instead, Congress specified that gaps in § 1983 “should be filled by state law, as\\n\\nlong as that law is not inconsistent with federal law.” Hardin v. Straub, 490 U.S. 536,\\n\\n538 (1989).\\n\\n The Supreme Court has directed that we apply a state’s “statute of limitations\\n\\ngoverning general personal injury actions” when considering § 1983 claims. Owens v.\\n\\nOkure, 488 U.S. 235, 251 (1989). A state’s limitations and tolling rules are to be\\n\\nfollowed unless doing so “defeat[s] either § 1983’s chief goals of compensation and\\n\\ndeterrence or its subsidiary goals of uniformity and federalism.” Hardin, 490 U.S. at 539\\n\\n(footnote omitted). If Virginia law allows tolling of Battle’s limitations period, that ends\\n\\nthe inquiry. See id. at 543 (establishing that states may grant extensions to prisoners\\n\\n\\n\\n 3\\n Section 1988 provides that where a § 1983 cause of action is\\n\\n deficient in the provisions necessary to furnish suitable remedies, . . . the\\n common law, as modified and changed by the constitution and statutes of\\n the State wherein the court having jurisdiction of such civil or criminal\\n cause is held, so far as the same is not inconsistent with the Constitution\\n and laws of the United States, shall be extended to and govern the said\\n courts in the trial and disposition of the cause[.]\\n\\n42 U.S.C. § 1988(a) (emphasis added).\\n\\n 6\\n\\fconsistent with § 1983). If not, Battle’s claim may survive only if federal equitable\\n\\nprinciples apply to his case.\\n\\n A.\\n\\n Virginia lacks a generally applicable statute that pauses limitations to\\n\\naccommodate administrative exhaustion requirements. See Va. Code Ann. § 8.01-229\\n\\n(enumerating eleven unrelated exceptions suspending tolling limitations periods). 4 Battle\\n\\nthus asks us to borrow a tolling provision in the Virginia Tort Claims Act. He does so on\\n\\nthe theory that he could have brought suit under that law for the same actions against the\\n\\nsame parties.\\n\\n To bring suit under the VTCA, a person must provide a notice of claim to the state\\n\\n“within one year after the cause of action accrues” as a precursor to litigation. Va. Code\\n\\nAnn. § 8.01-195.7. The claimant must file a complaint in court “within 18 months of the\\n\\nfiling of the notice of claim, or within two years after the cause of action accrues.” Id. If\\n\\nthe claimant is a state prisoner, the VTCA provides that the “time for filing the notice of\\n\\n 4\\n We note that Virginia does have its own statute, the Virginia Prisoner Litigation\\nReform Act (“VPLRA”), which directly addresses the interaction of limitations and\\nexhaustion. Va. Code Ann. § 8.01-243.2 provides:\\n\\n No person confined in a state or local correctional facility shall bring or\\n have brought on his behalf any personal action relating to the conditions of\\n his confinement until all available administrative remedies are exhausted.\\n Such action shall be brought by or on behalf of such person within one year\\n after cause of action accrues or within six months after all administrative\\n remedies are exhausted, whichever occurs later.\\n\\nThis provision does not control Battle’s § 1983 action because the Supreme Court has\\nunequivocally held that personal injury limitations periods apply to § 1983 claims. See\\nOwens, 488 U.S. at 251; Wilson v. Garcia, 471 U.S. 261, 280 (1985).\\n\\n 7\\n\\ftort claim shall be tolled during the pendency of the grievance procedure.” Va. Code\\n\\nAnn. § 8.01-195.3(7).\\n\\n The VTCA does not save Battle’s claims for two reasons. First, the VTCA\\n\\noperates on a tighter schedule than § 1983. It gives a plaintiff only one year to assert his\\n\\nrights, plus exhaustion. The VTCA’s tolling provision would thus afford Battle one year\\n\\nand 83 days to take legal action.\\n\\n Second, and more fundamentally, the VTCA does not govern suits against state\\n\\nemployees like the one Battle brings here. Rather, it provides a limited waiver of\\n\\nsovereign immunity that “applies to one type of litigation, tort actions against the\\n\\nCommonwealth.” Ogunde v. Virginia, 628 S.E.2d 370, 373 (Va. 2006). But § 1983 does\\n\\nthe reverse: it applies only to state officials, not states themselves. See Will v. Mich.\\n\\nDep’t of State Police, 491 U.S. 58, 66 (1989). Because Battle could not have substituted\\n\\na VTCA claim for a § 1983 action, the VTCA’s tolling provision cannot be integrated\\n\\ninto the federal scheme.\\n\\n B.\\n\\n When state statutory tolling rules provide no relief to a prisoner seeking to bring a\\n\\n§ 1983 claim, some courts have turned to state equitable tolling rules to suspend\\n\\nlimitations during the mandated exhaustion period. See Heck v. Humphrey, 997 F.2d\\n\\n355, 358 (7th Cir. 1993) (applying state equitable tolling to suspend limitations period for\\n\\n§ 1983 plaintiff seeking to bring habeas claim), aff’d on other grounds, 512 U.S. 477\\n\\n(1994); Rodriguez v. Holmes, 963 F.2d 799, 804–05 (5th Cir. 1992) (same).\\n\\n\\n\\n 8\\n\\f Under Virginia law, equitable estoppel provides the only arguable exception to the\\n\\nCommonwealth’s general rule against “recogniz[ing] any non-statutory basis for tolling”\\n\\nlimitations. City of Bedford v. James Leffel & Co., 558 F.2d 216, 217 (4th Cir. 1977)\\n\\n(internal quotation marks omitted); see also Casey v. Merck & Co., 722 S.E.2d 842, 845\\n\\n(Va. 2012) (“A statute of limitations may not be tolled, or an exception applied, in the\\n\\nabsence of a clear statutory enactment to such effect.” (internal quotation marks\\n\\nomitted)).\\n\\n To invoke equitable estoppel under Virginia law, a plaintiff must prove, inter alia,\\n\\nthat the “party claiming estoppel was misled to his injury” by the defendant in a way that\\n\\nprevented timely filing. Boykins Narrow Fabrics Corp. v. Weldon Roofing & Sheet\\n\\nMetal, Inc., 266 S.E.2d 887, 890 (Va. 1980). The corrections officers did not mislead\\n\\nBattle as to his injury or the accrual date by operation of the prison administrative review\\n\\nprocess. Accordingly, as each party acknowledges, Battle cannot invoke the doctrine.\\n\\n Battle further concedes that no other Virginia common law rule could save his\\n\\nclaim.\\n\\n\\n\\n III.\\n\\n A.\\n\\n With no Virginia rule available to toll the limitations period, we must determine\\n\\nwhether refusal to do so during a prisoner’s mandatory exhaustion period is “consistent\\n\\nwith federal law and policy.” Owens, 488 U.S. at 239.\\n\\n\\n\\n 9\\n\\f When a court borrows a state rule “to assist in the enforcement of [a] federal\\n\\nremedy,” the federal interest always controls. Wilson, 471 U.S. at 269. This is so\\n\\nbecause “the policies and purposes of the States” do not constitute “the primary office of\\n\\nthe borrowing provision in § 1988,” which governs § 1983 actions. Id. Rather, § 1988\\n\\n“is designed to assure that neutral rules of decision will be available to enforce the civil\\n\\nrights actions, among them § 1983.” Id. Thus, it is the “duty of the federal courts to\\n\\nassure that the importation of state law will not frustrate or interfere with the\\n\\nimplementation of national policies.” Occidental Life Ins. Co. of Cal. v. EEOC, 432 U.S.\\n\\n355, 367 (1977).\\n\\n But to be held “inconsistent” with § 1983, a state rule must do more than “cause[]\\n\\nthe plaintiff to lose the litigation.” Robertson v. Wegmann, 436 U.S. 584, 593 (1978).\\n\\nThe state rule must “defeat either § 1983’s chief goals of compensation and deterrence or\\n\\nits subsidiary goals of uniformity and federalism.” Hardin, 490 U.S. at 539 (footnote\\n\\nomitted). If a state’s timing requirement contravenes one or more of these goals, it is\\n\\n“inconsistent with federal law,” and § 1988 bars us from adopting it. Id. at 538.\\n\\n The Supreme Court has explained that it is inconsistent with § 1983’s policies to\\n\\napply “a state statute of limitations” to require a litigant “to refrain from commencing a\\n\\ncivil action until it has discharged” a process mandated by federal law. Occidental, 432\\n\\nU.S. at 367–68. “For the State’s wisdom in establishing a general limitation period could\\n\\nnot have taken into account the decision of Congress to delay judicial action” while the\\n\\nlitigant “performs its administrative responsibilities.” Id. (internal quotation marks\\n\\nomitted). The Court has further suggested that tolling of § 1983 limitations may be\\n\\n 10\\n\\fnecessary where a remedy “is structured to require previous resort to state proceedings,\\n\\nso that the claim may not even be maintained in federal court unless such resort be had.”\\n\\nBd. of Regents of Univ. of State of N.Y. v. Tomanio, 446 U.S. 478, 490 (1980). The Court\\n\\nhas even warned that the imposition of an “exhaustion requirement might result in the\\n\\neffective repeal of § 1983” if “statutes of limitations are not tolled pending exhaustion.”\\n\\nPatsy v. Bd. of Regents of State of Fla., 457 U.S. 496, 514 n.17 (1982).\\n\\n B.\\n\\n With this precedent in mind, we consider its application to the case at hand.\\n\\n Virginia law provides an elaborate administrative grievance process for prisoner\\n\\ncomplaints. Exhaustion of this remedy involves at least three levels of review. See\\n\\nVDOC OP 866.1(IV-VI) (describing emergency grievance review, review of informal\\n\\ncomplaints, and three-stage review of formal complaints). A prisoner has 30 days to\\n\\nsubmit a formal grievance, and corrections administrators are then given another 180\\n\\ndays to resolve the grievance. 5 See id.\\n\\n Given this structure, Virginia’s no-tolling rule, as applied to prisoners seeking to\\n\\nbring § 1983 claims, frustrates the goals of § 1983 and is thus clearly “inconsistent” with\\n\\nsettled federal policy. Hardin, 490 U.S. at 538.\\n\\n\\n\\n\\n 5\\n Virginia’s corrections regulations exempt sexual abuse allegations from the 30-\\nday filing requirement so that vulnerable victims may press their claims once it is safe for\\nthem to do so. VDOC OP 866.1(VI)(A)(1)(c). Absent tolling, this policy could have the\\nunintended effect of substantially reducing a prisoner’s § 1983 filing time when bringing\\na serious abuse claim against a corrections officer.\\n\\n 11\\n\\f First, application of the no-tolling rule would frustrate the purpose of\\n\\ncompensating prisoners who have sustained constitutional injuries. Under Virginia\\n\\nregulations — as implemented by state officials — as much as seven months could be\\n\\nsubtracted from the period in which a prisoner can file a federal claim. This inevitable\\n\\nand indeterminate reduction in limitations would be wholly contingent on the efficiency\\n\\nof administrators and the complexity of the case. And as other circuits have noted and\\n\\ncommon sense suggests, a state’s grievance process may extend beyond the state’s\\n\\nregulatory deadlines. See, e.g., Brown v. Valoff, 422 F.3d 926, 932–34 (9th Cir. 2005)\\n\\n(describing grievance process lasting 2 years and 10 months from injury to investigation\\n\\nreport); see also Gonzalez v. Hasty, 651 F.3d 318, 323 (2d Cir. 2011) (“[T]he time for\\n\\nachieving a resolution under the PLRA could be considerably longer than 140 days. . . .\\n\\n[I]t is certainly possible that a full three years could pass while an inmate exhausts his\\n\\nadministrative remedies.”). Far from advancing compensation, a no-tolling rule would\\n\\namount to a penalty in which incarcerated persons — subject to severe state control and\\n\\noften limited in access to legal resources — would receive less time to vindicate § 1983\\n\\nclaims than all other litigants.\\n\\n Application of a no-tolling rule here would also fail to serve § 1983’s second\\n\\nprimary goal — deterrence. Instead, this rule would enable state officials to shrink a\\n\\nprisoner’s filing window and so limit his opportunity to bring a claim. In this way, a no-\\n\\ntolling rule would even create perverse incentives for prison commissioners to extend\\n\\nregulatory deadlines and for wardens and investigators to stall in their review of\\n\\n\\n\\n 12\\n\\findividual grievances, for doing so might limit government officials’ legal exposure. 6 As\\n\\nthe Seventh Circuit has observed, no-tolling rules thus encourage prison officials to run\\n\\nout the clock and “exploit the exhaustion requirement through indefinite delay in\\n\\nresponding to grievances.” Lewis v. Washington, 300 F.3d 829, 833 (7th Cir. 2002)\\n\\n(internal quotation marks omitted).\\n\\n Nor would the no-tolling rule advance § 1983’s subsidiary interest in uniformity.\\n\\nOf course, Virginia’s rule would set a consistent two-year period between accrual and the\\n\\nlimitations deadline across claims, furthering uniformity in this formalistic respect. But a\\n\\nrule that calculates the limitations deadline from the date of exhaustion is just as “firmly\\n\\ndefined” and “easily applied.” Wilson, 471 U.S. at 270 (quoting Chardon v. Fumero\\n\\nSoto, 462 U.S. 650, 667 (1983) (Rehnquist, J., dissenting)). Moreover, a no-tolling rule\\n\\nwould destroy any semblance of meaningful uniformity by creating dramatic claim-to-\\n\\nclaim variance in the actual filing time available to different § 1983 litigants. Between\\n\\nprisoners, a no-tolling rule would afford a prisoner whose grievance was processed with\\n\\ndelay less time to file than one whose grievance received speedy resolution. It would\\n\\nalso create a disparity between those who are incarcerated and those who are not. For\\n\\nexample, if the injuries claimed here had occurred in the context of an arrest rather than a\\n\\nprison escort, Battle would have been guaranteed a full two years to file his § 1983 suit,\\n\\nrather than the abbreviated period he would receive under a no-tolling rule. Such\\n\\n\\n\\n 6\\n We do not discern or suggest any bad faith or intentional delay by prison\\nofficials in Battle’s case. Our point is only that this is possible absent tolling.\\n\\n 13\\n\\fsweeping and arbitrary deviations in procedural rights would hardly advance a policy of\\n\\nuniformity.\\n\\n Finally, we also cannot even say that accepting Virginia’s no-tolling rule would\\n\\nfoster federalism interests. This is so because the Commonwealth itself has adopted two\\n\\nstatutes, the VTCA and VPLRA, that toll prisoner exhaustion periods. See Va. Code\\n\\nAnn. §§ 8.01-195.7, 8.01-243.2. Although neither provides relief to prisoners seeking to\\n\\nbring § 1983 claims, their enactment demonstrates that Virginia otherwise has adopted a\\n\\npolicy of tolling limitations while prison administrators review inmate claims. These\\n\\nstatutes also make clear that an exhaustion reprieve does not conflict with Virginia’s\\n\\n“important and salutary purpose” in strictly construing statutes of limitations, which is to\\n\\nprotect defendants from “unscrupulous plaintiffs who hoard evidence that supports their\\n\\nposition while waiting for their prospective opponents to discard evidence that would\\n\\nhelp make a defense.” Burns v. Stafford Cty., 315 S.E.2d 856, 859 (Va. 1984).\\n\\nAdministrative exhaustion does the opposite: it notifies defendants of a potential claim\\n\\nand allows both parties to develop a record before coming to court.\\n\\n In sum, because Virginia’s no-tolling rule is inconsistent with federal law and\\n\\npolicy, we cannot apply it here.\\n\\n C.\\n\\n Notwithstanding this analysis, the officers contend that Virginia’s no-tolling rule\\n\\nnecessarily comports with federal policies because a separate federal law — the PLRA —\\n\\nimposes the relevant exhaustion requirement. But by enacting the PLRA, Congress did\\n\\nnot endorse such a no-tolling rule or diminish the interests underlying § 1983. To so\\n\\n 14\\n\\fconclude would be to overread the PLRA’s silence on tolling, misread the PLRA’s\\n\\npurpose, and ignore the text of § 1983 and § 1988.\\n\\n First, the silence in the PLRA. It is a cardinal rule that “repeals by implication are\\n\\nnot favored and will not be presumed unless the intention of the legislature to repeal is\\n\\nclear and manifest.” Hui v. Castaneda, 559 U.S. 799, 810 (2010) (internal quotation\\n\\nmarks omitted). Nothing in the text of the PLRA suggests that Congress sought to limit\\n\\nor modify § 1988(a)’s express command that borrowed provisions of state law must be\\n\\nconsistent with important, long-recognized federal policies. The PLRA’s legislative\\n\\nhistory is also silent as to § 1988(a)’s borrowing framework and the Court’s\\n\\ninterpretation thereof. The conference reports, floor debates, and committee hearings\\n\\ncontain no discussion of the pressure that mandatory exhaustion would exert on § 1983’s\\n\\nstate-derived limitations rule absent tolling. See generally Bernard D. Reams & William\\n\\nH. Manz, A Legislative History of the Prison Litigation Reform Act of 1996, Pub. L. No.\\n\\n104–134, 110 Stat. 1321 (1997). When confronted with statutory silence, we must\\n\\n“presume that Congress is aware of the legal context in which it is legislating.” Palisades\\n\\nCollections LLC v. Shorts, 552 F.3d 327, 335 n.4 (4th Cir. 2008) (internal quotation\\n\\nmarks omitted).\\n\\n Nor do we see any indication that Congress intended, through the PLRA, to amend\\n\\nor override the specific federal policies underlying § 1983 and incorporated into\\n\\n§ 1988(a). Instead, as the Supreme Court has explained, it is “[b]eyond doubt” that\\n\\nCongress enacted the PLRA’s exhaustion requirement “to reduce the quantity and\\n\\nimprove the quality of prisoner suits” by allowing officials the opportunity to take\\n\\n 15\\n\\f“corrective action” and ideally “obviating the need for litigation.” Porter v. Nussle, 534\\n\\nU.S. 516, 524–25 (2002); see also McLean v. United States, 566 F.3d 391, 397 (4th Cir.\\n\\n2009) (“The purpose of the PLRA was not, however, to impose indiscriminate\\n\\nrestrictions on prisoners’ access to the federal courts.”).\\n\\n Senator Kyl, the lead Senate sponsor of the PLRA, explained that an exhaustion\\n\\nrequirement would “free up judicial resources for claims with merit by both prisoners and\\n\\nnonprisoners” alike by winnowing meritless claims. 141 Cong. Rec. S7526 (daily ed.\\n\\nMay 25, 1995) (statement of Sen. Kyl). Similarly, the lead House sponsor, Rep.\\n\\nLoBiondo, described mandatory exhaustion as promoting more efficient resolution of\\n\\nprisoner problems and ensuring “some degree of fact-finding so that when or if the matter\\n\\nreaches Federal court there will be a record upon which to proceed in a more efficient\\n\\nmanner.” 141 Cong. Rec. H14105 (daily ed. Dec. 6, 1995) (statement of Rep.\\n\\nLoBiondo). He further characterized mandatory exhaustion as a tool to filter frivolous\\n\\nclaims so “only those claims with a greater probability . . . of success would, presumably,\\n\\nproceed.” Id.\\n\\n Each of these goals entirely accords with those underlying § 1983, and neither\\n\\nstatute is served by allowing mandatory exhaustion to chip away at a prisoner’s\\n\\nlimitations period. Rather, as several of our sister circuits have recognized, refusal to toll\\n\\nlimitations during the PLRA’s mandatory exhaustion period would trap prisoners in a\\n\\n“catch-22”: one “who files suit . . . prior to exhausting administrative remedies risks\\n\\ndismissal based upon § 1997e [of the PLRA]; whereas the prisoner who waits to exhaust\\n\\nhis administrative remedies risks dismissal based upon untimeliness.” Gonzalez, 651\\n\\n 16\\n\\fF.3d at 323 (quoting Johnson v. Rivera, 272 F.3d 519, 522 (7th Cir. 2001)); accord\\n\\nPearson v. Sec’y Dep’t of Corr., 775 F.3d 598, 602 (3d Cir. 2015).\\n\\n As previously noted, the Supreme Court expressed a similar concern well before\\n\\nenactment of the PLRA. The Court made plain that imposing a mandatory exhaustion\\n\\nrequirement without tolling limitations during the exhaustion period could “result in the\\n\\neffective repeal of § 1983.” Patsy, 457 U.S. at 514 n.17. The text and legislative history\\n\\nof the PLRA offer no indication that Congress intended to effect such a repeal. Because\\n\\nthe PLRA does no more than require exhaustion before filing suit, we cannot read it to\\n\\namend § 1983’s well-established policy objectives, as incorporated into § 1988(a).\\n\\n\\n\\n IV.\\n\\n Because we hold that Virginia’s no-tolling rule is inconsistent with § 1983, we\\n\\nmust determine a proper remedy. Battle asks that we apply federal equitable tolling\\n\\nprinciples to account for the time lost during his 83-day mandatory exhaustion period.\\n\\nWe agree with Battle (and our sister circuits) that those principles apply during this\\n\\nperiod.\\n\\n Equitable tolling is “reserved for ‘those rare instances where — due to\\n\\ncircumstances external to the party’s own conduct — it would be unconscionable to\\n\\nenforce the limitation period against the party and gross injustice would result.’” Raplee\\n\\nv. United States, 842 F.3d 328, 333 (4th Cir. 2016) (quoting Harris v. Hutchinson, 209\\n\\nF.3d 325, 330 (4th Cir. 2000)). The Supreme Court has explained that “[g]enerally, a\\n\\nlitigant seeking equitable tolling bears the burden of establishing two elements: (1) that\\n\\n 17\\n\\fhe has been pursuing his rights diligently, and (2) that some extraordinary circumstance\\n\\nstood in his way.” Pace v. DiGuglielmo, 544 U.S. 408, 418 (2005); see also Holland v.\\n\\nFlorida, 560 U.S. 631, 653 (2010) (clarifying that “[t]he diligence required for equitable\\n\\ntolling purposes is reasonable diligence, not maximum feasible diligence” (internal\\n\\ncitation and quotation marks omitted)).\\n\\n Given these principles, the Supreme Court and this court have found equitable\\n\\ntolling inappropriate where a plaintiff unnecessarily waits to file one claim that does not\\n\\nrequire exhaustion while exhausting administrative remedies required for a different\\n\\ncause of action. See Johnson v. Ry. Exp. Agency, Inc., 421 U.S. 454, 465–66 (1975)\\n\\n(declining to toll limitations for § 1981 claims during exhaustion required for separate\\n\\nTitle VII remedy); Ott v. Md. Dep’t of Pub. Safety & Corr. Servs., 909 F.3d 655, 661 (4th\\n\\nCir. 2018) (declining to toll limitations for Rehabilitation Act claims where litigant\\n\\n“could have timely filed [those] claims without completing the administrative process as\\n\\nto her [Americans with Disabilities Act] claims”).\\n\\n In contrast, equitable tolling is appropriate in the narrower context presented here.\\n\\nFirst, Battle showed reasonable diligence during the 83-day exhaustion period. He\\n\\npromptly denied the disciplinary charge against him and then underwent two rounds of\\n\\nappeals, properly pursuing the process through to the “last level.” Second, during this\\n\\nadministrative process, an extraordinary circumstance “stood in [the] way” of filing suit.\\n\\nHolland, 560 U.S. at 649 (internal quotation marks omitted). Unlike the litigants in\\n\\nJohnson and Ott, who remained free to file their § 1981 and Rehabilitation Act claims at\\n\\nany point after accrual, prisoners face a complete and absolute barrier to litigation of any\\n\\n 18\\n\\f§ 1983 claim during their mandatory administrative grievance proceedings. And this\\n\\nbarrier is far from ordinary. We are aware of no other federal statute in which a\\n\\nmandatory exhaustion requirement could erode a litigant’s limitations period. 7 Under\\n\\nthese circumstances, such a total and unusual barrier to filing constitutes an extraordinary\\n\\ncircumstance.\\n\\n Thus, every circuit that has confronted a state no-tolling rule and reached this\\n\\nquestion has applied federal law to equitably toll § 1983 limitations during the PLRA\\n\\nexhaustion period. See Gonzalez, 651 F.3d at 322–24; Brown, 422 F.3d at 942–43;\\n\\nBrown v. Morgan, 209 F.3d 595, 596 (6th Cir. 2000). In addition to these three circuits\\n\\nthat have expressly applied federal equitable tolling, four others have impliedly done so\\n\\nor suggested that this would be appropriate. See Thompson v. Pitkins, 514 F. App’x 88,\\n\\n90 (3d Cir. 2013) (“Because exhaustion of prison administrative remedies is mandatory\\n\\nunder the Prison Litigation Reform Act, the statute of limitations applicable to § 1983\\n\\n\\n 7\\n For example, the limitations period for habeas petitions by those in state custody,\\n28 U.S.C. § 2244(d)(1), does not begin to run until mandatory exhaustion of state\\nremedies is complete, 28 U.S.C. § 2244(d)(2). And under numerous other statutes that\\nrequire administrative review prior to filing suit, limitations run only after the agency’s\\naction is final. See, e.g., 28 U.S.C. § 2401(b) (requiring filing of Federal Tort Claims Act\\nsuit within six months of agency’s denial of claim); 42 U.S.C. § 2000e-5(f)(1) (requiring\\nemployee to file Title VII suit within 90 days of dismissal of administrative proceedings);\\n20 U.S.C. § 1415(i)(2)(B) (requiring litigants to file suit under Individuals with\\nDisabilities Education Act within 90 days of hearing officer’s decision, or as prescribed\\nby state law); 8 U.S.C. § 1252(b)(1) (requiring noncitizens to seek judicial review of\\ndeportation orders within 30 days of conclusion of administrative proceedings). Notably,\\nin considering a prior and identical version of § 1997e(a), the House Judiciary Committee\\nexplained that the exhaustion requirement was drafted to align “with administrative\\nexhaustion rules that apply in other contexts.” H.R. Rep No. 104-21, at 32 (1995).\\n\\n\\n 19\\n\\factions may be tolled while a prisoner exhausts.”); Napier v. Preslicka, 314 F.3d 528,\\n\\n534 n.3 (11th Cir. 2002) (“We proffer, but do not hold, as that issue is not before us, that\\n\\nsuch a result may be mitigated by the doctrine of equitable tolling, as other circuits have\\n\\napplied that doctrine to the administrative exhaustion requirement for prison condition\\n\\nsuits . . . .”); Clifford v. Gibbs, 298 F.3d 328, 333 (5th Cir. 2002) (granting “request to\\n\\nequitably toll limitations” during administrative proceedings); Johnson, 272 F.3d at 521\\n\\n(agreeing with other circuits that “federal courts should toll state statutes of limitations\\n\\nwhile inmates exhaust their administrative remedies under § 1997e” while applying state\\n\\ntolling provision); Heck, 997 F.2d at 358 (“[A] body of state tolling law that lacks a\\n\\nprovision for equitable tolling is inconsistent with the provision of a complete federal\\n\\nremedy under section 1983 and therefore is overridden by the federal doctrine.”).\\n\\n Tellingly, not one of these courts has required a claimant to prove additional\\n\\nextraordinary circumstances beyond the exhaustion requirement or to show constant\\n\\ndiligence until the moment of filing, as the officers would have us do here. In fact, the\\n\\nSecond Circuit even acknowledged “substantial delay arising from [the plaintiff]’s\\n\\nfailure” to properly litigate the claim before it, but still equitably tolled the administrative\\n\\ngrievance period in light of § 1983’s well-established policies. Gonzalez, 651 F.3d at\\n\\n320, 323.\\n\\n Finally, in joining this consensus, we note that the ordinary arguments against\\n\\nequitable tolling do not apply. For example, there is no “potential for . . . endless tolling”\\n\\nof a prisoner’s § 1983 claim, because the clock would only stop for the length of the\\n\\nstate’s exhaustion period. Credit Suisse Sec. (USA) LLC v. Simmonds, 566 U.S. 221,\\n\\n 20\\n\\f227–28 (2012). If defendants are correct that Virginia’s administrative grievance process\\n\\nwill never exceed 180 days from the time a grievance is filed, then Virginia’s officials\\n\\nwill never be subject to a tolling period exceeding seven months. A maximum extension\\n\\nof seven months will not prejudice these officials, given that the grievance process will\\n\\nput them on notice of a potential civil rights claim and allow the parties to develop a\\n\\ncontemporaneous “administrative record that clarifies the contours of the controversy.”\\n\\nPorter, 534 U.S. at 525.\\n\\n A clear rule that tolls limitations during the grievance process also avoids any risk\\n\\nof “loose[ning] the rule of law to whims about the adequacy of excuses, divergent\\n\\nresponses to claims of hardship, and subjective notions of fair accommodation.” Harris,\\n\\n209 F.3d at 330. The inquiry here is objective. All a court must do is determine the point\\n\\nof exhaustion and run the limitations period from that date.\\n\\n We therefore reject the officers’ invitation to deviate from the path followed by\\n\\nseven other circuits. Battle’s limitations period must be tolled for the 83 days in which\\n\\nhe exhausted his administrative remedies, as he was required to do before bringing suit.\\n\\nThis satisfies the goals of § 1983 and the PLRA while also comporting with principles of\\n\\nequity: it gives Battle the benefit of the full limitations period applicable to other\\n\\nlitigants, no more and no less. In sum, Battle’s § 1983 complaint is timely; it was filed\\n\\nwithin two years of the date he exhausted administrative remedies required by the PLRA.\\n\\n\\n\\n\\n 21\\n\\f V.\\n\\n For the foregoing reasons, we vacate the judgment of the district court and remand\\n\\nfor further proceedings consistent with this opinion.\\n\\n VACATED AND REMANDED\\n\\n\\n\\n\\n 22\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4356941/\", \"author_raw\": \"DIANA GRIBBON MOTZ, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"MOTZ"},"judge2":{"kind":"string","value":"DUNCAN"},"judge3":{"kind":"string","value":"THACKER"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4579688/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: William D. BATTLE, III, Plaintiff - Appellant, v. J. LEDFORD, Correctional Officer; R. Edwards, Correctional Officer; Gregory Holloway, Warden of Wallens Ridge State Prison; George Hinkle, Regional Administrator for Virginia Department of Corrections, Defendants - Appellees.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-08\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-6287\n\n\nWILLIAM D. BATTLE, III,\n\n Plaintiff - Appellant,\n\n v.\n\nJ. LEDFORD, Correctional Officer; R. EDWARDS, Correctional Officer;\nGREGORY HOLLOWAY, Warden of Wallens Ridge State Prison; GEORGE\nHINKLE, Regional Administrator for Virginia Department of Corrections,\n\n Defendants - Appellees.\n\n\nAppeal from the United States District Court for the Western District of Virginia, at\nRoanoke. Elizabeth Kay Dillon, District Judge. (7:16-cv-00020-EKD-RSB)\n\n\nArgued: September 25, 2018 Decided: January 8, 2019\n\n\nBefore MOTZ, DUNCAN, and THACKER, Circuit Judges.\n\n\nVacated and remanded by published opinion. Judge Motz wrote the opinion, in which\nJudge Duncan and Judge Thacker joined.\n\n\nARGUED: Sarah Crandall, Elizabeth Joynes, UNIVERSITY OF VIRGINIA SCHOOL\nOF LAW, Charlottesville, Virginia, for Appellant. Michelle Shane Kallen, OFFICE OF\nTHE ATTORNEY GENERAL OF VIRGINIA, Richmond, Virginia, for Appellees. ON\nBRIEF: Joseph Charlet, Third Year Law Student, Megan Keenan, Third Year Law\nStudent, Evan Ward, Third Year Law Student, Appellate Litigation Clinic,\nUNIVERSITY OF VIRGINIA SCHOOL OF LAW, Charlottesville, Virginia, for\nAppellant. Mark R. Herring, Attorney General, Trevor S. Cox, Acting Solicitor General,\n\fLaura H. Cahill, Assistant Attorney General, Matthew R. McGuire, Deputy Solicitor\nGeneral, OFFICE OF THE ATTORNEY GENERAL OF VIRGINIA, Richmond,\nVirginia, for Appellees.\n\n\n\n\n 2\n\fDIANA GRIBBON MOTZ, Circuit Judge:\n\n The Prison Litigation Reform Act requires a prisoner to exhaust administrative\n\nremedies before filing suit. When a prisoner filed this action under 42 U.S.C. § 1983\n\nafter exhausting those remedies, the district court held the statute of limitations barred his\n\nsuit. For the reasons that follow, we vacate and remand for further proceedings\n\nconsistent with this opinion.\n\n\n\n I.\n\n William D. Battle, III, entered Wallens Ridge State Prison in Roanoke, Virginia,\n\non December 6, 2013. After Battle completed the inmate intake process, corrections\n\nofficers J. Ledford and R. Edwards (collectively, “the officers”) escorted him to his\n\nassigned housing unit. A physical altercation between Battle and the officers occurred\n\nalong the way.\n\n The officers subsequently filed a disciplinary report against Battle. They charged\n\nthat Battle, who was restrained in handcuffs and leg irons during the transfer, used his\n\nbody to push one of the officers into a food cart. According to the officers, they subdued\n\nBattle by “plac[ing]” him on the ground. Battle disputed this account before a prison\n\nhearing administrator. He denied shoving any officer and instead claimed that a pain in\n\nhis ankle caused him to trip. He stated that the officers responded with unnecessary\n\nviolence: pulling his hair and slamming his head into the concrete floor, causing\n\n“bruising, lacerations, [and] swelling of the face.” Battle requested that the hearing\n\nadministrator examine video footage of the incident to corroborate his account.\n\n 3\n\f The hearing administrator declined to do so; instead, he simply credited the\n\nofficers’ version of the incident. After unsuccessfully appealing this decision to the\n\nprison’s chief warden, Battle submitted a second appeal to the regional corrections\n\nadministrator. On February 27, 2014, the regional administrator rejected Battle’s claim\n\nand issued a form confirming that Battle had reached the “last level of appeal for this\n\ngrievance.” A total of 83 days had passed since the altercation.\n\n On January 11, 2016 — two years and 36 days after the altercation — Battle\n\ncompleted a postage request for a pro se § 1983 complaint alleging the officers used\n\nexcessive force against him, in violation of the Eighth and Fourteenth Amendments. 1\n\nThe parties accept that this postage request establishes the filing date.\n\n The officers moved for summary judgment, arguing that Battle filed outside\n\nVirginia’s two-year statute of limitations applicable to § 1983 claims filed within the\n\njurisdiction. See Va. Code Ann. § 8.01-243(A) (setting limitations for personal injury\n\nactions). Battle countered that his complaint was timely because 42 U.S.C. § 1997e(a) of\n\nthe Prison Litigation Reform Act (“PLRA”) required him to exhaust available\n\nadministrative remedies before bringing a § 1983 claim. He argued that the 83 days\n\nduring which he participated in the required exhaustion should be tolled under two\n\n\n\n\n 1\n Battle’s complaint also named corrections administrators Gregory Holloway and\nGeorge Hinkle as defendants. The district court held that Battle failed to state a claim\nagainst these two officials. Battle does not appeal their dismissal.\n\n 4\n\fVirginia statutes and federal law, thus extending his filing deadline to February 27,\n\n2016. 2\n\n The first state statute on which Battle relied, Va. Code § 8.01-229(K), suspends\n\nthe statute of limitations for personal injury actions during criminal proceedings. The\n\nsecond, Va. Code § 8.01-195.3(7), governs actions brought under the Virginia Tort\n\nClaims Act (“VTCA”) and tolls the time for filing a claim notice during the pendency of\n\na prison grievance process. Additionally, Battle relied on federal equitable tolling law.\n\n The district court considered only Battle’s argument as to Va. Code § 8.01-\n\n229(K). It held that statute could not be used to toll Battle’s limitations period because a\n\n“prison disciplinary proceeding is not a criminal prosecution.” Battle v. Ledford, No.\n\n7:16CV00020, 2017 WL 432822, at *3 n.5 (W.D. Va. Jan. 30, 2017) (citing Wolff v.\n\nMcDonnell, 418 U.S. 539, 556 (1974)). The court then granted the officers’ motion for\n\nsummary judgment, concluding that Battle filed his complaint 36 days too late.\n\n On appeal, Battle concedes that the district court properly rejected his claim under\n\nVa. Code Ann. § 8.01-229(K). He maintains, however, that the court overlooked his\n\nclaims of state statutory tolling under the VTCA and federal equitable tolling, and so\n\nerred in deeming his complaint time-barred.\n\n We review a district court’s grant of summary judgment de novo. Henry v.\n\nPurnell, 652 F.3d 524, 531 (4th Cir. 2011) (en banc). Summary judgment is appropriate\n\n 2\n Battle explained in a related affidavit that he understood from a prisoners’ rights\npamphlet that the exhaustion of administrative remedies required by the Prison Litigation\nReform Act mandated tolling, but could not easily verify the proposition because he had\nlimited access to the law library.\n\n 5\n\fonly when “there is no genuine dispute as to any material fact and the movant is entitled\n\nto judgment as a matter of law.” Fed. R. Civ. P. 56(a).\n\n\n\n II.\n\n Congress did not provide fixed timing rules in § 1983 or its companion provision,\n\n§ 1988. 3 Instead, Congress specified that gaps in § 1983 “should be filled by state law, as\n\nlong as that law is not inconsistent with federal law.” Hardin v. Straub, 490 U.S. 536,\n\n538 (1989).\n\n The Supreme Court has directed that we apply a state’s “statute of limitations\n\ngoverning general personal injury actions” when considering § 1983 claims. Owens v.\n\nOkure, 488 U.S. 235, 251 (1989). A state’s limitations and tolling rules are to be\n\nfollowed unless doing so “defeat[s] either § 1983’s chief goals of compensation and\n\ndeterrence or its subsidiary goals of uniformity and federalism.” Hardin, 490 U.S. at 539\n\n(footnote omitted). If Virginia law allows tolling of Battle’s limitations period, that ends\n\nthe inquiry. See id. at 543 (establishing that states may grant extensions to prisoners\n\n\n\n 3\n Section 1988 provides that where a § 1983 cause of action is\n\n deficient in the provisions necessary to furnish suitable remedies, . . . the\n common law, as modified and changed by the constitution and statutes of\n the State wherein the court having jurisdiction of such civil or criminal\n cause is held, so far as the same is not inconsistent with the Constitution\n and laws of the United States, shall be extended to and govern the said\n courts in the trial and disposition of the cause[.]\n\n42 U.S.C. § 1988(a) (emphasis added).\n\n 6\n\fconsistent with § 1983). If not, Battle’s claim may survive only if federal equitable\n\nprinciples apply to his case.\n\n A.\n\n Virginia lacks a generally applicable statute that pauses limitations to\n\naccommodate administrative exhaustion requirements. See Va. Code Ann. § 8.01-229\n\n(enumerating eleven unrelated exceptions suspending tolling limitations periods). 4 Battle\n\nthus asks us to borrow a tolling provision in the Virginia Tort Claims Act. He does so on\n\nthe theory that he could have brought suit under that law for the same actions against the\n\nsame parties.\n\n To bring suit under the VTCA, a person must provide a notice of claim to the state\n\n“within one year after the cause of action accrues” as a precursor to litigation. Va. Code\n\nAnn. § 8.01-195.7. The claimant must file a complaint in court “within 18 months of the\n\nfiling of the notice of claim, or within two years after the cause of action accrues.” Id. If\n\nthe claimant is a state prisoner, the VTCA provides that the “time for filing the notice of\n\n 4\n We note that Virginia does have its own statute, the Virginia Prisoner Litigation\nReform Act (“VPLRA”), which directly addresses the interaction of limitations and\nexhaustion. Va. Code Ann. § 8.01-243.2 provides:\n\n No person confined in a state or local correctional facility shall bring or\n have brought on his behalf any personal action relating to the conditions of\n his confinement until all available administrative remedies are exhausted.\n Such action shall be brought by or on behalf of such person within one year\n after cause of action accrues or within six months after all administrative\n remedies are exhausted, whichever occurs later.\n\nThis provision does not control Battle’s § 1983 action because the Supreme Court has\nunequivocally held that personal injury limitations periods apply to § 1983 claims. See\nOwens, 488 U.S. at 251; Wilson v. Garcia, 471 U.S. 261, 280 (1985).\n\n 7\n\ftort claim shall be tolled during the pendency of the grievance procedure.” Va. Code\n\nAnn. § 8.01-195.3(7).\n\n The VTCA does not save Battle’s claims for two reasons. First, the VTCA\n\noperates on a tighter schedule than § 1983. It gives a plaintiff only one year to assert his\n\nrights, plus exhaustion. The VTCA’s tolling provision would thus afford Battle one year\n\nand 83 days to take legal action.\n\n Second, and more fundamentally, the VTCA does not govern suits against state\n\nemployees like the one Battle brings here. Rather, it provides a limited waiver of\n\nsovereign immunity that “applies to one type of litigation, tort actions against the\n\nCommonwealth.” Ogunde v. Virginia, 628 S.E.2d 370, 373 (Va. 2006). But § 1983 does\n\nthe reverse: it applies only to state officials, not states themselves. See Will v. Mich.\n\nDep’t of State Police, 491 U.S. 58, 66 (1989). Because Battle could not have substituted\n\na VTCA claim for a § 1983 action, the VTCA’s tolling provision cannot be integrated\n\ninto the federal scheme.\n\n B.\n\n When state statutory tolling rules provide no relief to a prisoner seeking to bring a\n\n§ 1983 claim, some courts have turned to state equitable tolling rules to suspend\n\nlimitations during the mandated exhaustion period. See Heck v. Humphrey, 997 F.2d\n\n355, 358 (7th Cir. 1993) (applying state equitable tolling to suspend limitations period for\n\n§ 1983 plaintiff seeking to bring habeas claim), aff’d on other grounds, 512 U.S. 477\n\n(1994); Rodriguez v. Holmes, 963 F.2d 799, 804–05 (5th Cir. 1992) (same).\n\n\n\n 8\n\f Under Virginia law, equitable estoppel provides the only arguable exception to the\n\nCommonwealth’s general rule against “recogniz[ing] any non-statutory basis for tolling”\n\nlimitations. City of Bedford v. James Leffel & Co., 558 F.2d 216, 217 (4th Cir. 1977)\n\n(internal quotation marks omitted); see also Casey v. Merck & Co., 722 S.E.2d 842, 845\n\n(Va. 2012) (“A statute of limitations may not be tolled, or an exception applied, in the\n\nabsence of a clear statutory enactment to such effect.” (internal quotation marks\n\nomitted)).\n\n To invoke equitable estoppel under Virginia law, a plaintiff must prove, inter alia,\n\nthat the “party claiming estoppel was misled to his injury” by the defendant in a way that\n\nprevented timely filing. Boykins Narrow Fabrics Corp. v. Weldon Roofing & Sheet\n\nMetal, Inc., 266 S.E.2d 887, 890 (Va. 1980). The corrections officers did not mislead\n\nBattle as to his injury or the accrual date by operation of the prison administrative review\n\nprocess. Accordingly, as each party acknowledges, Battle cannot invoke the doctrine.\n\n Battle further concedes that no other Virginia common law rule could save his\n\nclaim.\n\n\n\n III.\n\n A.\n\n With no Virginia rule available to toll the limitations period, we must determine\n\nwhether refusal to do so during a prisoner’s mandatory exhaustion period is “consistent\n\nwith federal law and policy.” Owens, 488 U.S. at 239.\n\n\n\n 9\n\f When a court borrows a state rule “to assist in the enforcement of [a] federal\n\nremedy,” the federal interest always controls. Wilson, 471 U.S. at 269. This is so\n\nbecause “the policies and purposes of the States” do not constitute “the primary office of\n\nthe borrowing provision in § 1988,” which governs § 1983 actions. Id. Rather, § 1988\n\n“is designed to assure that neutral rules of decision will be available to enforce the civil\n\nrights actions, among them § 1983.” Id. Thus, it is the “duty of the federal courts to\n\nassure that the importation of state law will not frustrate or interfere with the\n\nimplementation of national policies.” Occidental Life Ins. Co. of Cal. v. EEOC, 432 U.S.\n\n355, 367 (1977).\n\n But to be held “inconsistent” with § 1983, a state rule must do more than “cause[]\n\nthe plaintiff to lose the litigation.” Robertson v. Wegmann, 436 U.S. 584, 593 (1978).\n\nThe state rule must “defeat either § 1983’s chief goals of compensation and deterrence or\n\nits subsidiary goals of uniformity and federalism.” Hardin, 490 U.S. at 539 (footnote\n\nomitted). If a state’s timing requirement contravenes one or more of these goals, it is\n\n“inconsistent with federal law,” and § 1988 bars us from adopting it. Id. at 538.\n\n The Supreme Court has explained that it is inconsistent with § 1983’s policies to\n\napply “a state statute of limitations” to require a litigant “to refrain from commencing a\n\ncivil action until it has discharged” a process mandated by federal law. Occidental, 432\n\nU.S. at 367–68. “For the State’s wisdom in establishing a general limitation period could\n\nnot have taken into account the decision of Congress to delay judicial action” while the\n\nlitigant “performs its administrative responsibilities.” Id. (internal quotation marks\n\nomitted). The Court has further suggested that tolling of § 1983 limitations may be\n\n 10\n\fnecessary where a remedy “is structured to require previous resort to state proceedings,\n\nso that the claim may not even be maintained in federal court unless such resort be had.”\n\nBd. of Regents of Univ. of State of N.Y. v. Tomanio, 446 U.S. 478, 490 (1980). The Court\n\nhas even warned that the imposition of an “exhaustion requirement might result in the\n\neffective repeal of § 1983” if “statutes of limitations are not tolled pending exhaustion.”\n\nPatsy v. Bd. of Regents of State of Fla., 457 U.S. 496, 514 n.17 (1982).\n\n B.\n\n With this precedent in mind, we consider its application to the case at hand.\n\n Virginia law provides an elaborate administrative grievance process for prisoner\n\ncomplaints. Exhaustion of this remedy involves at least three levels of review. See\n\nVDOC OP 866.1(IV-VI) (describing emergency grievance review, review of informal\n\ncomplaints, and three-stage review of formal complaints). A prisoner has 30 days to\n\nsubmit a formal grievance, and corrections administrators are then given another 180\n\ndays to resolve the grievance. 5 See id.\n\n Given this structure, Virginia’s no-tolling rule, as applied to prisoners seeking to\n\nbring § 1983 claims, frustrates the goals of § 1983 and is thus clearly “inconsistent” with\n\nsettled federal policy. Hardin, 490 U.S. at 538.\n\n\n\n\n 5\n Virginia’s corrections regulations exempt sexual abuse allegations from the 30-\nday filing requirement so that vulnerable victims may press their claims once it is safe for\nthem to do so. VDOC OP 866.1(VI)(A)(1)(c). Absent tolling, this policy could have the\nunintended effect of substantially reducing a prisoner’s § 1983 filing time when bringing\na serious abuse claim against a corrections officer.\n\n 11\n\f First, application of the no-tolling rule would frustrate the purpose of\n\ncompensating prisoners who have sustained constitutional injuries. Under Virginia\n\nregulations — as implemented by state officials — as much as seven months could be\n\nsubtracted from the period in which a prisoner can file a federal claim. This inevitable\n\nand indeterminate reduction in limitations would be wholly contingent on the efficiency\n\nof administrators and the complexity of the case. And as other circuits have noted and\n\ncommon sense suggests, a state’s grievance process may extend beyond the state’s\n\nregulatory deadlines. See, e.g., Brown v. Valoff, 422 F.3d 926, 932–34 (9th Cir. 2005)\n\n(describing grievance process lasting 2 years and 10 months from injury to investigation\n\nreport); see also Gonzalez v. Hasty, 651 F.3d 318, 323 (2d Cir. 2011) (“[T]he time for\n\nachieving a resolution under the PLRA could be considerably longer than 140 days. . . .\n\n[I]t is certainly possible that a full three years could pass while an inmate exhausts his\n\nadministrative remedies.”). Far from advancing compensation, a no-tolling rule would\n\namount to a penalty in which incarcerated persons — subject to severe state control and\n\noften limited in access to legal resources — would receive less time to vindicate § 1983\n\nclaims than all other litigants.\n\n Application of a no-tolling rule here would also fail to serve § 1983’s second\n\nprimary goal — deterrence. Instead, this rule would enable state officials to shrink a\n\nprisoner’s filing window and so limit his opportunity to bring a claim. In this way, a no-\n\ntolling rule would even create perverse incentives for prison commissioners to extend\n\nregulatory deadlines and for wardens and investigators to stall in their review of\n\n\n\n 12\n\findividual grievances, for doing so might limit government officials’ legal exposure. 6 As\n\nthe Seventh Circuit has observed, no-tolling rules thus encourage prison officials to run\n\nout the clock and “exploit the exhaustion requirement through indefinite delay in\n\nresponding to grievances.” Lewis v. Washington, 300 F.3d 829, 833 (7th Cir. 2002)\n\n(internal quotation marks omitted).\n\n Nor would the no-tolling rule advance § 1983’s subsidiary interest in uniformity.\n\nOf course, Virginia’s rule would set a consistent two-year period between accrual and the\n\nlimitations deadline across claims, furthering uniformity in this formalistic respect. But a\n\nrule that calculates the limitations deadline from the date of exhaustion is just as “firmly\n\ndefined” and “easily applied.” Wilson, 471 U.S. at 270 (quoting Chardon v. Fumero\n\nSoto, 462 U.S. 650, 667 (1983) (Rehnquist, J., dissenting)). Moreover, a no-tolling rule\n\nwould destroy any semblance of meaningful uniformity by creating dramatic claim-to-\n\nclaim variance in the actual filing time available to different § 1983 litigants. Between\n\nprisoners, a no-tolling rule would afford a prisoner whose grievance was processed with\n\ndelay less time to file than one whose grievance received speedy resolution. It would\n\nalso create a disparity between those who are incarcerated and those who are not. For\n\nexample, if the injuries claimed here had occurred in the context of an arrest rather than a\n\nprison escort, Battle would have been guaranteed a full two years to file his § 1983 suit,\n\nrather than the abbreviated period he would receive under a no-tolling rule. Such\n\n\n\n 6\n We do not discern or suggest any bad faith or intentional delay by prison\nofficials in Battle’s case. Our point is only that this is possible absent tolling.\n\n 13\n\fsweeping and arbitrary deviations in procedural rights would hardly advance a policy of\n\nuniformity.\n\n Finally, we also cannot even say that accepting Virginia’s no-tolling rule would\n\nfoster federalism interests. This is so because the Commonwealth itself has adopted two\n\nstatutes, the VTCA and VPLRA, that toll prisoner exhaustion periods. See Va. Code\n\nAnn. §§ 8.01-195.7, 8.01-243.2. Although neither provides relief to prisoners seeking to\n\nbring § 1983 claims, their enactment demonstrates that Virginia otherwise has adopted a\n\npolicy of tolling limitations while prison administrators review inmate claims. These\n\nstatutes also make clear that an exhaustion reprieve does not conflict with Virginia’s\n\n“important and salutary purpose” in strictly construing statutes of limitations, which is to\n\nprotect defendants from “unscrupulous plaintiffs who hoard evidence that supports their\n\nposition while waiting for their prospective opponents to discard evidence that would\n\nhelp make a defense.” Burns v. Stafford Cty., 315 S.E.2d 856, 859 (Va. 1984).\n\nAdministrative exhaustion does the opposite: it notifies defendants of a potential claim\n\nand allows both parties to develop a record before coming to court.\n\n In sum, because Virginia’s no-tolling rule is inconsistent with federal law and\n\npolicy, we cannot apply it here.\n\n C.\n\n Notwithstanding this analysis, the officers contend that Virginia’s no-tolling rule\n\nnecessarily comports with federal policies because a separate federal law — the PLRA —\n\nimposes the relevant exhaustion requirement. But by enacting the PLRA, Congress did\n\nnot endorse such a no-tolling rule or diminish the interests underlying § 1983. To so\n\n 14\n\fconclude would be to overread the PLRA’s silence on tolling, misread the PLRA’s\n\npurpose, and ignore the text of § 1983 and § 1988.\n\n First, the silence in the PLRA. It is a cardinal rule that “repeals by implication are\n\nnot favored and will not be presumed unless the intention of the legislature to repeal is\n\nclear and manifest.” Hui v. Castaneda, 559 U.S. 799, 810 (2010) (internal quotation\n\nmarks omitted). Nothing in the text of the PLRA suggests that Congress sought to limit\n\nor modify § 1988(a)’s express command that borrowed provisions of state law must be\n\nconsistent with important, long-recognized federal policies. The PLRA’s legislative\n\nhistory is also silent as to § 1988(a)’s borrowing framework and the Court’s\n\ninterpretation thereof. The conference reports, floor debates, and committee hearings\n\ncontain no discussion of the pressure that mandatory exhaustion would exert on § 1983’s\n\nstate-derived limitations rule absent tolling. See generally Bernard D. Reams & William\n\nH. Manz, A Legislative History of the Prison Litigation Reform Act of 1996, Pub. L. No.\n\n104–134, 110 Stat. 1321 (1997). When confronted with statutory silence, we must\n\n“presume that Congress is aware of the legal context in which it is legislating.” Palisades\n\nCollections LLC v. Shorts, 552 F.3d 327, 335 n.4 (4th Cir. 2008) (internal quotation\n\nmarks omitted).\n\n Nor do we see any indication that Congress intended, through the PLRA, to amend\n\nor override the specific federal policies underlying § 1983 and incorporated into\n\n§ 1988(a). Instead, as the Supreme Court has explained, it is “[b]eyond doubt” that\n\nCongress enacted the PLRA’s exhaustion requirement “to reduce the quantity and\n\nimprove the quality of prisoner suits” by allowing officials the opportunity to take\n\n 15\n\f“corrective action” and ideally “obviating the need for litigation.” Porter v. Nussle, 534\n\nU.S. 516, 524–25 (2002); see also McLean v. United States, 566 F.3d 391, 397 (4th Cir.\n\n2009) (“The purpose of the PLRA was not, however, to impose indiscriminate\n\nrestrictions on prisoners’ access to the federal courts.”).\n\n Senator Kyl, the lead Senate sponsor of the PLRA, explained that an exhaustion\n\nrequirement would “free up judicial resources for claims with merit by both prisoners and\n\nnonprisoners” alike by winnowing meritless claims. 141 Cong. Rec. S7526 (daily ed.\n\nMay 25, 1995) (statement of Sen. Kyl). Similarly, the lead House sponsor, Rep.\n\nLoBiondo, described mandatory exhaustion as promoting more efficient resolution of\n\nprisoner problems and ensuring “some degree of fact-finding so that when or if the matter\n\nreaches Federal court there will be a record upon which to proceed in a more efficient\n\nmanner.” 141 Cong. Rec. H14105 (daily ed. Dec. 6, 1995) (statement of Rep.\n\nLoBiondo). He further characterized mandatory exhaustion as a tool to filter frivolous\n\nclaims so “only those claims with a greater probability . . . of success would, presumably,\n\nproceed.” Id.\n\n Each of these goals entirely accords with those underlying § 1983, and neither\n\nstatute is served by allowing mandatory exhaustion to chip away at a prisoner’s\n\nlimitations period. Rather, as several of our sister circuits have recognized, refusal to toll\n\nlimitations during the PLRA’s mandatory exhaustion period would trap prisoners in a\n\n“catch-22”: one “who files suit . . . prior to exhausting administrative remedies risks\n\ndismissal based upon § 1997e [of the PLRA]; whereas the prisoner who waits to exhaust\n\nhis administrative remedies risks dismissal based upon untimeliness.” Gonzalez, 651\n\n 16\n\fF.3d at 323 (quoting Johnson v. Rivera, 272 F.3d 519, 522 (7th Cir. 2001)); accord\n\nPearson v. Sec’y Dep’t of Corr., 775 F.3d 598, 602 (3d Cir. 2015).\n\n As previously noted, the Supreme Court expressed a similar concern well before\n\nenactment of the PLRA. The Court made plain that imposing a mandatory exhaustion\n\nrequirement without tolling limitations during the exhaustion period could “result in the\n\neffective repeal of § 1983.” Patsy, 457 U.S. at 514 n.17. The text and legislative history\n\nof the PLRA offer no indication that Congress intended to effect such a repeal. Because\n\nthe PLRA does no more than require exhaustion before filing suit, we cannot read it to\n\namend § 1983’s well-established policy objectives, as incorporated into § 1988(a).\n\n\n\n IV.\n\n Because we hold that Virginia’s no-tolling rule is inconsistent with § 1983, we\n\nmust determine a proper remedy. Battle asks that we apply federal equitable tolling\n\nprinciples to account for the time lost during his 83-day mandatory exhaustion period.\n\nWe agree with Battle (and our sister circuits) that those principles apply during this\n\nperiod.\n\n Equitable tolling is “reserved for ‘those rare instances where — due to\n\ncircumstances external to the party’s own conduct — it would be unconscionable to\n\nenforce the limitation period against the party and gross injustice would result.’” Raplee\n\nv. United States, 842 F.3d 328, 333 (4th Cir. 2016) (quoting Harris v. Hutchinson, 209\n\nF.3d 325, 330 (4th Cir. 2000)). The Supreme Court has explained that “[g]enerally, a\n\nlitigant seeking equitable tolling bears the burden of establishing two elements: (1) that\n\n 17\n\fhe has been pursuing his rights diligently, and (2) that some extraordinary circumstance\n\nstood in his way.” Pace v. DiGuglielmo, 544 U.S. 408, 418 (2005); see also Holland v.\n\nFlorida, 560 U.S. 631, 653 (2010) (clarifying that “[t]he diligence required for equitable\n\ntolling purposes is reasonable diligence, not maximum feasible diligence” (internal\n\ncitation and quotation marks omitted)).\n\n Given these principles, the Supreme Court and this court have found equitable\n\ntolling inappropriate where a plaintiff unnecessarily waits to file one claim that does not\n\nrequire exhaustion while exhausting administrative remedies required for a different\n\ncause of action. See Johnson v. Ry. Exp. Agency, Inc., 421 U.S. 454, 465–66 (1975)\n\n(declining to toll limitations for § 1981 claims during exhaustion required for separate\n\nTitle VII remedy); Ott v. Md. Dep’t of Pub. Safety & Corr. Servs., 909 F.3d 655, 661 (4th\n\nCir. 2018) (declining to toll limitations for Rehabilitation Act claims where litigant\n\n“could have timely filed [those] claims without completing the administrative process as\n\nto her [Americans with Disabilities Act] claims”).\n\n In contrast, equitable tolling is appropriate in the narrower context presented here.\n\nFirst, Battle showed reasonable diligence during the 83-day exhaustion period. He\n\npromptly denied the disciplinary charge against him and then underwent two rounds of\n\nappeals, properly pursuing the process through to the “last level.” Second, during this\n\nadministrative process, an extraordinary circumstance “stood in [the] way” of filing suit.\n\nHolland, 560 U.S. at 649 (internal quotation marks omitted). Unlike the litigants in\n\nJohnson and Ott, who remained free to file their § 1981 and Rehabilitation Act claims at\n\nany point after accrual, prisoners face a complete and absolute barrier to litigation of any\n\n 18\n\f§ 1983 claim during their mandatory administrative grievance proceedings. And this\n\nbarrier is far from ordinary. We are aware of no other federal statute in which a\n\nmandatory exhaustion requirement could erode a litigant’s limitations period. 7 Under\n\nthese circumstances, such a total and unusual barrier to filing constitutes an extraordinary\n\ncircumstance.\n\n Thus, every circuit that has confronted a state no-tolling rule and reached this\n\nquestion has applied federal law to equitably toll § 1983 limitations during the PLRA\n\nexhaustion period. See Gonzalez, 651 F.3d at 322–24; Brown, 422 F.3d at 942–43;\n\nBrown v. Morgan, 209 F.3d 595, 596 (6th Cir. 2000). In addition to these three circuits\n\nthat have expressly applied federal equitable tolling, four others have impliedly done so\n\nor suggested that this would be appropriate. See Thompson v. Pitkins, 514 F. App’x 88,\n\n90 (3d Cir. 2013) (“Because exhaustion of prison administrative remedies is mandatory\n\nunder the Prison Litigation Reform Act, the statute of limitations applicable to § 1983\n\n\n 7\n For example, the limitations period for habeas petitions by those in state custody,\n28 U.S.C. § 2244(d)(1), does not begin to run until mandatory exhaustion of state\nremedies is complete, 28 U.S.C. § 2244(d)(2). And under numerous other statutes that\nrequire administrative review prior to filing suit, limitations run only after the agency’s\naction is final. See, e.g., 28 U.S.C. § 2401(b) (requiring filing of Federal Tort Claims Act\nsuit within six months of agency’s denial of claim); 42 U.S.C. § 2000e-5(f)(1) (requiring\nemployee to file Title VII suit within 90 days of dismissal of administrative proceedings);\n20 U.S.C. § 1415(i)(2)(B) (requiring litigants to file suit under Individuals with\nDisabilities Education Act within 90 days of hearing officer’s decision, or as prescribed\nby state law); 8 U.S.C. § 1252(b)(1) (requiring noncitizens to seek judicial review of\ndeportation orders within 30 days of conclusion of administrative proceedings). Notably,\nin considering a prior and identical version of § 1997e(a), the House Judiciary Committee\nexplained that the exhaustion requirement was drafted to align “with administrative\nexhaustion rules that apply in other contexts.” H.R. Rep No. 104-21, at 32 (1995).\n\n\n 19\n\factions may be tolled while a prisoner exhausts.”); Napier v. Preslicka, 314 F.3d 528,\n\n534 n.3 (11th Cir. 2002) (“We proffer, but do not hold, as that issue is not before us, that\n\nsuch a result may be mitigated by the doctrine of equitable tolling, as other circuits have\n\napplied that doctrine to the administrative exhaustion requirement for prison condition\n\nsuits . . . .”); Clifford v. Gibbs, 298 F.3d 328, 333 (5th Cir. 2002) (granting “request to\n\nequitably toll limitations” during administrative proceedings); Johnson, 272 F.3d at 521\n\n(agreeing with other circuits that “federal courts should toll state statutes of limitations\n\nwhile inmates exhaust their administrative remedies under § 1997e” while applying state\n\ntolling provision); Heck, 997 F.2d at 358 (“[A] body of state tolling law that lacks a\n\nprovision for equitable tolling is inconsistent with the provision of a complete federal\n\nremedy under section 1983 and therefore is overridden by the federal doctrine.”).\n\n Tellingly, not one of these courts has required a claimant to prove additional\n\nextraordinary circumstances beyond the exhaustion requirement or to show constant\n\ndiligence until the moment of filing, as the officers would have us do here. In fact, the\n\nSecond Circuit even acknowledged “substantial delay arising from [the plaintiff]’s\n\nfailure” to properly litigate the claim before it, but still equitably tolled the administrative\n\ngrievance period in light of § 1983’s well-established policies. Gonzalez, 651 F.3d at\n\n320, 323.\n\n Finally, in joining this consensus, we note that the ordinary arguments against\n\nequitable tolling do not apply. For example, there is no “potential for . . . endless tolling”\n\nof a prisoner’s § 1983 claim, because the clock would only stop for the length of the\n\nstate’s exhaustion period. Credit Suisse Sec. (USA) LLC v. Simmonds, 566 U.S. 221,\n\n 20\n\f227–28 (2012). If defendants are correct that Virginia’s administrative grievance process\n\nwill never exceed 180 days from the time a grievance is filed, then Virginia’s officials\n\nwill never be subject to a tolling period exceeding seven months. A maximum extension\n\nof seven months will not prejudice these officials, given that the grievance process will\n\nput them on notice of a potential civil rights claim and allow the parties to develop a\n\ncontemporaneous “administrative record that clarifies the contours of the controversy.”\n\nPorter, 534 U.S. at 525.\n\n A clear rule that tolls limitations during the grievance process also avoids any risk\n\nof “loose[ning] the rule of law to whims about the adequacy of excuses, divergent\n\nresponses to claims of hardship, and subjective notions of fair accommodation.” Harris,\n\n209 F.3d at 330. The inquiry here is objective. All a court must do is determine the point\n\nof exhaustion and run the limitations period from that date.\n\n We therefore reject the officers’ invitation to deviate from the path followed by\n\nseven other circuits. Battle’s limitations period must be tolled for the 83 days in which\n\nhe exhausted his administrative remedies, as he was required to do before bringing suit.\n\nThis satisfies the goals of § 1983 and the PLRA while also comporting with principles of\n\nequity: it gives Battle the benefit of the full limitations period applicable to other\n\nlitigants, no more and no less. In sum, Battle’s § 1983 complaint is timely; it was filed\n\nwithin two years of the date he exhausted administrative remedies required by the PLRA.\n\n\n\n\n 21\n\f V.\n\n For the foregoing reasons, we vacate the judgment of the district court and remand\n\nfor further proceedings consistent with this opinion.\n\n VACATED AND REMANDED\n\n\n\n\n 22\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: William D. BATTLE, III, Plaintiff - Appellant, v. J. LEDFORD, Correctional Officer; R. Edwards, Correctional Officer; Gregory Holloway, Warden of Wallens Ridge State Prison; George Hinkle, Regional Administrator for Virginia Department of Corrections, Defendants - Appellees.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-08\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-6287\\n\\n\\nWILLIAM D. BATTLE, III,\\n\\n Plaintiff - Appellant,\\n\\n v.\\n\\nJ. LEDFORD, Correctional Officer; R. EDWARDS, Correctional Officer;\\nGREGORY HOLLOWAY, Warden of Wallens Ridge State Prison; GEORGE\\nHINKLE, Regional Administrator for Virginia Department of Corrections,\\n\\n Defendants - Appellees.\\n\\n\\nAppeal from the United States District Court for the Western District of Virginia, at\\nRoanoke. Elizabeth Kay Dillon, District Judge. (7:16-cv-00020-EKD-RSB)\\n\\n\\nArgued: September 25, 2018 Decided: January 8, 2019\\n\\n\\nBefore MOTZ, DUNCAN, and THACKER, Circuit Judges.\\n\\n\\nVacated and remanded by published opinion. Judge Motz wrote the opinion, in which\\nJudge Duncan and Judge Thacker joined.\\n\\n\\nARGUED: Sarah Crandall, Elizabeth Joynes, UNIVERSITY OF VIRGINIA SCHOOL\\nOF LAW, Charlottesville, Virginia, for Appellant. Michelle Shane Kallen, OFFICE OF\\nTHE ATTORNEY GENERAL OF VIRGINIA, Richmond, Virginia, for Appellees. ON\\nBRIEF: Joseph Charlet, Third Year Law Student, Megan Keenan, Third Year Law\\nStudent, Evan Ward, Third Year Law Student, Appellate Litigation Clinic,\\nUNIVERSITY OF VIRGINIA SCHOOL OF LAW, Charlottesville, Virginia, for\\nAppellant. Mark R. Herring, Attorney General, Trevor S. Cox, Acting Solicitor General,\\n\\fLaura H. Cahill, Assistant Attorney General, Matthew R. McGuire, Deputy Solicitor\\nGeneral, OFFICE OF THE ATTORNEY GENERAL OF VIRGINIA, Richmond,\\nVirginia, for Appellees.\\n\\n\\n\\n\\n 2\\n\\fDIANA GRIBBON MOTZ, Circuit Judge:\\n\\n The Prison Litigation Reform Act requires a prisoner to exhaust administrative\\n\\nremedies before filing suit. When a prisoner filed this action under 42 U.S.C. § 1983\\n\\nafter exhausting those remedies, the district court held the statute of limitations barred his\\n\\nsuit. For the reasons that follow, we vacate and remand for further proceedings\\n\\nconsistent with this opinion.\\n\\n\\n\\n I.\\n\\n William D. Battle, III, entered Wallens Ridge State Prison in Roanoke, Virginia,\\n\\non December 6, 2013. After Battle completed the inmate intake process, corrections\\n\\nofficers J. Ledford and R. Edwards (collectively, “the officers”) escorted him to his\\n\\nassigned housing unit. A physical altercation between Battle and the officers occurred\\n\\nalong the way.\\n\\n The officers subsequently filed a disciplinary report against Battle. They charged\\n\\nthat Battle, who was restrained in handcuffs and leg irons during the transfer, used his\\n\\nbody to push one of the officers into a food cart. According to the officers, they subdued\\n\\nBattle by “plac[ing]” him on the ground. Battle disputed this account before a prison\\n\\nhearing administrator. He denied shoving any officer and instead claimed that a pain in\\n\\nhis ankle caused him to trip. He stated that the officers responded with unnecessary\\n\\nviolence: pulling his hair and slamming his head into the concrete floor, causing\\n\\n“bruising, lacerations, [and] swelling of the face.” Battle requested that the hearing\\n\\nadministrator examine video footage of the incident to corroborate his account.\\n\\n 3\\n\\f The hearing administrator declined to do so; instead, he simply credited the\\n\\nofficers’ version of the incident. After unsuccessfully appealing this decision to the\\n\\nprison’s chief warden, Battle submitted a second appeal to the regional corrections\\n\\nadministrator. On February 27, 2014, the regional administrator rejected Battle’s claim\\n\\nand issued a form confirming that Battle had reached the “last level of appeal for this\\n\\ngrievance.” A total of 83 days had passed since the altercation.\\n\\n On January 11, 2016 — two years and 36 days after the altercation — Battle\\n\\ncompleted a postage request for a pro se § 1983 complaint alleging the officers used\\n\\nexcessive force against him, in violation of the Eighth and Fourteenth Amendments. 1\\n\\nThe parties accept that this postage request establishes the filing date.\\n\\n The officers moved for summary judgment, arguing that Battle filed outside\\n\\nVirginia’s two-year statute of limitations applicable to § 1983 claims filed within the\\n\\njurisdiction. See Va. Code Ann. § 8.01-243(A) (setting limitations for personal injury\\n\\nactions). Battle countered that his complaint was timely because 42 U.S.C. § 1997e(a) of\\n\\nthe Prison Litigation Reform Act (“PLRA”) required him to exhaust available\\n\\nadministrative remedies before bringing a § 1983 claim. He argued that the 83 days\\n\\nduring which he participated in the required exhaustion should be tolled under two\\n\\n\\n\\n\\n 1\\n Battle’s complaint also named corrections administrators Gregory Holloway and\\nGeorge Hinkle as defendants. The district court held that Battle failed to state a claim\\nagainst these two officials. Battle does not appeal their dismissal.\\n\\n 4\\n\\fVirginia statutes and federal law, thus extending his filing deadline to February 27,\\n\\n2016. 2\\n\\n The first state statute on which Battle relied, Va. Code § 8.01-229(K), suspends\\n\\nthe statute of limitations for personal injury actions during criminal proceedings. The\\n\\nsecond, Va. Code § 8.01-195.3(7), governs actions brought under the Virginia Tort\\n\\nClaims Act (“VTCA”) and tolls the time for filing a claim notice during the pendency of\\n\\na prison grievance process. Additionally, Battle relied on federal equitable tolling law.\\n\\n The district court considered only Battle’s argument as to Va. Code § 8.01-\\n\\n229(K). It held that statute could not be used to toll Battle’s limitations period because a\\n\\n“prison disciplinary proceeding is not a criminal prosecution.” Battle v. Ledford, No.\\n\\n7:16CV00020, 2017 WL 432822, at *3 n.5 (W.D. Va. Jan. 30, 2017) (citing Wolff v.\\n\\nMcDonnell, 418 U.S. 539, 556 (1974)). The court then granted the officers’ motion for\\n\\nsummary judgment, concluding that Battle filed his complaint 36 days too late.\\n\\n On appeal, Battle concedes that the district court properly rejected his claim under\\n\\nVa. Code Ann. § 8.01-229(K). He maintains, however, that the court overlooked his\\n\\nclaims of state statutory tolling under the VTCA and federal equitable tolling, and so\\n\\nerred in deeming his complaint time-barred.\\n\\n We review a district court’s grant of summary judgment de novo. Henry v.\\n\\nPurnell, 652 F.3d 524, 531 (4th Cir. 2011) (en banc). Summary judgment is appropriate\\n\\n 2\\n Battle explained in a related affidavit that he understood from a prisoners’ rights\\npamphlet that the exhaustion of administrative remedies required by the Prison Litigation\\nReform Act mandated tolling, but could not easily verify the proposition because he had\\nlimited access to the law library.\\n\\n 5\\n\\fonly when “there is no genuine dispute as to any material fact and the movant is entitled\\n\\nto judgment as a matter of law.” Fed. R. Civ. P. 56(a).\\n\\n\\n\\n II.\\n\\n Congress did not provide fixed timing rules in § 1983 or its companion provision,\\n\\n§ 1988. 3 Instead, Congress specified that gaps in § 1983 “should be filled by state law, as\\n\\nlong as that law is not inconsistent with federal law.” Hardin v. Straub, 490 U.S. 536,\\n\\n538 (1989).\\n\\n The Supreme Court has directed that we apply a state’s “statute of limitations\\n\\ngoverning general personal injury actions” when considering § 1983 claims. Owens v.\\n\\nOkure, 488 U.S. 235, 251 (1989). A state’s limitations and tolling rules are to be\\n\\nfollowed unless doing so “defeat[s] either § 1983’s chief goals of compensation and\\n\\ndeterrence or its subsidiary goals of uniformity and federalism.” Hardin, 490 U.S. at 539\\n\\n(footnote omitted). If Virginia law allows tolling of Battle’s limitations period, that ends\\n\\nthe inquiry. See id. at 543 (establishing that states may grant extensions to prisoners\\n\\n\\n\\n 3\\n Section 1988 provides that where a § 1983 cause of action is\\n\\n deficient in the provisions necessary to furnish suitable remedies, . . . the\\n common law, as modified and changed by the constitution and statutes of\\n the State wherein the court having jurisdiction of such civil or criminal\\n cause is held, so far as the same is not inconsistent with the Constitution\\n and laws of the United States, shall be extended to and govern the said\\n courts in the trial and disposition of the cause[.]\\n\\n42 U.S.C. § 1988(a) (emphasis added).\\n\\n 6\\n\\fconsistent with § 1983). If not, Battle’s claim may survive only if federal equitable\\n\\nprinciples apply to his case.\\n\\n A.\\n\\n Virginia lacks a generally applicable statute that pauses limitations to\\n\\naccommodate administrative exhaustion requirements. See Va. Code Ann. § 8.01-229\\n\\n(enumerating eleven unrelated exceptions suspending tolling limitations periods). 4 Battle\\n\\nthus asks us to borrow a tolling provision in the Virginia Tort Claims Act. He does so on\\n\\nthe theory that he could have brought suit under that law for the same actions against the\\n\\nsame parties.\\n\\n To bring suit under the VTCA, a person must provide a notice of claim to the state\\n\\n“within one year after the cause of action accrues” as a precursor to litigation. Va. Code\\n\\nAnn. § 8.01-195.7. The claimant must file a complaint in court “within 18 months of the\\n\\nfiling of the notice of claim, or within two years after the cause of action accrues.” Id. If\\n\\nthe claimant is a state prisoner, the VTCA provides that the “time for filing the notice of\\n\\n 4\\n We note that Virginia does have its own statute, the Virginia Prisoner Litigation\\nReform Act (“VPLRA”), which directly addresses the interaction of limitations and\\nexhaustion. Va. Code Ann. § 8.01-243.2 provides:\\n\\n No person confined in a state or local correctional facility shall bring or\\n have brought on his behalf any personal action relating to the conditions of\\n his confinement until all available administrative remedies are exhausted.\\n Such action shall be brought by or on behalf of such person within one year\\n after cause of action accrues or within six months after all administrative\\n remedies are exhausted, whichever occurs later.\\n\\nThis provision does not control Battle’s § 1983 action because the Supreme Court has\\nunequivocally held that personal injury limitations periods apply to § 1983 claims. See\\nOwens, 488 U.S. at 251; Wilson v. Garcia, 471 U.S. 261, 280 (1985).\\n\\n 7\\n\\ftort claim shall be tolled during the pendency of the grievance procedure.” Va. Code\\n\\nAnn. § 8.01-195.3(7).\\n\\n The VTCA does not save Battle’s claims for two reasons. First, the VTCA\\n\\noperates on a tighter schedule than § 1983. It gives a plaintiff only one year to assert his\\n\\nrights, plus exhaustion. The VTCA’s tolling provision would thus afford Battle one year\\n\\nand 83 days to take legal action.\\n\\n Second, and more fundamentally, the VTCA does not govern suits against state\\n\\nemployees like the one Battle brings here. Rather, it provides a limited waiver of\\n\\nsovereign immunity that “applies to one type of litigation, tort actions against the\\n\\nCommonwealth.” Ogunde v. Virginia, 628 S.E.2d 370, 373 (Va. 2006). But § 1983 does\\n\\nthe reverse: it applies only to state officials, not states themselves. See Will v. Mich.\\n\\nDep’t of State Police, 491 U.S. 58, 66 (1989). Because Battle could not have substituted\\n\\na VTCA claim for a § 1983 action, the VTCA’s tolling provision cannot be integrated\\n\\ninto the federal scheme.\\n\\n B.\\n\\n When state statutory tolling rules provide no relief to a prisoner seeking to bring a\\n\\n§ 1983 claim, some courts have turned to state equitable tolling rules to suspend\\n\\nlimitations during the mandated exhaustion period. See Heck v. Humphrey, 997 F.2d\\n\\n355, 358 (7th Cir. 1993) (applying state equitable tolling to suspend limitations period for\\n\\n§ 1983 plaintiff seeking to bring habeas claim), aff’d on other grounds, 512 U.S. 477\\n\\n(1994); Rodriguez v. Holmes, 963 F.2d 799, 804–05 (5th Cir. 1992) (same).\\n\\n\\n\\n 8\\n\\f Under Virginia law, equitable estoppel provides the only arguable exception to the\\n\\nCommonwealth’s general rule against “recogniz[ing] any non-statutory basis for tolling”\\n\\nlimitations. City of Bedford v. James Leffel & Co., 558 F.2d 216, 217 (4th Cir. 1977)\\n\\n(internal quotation marks omitted); see also Casey v. Merck & Co., 722 S.E.2d 842, 845\\n\\n(Va. 2012) (“A statute of limitations may not be tolled, or an exception applied, in the\\n\\nabsence of a clear statutory enactment to such effect.” (internal quotation marks\\n\\nomitted)).\\n\\n To invoke equitable estoppel under Virginia law, a plaintiff must prove, inter alia,\\n\\nthat the “party claiming estoppel was misled to his injury” by the defendant in a way that\\n\\nprevented timely filing. Boykins Narrow Fabrics Corp. v. Weldon Roofing & Sheet\\n\\nMetal, Inc., 266 S.E.2d 887, 890 (Va. 1980). The corrections officers did not mislead\\n\\nBattle as to his injury or the accrual date by operation of the prison administrative review\\n\\nprocess. Accordingly, as each party acknowledges, Battle cannot invoke the doctrine.\\n\\n Battle further concedes that no other Virginia common law rule could save his\\n\\nclaim.\\n\\n\\n\\n III.\\n\\n A.\\n\\n With no Virginia rule available to toll the limitations period, we must determine\\n\\nwhether refusal to do so during a prisoner’s mandatory exhaustion period is “consistent\\n\\nwith federal law and policy.” Owens, 488 U.S. at 239.\\n\\n\\n\\n 9\\n\\f When a court borrows a state rule “to assist in the enforcement of [a] federal\\n\\nremedy,” the federal interest always controls. Wilson, 471 U.S. at 269. This is so\\n\\nbecause “the policies and purposes of the States” do not constitute “the primary office of\\n\\nthe borrowing provision in § 1988,” which governs § 1983 actions. Id. Rather, § 1988\\n\\n“is designed to assure that neutral rules of decision will be available to enforce the civil\\n\\nrights actions, among them § 1983.” Id. Thus, it is the “duty of the federal courts to\\n\\nassure that the importation of state law will not frustrate or interfere with the\\n\\nimplementation of national policies.” Occidental Life Ins. Co. of Cal. v. EEOC, 432 U.S.\\n\\n355, 367 (1977).\\n\\n But to be held “inconsistent” with § 1983, a state rule must do more than “cause[]\\n\\nthe plaintiff to lose the litigation.” Robertson v. Wegmann, 436 U.S. 584, 593 (1978).\\n\\nThe state rule must “defeat either § 1983’s chief goals of compensation and deterrence or\\n\\nits subsidiary goals of uniformity and federalism.” Hardin, 490 U.S. at 539 (footnote\\n\\nomitted). If a state’s timing requirement contravenes one or more of these goals, it is\\n\\n“inconsistent with federal law,” and § 1988 bars us from adopting it. Id. at 538.\\n\\n The Supreme Court has explained that it is inconsistent with § 1983’s policies to\\n\\napply “a state statute of limitations” to require a litigant “to refrain from commencing a\\n\\ncivil action until it has discharged” a process mandated by federal law. Occidental, 432\\n\\nU.S. at 367–68. “For the State’s wisdom in establishing a general limitation period could\\n\\nnot have taken into account the decision of Congress to delay judicial action” while the\\n\\nlitigant “performs its administrative responsibilities.” Id. (internal quotation marks\\n\\nomitted). The Court has further suggested that tolling of § 1983 limitations may be\\n\\n 10\\n\\fnecessary where a remedy “is structured to require previous resort to state proceedings,\\n\\nso that the claim may not even be maintained in federal court unless such resort be had.”\\n\\nBd. of Regents of Univ. of State of N.Y. v. Tomanio, 446 U.S. 478, 490 (1980). The Court\\n\\nhas even warned that the imposition of an “exhaustion requirement might result in the\\n\\neffective repeal of § 1983” if “statutes of limitations are not tolled pending exhaustion.”\\n\\nPatsy v. Bd. of Regents of State of Fla., 457 U.S. 496, 514 n.17 (1982).\\n\\n B.\\n\\n With this precedent in mind, we consider its application to the case at hand.\\n\\n Virginia law provides an elaborate administrative grievance process for prisoner\\n\\ncomplaints. Exhaustion of this remedy involves at least three levels of review. See\\n\\nVDOC OP 866.1(IV-VI) (describing emergency grievance review, review of informal\\n\\ncomplaints, and three-stage review of formal complaints). A prisoner has 30 days to\\n\\nsubmit a formal grievance, and corrections administrators are then given another 180\\n\\ndays to resolve the grievance. 5 See id.\\n\\n Given this structure, Virginia’s no-tolling rule, as applied to prisoners seeking to\\n\\nbring § 1983 claims, frustrates the goals of § 1983 and is thus clearly “inconsistent” with\\n\\nsettled federal policy. Hardin, 490 U.S. at 538.\\n\\n\\n\\n\\n 5\\n Virginia’s corrections regulations exempt sexual abuse allegations from the 30-\\nday filing requirement so that vulnerable victims may press their claims once it is safe for\\nthem to do so. VDOC OP 866.1(VI)(A)(1)(c). Absent tolling, this policy could have the\\nunintended effect of substantially reducing a prisoner’s § 1983 filing time when bringing\\na serious abuse claim against a corrections officer.\\n\\n 11\\n\\f First, application of the no-tolling rule would frustrate the purpose of\\n\\ncompensating prisoners who have sustained constitutional injuries. Under Virginia\\n\\nregulations — as implemented by state officials — as much as seven months could be\\n\\nsubtracted from the period in which a prisoner can file a federal claim. This inevitable\\n\\nand indeterminate reduction in limitations would be wholly contingent on the efficiency\\n\\nof administrators and the complexity of the case. And as other circuits have noted and\\n\\ncommon sense suggests, a state’s grievance process may extend beyond the state’s\\n\\nregulatory deadlines. See, e.g., Brown v. Valoff, 422 F.3d 926, 932–34 (9th Cir. 2005)\\n\\n(describing grievance process lasting 2 years and 10 months from injury to investigation\\n\\nreport); see also Gonzalez v. Hasty, 651 F.3d 318, 323 (2d Cir. 2011) (“[T]he time for\\n\\nachieving a resolution under the PLRA could be considerably longer than 140 days. . . .\\n\\n[I]t is certainly possible that a full three years could pass while an inmate exhausts his\\n\\nadministrative remedies.”). Far from advancing compensation, a no-tolling rule would\\n\\namount to a penalty in which incarcerated persons — subject to severe state control and\\n\\noften limited in access to legal resources — would receive less time to vindicate § 1983\\n\\nclaims than all other litigants.\\n\\n Application of a no-tolling rule here would also fail to serve § 1983’s second\\n\\nprimary goal — deterrence. Instead, this rule would enable state officials to shrink a\\n\\nprisoner’s filing window and so limit his opportunity to bring a claim. In this way, a no-\\n\\ntolling rule would even create perverse incentives for prison commissioners to extend\\n\\nregulatory deadlines and for wardens and investigators to stall in their review of\\n\\n\\n\\n 12\\n\\findividual grievances, for doing so might limit government officials’ legal exposure. 6 As\\n\\nthe Seventh Circuit has observed, no-tolling rules thus encourage prison officials to run\\n\\nout the clock and “exploit the exhaustion requirement through indefinite delay in\\n\\nresponding to grievances.” Lewis v. Washington, 300 F.3d 829, 833 (7th Cir. 2002)\\n\\n(internal quotation marks omitted).\\n\\n Nor would the no-tolling rule advance § 1983’s subsidiary interest in uniformity.\\n\\nOf course, Virginia’s rule would set a consistent two-year period between accrual and the\\n\\nlimitations deadline across claims, furthering uniformity in this formalistic respect. But a\\n\\nrule that calculates the limitations deadline from the date of exhaustion is just as “firmly\\n\\ndefined” and “easily applied.” Wilson, 471 U.S. at 270 (quoting Chardon v. Fumero\\n\\nSoto, 462 U.S. 650, 667 (1983) (Rehnquist, J., dissenting)). Moreover, a no-tolling rule\\n\\nwould destroy any semblance of meaningful uniformity by creating dramatic claim-to-\\n\\nclaim variance in the actual filing time available to different § 1983 litigants. Between\\n\\nprisoners, a no-tolling rule would afford a prisoner whose grievance was processed with\\n\\ndelay less time to file than one whose grievance received speedy resolution. It would\\n\\nalso create a disparity between those who are incarcerated and those who are not. For\\n\\nexample, if the injuries claimed here had occurred in the context of an arrest rather than a\\n\\nprison escort, Battle would have been guaranteed a full two years to file his § 1983 suit,\\n\\nrather than the abbreviated period he would receive under a no-tolling rule. Such\\n\\n\\n\\n 6\\n We do not discern or suggest any bad faith or intentional delay by prison\\nofficials in Battle’s case. Our point is only that this is possible absent tolling.\\n\\n 13\\n\\fsweeping and arbitrary deviations in procedural rights would hardly advance a policy of\\n\\nuniformity.\\n\\n Finally, we also cannot even say that accepting Virginia’s no-tolling rule would\\n\\nfoster federalism interests. This is so because the Commonwealth itself has adopted two\\n\\nstatutes, the VTCA and VPLRA, that toll prisoner exhaustion periods. See Va. Code\\n\\nAnn. §§ 8.01-195.7, 8.01-243.2. Although neither provides relief to prisoners seeking to\\n\\nbring § 1983 claims, their enactment demonstrates that Virginia otherwise has adopted a\\n\\npolicy of tolling limitations while prison administrators review inmate claims. These\\n\\nstatutes also make clear that an exhaustion reprieve does not conflict with Virginia’s\\n\\n“important and salutary purpose” in strictly construing statutes of limitations, which is to\\n\\nprotect defendants from “unscrupulous plaintiffs who hoard evidence that supports their\\n\\nposition while waiting for their prospective opponents to discard evidence that would\\n\\nhelp make a defense.” Burns v. Stafford Cty., 315 S.E.2d 856, 859 (Va. 1984).\\n\\nAdministrative exhaustion does the opposite: it notifies defendants of a potential claim\\n\\nand allows both parties to develop a record before coming to court.\\n\\n In sum, because Virginia’s no-tolling rule is inconsistent with federal law and\\n\\npolicy, we cannot apply it here.\\n\\n C.\\n\\n Notwithstanding this analysis, the officers contend that Virginia’s no-tolling rule\\n\\nnecessarily comports with federal policies because a separate federal law — the PLRA —\\n\\nimposes the relevant exhaustion requirement. But by enacting the PLRA, Congress did\\n\\nnot endorse such a no-tolling rule or diminish the interests underlying § 1983. To so\\n\\n 14\\n\\fconclude would be to overread the PLRA’s silence on tolling, misread the PLRA’s\\n\\npurpose, and ignore the text of § 1983 and § 1988.\\n\\n First, the silence in the PLRA. It is a cardinal rule that “repeals by implication are\\n\\nnot favored and will not be presumed unless the intention of the legislature to repeal is\\n\\nclear and manifest.” Hui v. Castaneda, 559 U.S. 799, 810 (2010) (internal quotation\\n\\nmarks omitted). Nothing in the text of the PLRA suggests that Congress sought to limit\\n\\nor modify § 1988(a)’s express command that borrowed provisions of state law must be\\n\\nconsistent with important, long-recognized federal policies. The PLRA’s legislative\\n\\nhistory is also silent as to § 1988(a)’s borrowing framework and the Court’s\\n\\ninterpretation thereof. The conference reports, floor debates, and committee hearings\\n\\ncontain no discussion of the pressure that mandatory exhaustion would exert on § 1983’s\\n\\nstate-derived limitations rule absent tolling. See generally Bernard D. Reams & William\\n\\nH. Manz, A Legislative History of the Prison Litigation Reform Act of 1996, Pub. L. No.\\n\\n104–134, 110 Stat. 1321 (1997). When confronted with statutory silence, we must\\n\\n“presume that Congress is aware of the legal context in which it is legislating.” Palisades\\n\\nCollections LLC v. Shorts, 552 F.3d 327, 335 n.4 (4th Cir. 2008) (internal quotation\\n\\nmarks omitted).\\n\\n Nor do we see any indication that Congress intended, through the PLRA, to amend\\n\\nor override the specific federal policies underlying § 1983 and incorporated into\\n\\n§ 1988(a). Instead, as the Supreme Court has explained, it is “[b]eyond doubt” that\\n\\nCongress enacted the PLRA’s exhaustion requirement “to reduce the quantity and\\n\\nimprove the quality of prisoner suits” by allowing officials the opportunity to take\\n\\n 15\\n\\f“corrective action” and ideally “obviating the need for litigation.” Porter v. Nussle, 534\\n\\nU.S. 516, 524–25 (2002); see also McLean v. United States, 566 F.3d 391, 397 (4th Cir.\\n\\n2009) (“The purpose of the PLRA was not, however, to impose indiscriminate\\n\\nrestrictions on prisoners’ access to the federal courts.”).\\n\\n Senator Kyl, the lead Senate sponsor of the PLRA, explained that an exhaustion\\n\\nrequirement would “free up judicial resources for claims with merit by both prisoners and\\n\\nnonprisoners” alike by winnowing meritless claims. 141 Cong. Rec. S7526 (daily ed.\\n\\nMay 25, 1995) (statement of Sen. Kyl). Similarly, the lead House sponsor, Rep.\\n\\nLoBiondo, described mandatory exhaustion as promoting more efficient resolution of\\n\\nprisoner problems and ensuring “some degree of fact-finding so that when or if the matter\\n\\nreaches Federal court there will be a record upon which to proceed in a more efficient\\n\\nmanner.” 141 Cong. Rec. H14105 (daily ed. Dec. 6, 1995) (statement of Rep.\\n\\nLoBiondo). He further characterized mandatory exhaustion as a tool to filter frivolous\\n\\nclaims so “only those claims with a greater probability . . . of success would, presumably,\\n\\nproceed.” Id.\\n\\n Each of these goals entirely accords with those underlying § 1983, and neither\\n\\nstatute is served by allowing mandatory exhaustion to chip away at a prisoner’s\\n\\nlimitations period. Rather, as several of our sister circuits have recognized, refusal to toll\\n\\nlimitations during the PLRA’s mandatory exhaustion period would trap prisoners in a\\n\\n“catch-22”: one “who files suit . . . prior to exhausting administrative remedies risks\\n\\ndismissal based upon § 1997e [of the PLRA]; whereas the prisoner who waits to exhaust\\n\\nhis administrative remedies risks dismissal based upon untimeliness.” Gonzalez, 651\\n\\n 16\\n\\fF.3d at 323 (quoting Johnson v. Rivera, 272 F.3d 519, 522 (7th Cir. 2001)); accord\\n\\nPearson v. Sec’y Dep’t of Corr., 775 F.3d 598, 602 (3d Cir. 2015).\\n\\n As previously noted, the Supreme Court expressed a similar concern well before\\n\\nenactment of the PLRA. The Court made plain that imposing a mandatory exhaustion\\n\\nrequirement without tolling limitations during the exhaustion period could “result in the\\n\\neffective repeal of § 1983.” Patsy, 457 U.S. at 514 n.17. The text and legislative history\\n\\nof the PLRA offer no indication that Congress intended to effect such a repeal. Because\\n\\nthe PLRA does no more than require exhaustion before filing suit, we cannot read it to\\n\\namend § 1983’s well-established policy objectives, as incorporated into § 1988(a).\\n\\n\\n\\n IV.\\n\\n Because we hold that Virginia’s no-tolling rule is inconsistent with § 1983, we\\n\\nmust determine a proper remedy. Battle asks that we apply federal equitable tolling\\n\\nprinciples to account for the time lost during his 83-day mandatory exhaustion period.\\n\\nWe agree with Battle (and our sister circuits) that those principles apply during this\\n\\nperiod.\\n\\n Equitable tolling is “reserved for ‘those rare instances where — due to\\n\\ncircumstances external to the party’s own conduct — it would be unconscionable to\\n\\nenforce the limitation period against the party and gross injustice would result.’” Raplee\\n\\nv. United States, 842 F.3d 328, 333 (4th Cir. 2016) (quoting Harris v. Hutchinson, 209\\n\\nF.3d 325, 330 (4th Cir. 2000)). The Supreme Court has explained that “[g]enerally, a\\n\\nlitigant seeking equitable tolling bears the burden of establishing two elements: (1) that\\n\\n 17\\n\\fhe has been pursuing his rights diligently, and (2) that some extraordinary circumstance\\n\\nstood in his way.” Pace v. DiGuglielmo, 544 U.S. 408, 418 (2005); see also Holland v.\\n\\nFlorida, 560 U.S. 631, 653 (2010) (clarifying that “[t]he diligence required for equitable\\n\\ntolling purposes is reasonable diligence, not maximum feasible diligence” (internal\\n\\ncitation and quotation marks omitted)).\\n\\n Given these principles, the Supreme Court and this court have found equitable\\n\\ntolling inappropriate where a plaintiff unnecessarily waits to file one claim that does not\\n\\nrequire exhaustion while exhausting administrative remedies required for a different\\n\\ncause of action. See Johnson v. Ry. Exp. Agency, Inc., 421 U.S. 454, 465–66 (1975)\\n\\n(declining to toll limitations for § 1981 claims during exhaustion required for separate\\n\\nTitle VII remedy); Ott v. Md. Dep’t of Pub. Safety & Corr. Servs., 909 F.3d 655, 661 (4th\\n\\nCir. 2018) (declining to toll limitations for Rehabilitation Act claims where litigant\\n\\n“could have timely filed [those] claims without completing the administrative process as\\n\\nto her [Americans with Disabilities Act] claims”).\\n\\n In contrast, equitable tolling is appropriate in the narrower context presented here.\\n\\nFirst, Battle showed reasonable diligence during the 83-day exhaustion period. He\\n\\npromptly denied the disciplinary charge against him and then underwent two rounds of\\n\\nappeals, properly pursuing the process through to the “last level.” Second, during this\\n\\nadministrative process, an extraordinary circumstance “stood in [the] way” of filing suit.\\n\\nHolland, 560 U.S. at 649 (internal quotation marks omitted). Unlike the litigants in\\n\\nJohnson and Ott, who remained free to file their § 1981 and Rehabilitation Act claims at\\n\\nany point after accrual, prisoners face a complete and absolute barrier to litigation of any\\n\\n 18\\n\\f§ 1983 claim during their mandatory administrative grievance proceedings. And this\\n\\nbarrier is far from ordinary. We are aware of no other federal statute in which a\\n\\nmandatory exhaustion requirement could erode a litigant’s limitations period. 7 Under\\n\\nthese circumstances, such a total and unusual barrier to filing constitutes an extraordinary\\n\\ncircumstance.\\n\\n Thus, every circuit that has confronted a state no-tolling rule and reached this\\n\\nquestion has applied federal law to equitably toll § 1983 limitations during the PLRA\\n\\nexhaustion period. See Gonzalez, 651 F.3d at 322–24; Brown, 422 F.3d at 942–43;\\n\\nBrown v. Morgan, 209 F.3d 595, 596 (6th Cir. 2000). In addition to these three circuits\\n\\nthat have expressly applied federal equitable tolling, four others have impliedly done so\\n\\nor suggested that this would be appropriate. See Thompson v. Pitkins, 514 F. App’x 88,\\n\\n90 (3d Cir. 2013) (“Because exhaustion of prison administrative remedies is mandatory\\n\\nunder the Prison Litigation Reform Act, the statute of limitations applicable to § 1983\\n\\n\\n 7\\n For example, the limitations period for habeas petitions by those in state custody,\\n28 U.S.C. § 2244(d)(1), does not begin to run until mandatory exhaustion of state\\nremedies is complete, 28 U.S.C. § 2244(d)(2). And under numerous other statutes that\\nrequire administrative review prior to filing suit, limitations run only after the agency’s\\naction is final. See, e.g., 28 U.S.C. § 2401(b) (requiring filing of Federal Tort Claims Act\\nsuit within six months of agency’s denial of claim); 42 U.S.C. § 2000e-5(f)(1) (requiring\\nemployee to file Title VII suit within 90 days of dismissal of administrative proceedings);\\n20 U.S.C. § 1415(i)(2)(B) (requiring litigants to file suit under Individuals with\\nDisabilities Education Act within 90 days of hearing officer’s decision, or as prescribed\\nby state law); 8 U.S.C. § 1252(b)(1) (requiring noncitizens to seek judicial review of\\ndeportation orders within 30 days of conclusion of administrative proceedings). Notably,\\nin considering a prior and identical version of § 1997e(a), the House Judiciary Committee\\nexplained that the exhaustion requirement was drafted to align “with administrative\\nexhaustion rules that apply in other contexts.” H.R. Rep No. 104-21, at 32 (1995).\\n\\n\\n 19\\n\\factions may be tolled while a prisoner exhausts.”); Napier v. Preslicka, 314 F.3d 528,\\n\\n534 n.3 (11th Cir. 2002) (“We proffer, but do not hold, as that issue is not before us, that\\n\\nsuch a result may be mitigated by the doctrine of equitable tolling, as other circuits have\\n\\napplied that doctrine to the administrative exhaustion requirement for prison condition\\n\\nsuits . . . .”); Clifford v. Gibbs, 298 F.3d 328, 333 (5th Cir. 2002) (granting “request to\\n\\nequitably toll limitations” during administrative proceedings); Johnson, 272 F.3d at 521\\n\\n(agreeing with other circuits that “federal courts should toll state statutes of limitations\\n\\nwhile inmates exhaust their administrative remedies under § 1997e” while applying state\\n\\ntolling provision); Heck, 997 F.2d at 358 (“[A] body of state tolling law that lacks a\\n\\nprovision for equitable tolling is inconsistent with the provision of a complete federal\\n\\nremedy under section 1983 and therefore is overridden by the federal doctrine.”).\\n\\n Tellingly, not one of these courts has required a claimant to prove additional\\n\\nextraordinary circumstances beyond the exhaustion requirement or to show constant\\n\\ndiligence until the moment of filing, as the officers would have us do here. In fact, the\\n\\nSecond Circuit even acknowledged “substantial delay arising from [the plaintiff]’s\\n\\nfailure” to properly litigate the claim before it, but still equitably tolled the administrative\\n\\ngrievance period in light of § 1983’s well-established policies. Gonzalez, 651 F.3d at\\n\\n320, 323.\\n\\n Finally, in joining this consensus, we note that the ordinary arguments against\\n\\nequitable tolling do not apply. For example, there is no “potential for . . . endless tolling”\\n\\nof a prisoner’s § 1983 claim, because the clock would only stop for the length of the\\n\\nstate’s exhaustion period. Credit Suisse Sec. (USA) LLC v. Simmonds, 566 U.S. 221,\\n\\n 20\\n\\f227–28 (2012). If defendants are correct that Virginia’s administrative grievance process\\n\\nwill never exceed 180 days from the time a grievance is filed, then Virginia’s officials\\n\\nwill never be subject to a tolling period exceeding seven months. A maximum extension\\n\\nof seven months will not prejudice these officials, given that the grievance process will\\n\\nput them on notice of a potential civil rights claim and allow the parties to develop a\\n\\ncontemporaneous “administrative record that clarifies the contours of the controversy.”\\n\\nPorter, 534 U.S. at 525.\\n\\n A clear rule that tolls limitations during the grievance process also avoids any risk\\n\\nof “loose[ning] the rule of law to whims about the adequacy of excuses, divergent\\n\\nresponses to claims of hardship, and subjective notions of fair accommodation.” Harris,\\n\\n209 F.3d at 330. The inquiry here is objective. All a court must do is determine the point\\n\\nof exhaustion and run the limitations period from that date.\\n\\n We therefore reject the officers’ invitation to deviate from the path followed by\\n\\nseven other circuits. Battle’s limitations period must be tolled for the 83 days in which\\n\\nhe exhausted his administrative remedies, as he was required to do before bringing suit.\\n\\nThis satisfies the goals of § 1983 and the PLRA while also comporting with principles of\\n\\nequity: it gives Battle the benefit of the full limitations period applicable to other\\n\\nlitigants, no more and no less. In sum, Battle’s § 1983 complaint is timely; it was filed\\n\\nwithin two years of the date he exhausted administrative remedies required by the PLRA.\\n\\n\\n\\n\\n 21\\n\\f V.\\n\\n For the foregoing reasons, we vacate the judgment of the district court and remand\\n\\nfor further proceedings consistent with this opinion.\\n\\n VACATED AND REMANDED\\n\\n\\n\\n\\n 22\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":86,"cells":{"id":{"kind":"number","value":4579689,"string":"4,579,689"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff - Appellee, v. Michael SLAGER, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Michael Slager"},"decision_date":{"kind":"string","value":"2019-01-08"},"docket_number":{"kind":"string","value":"18-4036"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Wilkinson, Wynn, Diaz\", \"parties\": \"\", \"opinions\": [{\"author\": \"WYNN, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-4036\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff – Appellee,\\n\\nv.\\n\\nMICHAEL SLAGER,\\n\\n Defendant – Appellant.\\n\\n\\n\\nAppeal from the United States District Court for the District of South Carolina, at\\nCharleston. David C. Norton, District Judge. (2:16-cr-00378-DCN-1)\\n\\n\\nArgued: November 1, 2018 Decided: January 8, 2019\\n\\n\\nBefore WILKINSON, WYNN, and DIAZ, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Wynn wrote the opinion, in which Judge Wilkinson\\nand Judge Diaz joined.\\n\\n\\nARGUED: Elizabeth Anne Franklin-Best, BLUME, FRANKLIN-BEST & YOUNG,\\nLLC, Columbia, South Carolina, for Appellant. Elizabeth Parr Hecker, UNITED STATES\\nDEPARTMENT OF JUSTICE, Washington, D.C., for Appellee. ON BRIEF: John M.\\nGore, Acting Assistant Attorney General, Tovah R. Calderon, Appellate Section, Civil\\nRights Division, UNITED STATES DEPARTMENT OF JUSTICE, Washington, D.C., for\\nAppellee.\\n\\fWYNN, Circuit Judge:\\n\\n Defendant Michael Slager (“Defendant”), a former officer with the North\\n\\nCharleston Police Department, admitted that he “willfully” shot and killed Walter Scott\\n\\n(“Scott”), when Scott was unarmed and fleeing arrest. Defendant further admitted that his\\n\\ndecision to shoot Scott was “objectively unreasonable.” Based on those admissions,\\n\\nDefendant pleaded guilty to depriving Scott of his civil rights under color of law.\\n\\n The district court sentenced Defendant to a 240-month term of imprisonment.\\n\\nBefore this Court, Defendant argues that the district court reversibly erred in setting his\\n\\nsentence by: (1) using second-degree murder as the sentencing cross-reference for his\\n\\noffense rather than voluntary manslaughter, and (2) applying a two-level enhancement for\\n\\nobstruction of justice. Finding no reversible error, we affirm Defendant’s sentence.\\n\\n I.\\n\\n A.\\n\\n In May 2016, a federal grand jury in the District of South Carolina returned an\\n\\nindictment alleging, among other things, that Defendant, “while acting under color of law\\n\\nas an officer with the North Charleston Police Department, shot [and killed] Walter Scott\\n\\nwithout legal justification, willfully depriving him of the right . . . to be free from the use\\n\\nof unreasonable force by a law enforcement officer.” J.A. 13. In the meantime, Defendant\\n\\nwas tried in state court on one count of murder. That trial resulted in a hung jury and\\n\\nmistrial.\\n\\n Thereafter, Defendant entered into a global plea agreement with the United States\\n\\nand the State of South Carolina. Under that agreement, in exchange for Defendant’s guilty\\n\\n\\n 2\\n\\fplea in federal court to one count of depriving Scott of his civil rights under color of law,\\n\\nthe United States agreed to drop the remaining counts of the indictment 1 and agreed to\\n\\nrecommend a three-level reduction in the applicable sentencing level for acceptance of\\n\\nresponsibility. Additionally, South Carolina agreed not to retry Defendant and dismissed\\n\\nthe murder charge against him.\\n\\n Some of the undisputed facts that formed the basis for Defendant’s plea includes\\n\\nevidence showing that on the morning of April 4, 2015, while on duty, Defendant stopped\\n\\nScott’s vehicle after observing that his center brake light was not working. After the stop,\\n\\nScott fled on foot and Defendant chased him. During the chase, Defendant shot his taser\\n\\nprobes twice, hitting and bringing Scott down with the second shot. See United States v.\\n\\nSlager, No. 2:16-CR-00378-DCN, 2018 WL 445497, at *2 (D.S.C. Jan. 16, 2018).\\n\\n At some point thereafter, Scott got up and fled. While Scott was unarmed and\\n\\nrunning away, Defendant drew his department-issued firearm and fired eight shots at Scott,\\n\\nfive of which struck Scott in the back. Scott died on the scene from these wounds. Id.\\n\\n A bystander witnessed and testified about the incident. The bystander also filmed\\n\\nparts of the incident. The bystander’s testimony and video of the incident directly\\n\\ncontradicted Defendant’s initial account of the incident. In conformance with the global\\n\\nguilty plea agreement, Defendant admitted that he “used deadly force even though it was\\n\\nobjectively unreasonable under the circumstances.” Id. And, Defendant acknowledged\\n\\n\\n 1\\n The federal indictment charged Defendant with: depriving Scott of his civil rights\\nunder color of law, in violation of 18 U.S.C. § 242; using a weapon during the commission\\nof a crime of violence, in violation of 18 U.S.C. § 924(c); and obstruction of justice, in\\nviolation of 18 U.S.C. § 1512(b)(3).\\n\\n 3\\n\\fthat “his actions were done willfully, that is he acted voluntarily and intentionally and with\\n\\nspecific intent to do something that the law forbids.” Id.\\n\\n B.\\n\\n Defendant’s sentencing hearing began on December 4, 2017, and lasted four days.\\n\\nBecause Defendant pleaded guilty to depriving Scott of his civil rights under color of law,\\n\\nthe district court was required during sentencing to cross-reference the offense underlying\\n\\nthe deprivation. See U.S.S.G. § 2H1.1(a)(1). The government contended that the proper\\n\\ncross-reference was second-degree murder because Defendant was acting with malice\\n\\naforethought when he shot Scott. In contrast, Defendant argued that the proper cross-\\n\\nreference was voluntary manslaughter because he was provoked by Scott and was thus not\\n\\nacting with malice.\\n\\n Although most of the facts were undisputed at Defendant’s sentencing hearing, the\\n\\ngovernment and Defendant disagreed as to what occurred after Scott fell to the ground, but\\n\\nbefore Scott got up and ran away from Defendant.\\n\\n i.\\n\\n The government’s version of events is based primarily on the only third-party\\n\\neyewitness to the shooting, Feidin Santana. Santana recounted the shooting during a South\\n\\nCarolina Law Enforcement Division (“SLED”) interview, and during Defendant’s state\\n\\nand federal proceedings. Each time, Santana provided a consistent account of the shooting.\\n\\n While traveling to work on the morning of the shooting, Santana saw Scott running\\n\\nfrom Defendant. Santana followed, but briefly lost sight of Scott and Defendant. When\\n\\nSantana next saw them, Scott was facing down, and Defendant was on top of Scott and\\n\\n\\n 4\\n\\f“trying to control” him. J.A. 971. Santana testified that it sounded like Scott was “being\\n\\nhurt” and he heard something “electric.” J.A. 972. According to Santana, Defendant\\n\\npunched Scott in the back, but Scott never flipped over. Santana did not see Scott punch\\n\\nback. Nor did Santana see Scott grab the taser and charge toward Defendant. Indeed,\\n\\nSantana never saw Scott holding the taser. Rather, according to Santana, Scott did not\\n\\nseem to want to “hurt” Defendant but was “just trying to leave.” J.A. 974. At some point,\\n\\nScott shot up “aggressively,” Santana testified. J.A. 975. By this, Santana meant that Scott\\n\\nwas “determined to . . . just leave.” Id. When Scott broke free and began to run, Defendant\\n\\nshot him. Defendant then handcuffed Scott and checked his pulse but did not treat him.\\n\\n Santana also recorded a portion of the encounter with his cell phone. Santana’s\\n\\nvideo does not clearly show the period during which Scott and Defendant were allegedly\\n\\non the ground. But the video does show that Scott stood up and was running away—not\\n\\npointing a taser at Defendant or advancing toward Defendant—when Defendant fired at\\n\\nhim. Additionally, the video shows Defendant picked up the taser approximately ten feet\\n\\nbehind the point where Defendant was standing when he shot Scott—not between Scott\\n\\nand Defendant.\\n\\n ii.\\n\\n In contrast to Santana’s consistent recollection of the encounter, Defendant provided\\n\\nfour different accounts as to what happened on the morning of April 4, 2015.\\n\\n First, Defendant made an on-scene statement to his superior officer, Lieutenant\\n\\nDaniel Bowman, who arrived shortly after the shooting occurred. Defendant told Lt.\\n\\nBowman that Scott continued to resist arrest after being tasered and falling to the ground.\\n\\n\\n 5\\n\\fDefendant tased Scott twice more while he laid on the ground, but Scott resisted and “was\\n\\nable to roll over onto his back.” Supp. J.A. 75. Scott then “use[d] both hands to grab the\\n\\ntaser” and after “a short struggle,” Scott “was able to wrestle it away.” Id. Scott then\\n\\n“stood up and pointed the taser at” Defendant. Id. Defendant told Lt. Bowman that, when\\n\\nfaced with this alleged threat, he “drew his weapon as he was returning to the standing\\n\\nposition and fired multiple times.” Id. Several of Defendant’s shots struck Scott, who then\\n\\nfell to the ground. According to this account, Defendant then “rendered emergency aid\\n\\nuntil other officers arrived seconds later.” Id.\\n\\n Three days after the shooting, on April 7, 2015, Defendant gave a second account\\n\\nof the encounter in an unsworn interview with SLED investigators. Before giving this\\n\\nstatement, Defendant asked his attorney to verify with the SLED investigators whether\\n\\nthere was “[a]ny video, surveillance video of businesses, security cameras, [or] anything”\\n\\nelse documenting the shooting. J.A. 702. Defendant also asked whether there were any\\n\\nwitnesses who viewed the shooting. The SLED investigators did not apprise Defendant of\\n\\nSantana or his recorded video.\\n\\n At the start of the interview, the SLED investigators informed Defendant that the\\n\\ninterview was part of a criminal investigation and that Defendant could decline to\\n\\nparticipate. Still, Defendant agreed to make a statement. Over the course of the interview,\\n\\nDefendant added new details not mentioned in his prior statement to Lt. Bowman and\\n\\nphysically reenacted key aspects of the encounter. For example, Defendant claimed that\\n\\nScott was “coming straight at him” holding the taser, with his “arm extending straight out.”\\n\\nJ.A. 1640. Defendant told the SLED investigators that he was “shuffle-stepping” to avoid\\n\\n\\n 6\\n\\fthe taser as he “pulled his gun.” Id. According to this account, Scott was “turning to his\\n\\nleft” when Defendant fired. Id. Then, “Scott ran off, stumbled into the grass, [and] fell to\\n\\nthe ground.” Id. Defendant further told the investigators that “Scott must have dropped”\\n\\nthe taser during this altercation, because he retrieved it “between the place where he had\\n\\nbeen shooting and where Scott landed.” J.A. 1641.\\n\\n During his state trial, Defendant provided a third description of his encounter with\\n\\nScott. In this retelling, Defendant claimed that, during the alleged ground struggle, he had\\n\\nattempted to put Scott’s left hand “behind his back to handcuff him.” J.A. 282. However,\\n\\nScott was in a “pushup position” and was “trying to get up” at the same time. Id. Defendant\\n\\ntestified that while this was occurring, he and Scott were “fighting” and “rolling around on\\n\\nthe ground.” J.A. 285. According to this account, Scott eventually “overpowered”\\n\\nDefendant and took his taser. J.A. 286. Defendant testified that at that point, he “instructed\\n\\nMr. Scott to turn right away and go, but he didn’t.” J.A. 288. Instead, Scott continued to\\n\\napproach Defendant, so Defendant “pulled [his] firearm” and “fired until the threat was\\n\\nstopped.” J.A. 289. Defendant’s testimony made clear that he was neither “provoked” nor\\n\\n“angry” during the shooting. J.A. 346–47. Instead, Defendant testified that he was simply\\n\\n“doing [his] job” and acting in “self-defense.” Id. at 347.\\n\\n Defendant provided his fourth description of the shooting over two days of\\n\\ntestimony at his federal pre-trial hearings. Again, Defendant added new details. For the\\n\\nfirst time, Defendant testified that Scott “punched [him] in the chest” during the ground\\n\\naltercation. J.A. 732. And for the first time, Defendant testified that Scott was “on top of\\n\\n[him] at some point.” J.A. 727. Defendant also testified—again, for the first time—that\\n\\n\\n 7\\n\\fScott “drive stunned” 2 him during the altercation. J.A. 728. When asked why he had not\\n\\npreviously provided these details, Defendant testified that the surrounding events were\\n\\n“fuzzy” and there were still “some things [he did not] recall.” J.A. 727. But “some of [his]\\n\\nmemory [had] come back since” the shooting, he testified. Id. Still, Defendant testified\\n\\nthat he could not “recall anything [that he had] told SLED Agents” during his prior\\n\\ninterview. J.A. 860 (emphasis added).\\n\\n Defendant did not testify during his sentencing hearing, but he did attempt to\\n\\nbuttress aspects of his final account of the encounter through three expert witnesses. First,\\n\\nDefendant offered Eugene Liscio, an expert forensic analyst who reconstructs crime\\n\\nscenes. Using Santana’s video, Liscio created a 3D model of the scene of the encounter in\\n\\nan effort to determine whether Defendant or Scott was holding the taser prior to the\\n\\nshooting. Based upon the final position of the taser, Liscio opined that the video was\\n\\n“inconsistent” with Defendant throwing the taser with his right arm. J.A. 1257–58.\\n\\nHowever, Liscio equivocated as to this opinion, acknowledging that there was “no part in\\n\\n[the Santana video] where you can actually see the taser being held.” J.A. 1275. Liscio\\n\\nalso testified that, due to this limitation, the court would have to “make [its] own judgment\\n\\ncall” as to what in fact occurred. J.A. 1279–80.\\n\\n\\n\\n 2\\n “Tasers generally have two modes. In dart mode, a taser shoots probes into a\\nsubject and overrides the central nervous system. Drive stun mode, on the other hand, does\\nnot cause an override of the victim’s central nervous system; that mode is used as a pain\\ncompliance tool with limited threat reduction.” Estate of Armstrong ex rel. Armstrong v.\\nVill. of Pinehurst, 810 F.3d 892, 897 n.3 (4th Cir.), cert. denied sub nom. Vill. of Pinehurst,\\nN.C. v. Estate of Armstrong, 137 S. Ct. 61, 196 L. Ed. 2d 32 (2016) (internal quotations\\nmarks and citations omitted).\\n\\n 8\\n\\f Second, Defendant offered David Hallimore, a forensic audio analyst, who applied\\n\\n“filtration[s] to [the Santana Video] to allow the speech to become more clear.” J.A. 1192,\\n\\n1216. Through these filtrations and “critical listening”—a skill Hallimore purportedly\\n\\nlearned by “train[ing his] brain effectively to better understand certain tones”—Hallimore\\n\\ntestified that he heard “fuck police” and “Let go of the taser or I’ll shoot” on the Santana\\n\\nvideo. J.A. 1204, 1216, 1218. But Hallimore also recognized this was his “interpretation”\\n\\nof the enhanced audio. J.A. 1220.\\n\\n Finally, Defendant introduced opinions and analyses rendered by Megan Fletcher,\\n\\nan agent with the SLED’s Trace Evidence Unit. Fletcher did not testify at the federal\\n\\nsentencing, but Defendant did reference her state trial testimony and report. Fletcher\\n\\nidentified polyester fibers in Defendant’s shirt that had been melted. Fletcher analyzed\\n\\nthese fibers and opined that a “taser drive-stun cannot be excluded as a possible heat source\\n\\nwhich has the potential to melt polyester fibers.” Supp. J.A. 89–90. But Fletcher averred\\n\\nthat she was “unable to definitively conclude whether a Taser did or did not cause the marks\\n\\non the uniform.” Supp. J.A. 89. Fletcher also acknowledged that she never determined—\\n\\nand therefore did not know—the melting point of the fibers in Defendant’s shirt.\\n\\n C.\\n\\n On January 16, 2018, the district court sentenced Defendant to a 240-month term of\\n\\nimprisonment. In an accompanying order explaining its sentencing decision, the court first\\n\\ndetermined that second-degree murder was the appropriate sentencing cross-reference for\\n\\nDefendant’s offense because “malice aforethought is proven by a gross deviation from the\\n\\nstandard of reasonable care, and [because] there is insufficient evidence that the defendant\\n\\n\\n 9\\n\\facted in heat of passion.” Slager, 2018 WL 445497, at *2. To support that judgment, the\\n\\ndistrict court made extensive credibility determinations and factual findings.\\n\\n To begin, the court assessed the credibility of the only two testifying eyewitnesses\\n\\nto Scott’s shooting: Santana and Defendant. Recounting at length Defendant’s various\\n\\naccounts of the encounter, the district court discredited Defendant’s testimony,\\n\\ncharacterizing it as “contradictory,” “self-serving, evolving, and internally inconsistent.”\\n\\nId. at *4–6. Furthermore, the court found that Defendant’s experts did not bolster the\\n\\ncredibility of his account because each expert admitted that his or her respective technique\\n\\nprovided no definitive answer as to the key aspects of Defendant’s final version of the\\n\\nencounter. In contrast, Santana presented a “consistent story,” which the court found\\n\\ncredible. Id. at *4 (“[A] review of the statement Santana gave to SLED, Santana’s state\\n\\ncourt testimony, and his federal court testimony reveals a consistent story that is at odds\\n\\nwith [Defendant’s] presentation of the sequence of events . . . making Santana a more\\n\\ncredible witness.”).\\n\\n Based upon these credibility determinations, the district court made the following\\n\\nfindings of fact. First, the court found that the Santana video did not provide any grounds\\n\\nto support a finding of provocation. Second, the court found that the portion of the\\n\\nencounter not covered by the video—when Defendant and Scott were on the ground—also\\n\\ndid not support a finding of provocation. In particular, the court found that Scott “yelled\\n\\n‘Fuck the police,’ [and] that Scott ran away from [Defendant] during the initial traffic stop\\n\\nand disobeyed commands to stop.” Id. at *8. But the court further found that—contrary\\n\\nto Defendant’s statements—Scott was “never on top of [Defendant].” Id. The court found\\n\\n\\n 10\\n\\fthat Scott did not wrestle the taser away and attempt to drive-stun Defendant because Scott\\n\\n“never had the taser in his hands.” Id. Rather than coming straight at Defendant with a\\n\\ntaser, Scott got “up from the ground [and] ran away from [Defendant],” the court found.\\n\\nId. Instead “of giving chase once again, [Defendant] shot at Scott eight times” and “five\\n\\nof those shots hit Scott in the back.” Id. Moreover, at “no point after [Defendant] fired the\\n\\nfirst shot—when Scott was nearly fifteen feet away—to when [Defendant] fired the eighth\\n\\nshot—when Scott was nearly forty feet away—did Scott turn around.” Id. Emphasizing\\n\\nthat “[w]ords alone will not suffice for a ‘heat of passion’ finding,” the court concluded\\n\\nthat these facts, “taken together,” “did not constitute adequate provocation to apply the\\n\\n‘heat of passion’ mitigation.” Id.\\n\\n In determining Defendant’s sentence, the district court also applied a two-level\\n\\nsentencing enhancement for obstruction of justice based upon Defendant’s false statements\\n\\nto the SLED investigators during his unsworn interview. U.S.S.G. § 3C1.1. In so doing,\\n\\nthe court recognized that Defendant was “represented by an attorney” and “was aware that\\n\\nthere was an investigation . . . underway for the shooting.” Id. at *14. The court also\\n\\nemphasized that, before making the statement, Defendant specifically inquired “about the\\n\\npresence of a video that captured the shooting.” Id. at *17. Believing that no video existed,\\n\\nDefendant “used the SLED interview to advance his false narrative of being forced to fire\\n\\nwhen Scott was coming toward him with a taser,” the court explained. Id.\\n\\n In deciding to apply the obstruction enhancement, the district court acknowledged\\n\\nthat SLED had already obtained Santana’s video when they interviewed Defendant. Still,\\n\\nwithout the video, some of Defendant’s false statements would have significantly\\n\\n\\n 11\\n\\fobstructed the investigation, the court determined. Specifically, if it were “not for the\\n\\nSantana’s video,” Defendant’s statement that “Scott was coming toward him with a taser\\n\\nat the time he fired his first shot” “would certainly have hindered the investigation.” Id.\\n\\nThis was especially true because Defendant’s “status as a [law enforcement] officer would\\n\\nlikely have meant that his rendition of the events would not have been immediately\\n\\nquestioned.” Id.\\n\\n Defendant timely appealed his sentence.\\n\\n II.\\n\\n A.\\n\\n When, as here, a defendant is sentenced for deprivation of civil rights under color\\n\\nof law, the Sentencing Guidelines require the court to cross-reference the “offense\\n\\nguideline applicable to any underlying offense.” U.S.S.G. § 2H1.1(a)(1).\\n\\n Defendant first argues that the district court erred by determining that second-degree\\n\\nmurder was the proper cross-reference under Section 2H1.1. Specifically, Defendant\\n\\nclaims that when he shot Scott, he was provoked and thus acting without malice.\\n\\nConsequently, Defendant argues that the proper cross-reference was voluntary\\n\\nmanslaughter, not second-degree murder.\\n\\n At sentencing, the government “has the burden to prove a cross-referenced offense\\n\\nby a preponderance of the evidence[.]” United States v. Davis, 679 F.3d 177, 182 (4th Cir.\\n\\n2012). In reviewing “whether a district court properly applied . . . its application of a\\n\\ncross-reference, we review the district court’s legal conclusions de novo and its factual\\n\\nfindings for clear error.” United States v. Ashford, 718 F.3d 377, 380 (4th Cir. 2013)\\n\\n\\n 12\\n\\f(quoting United States v. Layton, 564 F.3d 330, 334 (4th Cir. 2009)) (internal quotation\\n\\nmarks omitted). For the reasons that follow, we hold that the district court did not clearly\\n\\nerr in making its factual findings. We further conclude that the court correctly determined,\\n\\nbased on those findings, that second-degree murder was the proper cross-reference.\\n\\n i.\\n\\n “When sentencing courts engage in fact finding, preponderance of the evidence is\\n\\nthe appropriate standard of proof.” United States v. Span, 789 F.3d 320, 334 (4th Cir.\\n\\n2015) (citations and alterations omitted). We “will not reverse a lower court’s findings of\\n\\nfact simply because we would have decided the case differently.” Id. (quoting Easley v.\\n\\nCromartie, 532 U.S. 234, 242 (2001)). Instead, clear error exists only when “the reviewing\\n\\ncourt on the entire evidence is left with the definite and firm conviction that a mistake has\\n\\nbeen committed.” Id. (quoting Easley, 532 U.S. at 242).\\n\\n When a district court renders factual findings “based on determinations regarding\\n\\nthe credibility of witnesses, we give even greater deference to the trial court’s findings.”\\n\\nUnited States v. Hall, 664 F.3d 456, 462 (4th Cir. 2012) (quoting Anderson v. Bessemer\\n\\nCity, 470 U.S. 564, 575 (1985)) (internal quotation marks omitted); see also Teleguz v.\\n\\nZook, 806 F.3d 803, 812 (4th Cir. 2015) (“[C]redibility determinations are deserving of the\\n\\nhighest degree of appellate deference.”), cert. denied, 137 S. Ct. 95 (2016). Indeed, if a\\n\\ndistrict court’s finding “is based on his decision to credit the testimony of one of two or\\n\\nmore witnesses, each of whom has told a coherent and facially plausible story that is not\\n\\ncontradicted by extrinsic evidence, that finding, if not internally inconsistent, can virtually\\n\\nnever be clear error.” Anderson, 470 U.S. at 575 (1985).\\n\\n\\n 13\\n\\f Because Santana’s video does not capture the entirety of the disputed period, the\\n\\ncourt based many of its factual findings on its assessment of the credibility of the two\\n\\ntestifying eyewitnesses to the encounter: Defendant and Santana. Examining at length each\\n\\nof Defendant’s four accounts of the encounter, the court discredited Defendant’s testimony\\n\\nas “contradictory,” “self-serving, evolving, and internally inconsistent.” Slager, 2018 WL\\n\\n445497, at *4–6. The record amply supports that credibility determination.\\n\\n Each time Defendant provided a new statement about the shooting, he put forward\\n\\nnew details materially bearing on his application of force. For example, in contrast to his\\n\\ntestimony in these proceedings, Defendant never told Lt. Bowman or the SLED\\n\\ninvestigators that Scott was “on top of [him] at some point” during the disputed period.\\n\\nJ.A. 727–28. Also, in contrast to his testimony in these proceedings, Defendant did not tell\\n\\nLt. Bowman or the SLED investigators that he was “drive stunned” by Scott. Id. And in\\n\\ncontrast to his testimony in these proceedings, Defendant did not tell either Lt. Bowman or\\n\\nthe SLED investigators that Scott “punched [him] in the chest.” J.A. 732. When Defendant\\n\\nwas asked why he previously failed to provide these details, he testified that his memory\\n\\nwas “fuzzy” and he still didn’t “recall” “some things.” Id. Defendant’s “evolving” account\\n\\nof the encounter provided the district court with ample factual basis to discredit\\n\\nDefendant’s testimony. See Munyakazi v. Lynch, 829 F.3d 291, 298 (4th Cir. 2016)\\n\\n(“Omissions, inconsistent statements, contradictory evidence, and inherently improbable\\n\\ntestimony are appropriate bases for making an adverse credibility determination.” (internal\\n\\nquotation marks and alterations omitted)).\\n\\n\\n\\n\\n 14\\n\\f That some of Defendant’s assertions are flatly contradicted by Santana’s video and\\n\\nby Defendant’s own plea agreement further supports the district court’s finding that\\n\\nDefendant’s account was not credible. Id. Santana’s video, for example, shows that when\\n\\nDefendant fired eight shots from his firearm, Scott was “running away, not pointing a Taser\\n\\nat [Defendant] or advancing toward him,” contrary to Defendant’s statement to Lt.\\n\\nBowman and the SLED investigators. Slager, 2018 WL 445497, at *6. And the video\\n\\nreveals that Defendant picked up his taser approximately ten feet behind where Defendant\\n\\nstood when he shot Scott—not between Scott and Defendant, as Defendant initially\\n\\nasserted. These contradictions further demonstrate that the district court did not clearly err\\n\\nin discerning Defendant’s testimony. See United States v. Savage, 885 F.3d 212, 220 (4th\\n\\nCir. 2018) (holding that it is for the factfinder to hear a witness’s “testimony, along with\\n\\nany alleged inconsistencies, and decide[] [whether] testimony [is] credible”).\\n\\n Santana, on the other hand, provided a consistent story, including as to the facts the\\n\\ndistrict court found significant in its sentencing opinion. Each time he was questioned,\\n\\nSantana testified that Scott never was on top of Defendant, always was facing down, never\\n\\ngained control of Defendant’s taser, and never charged at or tried to fight with Defendant.\\n\\nAnd each time he was questioned, Santana testified that once Scott was able to stand up,\\n\\nhe began to flee—that Scott never tried to stay and fight Defendant, much less charge at\\n\\nhim, as Defendant claimed.\\n\\n Additionally, unlike several of Defendant’s retellings of the encounter, Santana’s\\n\\nversion of events is—and always has been—consistent with the recorded video. On these\\n\\nfacts, the district court did not clearly err in crediting Santana’s consistent testimony. See\\n\\n\\n 15\\n\\fUnited States v. Stark, 8 F.3d 822 (4th Cir. 1993) (unpublished opinion) (District court did\\n\\nnot clearly err in finding one witness’s “consistent testimony, substantiated in part by\\n\\n[documentary evidence], was more credible than [another witness’s] testimony, which the\\n\\ncourt found inconsistent and incredible in many respects.”). 3\\n\\n Defendant nevertheless claims that the district court reversibly erred in declining to\\n\\nfind that the testimony of Defendant’s expert witnesses rendered Defendant’s account of\\n\\nthe encounter credible. “As with lay witnesses, evaluating the credibility of experts and\\n\\nthe value of their opinions is also a function best committed to the district courts, and one\\n\\nto which appellate courts should defer[.]” Hall, 664 F.3d at 462 (citations and alterations\\n\\nomitted).\\n\\n Here, the court did not reversibly err by declining to give weight to the testimony\\n\\nand evidence presented by Defendant’s experts. The district court emphasized—as the\\n\\nrecord demonstrates—that each expert admitted their respective techniques could not\\n\\nprovide the court with definitive conclusions as to what happened during the disputed\\n\\nperiod. Instead, the experts couched their opinions with statements of equivocation and\\n\\ninvited the court to make its own judgment as to what, in fact, occurred during the disputed\\n\\nperiod. See, e.g., Supp. J.A. 89–90 (Fletcher opining that a taser “drive-stun cannot be\\n\\nexcluded as a possible heat source which has the potential to melt polyester fibers”); J.A.\\n\\n\\n\\n 3\\n Defendant complains that the district court failed to point out in its sentencing\\norder that Santana viewed the shooting “from a distance of 136–180 feet.” Appellant’s Br.\\nat 16. Although we “do not dispute that there must be sufficient explanation for a sentence\\nto be procedurally reasonable,” the court’s “thorough explanation” here was more than\\nsufficient to meet this burden. United States v. Helton, 782 F.3d 148, 154 (4th Cir. 2015).\\n\\n 16\\n\\f1279–80 (Liscio testifying that the district court could not rely on his recreation of the\\n\\nscene, but instead “ha[d] to make your own judgment call,” to determine whether Scott\\n\\never held the taser); J.A. 1220 (Hallimore offering the court an “interpretation” of the\\n\\nenhanced audio). The district court thus did not reversibly err in choosing not to give\\n\\nweight to these equivocal opinions. 4\\n\\n In sum, the district court did not clearly err by crediting Santana’s version of the\\n\\nencounter—including that Scott was “never on top of [Defendant],” that Scott never had\\n\\nthe taser in his hands, that Scott immediately began to run away when he stood up, and that\\n\\nhe was running away when Defendant shot him, Slager, 2018 WL 445497, at *8—as\\n\\nopposed to Defendant’s (most recent) account. Notably, several of these key factual\\n\\ndeterminations are consistent with the facts Defendant admitted to in his plea agreement.\\n\\nSee, e.g., id. at *2 (Defendant “fired multiple shots at Scott while Scott was running away\\n\\nfrom him.”); id. (“[D]efendant’s Taser dropped to the ground behind [D]efendant.”).\\n\\n\\n\\n\\n 4\\n Defendant also relies upon the Federal Rules of Evidence and Daubert v. Merrell\\nDow Pharmaceuticals, Inc., 509 U.S. 579 (1993), to argue that the court erred by failing to\\ngive weight to Fletcher’s opinions. But the Rules of Evidence do not apply to sentencing.\\nFed. R. Evid. 1101(d)(3). And this Court has not applied Daubert to sentencing hearings.\\nUnited States v. Barnette, 211 F.3d 803, 815 (4th Cir. 2000); see also United States v.\\nFields, 483 F.3d 313, 342 (5th Cir. 2007) (“No Circuit that we are aware of has applied\\nDaubert to sentencing. . . . Since Daubert’s holding was based on the Federal Rules of\\nEvidence, it is not directly applicable.”). Applying Daubert would run contrary to the\\nsentencing court’s “wide discretion” to determine the “sources and types of evidence,”\\nwhich are relevant for defendants’ individualized sentencing. Pepper v. United States, 562\\nU.S. 476, 488 (2011). We thus reject Defendant’s Daubert argument.\\n\\n 17\\n\\f ii.\\n\\n Defendant next contends that the district court’s factual findings do not support a\\n\\nfinding of malice aforethought. Consequently, Defendant maintains that the court erred by\\n\\ndetermining the proper cross-reference was voluntary manslaughter, not second-degree\\n\\nmurder. Again, we disagree.\\n\\n Murder is “the unlawful killing of a human being with malice aforethought,” 18\\n\\nU.S.C. § 1111, whereas voluntary “manslaughter is the unlawful killing of a human being\\n\\nwithout malice . . . [u]pon a sudden quarrel or heat of passion,” 18 U.S.C. § 1112(a). In\\n\\nother words, malice aforethought “is the distinguishing characteristic which, when present,\\n\\nmakes a homicide murder rather than manslaughter.” United States v. Fleming, 739 F.2d\\n\\n945, 947 (4th Cir. 1984).\\n\\n “Malice aforethought may be established by evidence of conduct which is reckless\\n\\nand wanton and a gross deviation from a reasonable standard of care, of such a nature that\\n\\na [factfinder] is warranted in inferring that [the] defendant was aware of a serious risk of\\n\\ndeath or serious bodily harm.” Ashford, 718 F.3d at 384 (citations and alterations omitted).\\n\\nMalice does not “require proof of an intent to kill or injure.” Fleming, 739 F.2d at 947\\n\\n(citations omitted). Malice exists when the evidence demonstrates that the defendant acted\\n\\n“with a heart that was without regard for the life and safety of others.” Id. at 948 (citations\\n\\nomitted). A district court may infer malice when a defendant uses a weapon “in such a\\n\\nmanner as may be expected naturally and probably to cause death.” United States v.\\n\\nCelestine, 510 F.2d 457, 459 (9th Cir. 1975); accord United States v. Wright, 594 F.3d 259,\\n\\n268 (4th Cir. 2010) (finding malice when Defendant “engaged in a ‘reckless firing of the\\n\\n\\n 18\\n\\ffirearm, a random firing with the intent to hurt someone’” (emphasis in original)); Ashford,\\n\\n718 F.3d at 384 (finding malice when Defendant “drew his firearm and pursued the fleeing”\\n\\nvictim).\\n\\n As Defendant sought to do here, a defendant may negate a finding of malice by\\n\\ndemonstrating that an intentional killing occurred “upon a sudden quarrel or heat of\\n\\npassion.” 18 U.S.C. § 1112(a); United States v. Velazquez, 246 F.3d 204, 212 (2d Cir.\\n\\n2001); United States v. Browner, 889 F.2d 549, 552 (5th Cir. 1989); United States v.\\n\\nRoston, 986 F.2d 1287, 1291 (9th Cir. 1993); United States v. Scafe, 822 F.2d 928, 932\\n\\n(10th Cir. 1987). Federal courts apply the common-law meaning of “sudden quarrel or\\n\\nheat of passion.” See, e.g., United States v. Martinez, 988 F.2d 685, 694 (7th Cir. 1993).\\n\\nUnder the common law, a defendant’s “heat of passion” must arise from “adequate\\n\\nprovocation.” See id.; Roston, 986 F.2d at 1291; United States v. Collins, 690 F.2d 431,\\n\\n437 (5th Cir. 1982); United States v. Medina, 755 F.2d 1269, 1272 (7th Cir. 1985); United\\n\\nStates v. Paul, 37 F.3d 496, 498 (9th Cir. 1994). Provocation is adequate when it “would\\n\\narouse a reasonable and ordinary person to kill someone.” United States v. Wagner, 834\\n\\nF.2d 1474, 1487 (9th Cir. 1987); see Velazquez, 246 F.3d at 213. When a law enforcement\\n\\nofficer, like Defendant, seeks to rely on a sudden quarrel or heat of passion defense, a court\\n\\nmust assess the adequacy of the provocation “by the standards of a reasonable officer.”\\n\\nSee Velazquez, 246 F.3d at 213 (citing United States v. Cobb, 905 F.2d 784, 789 (4th Cir.\\n\\n1999)).\\n\\n “[M]ere words” generally provide inadequate provocation to negate a finding of\\n\\nmalice. See Allen v. United States, 164 U.S. 492, 497 (1896); Velazquez, 246 F.3d at 213;\\n\\n\\n 19\\n\\fUnited States v. McRae, 593 F.2d 700, 705 (5th Cir. 1979); see also 3 Wayne R. LaFave\\n\\n& Austin W. Scott, Jr., Substantive Criminal Law § 15.2(b)(6) (3d ed. 2018) (detailing\\n\\nextraordinary, but inapposite exceptions); Cobb, 905 F.2d at 789 (“mere words” cannot\\n\\n“justify the use of physical force by a police officer”). By contrast, “[m]utual combat” can\\n\\nconstitute adequate provocation under some circumstances. See Martinez, 988 F.2d at 696;\\n\\nUnited States v. Hardin, 443 F.2d 735, 738–39 (D.C. Cir. 1970); 3 LaFave at § 15.2(b)(2).\\n\\nBut when a victim is fleeing from combat and the defendant is neither angry nor in danger,\\n\\nmutual combat does not support a finding that a defendant acted in a heat of passion. See\\n\\nAshford, 718 F.3d at 380 (“[T]he ‘heat of passion’ mitigator plainly does not apply to an\\n\\naggressor who is ‘not angry,’ and has multiple opportunities to walk away from a dispute\\n\\nthat he incited.”).\\n\\n In this case, the district court did not reversibly err in determining that the facts\\n\\nsupported a finding of malice. In his plea agreement, Defendant admitted that he acted\\n\\n“voluntarily and intentionally with specific intent to do something the law forbids.” Slager,\\n\\n2018 WL 445497, at *2. Additionally, Defendant admitted that he “fired eight shots at\\n\\nScott, and each of those eight shots were fired while Scott was unarmed and running away.”\\n\\nId. Defendant’s voluntary, intentional, and repeated discharge of his firearm at Scott as he\\n\\nattempted to run away “may be expected naturally and probably to cause death.” Celestine,\\n\\n510 F.2d at 459; Cf. Wright, 594 F.3d at 268 (It is “perfectly foreseeable that someone\\n\\nw[ill] be killed” when firing a gun “with intent to hurt someone.”).\\n\\n Nor did the district court err in determining that Defendant’s malice was not negated\\n\\nby “sudden quarrel or heat of passion.” 18 U.S.C. § 1112(a). Even though Scott yelled\\n\\n\\n 20\\n\\f“Fuck the police” prior to the shooting, the court rightly found that these words were\\n\\ninsufficient to provoke a reasonable officer—or any reasonable person—to kill. Slager,\\n\\n2018 WL 445497, at *8; see Velazquez, 246 F.3d at 207 (holding that prisoner yelling\\n\\n“Fuck you, you are not going to tell me what to do” was insufficient to provoke guards to\\n\\nkill in the “heat of passion”).\\n\\n Additionally, Defendant’s alleged mutual combat with Scott did not provide\\n\\nDefendant with adequate provocation because Scott was running away when Defendant\\n\\nshot him. See Ashford, 718 F.3d at 380. Perhaps most importantly, even though Defendant\\n\\nnow claims he was provoked, Defendant testified at his state proceedings that he was\\n\\nneither “provoked” nor “angry” during his altercation but was merely acting in “self-\\n\\ndefense.” J.A. 346–47. 5 Defendant cannot negate his malice through “sudden quarrel or\\n\\nheat of passion” when he previously testified he was neither “provoked” nor “angry.”\\n\\nAshford, 718 F.3d at 380.\\n\\n In conclusion, the district court did not reversibly err by inferring Defendant’s\\n\\nmalice from the facts it found credible. Moreover, the court did not reversibly err by\\n\\ndetermining that Defendant’s malice was not negated by “sudden quarrel or heat of\\n\\npassion.” Accordingly, the court properly cross-referenced second-degree murder.\\n\\n\\n\\n\\n 5\\n Because Defendant admitted in his plea agreement that he acted “willfully,” the\\ndistrict court found that Defendant was foreclosed from arguing self-defense during his\\nfederal sentencing hearing. Slager, 2018 WL 445497, at *2.\\n\\n 21\\n\\f B.\\n\\n Next, Defendant argues that the district court erred in applying a two-level sentence\\n\\nenhancement for obstructing justice based on Defendant’s false statements to SLED.\\n\\nDefendant raises this issue for the first time on appeal. “Because this issue was not\\n\\nadvanced in the district court, we review the district court decision for plain error.” United\\n\\nStates v. Hughes, 401 F.3d 540, 547 (4th Cir. 2005); see United States v. Brack, 651 F.3d\\n\\n388, 392 (4th Cir. 2011). For an error to be “plain,” it must be “obvious or clear under\\n\\ncurrent law.” Brack, 651 F.3d at 392. Under this circumscribed standard of review, we do\\n\\nnot find that the district court plainly erred by applying the obstruction sentencing\\n\\nenhancement.\\n\\n A sentencing court may apply the obstruction enhancement when a defendant: (1)\\n\\n“willfully obstructed or impeded, or attempted to obstruct or impede, the administration of\\n\\njustice with respect to the investigation . . . of the instant offense of conviction,” and (2)\\n\\n“the obstructive conduct related to the defendant’s offense of conviction and any relevant\\n\\nconduct.” U.S.S.G. § 3C1.1 (emphasis added). Defendant argues that the district court\\n\\nplainly erred in applying this enhancement because Defendant’s false statements to the\\n\\nSLED investigators “were not made under oath” and the SLED investigators already had\\n\\nSantana’s video when they interviewed Defendant, meaning that Defendant’s false\\n\\nstatements “did not significantly impede the official investigation.” Appellant’s Br. at 45.\\n\\n In support of his argument, Defendant emphasizes that the comments to the\\n\\nobstruction guideline state “[o]rdinarily . . . making false statements, not under oath to law\\n\\nenforcement officers”—as was the case here—does not warrant application of the\\n\\n\\n 22\\n\\fenhancement. U.S.S.G. § 3C1.1 cmt. n.5 (emphases added). But the comments further\\n\\nstate that “providing a materially false statement to a law enforcement officer that\\n\\nsignificantly obstructed or impeded the official investigation” does warrant application of\\n\\nthe enhancement, regardless of whether the materially false statement was made under\\n\\noath. Id. cmt. n.4(G) (emphasis added). And the express text of the obstruction guideline\\n\\ncovers “attempted” obstruction of justice, indicating that application of the guideline is\\n\\nappropriate, at least in some circumstances, even when a defendant’s attempted obstruction\\n\\ndid not in fact result in the obstruction of an investigation. Id.\\n\\n Accordingly, Section 3C1.1 and its comments do not clearly answer the relevant\\n\\nquestion: whether an attempt to significantly obstruct an investigation through unsworn\\n\\nstatements warrants application of the enhancement. Nor has this Court’s case law\\n\\nprovided an “obvious” or “clear” answer to that question. Hughes, 401 F.3d at 547.\\n\\nNotably, as to that question, our sister circuits have reached divergent answers. Compare\\n\\nUnited States v. Girod, 646 F.3d 304, 318 (5th Cir. 2011) (enhancement can be appropriate\\n\\nbased upon attempted, but significant obstruction); United States v. Wolverine, 584 F.\\n\\nApp’x 646, 649 (9th Cir. 2014) (same); with United States v. Adejumo, 772 F.3d 513, 529\\n\\n(8th Cir. 2014) (enhancement is inappropriate based upon attempted, but significant\\n\\nobstruction); United States v. Griffin, 310 F.3d 1017, 1022–23 (7th Cir. 2002) (same). In\\n\\nsuch circumstances, Defendant cannot meet his burden to show that the district court\\n\\nplainly erred by applying a two-level sentencing enhancement for attempted, yet\\n\\n\\n\\n\\n 23\\n\\fsignificant, obstruction of justice through unsworn statements to law enforcement\\n\\ninvestigators. 6\\n\\n III.\\n\\n In sum, the district court committed no reversible error in sentencing Defendant.\\n\\nFirst, the district court did not clearly err in crediting Santana’s description of the encounter\\n\\nand discrediting Defendant’s description. Second, the court properly inferred, from these\\n\\nfacts, malice as required for a second-degree murder cross-reference. Finally, the district\\n\\ncourt did not plainly err in applying an obstruction of justice enhancement. Accordingly,\\n\\nthe district court’s sentence is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 6\\n Defendant also objects to his federal prosecution on double jeopardy grounds.\\nAcknowledging that current Supreme Court case law forecloses this argument, Defendant\\npreserves it pending a possible change in the law.\\n\\n 24\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4356942/\", \"author_raw\": \"WYNN, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"WILKINSON"},"judge2":{"kind":"string","value":"WYNN"},"judge3":{"kind":"string","value":"DIAZ"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4579689/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Michael SLAGER, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-08\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-4036\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff – Appellee,\n\nv.\n\nMICHAEL SLAGER,\n\n Defendant – Appellant.\n\n\n\nAppeal from the United States District Court for the District of South Carolina, at\nCharleston. David C. Norton, District Judge. (2:16-cr-00378-DCN-1)\n\n\nArgued: November 1, 2018 Decided: January 8, 2019\n\n\nBefore WILKINSON, WYNN, and DIAZ, Circuit Judges.\n\n\nAffirmed by published opinion. Judge Wynn wrote the opinion, in which Judge Wilkinson\nand Judge Diaz joined.\n\n\nARGUED: Elizabeth Anne Franklin-Best, BLUME, FRANKLIN-BEST & YOUNG,\nLLC, Columbia, South Carolina, for Appellant. Elizabeth Parr Hecker, UNITED STATES\nDEPARTMENT OF JUSTICE, Washington, D.C., for Appellee. ON BRIEF: John M.\nGore, Acting Assistant Attorney General, Tovah R. Calderon, Appellate Section, Civil\nRights Division, UNITED STATES DEPARTMENT OF JUSTICE, Washington, D.C., for\nAppellee.\n\fWYNN, Circuit Judge:\n\n Defendant Michael Slager (“Defendant”), a former officer with the North\n\nCharleston Police Department, admitted that he “willfully” shot and killed Walter Scott\n\n(“Scott”), when Scott was unarmed and fleeing arrest. Defendant further admitted that his\n\ndecision to shoot Scott was “objectively unreasonable.” Based on those admissions,\n\nDefendant pleaded guilty to depriving Scott of his civil rights under color of law.\n\n The district court sentenced Defendant to a 240-month term of imprisonment.\n\nBefore this Court, Defendant argues that the district court reversibly erred in setting his\n\nsentence by: (1) using second-degree murder as the sentencing cross-reference for his\n\noffense rather than voluntary manslaughter, and (2) applying a two-level enhancement for\n\nobstruction of justice. Finding no reversible error, we affirm Defendant’s sentence.\n\n I.\n\n A.\n\n In May 2016, a federal grand jury in the District of South Carolina returned an\n\nindictment alleging, among other things, that Defendant, “while acting under color of law\n\nas an officer with the North Charleston Police Department, shot [and killed] Walter Scott\n\nwithout legal justification, willfully depriving him of the right . . . to be free from the use\n\nof unreasonable force by a law enforcement officer.” J.A. 13. In the meantime, Defendant\n\nwas tried in state court on one count of murder. That trial resulted in a hung jury and\n\nmistrial.\n\n Thereafter, Defendant entered into a global plea agreement with the United States\n\nand the State of South Carolina. Under that agreement, in exchange for Defendant’s guilty\n\n\n 2\n\fplea in federal court to one count of depriving Scott of his civil rights under color of law,\n\nthe United States agreed to drop the remaining counts of the indictment 1 and agreed to\n\nrecommend a three-level reduction in the applicable sentencing level for acceptance of\n\nresponsibility. Additionally, South Carolina agreed not to retry Defendant and dismissed\n\nthe murder charge against him.\n\n Some of the undisputed facts that formed the basis for Defendant’s plea includes\n\nevidence showing that on the morning of April 4, 2015, while on duty, Defendant stopped\n\nScott’s vehicle after observing that his center brake light was not working. After the stop,\n\nScott fled on foot and Defendant chased him. During the chase, Defendant shot his taser\n\nprobes twice, hitting and bringing Scott down with the second shot. See United States v.\n\nSlager, No. 2:16-CR-00378-DCN, 2018 WL 445497, at *2 (D.S.C. Jan. 16, 2018).\n\n At some point thereafter, Scott got up and fled. While Scott was unarmed and\n\nrunning away, Defendant drew his department-issued firearm and fired eight shots at Scott,\n\nfive of which struck Scott in the back. Scott died on the scene from these wounds. Id.\n\n A bystander witnessed and testified about the incident. The bystander also filmed\n\nparts of the incident. The bystander’s testimony and video of the incident directly\n\ncontradicted Defendant’s initial account of the incident. In conformance with the global\n\nguilty plea agreement, Defendant admitted that he “used deadly force even though it was\n\nobjectively unreasonable under the circumstances.” Id. And, Defendant acknowledged\n\n\n 1\n The federal indictment charged Defendant with: depriving Scott of his civil rights\nunder color of law, in violation of 18 U.S.C. § 242; using a weapon during the commission\nof a crime of violence, in violation of 18 U.S.C. § 924(c); and obstruction of justice, in\nviolation of 18 U.S.C. § 1512(b)(3).\n\n 3\n\fthat “his actions were done willfully, that is he acted voluntarily and intentionally and with\n\nspecific intent to do something that the law forbids.” Id.\n\n B.\n\n Defendant’s sentencing hearing began on December 4, 2017, and lasted four days.\n\nBecause Defendant pleaded guilty to depriving Scott of his civil rights under color of law,\n\nthe district court was required during sentencing to cross-reference the offense underlying\n\nthe deprivation. See U.S.S.G. § 2H1.1(a)(1). The government contended that the proper\n\ncross-reference was second-degree murder because Defendant was acting with malice\n\naforethought when he shot Scott. In contrast, Defendant argued that the proper cross-\n\nreference was voluntary manslaughter because he was provoked by Scott and was thus not\n\nacting with malice.\n\n Although most of the facts were undisputed at Defendant’s sentencing hearing, the\n\ngovernment and Defendant disagreed as to what occurred after Scott fell to the ground, but\n\nbefore Scott got up and ran away from Defendant.\n\n i.\n\n The government’s version of events is based primarily on the only third-party\n\neyewitness to the shooting, Feidin Santana. Santana recounted the shooting during a South\n\nCarolina Law Enforcement Division (“SLED”) interview, and during Defendant’s state\n\nand federal proceedings. Each time, Santana provided a consistent account of the shooting.\n\n While traveling to work on the morning of the shooting, Santana saw Scott running\n\nfrom Defendant. Santana followed, but briefly lost sight of Scott and Defendant. When\n\nSantana next saw them, Scott was facing down, and Defendant was on top of Scott and\n\n\n 4\n\f“trying to control” him. J.A. 971. Santana testified that it sounded like Scott was “being\n\nhurt” and he heard something “electric.” J.A. 972. According to Santana, Defendant\n\npunched Scott in the back, but Scott never flipped over. Santana did not see Scott punch\n\nback. Nor did Santana see Scott grab the taser and charge toward Defendant. Indeed,\n\nSantana never saw Scott holding the taser. Rather, according to Santana, Scott did not\n\nseem to want to “hurt” Defendant but was “just trying to leave.” J.A. 974. At some point,\n\nScott shot up “aggressively,” Santana testified. J.A. 975. By this, Santana meant that Scott\n\nwas “determined to . . . just leave.” Id. When Scott broke free and began to run, Defendant\n\nshot him. Defendant then handcuffed Scott and checked his pulse but did not treat him.\n\n Santana also recorded a portion of the encounter with his cell phone. Santana’s\n\nvideo does not clearly show the period during which Scott and Defendant were allegedly\n\non the ground. But the video does show that Scott stood up and was running away—not\n\npointing a taser at Defendant or advancing toward Defendant—when Defendant fired at\n\nhim. Additionally, the video shows Defendant picked up the taser approximately ten feet\n\nbehind the point where Defendant was standing when he shot Scott—not between Scott\n\nand Defendant.\n\n ii.\n\n In contrast to Santana’s consistent recollection of the encounter, Defendant provided\n\nfour different accounts as to what happened on the morning of April 4, 2015.\n\n First, Defendant made an on-scene statement to his superior officer, Lieutenant\n\nDaniel Bowman, who arrived shortly after the shooting occurred. Defendant told Lt.\n\nBowman that Scott continued to resist arrest after being tasered and falling to the ground.\n\n\n 5\n\fDefendant tased Scott twice more while he laid on the ground, but Scott resisted and “was\n\nable to roll over onto his back.” Supp. J.A. 75. Scott then “use[d] both hands to grab the\n\ntaser” and after “a short struggle,” Scott “was able to wrestle it away.” Id. Scott then\n\n“stood up and pointed the taser at” Defendant. Id. Defendant told Lt. Bowman that, when\n\nfaced with this alleged threat, he “drew his weapon as he was returning to the standing\n\nposition and fired multiple times.” Id. Several of Defendant’s shots struck Scott, who then\n\nfell to the ground. According to this account, Defendant then “rendered emergency aid\n\nuntil other officers arrived seconds later.” Id.\n\n Three days after the shooting, on April 7, 2015, Defendant gave a second account\n\nof the encounter in an unsworn interview with SLED investigators. Before giving this\n\nstatement, Defendant asked his attorney to verify with the SLED investigators whether\n\nthere was “[a]ny video, surveillance video of businesses, security cameras, [or] anything”\n\nelse documenting the shooting. J.A. 702. Defendant also asked whether there were any\n\nwitnesses who viewed the shooting. The SLED investigators did not apprise Defendant of\n\nSantana or his recorded video.\n\n At the start of the interview, the SLED investigators informed Defendant that the\n\ninterview was part of a criminal investigation and that Defendant could decline to\n\nparticipate. Still, Defendant agreed to make a statement. Over the course of the interview,\n\nDefendant added new details not mentioned in his prior statement to Lt. Bowman and\n\nphysically reenacted key aspects of the encounter. For example, Defendant claimed that\n\nScott was “coming straight at him” holding the taser, with his “arm extending straight out.”\n\nJ.A. 1640. Defendant told the SLED investigators that he was “shuffle-stepping” to avoid\n\n\n 6\n\fthe taser as he “pulled his gun.” Id. According to this account, Scott was “turning to his\n\nleft” when Defendant fired. Id. Then, “Scott ran off, stumbled into the grass, [and] fell to\n\nthe ground.” Id. Defendant further told the investigators that “Scott must have dropped”\n\nthe taser during this altercation, because he retrieved it “between the place where he had\n\nbeen shooting and where Scott landed.” J.A. 1641.\n\n During his state trial, Defendant provided a third description of his encounter with\n\nScott. In this retelling, Defendant claimed that, during the alleged ground struggle, he had\n\nattempted to put Scott’s left hand “behind his back to handcuff him.” J.A. 282. However,\n\nScott was in a “pushup position” and was “trying to get up” at the same time. Id. Defendant\n\ntestified that while this was occurring, he and Scott were “fighting” and “rolling around on\n\nthe ground.” J.A. 285. According to this account, Scott eventually “overpowered”\n\nDefendant and took his taser. J.A. 286. Defendant testified that at that point, he “instructed\n\nMr. Scott to turn right away and go, but he didn’t.” J.A. 288. Instead, Scott continued to\n\napproach Defendant, so Defendant “pulled [his] firearm” and “fired until the threat was\n\nstopped.” J.A. 289. Defendant’s testimony made clear that he was neither “provoked” nor\n\n“angry” during the shooting. J.A. 346–47. Instead, Defendant testified that he was simply\n\n“doing [his] job” and acting in “self-defense.” Id. at 347.\n\n Defendant provided his fourth description of the shooting over two days of\n\ntestimony at his federal pre-trial hearings. Again, Defendant added new details. For the\n\nfirst time, Defendant testified that Scott “punched [him] in the chest” during the ground\n\naltercation. J.A. 732. And for the first time, Defendant testified that Scott was “on top of\n\n[him] at some point.” J.A. 727. Defendant also testified—again, for the first time—that\n\n\n 7\n\fScott “drive stunned” 2 him during the altercation. J.A. 728. When asked why he had not\n\npreviously provided these details, Defendant testified that the surrounding events were\n\n“fuzzy” and there were still “some things [he did not] recall.” J.A. 727. But “some of [his]\n\nmemory [had] come back since” the shooting, he testified. Id. Still, Defendant testified\n\nthat he could not “recall anything [that he had] told SLED Agents” during his prior\n\ninterview. J.A. 860 (emphasis added).\n\n Defendant did not testify during his sentencing hearing, but he did attempt to\n\nbuttress aspects of his final account of the encounter through three expert witnesses. First,\n\nDefendant offered Eugene Liscio, an expert forensic analyst who reconstructs crime\n\nscenes. Using Santana’s video, Liscio created a 3D model of the scene of the encounter in\n\nan effort to determine whether Defendant or Scott was holding the taser prior to the\n\nshooting. Based upon the final position of the taser, Liscio opined that the video was\n\n“inconsistent” with Defendant throwing the taser with his right arm. J.A. 1257–58.\n\nHowever, Liscio equivocated as to this opinion, acknowledging that there was “no part in\n\n[the Santana video] where you can actually see the taser being held.” J.A. 1275. Liscio\n\nalso testified that, due to this limitation, the court would have to “make [its] own judgment\n\ncall” as to what in fact occurred. J.A. 1279–80.\n\n\n\n 2\n “Tasers generally have two modes. In dart mode, a taser shoots probes into a\nsubject and overrides the central nervous system. Drive stun mode, on the other hand, does\nnot cause an override of the victim’s central nervous system; that mode is used as a pain\ncompliance tool with limited threat reduction.” Estate of Armstrong ex rel. Armstrong v.\nVill. of Pinehurst, 810 F.3d 892, 897 n.3 (4th Cir.), cert. denied sub nom. Vill. of Pinehurst,\nN.C. v. Estate of Armstrong, 137 S. Ct. 61, 196 L. Ed. 2d 32 (2016) (internal quotations\nmarks and citations omitted).\n\n 8\n\f Second, Defendant offered David Hallimore, a forensic audio analyst, who applied\n\n“filtration[s] to [the Santana Video] to allow the speech to become more clear.” J.A. 1192,\n\n1216. Through these filtrations and “critical listening”—a skill Hallimore purportedly\n\nlearned by “train[ing his] brain effectively to better understand certain tones”—Hallimore\n\ntestified that he heard “fuck police” and “Let go of the taser or I’ll shoot” on the Santana\n\nvideo. J.A. 1204, 1216, 1218. But Hallimore also recognized this was his “interpretation”\n\nof the enhanced audio. J.A. 1220.\n\n Finally, Defendant introduced opinions and analyses rendered by Megan Fletcher,\n\nan agent with the SLED’s Trace Evidence Unit. Fletcher did not testify at the federal\n\nsentencing, but Defendant did reference her state trial testimony and report. Fletcher\n\nidentified polyester fibers in Defendant’s shirt that had been melted. Fletcher analyzed\n\nthese fibers and opined that a “taser drive-stun cannot be excluded as a possible heat source\n\nwhich has the potential to melt polyester fibers.” Supp. J.A. 89–90. But Fletcher averred\n\nthat she was “unable to definitively conclude whether a Taser did or did not cause the marks\n\non the uniform.” Supp. J.A. 89. Fletcher also acknowledged that she never determined—\n\nand therefore did not know—the melting point of the fibers in Defendant’s shirt.\n\n C.\n\n On January 16, 2018, the district court sentenced Defendant to a 240-month term of\n\nimprisonment. In an accompanying order explaining its sentencing decision, the court first\n\ndetermined that second-degree murder was the appropriate sentencing cross-reference for\n\nDefendant’s offense because “malice aforethought is proven by a gross deviation from the\n\nstandard of reasonable care, and [because] there is insufficient evidence that the defendant\n\n\n 9\n\facted in heat of passion.” Slager, 2018 WL 445497, at *2. To support that judgment, the\n\ndistrict court made extensive credibility determinations and factual findings.\n\n To begin, the court assessed the credibility of the only two testifying eyewitnesses\n\nto Scott’s shooting: Santana and Defendant. Recounting at length Defendant’s various\n\naccounts of the encounter, the district court discredited Defendant’s testimony,\n\ncharacterizing it as “contradictory,” “self-serving, evolving, and internally inconsistent.”\n\nId. at *4–6. Furthermore, the court found that Defendant’s experts did not bolster the\n\ncredibility of his account because each expert admitted that his or her respective technique\n\nprovided no definitive answer as to the key aspects of Defendant’s final version of the\n\nencounter. In contrast, Santana presented a “consistent story,” which the court found\n\ncredible. Id. at *4 (“[A] review of the statement Santana gave to SLED, Santana’s state\n\ncourt testimony, and his federal court testimony reveals a consistent story that is at odds\n\nwith [Defendant’s] presentation of the sequence of events . . . making Santana a more\n\ncredible witness.”).\n\n Based upon these credibility determinations, the district court made the following\n\nfindings of fact. First, the court found that the Santana video did not provide any grounds\n\nto support a finding of provocation. Second, the court found that the portion of the\n\nencounter not covered by the video—when Defendant and Scott were on the ground—also\n\ndid not support a finding of provocation. In particular, the court found that Scott “yelled\n\n‘Fuck the police,’ [and] that Scott ran away from [Defendant] during the initial traffic stop\n\nand disobeyed commands to stop.” Id. at *8. But the court further found that—contrary\n\nto Defendant’s statements—Scott was “never on top of [Defendant].” Id. The court found\n\n\n 10\n\fthat Scott did not wrestle the taser away and attempt to drive-stun Defendant because Scott\n\n“never had the taser in his hands.” Id. Rather than coming straight at Defendant with a\n\ntaser, Scott got “up from the ground [and] ran away from [Defendant],” the court found.\n\nId. Instead “of giving chase once again, [Defendant] shot at Scott eight times” and “five\n\nof those shots hit Scott in the back.” Id. Moreover, at “no point after [Defendant] fired the\n\nfirst shot—when Scott was nearly fifteen feet away—to when [Defendant] fired the eighth\n\nshot—when Scott was nearly forty feet away—did Scott turn around.” Id. Emphasizing\n\nthat “[w]ords alone will not suffice for a ‘heat of passion’ finding,” the court concluded\n\nthat these facts, “taken together,” “did not constitute adequate provocation to apply the\n\n‘heat of passion’ mitigation.” Id.\n\n In determining Defendant’s sentence, the district court also applied a two-level\n\nsentencing enhancement for obstruction of justice based upon Defendant’s false statements\n\nto the SLED investigators during his unsworn interview. U.S.S.G. § 3C1.1. In so doing,\n\nthe court recognized that Defendant was “represented by an attorney” and “was aware that\n\nthere was an investigation . . . underway for the shooting.” Id. at *14. The court also\n\nemphasized that, before making the statement, Defendant specifically inquired “about the\n\npresence of a video that captured the shooting.” Id. at *17. Believing that no video existed,\n\nDefendant “used the SLED interview to advance his false narrative of being forced to fire\n\nwhen Scott was coming toward him with a taser,” the court explained. Id.\n\n In deciding to apply the obstruction enhancement, the district court acknowledged\n\nthat SLED had already obtained Santana’s video when they interviewed Defendant. Still,\n\nwithout the video, some of Defendant’s false statements would have significantly\n\n\n 11\n\fobstructed the investigation, the court determined. Specifically, if it were “not for the\n\nSantana’s video,” Defendant’s statement that “Scott was coming toward him with a taser\n\nat the time he fired his first shot” “would certainly have hindered the investigation.” Id.\n\nThis was especially true because Defendant’s “status as a [law enforcement] officer would\n\nlikely have meant that his rendition of the events would not have been immediately\n\nquestioned.” Id.\n\n Defendant timely appealed his sentence.\n\n II.\n\n A.\n\n When, as here, a defendant is sentenced for deprivation of civil rights under color\n\nof law, the Sentencing Guidelines require the court to cross-reference the “offense\n\nguideline applicable to any underlying offense.” U.S.S.G. § 2H1.1(a)(1).\n\n Defendant first argues that the district court erred by determining that second-degree\n\nmurder was the proper cross-reference under Section 2H1.1. Specifically, Defendant\n\nclaims that when he shot Scott, he was provoked and thus acting without malice.\n\nConsequently, Defendant argues that the proper cross-reference was voluntary\n\nmanslaughter, not second-degree murder.\n\n At sentencing, the government “has the burden to prove a cross-referenced offense\n\nby a preponderance of the evidence[.]” United States v. Davis, 679 F.3d 177, 182 (4th Cir.\n\n2012). In reviewing “whether a district court properly applied . . . its application of a\n\ncross-reference, we review the district court’s legal conclusions de novo and its factual\n\nfindings for clear error.” United States v. Ashford, 718 F.3d 377, 380 (4th Cir. 2013)\n\n\n 12\n\f(quoting United States v. Layton, 564 F.3d 330, 334 (4th Cir. 2009)) (internal quotation\n\nmarks omitted). For the reasons that follow, we hold that the district court did not clearly\n\nerr in making its factual findings. We further conclude that the court correctly determined,\n\nbased on those findings, that second-degree murder was the proper cross-reference.\n\n i.\n\n “When sentencing courts engage in fact finding, preponderance of the evidence is\n\nthe appropriate standard of proof.” United States v. Span, 789 F.3d 320, 334 (4th Cir.\n\n2015) (citations and alterations omitted). We “will not reverse a lower court’s findings of\n\nfact simply because we would have decided the case differently.” Id. (quoting Easley v.\n\nCromartie, 532 U.S. 234, 242 (2001)). Instead, clear error exists only when “the reviewing\n\ncourt on the entire evidence is left with the definite and firm conviction that a mistake has\n\nbeen committed.” Id. (quoting Easley, 532 U.S. at 242).\n\n When a district court renders factual findings “based on determinations regarding\n\nthe credibility of witnesses, we give even greater deference to the trial court’s findings.”\n\nUnited States v. Hall, 664 F.3d 456, 462 (4th Cir. 2012) (quoting Anderson v. Bessemer\n\nCity, 470 U.S. 564, 575 (1985)) (internal quotation marks omitted); see also Teleguz v.\n\nZook, 806 F.3d 803, 812 (4th Cir. 2015) (“[C]redibility determinations are deserving of the\n\nhighest degree of appellate deference.”), cert. denied, 137 S. Ct. 95 (2016). Indeed, if a\n\ndistrict court’s finding “is based on his decision to credit the testimony of one of two or\n\nmore witnesses, each of whom has told a coherent and facially plausible story that is not\n\ncontradicted by extrinsic evidence, that finding, if not internally inconsistent, can virtually\n\nnever be clear error.” Anderson, 470 U.S. at 575 (1985).\n\n\n 13\n\f Because Santana’s video does not capture the entirety of the disputed period, the\n\ncourt based many of its factual findings on its assessment of the credibility of the two\n\ntestifying eyewitnesses to the encounter: Defendant and Santana. Examining at length each\n\nof Defendant’s four accounts of the encounter, the court discredited Defendant’s testimony\n\nas “contradictory,” “self-serving, evolving, and internally inconsistent.” Slager, 2018 WL\n\n445497, at *4–6. The record amply supports that credibility determination.\n\n Each time Defendant provided a new statement about the shooting, he put forward\n\nnew details materially bearing on his application of force. For example, in contrast to his\n\ntestimony in these proceedings, Defendant never told Lt. Bowman or the SLED\n\ninvestigators that Scott was “on top of [him] at some point” during the disputed period.\n\nJ.A. 727–28. Also, in contrast to his testimony in these proceedings, Defendant did not tell\n\nLt. Bowman or the SLED investigators that he was “drive stunned” by Scott. Id. And in\n\ncontrast to his testimony in these proceedings, Defendant did not tell either Lt. Bowman or\n\nthe SLED investigators that Scott “punched [him] in the chest.” J.A. 732. When Defendant\n\nwas asked why he previously failed to provide these details, he testified that his memory\n\nwas “fuzzy” and he still didn’t “recall” “some things.” Id. Defendant’s “evolving” account\n\nof the encounter provided the district court with ample factual basis to discredit\n\nDefendant’s testimony. See Munyakazi v. Lynch, 829 F.3d 291, 298 (4th Cir. 2016)\n\n(“Omissions, inconsistent statements, contradictory evidence, and inherently improbable\n\ntestimony are appropriate bases for making an adverse credibility determination.” (internal\n\nquotation marks and alterations omitted)).\n\n\n\n\n 14\n\f That some of Defendant’s assertions are flatly contradicted by Santana’s video and\n\nby Defendant’s own plea agreement further supports the district court’s finding that\n\nDefendant’s account was not credible. Id. Santana’s video, for example, shows that when\n\nDefendant fired eight shots from his firearm, Scott was “running away, not pointing a Taser\n\nat [Defendant] or advancing toward him,” contrary to Defendant’s statement to Lt.\n\nBowman and the SLED investigators. Slager, 2018 WL 445497, at *6. And the video\n\nreveals that Defendant picked up his taser approximately ten feet behind where Defendant\n\nstood when he shot Scott—not between Scott and Defendant, as Defendant initially\n\nasserted. These contradictions further demonstrate that the district court did not clearly err\n\nin discerning Defendant’s testimony. See United States v. Savage, 885 F.3d 212, 220 (4th\n\nCir. 2018) (holding that it is for the factfinder to hear a witness’s “testimony, along with\n\nany alleged inconsistencies, and decide[] [whether] testimony [is] credible”).\n\n Santana, on the other hand, provided a consistent story, including as to the facts the\n\ndistrict court found significant in its sentencing opinion. Each time he was questioned,\n\nSantana testified that Scott never was on top of Defendant, always was facing down, never\n\ngained control of Defendant’s taser, and never charged at or tried to fight with Defendant.\n\nAnd each time he was questioned, Santana testified that once Scott was able to stand up,\n\nhe began to flee—that Scott never tried to stay and fight Defendant, much less charge at\n\nhim, as Defendant claimed.\n\n Additionally, unlike several of Defendant’s retellings of the encounter, Santana’s\n\nversion of events is—and always has been—consistent with the recorded video. On these\n\nfacts, the district court did not clearly err in crediting Santana’s consistent testimony. See\n\n\n 15\n\fUnited States v. Stark, 8 F.3d 822 (4th Cir. 1993) (unpublished opinion) (District court did\n\nnot clearly err in finding one witness’s “consistent testimony, substantiated in part by\n\n[documentary evidence], was more credible than [another witness’s] testimony, which the\n\ncourt found inconsistent and incredible in many respects.”). 3\n\n Defendant nevertheless claims that the district court reversibly erred in declining to\n\nfind that the testimony of Defendant’s expert witnesses rendered Defendant’s account of\n\nthe encounter credible. “As with lay witnesses, evaluating the credibility of experts and\n\nthe value of their opinions is also a function best committed to the district courts, and one\n\nto which appellate courts should defer[.]” Hall, 664 F.3d at 462 (citations and alterations\n\nomitted).\n\n Here, the court did not reversibly err by declining to give weight to the testimony\n\nand evidence presented by Defendant’s experts. The district court emphasized—as the\n\nrecord demonstrates—that each expert admitted their respective techniques could not\n\nprovide the court with definitive conclusions as to what happened during the disputed\n\nperiod. Instead, the experts couched their opinions with statements of equivocation and\n\ninvited the court to make its own judgment as to what, in fact, occurred during the disputed\n\nperiod. See, e.g., Supp. J.A. 89–90 (Fletcher opining that a taser “drive-stun cannot be\n\nexcluded as a possible heat source which has the potential to melt polyester fibers”); J.A.\n\n\n\n 3\n Defendant complains that the district court failed to point out in its sentencing\norder that Santana viewed the shooting “from a distance of 136–180 feet.” Appellant’s Br.\nat 16. Although we “do not dispute that there must be sufficient explanation for a sentence\nto be procedurally reasonable,” the court’s “thorough explanation” here was more than\nsufficient to meet this burden. United States v. Helton, 782 F.3d 148, 154 (4th Cir. 2015).\n\n 16\n\f1279–80 (Liscio testifying that the district court could not rely on his recreation of the\n\nscene, but instead “ha[d] to make your own judgment call,” to determine whether Scott\n\never held the taser); J.A. 1220 (Hallimore offering the court an “interpretation” of the\n\nenhanced audio). The district court thus did not reversibly err in choosing not to give\n\nweight to these equivocal opinions. 4\n\n In sum, the district court did not clearly err by crediting Santana’s version of the\n\nencounter—including that Scott was “never on top of [Defendant],” that Scott never had\n\nthe taser in his hands, that Scott immediately began to run away when he stood up, and that\n\nhe was running away when Defendant shot him, Slager, 2018 WL 445497, at *8—as\n\nopposed to Defendant’s (most recent) account. Notably, several of these key factual\n\ndeterminations are consistent with the facts Defendant admitted to in his plea agreement.\n\nSee, e.g., id. at *2 (Defendant “fired multiple shots at Scott while Scott was running away\n\nfrom him.”); id. (“[D]efendant’s Taser dropped to the ground behind [D]efendant.”).\n\n\n\n\n 4\n Defendant also relies upon the Federal Rules of Evidence and Daubert v. Merrell\nDow Pharmaceuticals, Inc., 509 U.S. 579 (1993), to argue that the court erred by failing to\ngive weight to Fletcher’s opinions. But the Rules of Evidence do not apply to sentencing.\nFed. R. Evid. 1101(d)(3). And this Court has not applied Daubert to sentencing hearings.\nUnited States v. Barnette, 211 F.3d 803, 815 (4th Cir. 2000); see also United States v.\nFields, 483 F.3d 313, 342 (5th Cir. 2007) (“No Circuit that we are aware of has applied\nDaubert to sentencing. . . . Since Daubert’s holding was based on the Federal Rules of\nEvidence, it is not directly applicable.”). Applying Daubert would run contrary to the\nsentencing court’s “wide discretion” to determine the “sources and types of evidence,”\nwhich are relevant for defendants’ individualized sentencing. Pepper v. United States, 562\nU.S. 476, 488 (2011). We thus reject Defendant’s Daubert argument.\n\n 17\n\f ii.\n\n Defendant next contends that the district court’s factual findings do not support a\n\nfinding of malice aforethought. Consequently, Defendant maintains that the court erred by\n\ndetermining the proper cross-reference was voluntary manslaughter, not second-degree\n\nmurder. Again, we disagree.\n\n Murder is “the unlawful killing of a human being with malice aforethought,” 18\n\nU.S.C. § 1111, whereas voluntary “manslaughter is the unlawful killing of a human being\n\nwithout malice . . . [u]pon a sudden quarrel or heat of passion,” 18 U.S.C. § 1112(a). In\n\nother words, malice aforethought “is the distinguishing characteristic which, when present,\n\nmakes a homicide murder rather than manslaughter.” United States v. Fleming, 739 F.2d\n\n945, 947 (4th Cir. 1984).\n\n “Malice aforethought may be established by evidence of conduct which is reckless\n\nand wanton and a gross deviation from a reasonable standard of care, of such a nature that\n\na [factfinder] is warranted in inferring that [the] defendant was aware of a serious risk of\n\ndeath or serious bodily harm.” Ashford, 718 F.3d at 384 (citations and alterations omitted).\n\nMalice does not “require proof of an intent to kill or injure.” Fleming, 739 F.2d at 947\n\n(citations omitted). Malice exists when the evidence demonstrates that the defendant acted\n\n“with a heart that was without regard for the life and safety of others.” Id. at 948 (citations\n\nomitted). A district court may infer malice when a defendant uses a weapon “in such a\n\nmanner as may be expected naturally and probably to cause death.” United States v.\n\nCelestine, 510 F.2d 457, 459 (9th Cir. 1975); accord United States v. Wright, 594 F.3d 259,\n\n268 (4th Cir. 2010) (finding malice when Defendant “engaged in a ‘reckless firing of the\n\n\n 18\n\ffirearm, a random firing with the intent to hurt someone’” (emphasis in original)); Ashford,\n\n718 F.3d at 384 (finding malice when Defendant “drew his firearm and pursued the fleeing”\n\nvictim).\n\n As Defendant sought to do here, a defendant may negate a finding of malice by\n\ndemonstrating that an intentional killing occurred “upon a sudden quarrel or heat of\n\npassion.” 18 U.S.C. § 1112(a); United States v. Velazquez, 246 F.3d 204, 212 (2d Cir.\n\n2001); United States v. Browner, 889 F.2d 549, 552 (5th Cir. 1989); United States v.\n\nRoston, 986 F.2d 1287, 1291 (9th Cir. 1993); United States v. Scafe, 822 F.2d 928, 932\n\n(10th Cir. 1987). Federal courts apply the common-law meaning of “sudden quarrel or\n\nheat of passion.” See, e.g., United States v. Martinez, 988 F.2d 685, 694 (7th Cir. 1993).\n\nUnder the common law, a defendant’s “heat of passion” must arise from “adequate\n\nprovocation.” See id.; Roston, 986 F.2d at 1291; United States v. Collins, 690 F.2d 431,\n\n437 (5th Cir. 1982); United States v. Medina, 755 F.2d 1269, 1272 (7th Cir. 1985); United\n\nStates v. Paul, 37 F.3d 496, 498 (9th Cir. 1994). Provocation is adequate when it “would\n\narouse a reasonable and ordinary person to kill someone.” United States v. Wagner, 834\n\nF.2d 1474, 1487 (9th Cir. 1987); see Velazquez, 246 F.3d at 213. When a law enforcement\n\nofficer, like Defendant, seeks to rely on a sudden quarrel or heat of passion defense, a court\n\nmust assess the adequacy of the provocation “by the standards of a reasonable officer.”\n\nSee Velazquez, 246 F.3d at 213 (citing United States v. Cobb, 905 F.2d 784, 789 (4th Cir.\n\n1999)).\n\n “[M]ere words” generally provide inadequate provocation to negate a finding of\n\nmalice. See Allen v. United States, 164 U.S. 492, 497 (1896); Velazquez, 246 F.3d at 213;\n\n\n 19\n\fUnited States v. McRae, 593 F.2d 700, 705 (5th Cir. 1979); see also 3 Wayne R. LaFave\n\n& Austin W. Scott, Jr., Substantive Criminal Law § 15.2(b)(6) (3d ed. 2018) (detailing\n\nextraordinary, but inapposite exceptions); Cobb, 905 F.2d at 789 (“mere words” cannot\n\n“justify the use of physical force by a police officer”). By contrast, “[m]utual combat” can\n\nconstitute adequate provocation under some circumstances. See Martinez, 988 F.2d at 696;\n\nUnited States v. Hardin, 443 F.2d 735, 738–39 (D.C. Cir. 1970); 3 LaFave at § 15.2(b)(2).\n\nBut when a victim is fleeing from combat and the defendant is neither angry nor in danger,\n\nmutual combat does not support a finding that a defendant acted in a heat of passion. See\n\nAshford, 718 F.3d at 380 (“[T]he ‘heat of passion’ mitigator plainly does not apply to an\n\naggressor who is ‘not angry,’ and has multiple opportunities to walk away from a dispute\n\nthat he incited.”).\n\n In this case, the district court did not reversibly err in determining that the facts\n\nsupported a finding of malice. In his plea agreement, Defendant admitted that he acted\n\n“voluntarily and intentionally with specific intent to do something the law forbids.” Slager,\n\n2018 WL 445497, at *2. Additionally, Defendant admitted that he “fired eight shots at\n\nScott, and each of those eight shots were fired while Scott was unarmed and running away.”\n\nId. Defendant’s voluntary, intentional, and repeated discharge of his firearm at Scott as he\n\nattempted to run away “may be expected naturally and probably to cause death.” Celestine,\n\n510 F.2d at 459; Cf. Wright, 594 F.3d at 268 (It is “perfectly foreseeable that someone\n\nw[ill] be killed” when firing a gun “with intent to hurt someone.”).\n\n Nor did the district court err in determining that Defendant’s malice was not negated\n\nby “sudden quarrel or heat of passion.” 18 U.S.C. § 1112(a). Even though Scott yelled\n\n\n 20\n\f“Fuck the police” prior to the shooting, the court rightly found that these words were\n\ninsufficient to provoke a reasonable officer—or any reasonable person—to kill. Slager,\n\n2018 WL 445497, at *8; see Velazquez, 246 F.3d at 207 (holding that prisoner yelling\n\n“Fuck you, you are not going to tell me what to do” was insufficient to provoke guards to\n\nkill in the “heat of passion”).\n\n Additionally, Defendant’s alleged mutual combat with Scott did not provide\n\nDefendant with adequate provocation because Scott was running away when Defendant\n\nshot him. See Ashford, 718 F.3d at 380. Perhaps most importantly, even though Defendant\n\nnow claims he was provoked, Defendant testified at his state proceedings that he was\n\nneither “provoked” nor “angry” during his altercation but was merely acting in “self-\n\ndefense.” J.A. 346–47. 5 Defendant cannot negate his malice through “sudden quarrel or\n\nheat of passion” when he previously testified he was neither “provoked” nor “angry.”\n\nAshford, 718 F.3d at 380.\n\n In conclusion, the district court did not reversibly err by inferring Defendant’s\n\nmalice from the facts it found credible. Moreover, the court did not reversibly err by\n\ndetermining that Defendant’s malice was not negated by “sudden quarrel or heat of\n\npassion.” Accordingly, the court properly cross-referenced second-degree murder.\n\n\n\n\n 5\n Because Defendant admitted in his plea agreement that he acted “willfully,” the\ndistrict court found that Defendant was foreclosed from arguing self-defense during his\nfederal sentencing hearing. Slager, 2018 WL 445497, at *2.\n\n 21\n\f B.\n\n Next, Defendant argues that the district court erred in applying a two-level sentence\n\nenhancement for obstructing justice based on Defendant’s false statements to SLED.\n\nDefendant raises this issue for the first time on appeal. “Because this issue was not\n\nadvanced in the district court, we review the district court decision for plain error.” United\n\nStates v. Hughes, 401 F.3d 540, 547 (4th Cir. 2005); see United States v. Brack, 651 F.3d\n\n388, 392 (4th Cir. 2011). For an error to be “plain,” it must be “obvious or clear under\n\ncurrent law.” Brack, 651 F.3d at 392. Under this circumscribed standard of review, we do\n\nnot find that the district court plainly erred by applying the obstruction sentencing\n\nenhancement.\n\n A sentencing court may apply the obstruction enhancement when a defendant: (1)\n\n“willfully obstructed or impeded, or attempted to obstruct or impede, the administration of\n\njustice with respect to the investigation . . . of the instant offense of conviction,” and (2)\n\n“the obstructive conduct related to the defendant’s offense of conviction and any relevant\n\nconduct.” U.S.S.G. § 3C1.1 (emphasis added). Defendant argues that the district court\n\nplainly erred in applying this enhancement because Defendant’s false statements to the\n\nSLED investigators “were not made under oath” and the SLED investigators already had\n\nSantana’s video when they interviewed Defendant, meaning that Defendant’s false\n\nstatements “did not significantly impede the official investigation.” Appellant’s Br. at 45.\n\n In support of his argument, Defendant emphasizes that the comments to the\n\nobstruction guideline state “[o]rdinarily . . . making false statements, not under oath to law\n\nenforcement officers”—as was the case here—does not warrant application of the\n\n\n 22\n\fenhancement. U.S.S.G. § 3C1.1 cmt. n.5 (emphases added). But the comments further\n\nstate that “providing a materially false statement to a law enforcement officer that\n\nsignificantly obstructed or impeded the official investigation” does warrant application of\n\nthe enhancement, regardless of whether the materially false statement was made under\n\noath. Id. cmt. n.4(G) (emphasis added). And the express text of the obstruction guideline\n\ncovers “attempted” obstruction of justice, indicating that application of the guideline is\n\nappropriate, at least in some circumstances, even when a defendant’s attempted obstruction\n\ndid not in fact result in the obstruction of an investigation. Id.\n\n Accordingly, Section 3C1.1 and its comments do not clearly answer the relevant\n\nquestion: whether an attempt to significantly obstruct an investigation through unsworn\n\nstatements warrants application of the enhancement. Nor has this Court’s case law\n\nprovided an “obvious” or “clear” answer to that question. Hughes, 401 F.3d at 547.\n\nNotably, as to that question, our sister circuits have reached divergent answers. Compare\n\nUnited States v. Girod, 646 F.3d 304, 318 (5th Cir. 2011) (enhancement can be appropriate\n\nbased upon attempted, but significant obstruction); United States v. Wolverine, 584 F.\n\nApp’x 646, 649 (9th Cir. 2014) (same); with United States v. Adejumo, 772 F.3d 513, 529\n\n(8th Cir. 2014) (enhancement is inappropriate based upon attempted, but significant\n\nobstruction); United States v. Griffin, 310 F.3d 1017, 1022–23 (7th Cir. 2002) (same). In\n\nsuch circumstances, Defendant cannot meet his burden to show that the district court\n\nplainly erred by applying a two-level sentencing enhancement for attempted, yet\n\n\n\n\n 23\n\fsignificant, obstruction of justice through unsworn statements to law enforcement\n\ninvestigators. 6\n\n III.\n\n In sum, the district court committed no reversible error in sentencing Defendant.\n\nFirst, the district court did not clearly err in crediting Santana’s description of the encounter\n\nand discrediting Defendant’s description. Second, the court properly inferred, from these\n\nfacts, malice as required for a second-degree murder cross-reference. Finally, the district\n\ncourt did not plainly err in applying an obstruction of justice enhancement. Accordingly,\n\nthe district court’s sentence is\n\n AFFIRMED.\n\n\n\n\n 6\n Defendant also objects to his federal prosecution on double jeopardy grounds.\nAcknowledging that current Supreme Court case law forecloses this argument, Defendant\npreserves it pending a possible change in the law.\n\n 24\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Michael SLAGER, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-08\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-4036\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff – Appellee,\\n\\nv.\\n\\nMICHAEL SLAGER,\\n\\n Defendant – Appellant.\\n\\n\\n\\nAppeal from the United States District Court for the District of South Carolina, at\\nCharleston. David C. Norton, District Judge. (2:16-cr-00378-DCN-1)\\n\\n\\nArgued: November 1, 2018 Decided: January 8, 2019\\n\\n\\nBefore WILKINSON, WYNN, and DIAZ, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Wynn wrote the opinion, in which Judge Wilkinson\\nand Judge Diaz joined.\\n\\n\\nARGUED: Elizabeth Anne Franklin-Best, BLUME, FRANKLIN-BEST & YOUNG,\\nLLC, Columbia, South Carolina, for Appellant. Elizabeth Parr Hecker, UNITED STATES\\nDEPARTMENT OF JUSTICE, Washington, D.C., for Appellee. ON BRIEF: John M.\\nGore, Acting Assistant Attorney General, Tovah R. Calderon, Appellate Section, Civil\\nRights Division, UNITED STATES DEPARTMENT OF JUSTICE, Washington, D.C., for\\nAppellee.\\n\\fWYNN, Circuit Judge:\\n\\n Defendant Michael Slager (“Defendant”), a former officer with the North\\n\\nCharleston Police Department, admitted that he “willfully” shot and killed Walter Scott\\n\\n(“Scott”), when Scott was unarmed and fleeing arrest. Defendant further admitted that his\\n\\ndecision to shoot Scott was “objectively unreasonable.” Based on those admissions,\\n\\nDefendant pleaded guilty to depriving Scott of his civil rights under color of law.\\n\\n The district court sentenced Defendant to a 240-month term of imprisonment.\\n\\nBefore this Court, Defendant argues that the district court reversibly erred in setting his\\n\\nsentence by: (1) using second-degree murder as the sentencing cross-reference for his\\n\\noffense rather than voluntary manslaughter, and (2) applying a two-level enhancement for\\n\\nobstruction of justice. Finding no reversible error, we affirm Defendant’s sentence.\\n\\n I.\\n\\n A.\\n\\n In May 2016, a federal grand jury in the District of South Carolina returned an\\n\\nindictment alleging, among other things, that Defendant, “while acting under color of law\\n\\nas an officer with the North Charleston Police Department, shot [and killed] Walter Scott\\n\\nwithout legal justification, willfully depriving him of the right . . . to be free from the use\\n\\nof unreasonable force by a law enforcement officer.” J.A. 13. In the meantime, Defendant\\n\\nwas tried in state court on one count of murder. That trial resulted in a hung jury and\\n\\nmistrial.\\n\\n Thereafter, Defendant entered into a global plea agreement with the United States\\n\\nand the State of South Carolina. Under that agreement, in exchange for Defendant’s guilty\\n\\n\\n 2\\n\\fplea in federal court to one count of depriving Scott of his civil rights under color of law,\\n\\nthe United States agreed to drop the remaining counts of the indictment 1 and agreed to\\n\\nrecommend a three-level reduction in the applicable sentencing level for acceptance of\\n\\nresponsibility. Additionally, South Carolina agreed not to retry Defendant and dismissed\\n\\nthe murder charge against him.\\n\\n Some of the undisputed facts that formed the basis for Defendant’s plea includes\\n\\nevidence showing that on the morning of April 4, 2015, while on duty, Defendant stopped\\n\\nScott’s vehicle after observing that his center brake light was not working. After the stop,\\n\\nScott fled on foot and Defendant chased him. During the chase, Defendant shot his taser\\n\\nprobes twice, hitting and bringing Scott down with the second shot. See United States v.\\n\\nSlager, No. 2:16-CR-00378-DCN, 2018 WL 445497, at *2 (D.S.C. Jan. 16, 2018).\\n\\n At some point thereafter, Scott got up and fled. While Scott was unarmed and\\n\\nrunning away, Defendant drew his department-issued firearm and fired eight shots at Scott,\\n\\nfive of which struck Scott in the back. Scott died on the scene from these wounds. Id.\\n\\n A bystander witnessed and testified about the incident. The bystander also filmed\\n\\nparts of the incident. The bystander’s testimony and video of the incident directly\\n\\ncontradicted Defendant’s initial account of the incident. In conformance with the global\\n\\nguilty plea agreement, Defendant admitted that he “used deadly force even though it was\\n\\nobjectively unreasonable under the circumstances.” Id. And, Defendant acknowledged\\n\\n\\n 1\\n The federal indictment charged Defendant with: depriving Scott of his civil rights\\nunder color of law, in violation of 18 U.S.C. § 242; using a weapon during the commission\\nof a crime of violence, in violation of 18 U.S.C. § 924(c); and obstruction of justice, in\\nviolation of 18 U.S.C. § 1512(b)(3).\\n\\n 3\\n\\fthat “his actions were done willfully, that is he acted voluntarily and intentionally and with\\n\\nspecific intent to do something that the law forbids.” Id.\\n\\n B.\\n\\n Defendant’s sentencing hearing began on December 4, 2017, and lasted four days.\\n\\nBecause Defendant pleaded guilty to depriving Scott of his civil rights under color of law,\\n\\nthe district court was required during sentencing to cross-reference the offense underlying\\n\\nthe deprivation. See U.S.S.G. § 2H1.1(a)(1). The government contended that the proper\\n\\ncross-reference was second-degree murder because Defendant was acting with malice\\n\\naforethought when he shot Scott. In contrast, Defendant argued that the proper cross-\\n\\nreference was voluntary manslaughter because he was provoked by Scott and was thus not\\n\\nacting with malice.\\n\\n Although most of the facts were undisputed at Defendant’s sentencing hearing, the\\n\\ngovernment and Defendant disagreed as to what occurred after Scott fell to the ground, but\\n\\nbefore Scott got up and ran away from Defendant.\\n\\n i.\\n\\n The government’s version of events is based primarily on the only third-party\\n\\neyewitness to the shooting, Feidin Santana. Santana recounted the shooting during a South\\n\\nCarolina Law Enforcement Division (“SLED”) interview, and during Defendant’s state\\n\\nand federal proceedings. Each time, Santana provided a consistent account of the shooting.\\n\\n While traveling to work on the morning of the shooting, Santana saw Scott running\\n\\nfrom Defendant. Santana followed, but briefly lost sight of Scott and Defendant. When\\n\\nSantana next saw them, Scott was facing down, and Defendant was on top of Scott and\\n\\n\\n 4\\n\\f“trying to control” him. J.A. 971. Santana testified that it sounded like Scott was “being\\n\\nhurt” and he heard something “electric.” J.A. 972. According to Santana, Defendant\\n\\npunched Scott in the back, but Scott never flipped over. Santana did not see Scott punch\\n\\nback. Nor did Santana see Scott grab the taser and charge toward Defendant. Indeed,\\n\\nSantana never saw Scott holding the taser. Rather, according to Santana, Scott did not\\n\\nseem to want to “hurt” Defendant but was “just trying to leave.” J.A. 974. At some point,\\n\\nScott shot up “aggressively,” Santana testified. J.A. 975. By this, Santana meant that Scott\\n\\nwas “determined to . . . just leave.” Id. When Scott broke free and began to run, Defendant\\n\\nshot him. Defendant then handcuffed Scott and checked his pulse but did not treat him.\\n\\n Santana also recorded a portion of the encounter with his cell phone. Santana’s\\n\\nvideo does not clearly show the period during which Scott and Defendant were allegedly\\n\\non the ground. But the video does show that Scott stood up and was running away—not\\n\\npointing a taser at Defendant or advancing toward Defendant—when Defendant fired at\\n\\nhim. Additionally, the video shows Defendant picked up the taser approximately ten feet\\n\\nbehind the point where Defendant was standing when he shot Scott—not between Scott\\n\\nand Defendant.\\n\\n ii.\\n\\n In contrast to Santana’s consistent recollection of the encounter, Defendant provided\\n\\nfour different accounts as to what happened on the morning of April 4, 2015.\\n\\n First, Defendant made an on-scene statement to his superior officer, Lieutenant\\n\\nDaniel Bowman, who arrived shortly after the shooting occurred. Defendant told Lt.\\n\\nBowman that Scott continued to resist arrest after being tasered and falling to the ground.\\n\\n\\n 5\\n\\fDefendant tased Scott twice more while he laid on the ground, but Scott resisted and “was\\n\\nable to roll over onto his back.” Supp. J.A. 75. Scott then “use[d] both hands to grab the\\n\\ntaser” and after “a short struggle,” Scott “was able to wrestle it away.” Id. Scott then\\n\\n“stood up and pointed the taser at” Defendant. Id. Defendant told Lt. Bowman that, when\\n\\nfaced with this alleged threat, he “drew his weapon as he was returning to the standing\\n\\nposition and fired multiple times.” Id. Several of Defendant’s shots struck Scott, who then\\n\\nfell to the ground. According to this account, Defendant then “rendered emergency aid\\n\\nuntil other officers arrived seconds later.” Id.\\n\\n Three days after the shooting, on April 7, 2015, Defendant gave a second account\\n\\nof the encounter in an unsworn interview with SLED investigators. Before giving this\\n\\nstatement, Defendant asked his attorney to verify with the SLED investigators whether\\n\\nthere was “[a]ny video, surveillance video of businesses, security cameras, [or] anything”\\n\\nelse documenting the shooting. J.A. 702. Defendant also asked whether there were any\\n\\nwitnesses who viewed the shooting. The SLED investigators did not apprise Defendant of\\n\\nSantana or his recorded video.\\n\\n At the start of the interview, the SLED investigators informed Defendant that the\\n\\ninterview was part of a criminal investigation and that Defendant could decline to\\n\\nparticipate. Still, Defendant agreed to make a statement. Over the course of the interview,\\n\\nDefendant added new details not mentioned in his prior statement to Lt. Bowman and\\n\\nphysically reenacted key aspects of the encounter. For example, Defendant claimed that\\n\\nScott was “coming straight at him” holding the taser, with his “arm extending straight out.”\\n\\nJ.A. 1640. Defendant told the SLED investigators that he was “shuffle-stepping” to avoid\\n\\n\\n 6\\n\\fthe taser as he “pulled his gun.” Id. According to this account, Scott was “turning to his\\n\\nleft” when Defendant fired. Id. Then, “Scott ran off, stumbled into the grass, [and] fell to\\n\\nthe ground.” Id. Defendant further told the investigators that “Scott must have dropped”\\n\\nthe taser during this altercation, because he retrieved it “between the place where he had\\n\\nbeen shooting and where Scott landed.” J.A. 1641.\\n\\n During his state trial, Defendant provided a third description of his encounter with\\n\\nScott. In this retelling, Defendant claimed that, during the alleged ground struggle, he had\\n\\nattempted to put Scott’s left hand “behind his back to handcuff him.” J.A. 282. However,\\n\\nScott was in a “pushup position” and was “trying to get up” at the same time. Id. Defendant\\n\\ntestified that while this was occurring, he and Scott were “fighting” and “rolling around on\\n\\nthe ground.” J.A. 285. According to this account, Scott eventually “overpowered”\\n\\nDefendant and took his taser. J.A. 286. Defendant testified that at that point, he “instructed\\n\\nMr. Scott to turn right away and go, but he didn’t.” J.A. 288. Instead, Scott continued to\\n\\napproach Defendant, so Defendant “pulled [his] firearm” and “fired until the threat was\\n\\nstopped.” J.A. 289. Defendant’s testimony made clear that he was neither “provoked” nor\\n\\n“angry” during the shooting. J.A. 346–47. Instead, Defendant testified that he was simply\\n\\n“doing [his] job” and acting in “self-defense.” Id. at 347.\\n\\n Defendant provided his fourth description of the shooting over two days of\\n\\ntestimony at his federal pre-trial hearings. Again, Defendant added new details. For the\\n\\nfirst time, Defendant testified that Scott “punched [him] in the chest” during the ground\\n\\naltercation. J.A. 732. And for the first time, Defendant testified that Scott was “on top of\\n\\n[him] at some point.” J.A. 727. Defendant also testified—again, for the first time—that\\n\\n\\n 7\\n\\fScott “drive stunned” 2 him during the altercation. J.A. 728. When asked why he had not\\n\\npreviously provided these details, Defendant testified that the surrounding events were\\n\\n“fuzzy” and there were still “some things [he did not] recall.” J.A. 727. But “some of [his]\\n\\nmemory [had] come back since” the shooting, he testified. Id. Still, Defendant testified\\n\\nthat he could not “recall anything [that he had] told SLED Agents” during his prior\\n\\ninterview. J.A. 860 (emphasis added).\\n\\n Defendant did not testify during his sentencing hearing, but he did attempt to\\n\\nbuttress aspects of his final account of the encounter through three expert witnesses. First,\\n\\nDefendant offered Eugene Liscio, an expert forensic analyst who reconstructs crime\\n\\nscenes. Using Santana’s video, Liscio created a 3D model of the scene of the encounter in\\n\\nan effort to determine whether Defendant or Scott was holding the taser prior to the\\n\\nshooting. Based upon the final position of the taser, Liscio opined that the video was\\n\\n“inconsistent” with Defendant throwing the taser with his right arm. J.A. 1257–58.\\n\\nHowever, Liscio equivocated as to this opinion, acknowledging that there was “no part in\\n\\n[the Santana video] where you can actually see the taser being held.” J.A. 1275. Liscio\\n\\nalso testified that, due to this limitation, the court would have to “make [its] own judgment\\n\\ncall” as to what in fact occurred. J.A. 1279–80.\\n\\n\\n\\n 2\\n “Tasers generally have two modes. In dart mode, a taser shoots probes into a\\nsubject and overrides the central nervous system. Drive stun mode, on the other hand, does\\nnot cause an override of the victim’s central nervous system; that mode is used as a pain\\ncompliance tool with limited threat reduction.” Estate of Armstrong ex rel. Armstrong v.\\nVill. of Pinehurst, 810 F.3d 892, 897 n.3 (4th Cir.), cert. denied sub nom. Vill. of Pinehurst,\\nN.C. v. Estate of Armstrong, 137 S. Ct. 61, 196 L. Ed. 2d 32 (2016) (internal quotations\\nmarks and citations omitted).\\n\\n 8\\n\\f Second, Defendant offered David Hallimore, a forensic audio analyst, who applied\\n\\n“filtration[s] to [the Santana Video] to allow the speech to become more clear.” J.A. 1192,\\n\\n1216. Through these filtrations and “critical listening”—a skill Hallimore purportedly\\n\\nlearned by “train[ing his] brain effectively to better understand certain tones”—Hallimore\\n\\ntestified that he heard “fuck police” and “Let go of the taser or I’ll shoot” on the Santana\\n\\nvideo. J.A. 1204, 1216, 1218. But Hallimore also recognized this was his “interpretation”\\n\\nof the enhanced audio. J.A. 1220.\\n\\n Finally, Defendant introduced opinions and analyses rendered by Megan Fletcher,\\n\\nan agent with the SLED’s Trace Evidence Unit. Fletcher did not testify at the federal\\n\\nsentencing, but Defendant did reference her state trial testimony and report. Fletcher\\n\\nidentified polyester fibers in Defendant’s shirt that had been melted. Fletcher analyzed\\n\\nthese fibers and opined that a “taser drive-stun cannot be excluded as a possible heat source\\n\\nwhich has the potential to melt polyester fibers.” Supp. J.A. 89–90. But Fletcher averred\\n\\nthat she was “unable to definitively conclude whether a Taser did or did not cause the marks\\n\\non the uniform.” Supp. J.A. 89. Fletcher also acknowledged that she never determined—\\n\\nand therefore did not know—the melting point of the fibers in Defendant’s shirt.\\n\\n C.\\n\\n On January 16, 2018, the district court sentenced Defendant to a 240-month term of\\n\\nimprisonment. In an accompanying order explaining its sentencing decision, the court first\\n\\ndetermined that second-degree murder was the appropriate sentencing cross-reference for\\n\\nDefendant’s offense because “malice aforethought is proven by a gross deviation from the\\n\\nstandard of reasonable care, and [because] there is insufficient evidence that the defendant\\n\\n\\n 9\\n\\facted in heat of passion.” Slager, 2018 WL 445497, at *2. To support that judgment, the\\n\\ndistrict court made extensive credibility determinations and factual findings.\\n\\n To begin, the court assessed the credibility of the only two testifying eyewitnesses\\n\\nto Scott’s shooting: Santana and Defendant. Recounting at length Defendant’s various\\n\\naccounts of the encounter, the district court discredited Defendant’s testimony,\\n\\ncharacterizing it as “contradictory,” “self-serving, evolving, and internally inconsistent.”\\n\\nId. at *4–6. Furthermore, the court found that Defendant’s experts did not bolster the\\n\\ncredibility of his account because each expert admitted that his or her respective technique\\n\\nprovided no definitive answer as to the key aspects of Defendant’s final version of the\\n\\nencounter. In contrast, Santana presented a “consistent story,” which the court found\\n\\ncredible. Id. at *4 (“[A] review of the statement Santana gave to SLED, Santana’s state\\n\\ncourt testimony, and his federal court testimony reveals a consistent story that is at odds\\n\\nwith [Defendant’s] presentation of the sequence of events . . . making Santana a more\\n\\ncredible witness.”).\\n\\n Based upon these credibility determinations, the district court made the following\\n\\nfindings of fact. First, the court found that the Santana video did not provide any grounds\\n\\nto support a finding of provocation. Second, the court found that the portion of the\\n\\nencounter not covered by the video—when Defendant and Scott were on the ground—also\\n\\ndid not support a finding of provocation. In particular, the court found that Scott “yelled\\n\\n‘Fuck the police,’ [and] that Scott ran away from [Defendant] during the initial traffic stop\\n\\nand disobeyed commands to stop.” Id. at *8. But the court further found that—contrary\\n\\nto Defendant’s statements—Scott was “never on top of [Defendant].” Id. The court found\\n\\n\\n 10\\n\\fthat Scott did not wrestle the taser away and attempt to drive-stun Defendant because Scott\\n\\n“never had the taser in his hands.” Id. Rather than coming straight at Defendant with a\\n\\ntaser, Scott got “up from the ground [and] ran away from [Defendant],” the court found.\\n\\nId. Instead “of giving chase once again, [Defendant] shot at Scott eight times” and “five\\n\\nof those shots hit Scott in the back.” Id. Moreover, at “no point after [Defendant] fired the\\n\\nfirst shot—when Scott was nearly fifteen feet away—to when [Defendant] fired the eighth\\n\\nshot—when Scott was nearly forty feet away—did Scott turn around.” Id. Emphasizing\\n\\nthat “[w]ords alone will not suffice for a ‘heat of passion’ finding,” the court concluded\\n\\nthat these facts, “taken together,” “did not constitute adequate provocation to apply the\\n\\n‘heat of passion’ mitigation.” Id.\\n\\n In determining Defendant’s sentence, the district court also applied a two-level\\n\\nsentencing enhancement for obstruction of justice based upon Defendant’s false statements\\n\\nto the SLED investigators during his unsworn interview. U.S.S.G. § 3C1.1. In so doing,\\n\\nthe court recognized that Defendant was “represented by an attorney” and “was aware that\\n\\nthere was an investigation . . . underway for the shooting.” Id. at *14. The court also\\n\\nemphasized that, before making the statement, Defendant specifically inquired “about the\\n\\npresence of a video that captured the shooting.” Id. at *17. Believing that no video existed,\\n\\nDefendant “used the SLED interview to advance his false narrative of being forced to fire\\n\\nwhen Scott was coming toward him with a taser,” the court explained. Id.\\n\\n In deciding to apply the obstruction enhancement, the district court acknowledged\\n\\nthat SLED had already obtained Santana’s video when they interviewed Defendant. Still,\\n\\nwithout the video, some of Defendant’s false statements would have significantly\\n\\n\\n 11\\n\\fobstructed the investigation, the court determined. Specifically, if it were “not for the\\n\\nSantana’s video,” Defendant’s statement that “Scott was coming toward him with a taser\\n\\nat the time he fired his first shot” “would certainly have hindered the investigation.” Id.\\n\\nThis was especially true because Defendant’s “status as a [law enforcement] officer would\\n\\nlikely have meant that his rendition of the events would not have been immediately\\n\\nquestioned.” Id.\\n\\n Defendant timely appealed his sentence.\\n\\n II.\\n\\n A.\\n\\n When, as here, a defendant is sentenced for deprivation of civil rights under color\\n\\nof law, the Sentencing Guidelines require the court to cross-reference the “offense\\n\\nguideline applicable to any underlying offense.” U.S.S.G. § 2H1.1(a)(1).\\n\\n Defendant first argues that the district court erred by determining that second-degree\\n\\nmurder was the proper cross-reference under Section 2H1.1. Specifically, Defendant\\n\\nclaims that when he shot Scott, he was provoked and thus acting without malice.\\n\\nConsequently, Defendant argues that the proper cross-reference was voluntary\\n\\nmanslaughter, not second-degree murder.\\n\\n At sentencing, the government “has the burden to prove a cross-referenced offense\\n\\nby a preponderance of the evidence[.]” United States v. Davis, 679 F.3d 177, 182 (4th Cir.\\n\\n2012). In reviewing “whether a district court properly applied . . . its application of a\\n\\ncross-reference, we review the district court’s legal conclusions de novo and its factual\\n\\nfindings for clear error.” United States v. Ashford, 718 F.3d 377, 380 (4th Cir. 2013)\\n\\n\\n 12\\n\\f(quoting United States v. Layton, 564 F.3d 330, 334 (4th Cir. 2009)) (internal quotation\\n\\nmarks omitted). For the reasons that follow, we hold that the district court did not clearly\\n\\nerr in making its factual findings. We further conclude that the court correctly determined,\\n\\nbased on those findings, that second-degree murder was the proper cross-reference.\\n\\n i.\\n\\n “When sentencing courts engage in fact finding, preponderance of the evidence is\\n\\nthe appropriate standard of proof.” United States v. Span, 789 F.3d 320, 334 (4th Cir.\\n\\n2015) (citations and alterations omitted). We “will not reverse a lower court’s findings of\\n\\nfact simply because we would have decided the case differently.” Id. (quoting Easley v.\\n\\nCromartie, 532 U.S. 234, 242 (2001)). Instead, clear error exists only when “the reviewing\\n\\ncourt on the entire evidence is left with the definite and firm conviction that a mistake has\\n\\nbeen committed.” Id. (quoting Easley, 532 U.S. at 242).\\n\\n When a district court renders factual findings “based on determinations regarding\\n\\nthe credibility of witnesses, we give even greater deference to the trial court’s findings.”\\n\\nUnited States v. Hall, 664 F.3d 456, 462 (4th Cir. 2012) (quoting Anderson v. Bessemer\\n\\nCity, 470 U.S. 564, 575 (1985)) (internal quotation marks omitted); see also Teleguz v.\\n\\nZook, 806 F.3d 803, 812 (4th Cir. 2015) (“[C]redibility determinations are deserving of the\\n\\nhighest degree of appellate deference.”), cert. denied, 137 S. Ct. 95 (2016). Indeed, if a\\n\\ndistrict court’s finding “is based on his decision to credit the testimony of one of two or\\n\\nmore witnesses, each of whom has told a coherent and facially plausible story that is not\\n\\ncontradicted by extrinsic evidence, that finding, if not internally inconsistent, can virtually\\n\\nnever be clear error.” Anderson, 470 U.S. at 575 (1985).\\n\\n\\n 13\\n\\f Because Santana’s video does not capture the entirety of the disputed period, the\\n\\ncourt based many of its factual findings on its assessment of the credibility of the two\\n\\ntestifying eyewitnesses to the encounter: Defendant and Santana. Examining at length each\\n\\nof Defendant’s four accounts of the encounter, the court discredited Defendant’s testimony\\n\\nas “contradictory,” “self-serving, evolving, and internally inconsistent.” Slager, 2018 WL\\n\\n445497, at *4–6. The record amply supports that credibility determination.\\n\\n Each time Defendant provided a new statement about the shooting, he put forward\\n\\nnew details materially bearing on his application of force. For example, in contrast to his\\n\\ntestimony in these proceedings, Defendant never told Lt. Bowman or the SLED\\n\\ninvestigators that Scott was “on top of [him] at some point” during the disputed period.\\n\\nJ.A. 727–28. Also, in contrast to his testimony in these proceedings, Defendant did not tell\\n\\nLt. Bowman or the SLED investigators that he was “drive stunned” by Scott. Id. And in\\n\\ncontrast to his testimony in these proceedings, Defendant did not tell either Lt. Bowman or\\n\\nthe SLED investigators that Scott “punched [him] in the chest.” J.A. 732. When Defendant\\n\\nwas asked why he previously failed to provide these details, he testified that his memory\\n\\nwas “fuzzy” and he still didn’t “recall” “some things.” Id. Defendant’s “evolving” account\\n\\nof the encounter provided the district court with ample factual basis to discredit\\n\\nDefendant’s testimony. See Munyakazi v. Lynch, 829 F.3d 291, 298 (4th Cir. 2016)\\n\\n(“Omissions, inconsistent statements, contradictory evidence, and inherently improbable\\n\\ntestimony are appropriate bases for making an adverse credibility determination.” (internal\\n\\nquotation marks and alterations omitted)).\\n\\n\\n\\n\\n 14\\n\\f That some of Defendant’s assertions are flatly contradicted by Santana’s video and\\n\\nby Defendant’s own plea agreement further supports the district court’s finding that\\n\\nDefendant’s account was not credible. Id. Santana’s video, for example, shows that when\\n\\nDefendant fired eight shots from his firearm, Scott was “running away, not pointing a Taser\\n\\nat [Defendant] or advancing toward him,” contrary to Defendant’s statement to Lt.\\n\\nBowman and the SLED investigators. Slager, 2018 WL 445497, at *6. And the video\\n\\nreveals that Defendant picked up his taser approximately ten feet behind where Defendant\\n\\nstood when he shot Scott—not between Scott and Defendant, as Defendant initially\\n\\nasserted. These contradictions further demonstrate that the district court did not clearly err\\n\\nin discerning Defendant’s testimony. See United States v. Savage, 885 F.3d 212, 220 (4th\\n\\nCir. 2018) (holding that it is for the factfinder to hear a witness’s “testimony, along with\\n\\nany alleged inconsistencies, and decide[] [whether] testimony [is] credible”).\\n\\n Santana, on the other hand, provided a consistent story, including as to the facts the\\n\\ndistrict court found significant in its sentencing opinion. Each time he was questioned,\\n\\nSantana testified that Scott never was on top of Defendant, always was facing down, never\\n\\ngained control of Defendant’s taser, and never charged at or tried to fight with Defendant.\\n\\nAnd each time he was questioned, Santana testified that once Scott was able to stand up,\\n\\nhe began to flee—that Scott never tried to stay and fight Defendant, much less charge at\\n\\nhim, as Defendant claimed.\\n\\n Additionally, unlike several of Defendant’s retellings of the encounter, Santana’s\\n\\nversion of events is—and always has been—consistent with the recorded video. On these\\n\\nfacts, the district court did not clearly err in crediting Santana’s consistent testimony. See\\n\\n\\n 15\\n\\fUnited States v. Stark, 8 F.3d 822 (4th Cir. 1993) (unpublished opinion) (District court did\\n\\nnot clearly err in finding one witness’s “consistent testimony, substantiated in part by\\n\\n[documentary evidence], was more credible than [another witness’s] testimony, which the\\n\\ncourt found inconsistent and incredible in many respects.”). 3\\n\\n Defendant nevertheless claims that the district court reversibly erred in declining to\\n\\nfind that the testimony of Defendant’s expert witnesses rendered Defendant’s account of\\n\\nthe encounter credible. “As with lay witnesses, evaluating the credibility of experts and\\n\\nthe value of their opinions is also a function best committed to the district courts, and one\\n\\nto which appellate courts should defer[.]” Hall, 664 F.3d at 462 (citations and alterations\\n\\nomitted).\\n\\n Here, the court did not reversibly err by declining to give weight to the testimony\\n\\nand evidence presented by Defendant’s experts. The district court emphasized—as the\\n\\nrecord demonstrates—that each expert admitted their respective techniques could not\\n\\nprovide the court with definitive conclusions as to what happened during the disputed\\n\\nperiod. Instead, the experts couched their opinions with statements of equivocation and\\n\\ninvited the court to make its own judgment as to what, in fact, occurred during the disputed\\n\\nperiod. See, e.g., Supp. J.A. 89–90 (Fletcher opining that a taser “drive-stun cannot be\\n\\nexcluded as a possible heat source which has the potential to melt polyester fibers”); J.A.\\n\\n\\n\\n 3\\n Defendant complains that the district court failed to point out in its sentencing\\norder that Santana viewed the shooting “from a distance of 136–180 feet.” Appellant’s Br.\\nat 16. Although we “do not dispute that there must be sufficient explanation for a sentence\\nto be procedurally reasonable,” the court’s “thorough explanation” here was more than\\nsufficient to meet this burden. United States v. Helton, 782 F.3d 148, 154 (4th Cir. 2015).\\n\\n 16\\n\\f1279–80 (Liscio testifying that the district court could not rely on his recreation of the\\n\\nscene, but instead “ha[d] to make your own judgment call,” to determine whether Scott\\n\\never held the taser); J.A. 1220 (Hallimore offering the court an “interpretation” of the\\n\\nenhanced audio). The district court thus did not reversibly err in choosing not to give\\n\\nweight to these equivocal opinions. 4\\n\\n In sum, the district court did not clearly err by crediting Santana’s version of the\\n\\nencounter—including that Scott was “never on top of [Defendant],” that Scott never had\\n\\nthe taser in his hands, that Scott immediately began to run away when he stood up, and that\\n\\nhe was running away when Defendant shot him, Slager, 2018 WL 445497, at *8—as\\n\\nopposed to Defendant’s (most recent) account. Notably, several of these key factual\\n\\ndeterminations are consistent with the facts Defendant admitted to in his plea agreement.\\n\\nSee, e.g., id. at *2 (Defendant “fired multiple shots at Scott while Scott was running away\\n\\nfrom him.”); id. (“[D]efendant’s Taser dropped to the ground behind [D]efendant.”).\\n\\n\\n\\n\\n 4\\n Defendant also relies upon the Federal Rules of Evidence and Daubert v. Merrell\\nDow Pharmaceuticals, Inc., 509 U.S. 579 (1993), to argue that the court erred by failing to\\ngive weight to Fletcher’s opinions. But the Rules of Evidence do not apply to sentencing.\\nFed. R. Evid. 1101(d)(3). And this Court has not applied Daubert to sentencing hearings.\\nUnited States v. Barnette, 211 F.3d 803, 815 (4th Cir. 2000); see also United States v.\\nFields, 483 F.3d 313, 342 (5th Cir. 2007) (“No Circuit that we are aware of has applied\\nDaubert to sentencing. . . . Since Daubert’s holding was based on the Federal Rules of\\nEvidence, it is not directly applicable.”). Applying Daubert would run contrary to the\\nsentencing court’s “wide discretion” to determine the “sources and types of evidence,”\\nwhich are relevant for defendants’ individualized sentencing. Pepper v. United States, 562\\nU.S. 476, 488 (2011). We thus reject Defendant’s Daubert argument.\\n\\n 17\\n\\f ii.\\n\\n Defendant next contends that the district court’s factual findings do not support a\\n\\nfinding of malice aforethought. Consequently, Defendant maintains that the court erred by\\n\\ndetermining the proper cross-reference was voluntary manslaughter, not second-degree\\n\\nmurder. Again, we disagree.\\n\\n Murder is “the unlawful killing of a human being with malice aforethought,” 18\\n\\nU.S.C. § 1111, whereas voluntary “manslaughter is the unlawful killing of a human being\\n\\nwithout malice . . . [u]pon a sudden quarrel or heat of passion,” 18 U.S.C. § 1112(a). In\\n\\nother words, malice aforethought “is the distinguishing characteristic which, when present,\\n\\nmakes a homicide murder rather than manslaughter.” United States v. Fleming, 739 F.2d\\n\\n945, 947 (4th Cir. 1984).\\n\\n “Malice aforethought may be established by evidence of conduct which is reckless\\n\\nand wanton and a gross deviation from a reasonable standard of care, of such a nature that\\n\\na [factfinder] is warranted in inferring that [the] defendant was aware of a serious risk of\\n\\ndeath or serious bodily harm.” Ashford, 718 F.3d at 384 (citations and alterations omitted).\\n\\nMalice does not “require proof of an intent to kill or injure.” Fleming, 739 F.2d at 947\\n\\n(citations omitted). Malice exists when the evidence demonstrates that the defendant acted\\n\\n“with a heart that was without regard for the life and safety of others.” Id. at 948 (citations\\n\\nomitted). A district court may infer malice when a defendant uses a weapon “in such a\\n\\nmanner as may be expected naturally and probably to cause death.” United States v.\\n\\nCelestine, 510 F.2d 457, 459 (9th Cir. 1975); accord United States v. Wright, 594 F.3d 259,\\n\\n268 (4th Cir. 2010) (finding malice when Defendant “engaged in a ‘reckless firing of the\\n\\n\\n 18\\n\\ffirearm, a random firing with the intent to hurt someone’” (emphasis in original)); Ashford,\\n\\n718 F.3d at 384 (finding malice when Defendant “drew his firearm and pursued the fleeing”\\n\\nvictim).\\n\\n As Defendant sought to do here, a defendant may negate a finding of malice by\\n\\ndemonstrating that an intentional killing occurred “upon a sudden quarrel or heat of\\n\\npassion.” 18 U.S.C. § 1112(a); United States v. Velazquez, 246 F.3d 204, 212 (2d Cir.\\n\\n2001); United States v. Browner, 889 F.2d 549, 552 (5th Cir. 1989); United States v.\\n\\nRoston, 986 F.2d 1287, 1291 (9th Cir. 1993); United States v. Scafe, 822 F.2d 928, 932\\n\\n(10th Cir. 1987). Federal courts apply the common-law meaning of “sudden quarrel or\\n\\nheat of passion.” See, e.g., United States v. Martinez, 988 F.2d 685, 694 (7th Cir. 1993).\\n\\nUnder the common law, a defendant’s “heat of passion” must arise from “adequate\\n\\nprovocation.” See id.; Roston, 986 F.2d at 1291; United States v. Collins, 690 F.2d 431,\\n\\n437 (5th Cir. 1982); United States v. Medina, 755 F.2d 1269, 1272 (7th Cir. 1985); United\\n\\nStates v. Paul, 37 F.3d 496, 498 (9th Cir. 1994). Provocation is adequate when it “would\\n\\narouse a reasonable and ordinary person to kill someone.” United States v. Wagner, 834\\n\\nF.2d 1474, 1487 (9th Cir. 1987); see Velazquez, 246 F.3d at 213. When a law enforcement\\n\\nofficer, like Defendant, seeks to rely on a sudden quarrel or heat of passion defense, a court\\n\\nmust assess the adequacy of the provocation “by the standards of a reasonable officer.”\\n\\nSee Velazquez, 246 F.3d at 213 (citing United States v. Cobb, 905 F.2d 784, 789 (4th Cir.\\n\\n1999)).\\n\\n “[M]ere words” generally provide inadequate provocation to negate a finding of\\n\\nmalice. See Allen v. United States, 164 U.S. 492, 497 (1896); Velazquez, 246 F.3d at 213;\\n\\n\\n 19\\n\\fUnited States v. McRae, 593 F.2d 700, 705 (5th Cir. 1979); see also 3 Wayne R. LaFave\\n\\n& Austin W. Scott, Jr., Substantive Criminal Law § 15.2(b)(6) (3d ed. 2018) (detailing\\n\\nextraordinary, but inapposite exceptions); Cobb, 905 F.2d at 789 (“mere words” cannot\\n\\n“justify the use of physical force by a police officer”). By contrast, “[m]utual combat” can\\n\\nconstitute adequate provocation under some circumstances. See Martinez, 988 F.2d at 696;\\n\\nUnited States v. Hardin, 443 F.2d 735, 738–39 (D.C. Cir. 1970); 3 LaFave at § 15.2(b)(2).\\n\\nBut when a victim is fleeing from combat and the defendant is neither angry nor in danger,\\n\\nmutual combat does not support a finding that a defendant acted in a heat of passion. See\\n\\nAshford, 718 F.3d at 380 (“[T]he ‘heat of passion’ mitigator plainly does not apply to an\\n\\naggressor who is ‘not angry,’ and has multiple opportunities to walk away from a dispute\\n\\nthat he incited.”).\\n\\n In this case, the district court did not reversibly err in determining that the facts\\n\\nsupported a finding of malice. In his plea agreement, Defendant admitted that he acted\\n\\n“voluntarily and intentionally with specific intent to do something the law forbids.” Slager,\\n\\n2018 WL 445497, at *2. Additionally, Defendant admitted that he “fired eight shots at\\n\\nScott, and each of those eight shots were fired while Scott was unarmed and running away.”\\n\\nId. Defendant’s voluntary, intentional, and repeated discharge of his firearm at Scott as he\\n\\nattempted to run away “may be expected naturally and probably to cause death.” Celestine,\\n\\n510 F.2d at 459; Cf. Wright, 594 F.3d at 268 (It is “perfectly foreseeable that someone\\n\\nw[ill] be killed” when firing a gun “with intent to hurt someone.”).\\n\\n Nor did the district court err in determining that Defendant’s malice was not negated\\n\\nby “sudden quarrel or heat of passion.” 18 U.S.C. § 1112(a). Even though Scott yelled\\n\\n\\n 20\\n\\f“Fuck the police” prior to the shooting, the court rightly found that these words were\\n\\ninsufficient to provoke a reasonable officer—or any reasonable person—to kill. Slager,\\n\\n2018 WL 445497, at *8; see Velazquez, 246 F.3d at 207 (holding that prisoner yelling\\n\\n“Fuck you, you are not going to tell me what to do” was insufficient to provoke guards to\\n\\nkill in the “heat of passion”).\\n\\n Additionally, Defendant’s alleged mutual combat with Scott did not provide\\n\\nDefendant with adequate provocation because Scott was running away when Defendant\\n\\nshot him. See Ashford, 718 F.3d at 380. Perhaps most importantly, even though Defendant\\n\\nnow claims he was provoked, Defendant testified at his state proceedings that he was\\n\\nneither “provoked” nor “angry” during his altercation but was merely acting in “self-\\n\\ndefense.” J.A. 346–47. 5 Defendant cannot negate his malice through “sudden quarrel or\\n\\nheat of passion” when he previously testified he was neither “provoked” nor “angry.”\\n\\nAshford, 718 F.3d at 380.\\n\\n In conclusion, the district court did not reversibly err by inferring Defendant’s\\n\\nmalice from the facts it found credible. Moreover, the court did not reversibly err by\\n\\ndetermining that Defendant’s malice was not negated by “sudden quarrel or heat of\\n\\npassion.” Accordingly, the court properly cross-referenced second-degree murder.\\n\\n\\n\\n\\n 5\\n Because Defendant admitted in his plea agreement that he acted “willfully,” the\\ndistrict court found that Defendant was foreclosed from arguing self-defense during his\\nfederal sentencing hearing. Slager, 2018 WL 445497, at *2.\\n\\n 21\\n\\f B.\\n\\n Next, Defendant argues that the district court erred in applying a two-level sentence\\n\\nenhancement for obstructing justice based on Defendant’s false statements to SLED.\\n\\nDefendant raises this issue for the first time on appeal. “Because this issue was not\\n\\nadvanced in the district court, we review the district court decision for plain error.” United\\n\\nStates v. Hughes, 401 F.3d 540, 547 (4th Cir. 2005); see United States v. Brack, 651 F.3d\\n\\n388, 392 (4th Cir. 2011). For an error to be “plain,” it must be “obvious or clear under\\n\\ncurrent law.” Brack, 651 F.3d at 392. Under this circumscribed standard of review, we do\\n\\nnot find that the district court plainly erred by applying the obstruction sentencing\\n\\nenhancement.\\n\\n A sentencing court may apply the obstruction enhancement when a defendant: (1)\\n\\n“willfully obstructed or impeded, or attempted to obstruct or impede, the administration of\\n\\njustice with respect to the investigation . . . of the instant offense of conviction,” and (2)\\n\\n“the obstructive conduct related to the defendant’s offense of conviction and any relevant\\n\\nconduct.” U.S.S.G. § 3C1.1 (emphasis added). Defendant argues that the district court\\n\\nplainly erred in applying this enhancement because Defendant’s false statements to the\\n\\nSLED investigators “were not made under oath” and the SLED investigators already had\\n\\nSantana’s video when they interviewed Defendant, meaning that Defendant’s false\\n\\nstatements “did not significantly impede the official investigation.” Appellant’s Br. at 45.\\n\\n In support of his argument, Defendant emphasizes that the comments to the\\n\\nobstruction guideline state “[o]rdinarily . . . making false statements, not under oath to law\\n\\nenforcement officers”—as was the case here—does not warrant application of the\\n\\n\\n 22\\n\\fenhancement. U.S.S.G. § 3C1.1 cmt. n.5 (emphases added). But the comments further\\n\\nstate that “providing a materially false statement to a law enforcement officer that\\n\\nsignificantly obstructed or impeded the official investigation” does warrant application of\\n\\nthe enhancement, regardless of whether the materially false statement was made under\\n\\noath. Id. cmt. n.4(G) (emphasis added). And the express text of the obstruction guideline\\n\\ncovers “attempted” obstruction of justice, indicating that application of the guideline is\\n\\nappropriate, at least in some circumstances, even when a defendant’s attempted obstruction\\n\\ndid not in fact result in the obstruction of an investigation. Id.\\n\\n Accordingly, Section 3C1.1 and its comments do not clearly answer the relevant\\n\\nquestion: whether an attempt to significantly obstruct an investigation through unsworn\\n\\nstatements warrants application of the enhancement. Nor has this Court’s case law\\n\\nprovided an “obvious” or “clear” answer to that question. Hughes, 401 F.3d at 547.\\n\\nNotably, as to that question, our sister circuits have reached divergent answers. Compare\\n\\nUnited States v. Girod, 646 F.3d 304, 318 (5th Cir. 2011) (enhancement can be appropriate\\n\\nbased upon attempted, but significant obstruction); United States v. Wolverine, 584 F.\\n\\nApp’x 646, 649 (9th Cir. 2014) (same); with United States v. Adejumo, 772 F.3d 513, 529\\n\\n(8th Cir. 2014) (enhancement is inappropriate based upon attempted, but significant\\n\\nobstruction); United States v. Griffin, 310 F.3d 1017, 1022–23 (7th Cir. 2002) (same). In\\n\\nsuch circumstances, Defendant cannot meet his burden to show that the district court\\n\\nplainly erred by applying a two-level sentencing enhancement for attempted, yet\\n\\n\\n\\n\\n 23\\n\\fsignificant, obstruction of justice through unsworn statements to law enforcement\\n\\ninvestigators. 6\\n\\n III.\\n\\n In sum, the district court committed no reversible error in sentencing Defendant.\\n\\nFirst, the district court did not clearly err in crediting Santana’s description of the encounter\\n\\nand discrediting Defendant’s description. Second, the court properly inferred, from these\\n\\nfacts, malice as required for a second-degree murder cross-reference. Finally, the district\\n\\ncourt did not plainly err in applying an obstruction of justice enhancement. Accordingly,\\n\\nthe district court’s sentence is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 6\\n Defendant also objects to his federal prosecution on double jeopardy grounds.\\nAcknowledging that current Supreme Court case law forecloses this argument, Defendant\\npreserves it pending a possible change in the law.\\n\\n 24\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":87,"cells":{"id":{"kind":"number","value":4579691,"string":"4,579,691"},"name":{"kind":"string","value":"UNITED STATES EX REL., Jon H. OBERG, Plaintiff-Appellant, v. PENNSYLVANIA HIGHER EDUCATION ASSISTANCE AGENCY, Defendant-Appellee, and Nelnet, Inc.; Kentucky Higher Education Student Loan Corp. ; SLM Corporation; Panhandle Plains Higher Education Authority ; Brazos Group; Arkansas Student Loan Authority; Education Loans Inc/SD; Southwest Student Services Corporation; Brazos Higher Education Service Corporation; Brazos Higher Education Authority, Inc.; Nelnet Education Loan Funding, Inc.; Panhandle-Plains Management and Servicing Corporation; Student Loan Finance Corporation; Education Loans Inc. ; Vermont Student Assistance Corporation, Defendants."},"name_abbreviation":{"kind":"string","value":"United States Ex Rel. Oberg v. Pa. Higher Educ. Assistance Agency"},"decision_date":{"kind":"string","value":"2019-01-08"},"docket_number":{"kind":"string","value":"18-1028"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Motz, Keenan, Harris\", \"parties\": \"\", \"opinions\": [{\"author\": \"DIANA GRIBBON MOTZ, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1028\\n\\n\\nUNITED STATES EX REL., JON H. OBERG,\\n\\n Plaintiff – Appellant,\\n\\n v.\\n\\nPENNSYLVANIA HIGHER EDUCATION ASSISTANCE AGENCY,\\n\\n Defendant – Appellee,\\n\\n and\\n\\nNELNET, INC.; KENTUCKY HIGHER EDUCATION STUDENT LOAN\\nCORP.; SLM CORPORATION; PANHANDLE PLAINS HIGHER EDUCATION\\nAUTHORITY; BRAZOS GROUP; ARKANSAS STUDENT LOAN\\nAUTHORITY; EDUCATION LOANS INC/SD; SOUTHWEST STUDENT\\nSERVICES CORPORATION; BRAZOS HIGHER EDUCATION SERVICE\\nCORPORATION; BRAZOS HIGHER EDUCATION AUTHORITY, INC.;\\nNELNET EDUCATION LOAN FUNDING, INC.; PANHANDLE-PLAINS\\nMANAGEMENT AND SERVICING CORPORATION; STUDENT LOAN\\nFINANCE CORPORATION; EDUCATION LOANS INC.; VERMONT\\nSTUDENT ASSISTANCE CORPORATION,\\n\\n Defendants.\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. Claude M. Hilton, Senior District Judge. (1:07-cv-00960-CMH-JFA)\\n\\n\\nArgued: October 31, 2018 Decided: January 8, 2019\\n\\n\\nBefore MOTZ, KEENAN, and HARRIS, Circuit Judges.\\n\\fAffirmed by published opinion. Judge Motz wrote the opinion, in which Judge Keenan\\nand Judge Harris joined.\\n\\n\\nARGUED: Eric Kenneth Bachman, ZUCKERMAN LAW, Chevy Chase, Maryland, for\\nAppellant. George W. Hicks, Jr., KIRKLAND & ELLIS LLP, Washington, D.C., for\\nAppellee. ON BRIEF: Jason M. Zuckerman, Washington, D.C., Dallas I. Hammer,\\nZUCKERMAN LAW, Tysons Corner, Virginia, for Appellant. Matthew T. Regan,\\nChicago, Illinois, Michael A. Glick, Tracie L. Bryant, Michael D. Lieberman,\\nKIRKLAND & ELLIS LLP, Washington, D.C.; Daniel B. Huyett, STEVENS & LEE,\\nP.C., Reading, Pennsylvania, for Appellee.\\n\\n\\n\\n\\n 2\\n\\fDIANA GRIBBON MOTZ, Circuit Judge:\\n\\n This case returns to us again, this time on appeal from an adverse jury verdict.\\n\\nDr. Jon Oberg, as relator for the United States, brought this qui tam action against four\\n\\nstudent loan corporations, including the Pennsylvania Higher Education Assistance\\n\\nAgency (“PHEAA”). He alleged that the corporations had defrauded the Department of\\n\\nEducation and so violated the False Claims Act (“FCA”), 31 U.S.C. § 3729 et seq.\\n\\n Over the course of several appeals, we affirmed the dismissal of one defendant and\\n\\ntwo of the other defendants settled. See United States ex rel. Oberg v. Pa. Higher Educ.\\n\\nAssistance Agency, 804 F.3d 646, 650 (4th Cir. 2015); United States ex rel. Oberg v. Pa.\\n\\nHigher Educ. Assistance Agency, 745 F.3d 131, 145 (4th Cir. 2014); United States ex rel.\\n\\nOberg v. Ky. Higher Educ. Student Loan Corp., 681 F.3d 575, 579–81 (4th Cir. 2012).\\n\\nThe case proceeded to trial only against PHEAA. Oberg now appeals the jury’s\\n\\nunanimous verdict in favor of PHEAA. For the reasons that follow, we affirm.\\n\\n\\n\\n I.\\n\\n Oberg’s claim concerns a Department of Education subsidy program meant to\\n\\nencourage the issuance of low-interest federal student loans. It did so by offering Special\\n\\nAllowance Payments (“SAPs”) to certain qualifying lenders. 20 U.S.C. § 1087-1. For\\n\\none particular category of loans — those financed through tax-exempt bonds — Congress\\n\\nguaranteed lenders a 9.5 percent return. Id. § 1087-1(b)(2)(B). In the low-interest\\n\\nenvironment of the mid-2000s, this guaranteed rate made tax-exempt bonds a particularly\\n\\nattractive investment vehicle.\\n\\n 3\\n\\f To take advantage of the favorable return offered by the program, Oberg claims\\n\\nthat between 2002 and 2006, PHEAA submitted false claims for SAP subsidies by\\n\\nimproperly transferring student loans from non-tax-exempt bonds into tax-exempt bonds.\\n\\nIn doing so, PHEAA converted lower-interest floating-rate loans into loans that\\n\\nguaranteed a 9.5 percent return. This translated into millions of dollars in additional\\n\\nrevenue for PHEAA.\\n\\n During a five-day trial, the court admitted more than 100 exhibits and the jury\\n\\nheard testimony from more than a dozen witnesses. After deliberating for less than three\\n\\nhours, the jury returned a unanimous verdict in favor of PHEAA.\\n\\n Oberg timely noted this appeal, asking that we vacate the judgment and remand\\n\\nfor a new trial. He maintains that the district court substantially impeded his ability to\\n\\nprove his claims by improperly excluding critical evidence and rejecting Oberg’s\\n\\nproposed jury instructions.\\n\\n\\n\\n II.\\n\\n Oberg first contends that the district court erred by excluding certain evidence at\\n\\ntrial. We review a district court’s evidentiary rulings for abuse of discretion. SAS Inst.,\\n\\nInc. v. World Programming Ltd., 874 F.3d 370, 384 (4th Cir. 2017). “A district court\\n\\nabuses its discretion if it relies on an error of law or a clearly erroneous factual finding.”\\n\\nEEOC v. Freeman, 778 F.3d 463, 466 (4th Cir. 2015).\\n\\n At trial, Oberg sought admission of a 2004–2007 Performance Audit of PHEAA\\n\\nperformed by the Pennsylvania Auditor General. The Audit “evaluate[d] PHEAA’s\\n\\n 4\\n\\fperformance in improving access to higher education for Pennsylvania residents” and\\n\\nconcluded that PHEAA had largely “failed its mission.” The Audit found that PHEAA\\n\\npaid excessive salaries and bonuses to its executives and managers. The Audit also\\n\\ncatalogued and strongly criticized PHEAA’s lavish spending on employee benefits and\\n\\n“extravagant” expenditures on other unnecessary expenses. It “concluded that PHEAA\\n\\nwas governed and managed within a culture that sometimes allowed self-reward to\\n\\nsupersede fiscal prudence.” The district court excluded the Audit as irrelevant under\\n\\nFederal Rule of Evidence 401.\\n\\n Oberg contends that the Audit was relevant for several reasons. First, he argues\\n\\nthat the Audit’s critical findings tended to establish scienter — i.e., that desire for\\n\\npersonal gain motivated PHEAA officers to submit false claims. This argument fails\\n\\nbecause unlike the securities fraud cases on which Oberg relies, 1 FCA claims require a\\n\\nrelator to show only that the defendant had knowledge of the illegality of its actions,\\n\\nrather than specific intent to defraud. See, e.g., United States ex rel. Harrison v.\\n\\nWestinghouse Savannah River Co., 352 F.3d 908, 921 (4th Cir. 2003) (“In establishing\\n\\nliability under the FCA, a plaintiff need not prove the defendant had a financial motive to\\n\\nmake a false statement relating to a claim seeking government funds.”); United States ex\\n\\nrel. K & R Ltd. P’ship v. Mass. Hous. Fin. Agency, 530 F.3d 980, 984 (D.C. Cir. 2008)\\n\\n(finding evidence of defendant’s “motive to submit false claims — the need to bail itself\\n\\n 1\\n Cases requiring proof of specific intent often turn on evidence of motive to prove\\nscienter. See, e.g., Tellabs, Inc. v. Makor Issues & Rights, Ltd., 551 U.S. 308, 319, 325\\n(2007) (finding motive “a relevant consideration” in measuring a defendant’s intent to\\n“deceive, manipulate, or defraud” (internal quotation marks omitted)).\\n\\n 5\\n\\fout of financial trouble — could not . . . support a finding of knowledge, be it actual,\\n\\ndeliberate ignorance, or reckless disregard”). As the district court correctly explained:\\n\\n“It doesn’t really make any difference whether they were operating well or not well or\\n\\nwhatever. The only issue in this case is: Did they commit fraud and file a false claim?”\\n\\n Oberg next maintains that the Audit would have allowed him to rebut PHEAA’s\\n\\nown improper argument that its management acted with the “benevolent motive” to\\n\\nbenefit borrowers in carrying out its scheme. Oberg lodged little objection to this\\n\\nevidence at trial. Indeed, Oberg himself elicited most of the “benevolent motive”\\n\\ntestimony through his questions to PHEAA’s management. In any event, whether\\n\\nPHEAA’s management had benevolent motive was a collateral issue of limited relevance,\\n\\nmaking any error harmless. See Smith v. Balt. City Police Dep’t, 840 F.3d 193, 200–01\\n\\n(4th Cir. 2016).\\n\\n Finally, Oberg contends that the Audit would have helped him attack the\\n\\ncredibility of PHEAA’s executives. He argues that because witness credibility is “always\\n\\nat issue,” any “evidence concerning a witness’s credibility is always relevant.” United\\n\\nStates v. Green, 617 F.3d 233, 251 (3d Cir. 2010). This argument also fails, for Oberg\\n\\nquestioned PHEAA’s executives on the company’s compensation practices and elicited\\n\\nmuch of the same information contained in the Audit. Moreover, because nothing in the\\n\\nAudit contradicted the trial testimony of PHEAA executives, its admission would hardly\\n\\nhave aided Oberg in impeaching the executives’ credibility.\\n\\n\\n\\n\\n 6\\n\\f In sum, the district court did not abuse its discretion in excluding the Audit as\\n\\nirrelevant. 2\\n\\n\\n\\n III.\\n\\n Oberg’s remaining claims center on the district court’s refusal to give several of\\n\\nhis proposed jury instructions.\\n\\n A.\\n\\n Before we consider the merit of his claims, we must first determine our standard\\n\\nof review.\\n\\n PHEAA contends that because Oberg did not object to the jury instructions before\\n\\nthe district court, he has failed to preserve his challenge to them and so we can review\\n\\nonly for plain error. Oberg counters that the district court rejected his properly requested\\n\\ninstructions in a “definitive ruling on the record,” and so we must instead review for\\n\\nabuse of discretion. Fed. R. Civ. P. 51(d)(1)(B); see also BMG Rights Mgmt. (US) LLC\\n\\nv. Cox Commc’ns, Inc., 881 F.3d 293, 305 (4th Cir. 2018).\\n\\n To resolve this question, we turn to the language of Federal Rule of Civil\\n\\nProcedure 51(d)(1)(B), which provides:\\n\\n A party may assign as error . . . a failure to give an instruction, if that party\\n properly requested it and — unless the court rejected the request in a\\n definitive ruling on the record — also properly objected.\\n\\n\\n 2\\n The parties also quarrel over whether the Audit was more prejudicial than\\nprobative under Federal Rule of Evidence 403. Because we hold that the district court\\ndid not err in excluding the Audit on relevance grounds, we need not address this issue.\\n\\n 7\\n\\fFed. R. Civ. P. 51(d)(1) (emphasis added).\\n\\n This provision was added to Rule 51 in 2003. See Fed. R. Civ. P. 51 advisory\\n\\ncommittee’s note to 2003 amendment (hereinafter, 2003 Advisory Committee Note).\\n\\nThe Advisory Committee explained that the change was motivated by concern over the\\n\\nmajority view “that a proper request for a jury instruction [was] not alone enough to\\n\\npreserve the right to appeal failure to give [an] instruction.” Id. The Committee\\n\\nconcluded that this rule was “appropriate when the court [had not] sufficiently focused on\\n\\nthe request” or “believe[d] that the request ha[d] been granted in substance although in\\n\\ndifferent words.” Id. But in other circumstances, the doctrine created “a trap for the\\n\\nunwary who fail[ed] to add an objection after the court . . . made it clear that the request\\n\\n[had] been considered and rejected on the merits.” Id. To correct this, the drafters added\\n\\nthe ruling-on-the-record language to “establish[] authority to review the failure to grant a\\n\\ntimely request, despite a failure to add an objection, when the court has made a definitive\\n\\nruling on the record rejecting the request.” Id.\\n\\n Notwithstanding the 2003 Amendment, some courts have seemed to continue to\\n\\nfollow a more stringent preservation rule than Rule 51(d)(1)(B) now appears to\\n\\ncommand. See EEOC v. New Breed Logistics, 783 F.3d 1057, 1075 (6th Cir. 2015); C.B.\\n\\nv. City of Sonora, 769 F.3d 1005, 1032 (9th Cir. 2014); Consumer Prod. Research &\\n\\nDesign, Inc. v. Jensen, 572 F.3d 436, 439 (7th Cir. 2009); Colon-Millin v. Sears Roebuck\\n\\nDe P.R., Inc., 455 F.3d 30, 41 (1st Cir. 2006); Collins v. Alco Parking Corp., 448 F.3d\\n\\n652, 656 (3d Cir. 2006).\\n\\n\\n\\n 8\\n\\f In our view, the Rule’s text and the Advisory Committee’s direction compel a\\n\\ndifferent approach. For a court’s rejection of a proposed instruction to constitute “a\\n\\ndefinitive ruling on the record,” the record must simply provide a reviewing court with a\\n\\nsufficient basis from which to determine the district court’s rejection was “on the merits”\\n\\n— in other words, that the court rejected the substance of the proposed instruction, not\\n\\nmerely the litigant’s choice of words. And, to be “definitive,” this rejection must be final\\n\\nrather than tentative.\\n\\n It remains true, of course, that “the mere tendering of a proposed instruction will\\n\\nnot preserve error for appeal.” Bunn v. Oldendorff Carriers GmbH & Co. KG, 723 F.3d\\n\\n454, 469 (4th Cir. 2013) (internal quotation marks omitted). But where a litigant\\n\\nproposes an instruction and the district court’s final ruling on the record demonstrates\\n\\nthat the court rejected it on the merits, the claim of error is preserved. This approach\\n\\nhews closely to the language and purpose of Rule 51(d)(1)(B) while remaining cognizant\\n\\nof the important interests embodied in requiring parties to raise objections in the district\\n\\ncourt. See Booker v. Mass. Dep’t of Pub. Health, 612 F.3d 34, 41 (1st Cir. 2010).\\n\\n Applied here, we must conclude that Oberg did not preserve his challenge to the\\n\\nfailure to give his proposed jury instructions. At the charge conference, the district court\\n\\noutlined its proposed jury instructions in broad terms, explaining that it would give\\n\\nstandard instructions on issues like the burden of proof and reasonable doubt, and would\\n\\nalso instruct the jury on the essential elements of an FCA claim. PHEAA raised several\\n\\nclarifying questions. Oberg sought only to ensure that the instructions contained a\\n\\nprovision not at issue on appeal, i.e., that proof of reckless disregard sufficed to establish\\n\\n 9\\n\\fan FCA claim. When the court called for any final comments, PHEAA asked whether\\n\\nthe court would read any of the instructions Oberg had submitted before the charge\\n\\nconference. The court responded that it was “not reading anybody’s instruction[s]” and it\\n\\nhad “the areas” it was “going to instruct on.” Oberg did not object. After instructing the\\n\\njury, the court once again asked whether the parties had any objections to the instructions.\\n\\nPHEAA raised two; Oberg responded: “[n]o objection from the relator.”\\n\\n Oberg argues that the district court’s statement that it would “not read anybody’s\\n\\ninstruction[s]” constitutes a “definitive ruling on the record” rejecting his instructions on\\n\\nthe merits. Fed. R. Civ. P. 51(d)(1)(B). This argument falls far short. Even assuming\\n\\nthat the court’s asserted “denial” — a brief response to a question by PHEAA, not Oberg\\n\\n— constituted a final ruling that foreclosed further discussion of the issue, we cannot\\n\\ndiscern from the record whether the court considered Oberg’s proposed instructions and\\n\\nrejected them for their substance, or simply believed that its own instructions were an\\n\\nadequate substitute. To preserve the issue, Oberg could have sought clarification as to\\n\\nthe court’s basis for rejecting his instructions, or he could have timely objected. Because\\n\\nhe did neither, we review only for plain error. 3\\n\\n\\n\\n\\n 3\\n Oberg’s reliance on dicta from Justice Scalia’s concurring opinion in Connick v.\\nThompson, 563 U.S. 51, 72 (2011), cannot aid him. In Connick, Justice Scalia found that\\na trial court’s response, “No, I’m not giving that,” to an appellant’s request for a jury\\ninstruction was sufficient to “preserve a claim of error.” Id. at 75 (citing Fed. Rule Civ.\\nP. 51(d)(1)(B)). The trial court in that case, however, had already ruled on the matter in a\\nmotion for summary judgment — perhaps the quintessential example of a definitive\\nruling on the merits.\\n\\n 10\\n\\f We note that the Tenth Circuit also recently addressed the 2003 amendment to\\n\\nRule 51. There, appellants claimed to have preserved their challenge to jury instructions\\n\\nby submitting proposed instructions and receiving a responsive email from the district\\n\\ncourt with the court’s tentative instructions, which did not incorporate their proposals.\\n\\nFirst Am. Title Ins. Co. v. Nw. Title Ins. Agency, 906 F.3d 884, 894–95 (10th Cir. 2018).\\n\\nThe Tenth Circuit observed that the district court did not suggest the email included its\\n\\nfinal instructions and that counsel had ample opportunity to discuss its proposed\\n\\ninstructions. Id. at 895. It thus held that the email did not constitute a “definitive”\\n\\nrejection as contemplated by Rule 51(d)(1)(B). Id. 4 Our holding here does not conflict\\n\\nwith the Tenth Circuit’s opinion, but that case does not provide as clear a parallel as\\n\\nPHEAA suggests. The district court’s statement that it would not read any party’s\\n\\ninstruction was arguably more final than that considered by the Tenth Circuit, but we\\n\\ncannot conclude that it was “on the merits,” and so it fails to satisfy the Rule for that\\n\\nreason.\\n\\n B.\\n\\n Because Oberg failed to preserve his objections to the jury instructions, we review\\n\\nonly for plain error. Oberg must show that in refusing to give his proposed instructions\\n\\n(1) the district court erred; “(2) the error is plain; (3) the error affects substantial rights;\\n\\n 4\\n The Tenth Circuit went further to state that for a rejection to be definitive, “the\\ndistrict court must expressly reject that specific argument.” Id. (emphasis added). In\\nlight of the Advisory Committee’s guidance, we doubt that Rule 51(d)(1)(B) requires\\nsuch specificity when a court’s ruling is otherwise final and on the merits. We need not\\ndecide this question, however, because we cannot determine that the court’s rejection\\nhere was on the merits.\\n\\n 11\\n\\fand (4) . . . the error seriously affects the fairness, integrity or public reputation of judicial\\n\\nproceedings.” Gregg v. Ham, 678 F.3d 333, 338 (4th Cir. 2012) (internal quotation\\n\\nmarks omitted). Even if his claim had been properly preserved, Oberg “faces a heavy\\n\\nburden, for we accord the district court much discretion to fashion the charge.” United\\n\\nStates v. Raza, 876 F.3d 604, 614 (4th Cir. 2017) (internal quotation marks omitted).\\n\\n Oberg first argues that the district court erred by failing to inform the jury that he\\n\\ndid not need to prove PHEAA had a “specific intent to defraud” the government for his\\n\\nFCA claim to succeed. Oberg’s proposed instruction did accurately restate a statutory\\n\\nelement of the FCA, 31 U.S.C. § 3729(b)(1)(B), but the instructions given by the district\\n\\ncourt “substantially covered” this issue. United States ex rel. Drakeford v. Tuomey, 792\\n\\nF.3d 364, 382 (4th Cir. 2015). The court’s instructions correctly listed the three ways in\\n\\nwhich the jury could find that PHEAA acted with the requisite knowledge, none of which\\n\\nrequired Oberg to show specific intent to defraud. The court did not err, much less\\n\\nplainly err, in declining to provide any additional instruction. See Noel v. Artson, 641\\n\\nF.3d 580, 590 (4th Cir. 2011) (“We have always left the choice between generality versus\\n\\nspecificity in the charge to the sound discretion of the trial courts.” (internal quotation\\n\\nmarks and alteration omitted)).\\n\\n Next, Oberg argues that the district court should have included an instruction\\n\\nstating that “benevolent motivation . . . is not a defense” to an FCA claim. Much like\\n\\nOberg’s previous objection, the instructions given by the court substantially covered this\\n\\ninstruction. Moreover, Oberg’s proposed instruction addresses only a collateral issue —\\n\\nattempting to “cure” any improper introduction of benevolent motive evidence — that\\n\\n 12\\n\\fwould not have affected the outcome in the district court. See Gregg, 678 F.3d at 338\\n\\n(requiring that proposed instruction must affect substantial rights to establish plain error).\\n\\n Finally, Oberg contends that the court erred by refusing to instruct the jury on how\\n\\nit could find PHEAA’s claims fraudulent. He asserts that because the court did not\\n\\nprovide the jury with the specific statutory language defining whether PHEAA’s claims\\n\\nwere eligible for the 9.5 percent SAP payments, the jury lacked the necessary tools to\\n\\ndecide an element of his FCA claim. Had the district court erred in its charge on this\\n\\nissue, it would have committed the type of error that would usually require reversal, even\\n\\non plain error review. See United States v. Jennings, 160 F.3d 1006, 1019 (4th Cir. 1998)\\n\\n(noting that “failure to instruct the jury on any essential element of an offense constitutes\\n\\nplain error”).\\n\\n But yet again, the district court’s instructions substantially covered the substance\\n\\nof Oberg’s proposal. Contrary to Oberg’s assertions, the court’s instructions sufficiently\\n\\nexplained that the jury had to consider whether PHEAA’s claims were “false or\\n\\nfraudulent,” and that the crux of Oberg’s argument was that PHEAA “was not entitled to\\n\\nthe 9.5 percent floor SAP on the claimed loans.” Although the district court did not detail\\n\\nthe precise steps the jury should follow to determine the eligibility of PHEAA’s SAP\\n\\nclaims, “where, as here, the instructions accurately covered all the issues in the case, the\\n\\nfailure to reference specific aspects of a party’s contentions cannot serve as a basis for a\\n\\nfinding of error.” Noel, 641 F.3d at 590 (internal quotation marks and alterations\\n\\nomitted).\\n\\n\\n\\n 13\\n\\f In contrast, Oberg’s proposed instruction provided a misleading framework that\\n\\npresumed his interpretation of the relevant statute and DOE’s regulations was correct,\\n\\nessentially requiring the jury to find PHEAA’s claims ineligible. See id. (“[W]e cannot\\n\\nfault the district court for declining to give a wink and a nod to the jury.”).\\n\\n Armed with extensive testimony and numerous exhibits, it was up to the jury to\\n\\ndetermine whether PHEAA’s claims were eligible and, if they were not, whether PHEAA\\n\\nknew so when it submitted its claims. This is precisely what the district court’s jury\\n\\ninstructions asked of them.\\n\\n\\n\\n IV.\\n\\n For the foregoing reasons, the judgment of the district court is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 14\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4356944/\", \"author_raw\": \"DIANA GRIBBON MOTZ, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"MOTZ"},"judge2":{"kind":"string","value":"KEENAN"},"judge3":{"kind":"string","value":"HARRIS"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4579691/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES EX REL., Jon H. OBERG, Plaintiff-Appellant, v. PENNSYLVANIA HIGHER EDUCATION ASSISTANCE AGENCY, Defendant-Appellee, and Nelnet, Inc.; Kentucky Higher Education Student Loan Corp. ; SLM Corporation; Panhandle Plains Higher Education Authority ; Brazos Group; Arkansas Student Loan Authority; Education Loans Inc/SD; Southwest Student Services Corporation; Brazos Higher Education Service Corporation; Brazos Higher Education Authority, Inc.; Nelnet Education Loan Funding, Inc.; Panhandle-Plains Management and Servicing Corporation; Student Loan Finance Corporation; Education Loans Inc. ; Vermont Student Assistance Corporation, Defendants.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-08\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1028\n\n\nUNITED STATES EX REL., JON H. OBERG,\n\n Plaintiff – Appellant,\n\n v.\n\nPENNSYLVANIA HIGHER EDUCATION ASSISTANCE AGENCY,\n\n Defendant – Appellee,\n\n and\n\nNELNET, INC.; KENTUCKY HIGHER EDUCATION STUDENT LOAN\nCORP.; SLM CORPORATION; PANHANDLE PLAINS HIGHER EDUCATION\nAUTHORITY; BRAZOS GROUP; ARKANSAS STUDENT LOAN\nAUTHORITY; EDUCATION LOANS INC/SD; SOUTHWEST STUDENT\nSERVICES CORPORATION; BRAZOS HIGHER EDUCATION SERVICE\nCORPORATION; BRAZOS HIGHER EDUCATION AUTHORITY, INC.;\nNELNET EDUCATION LOAN FUNDING, INC.; PANHANDLE-PLAINS\nMANAGEMENT AND SERVICING CORPORATION; STUDENT LOAN\nFINANCE CORPORATION; EDUCATION LOANS INC.; VERMONT\nSTUDENT ASSISTANCE CORPORATION,\n\n Defendants.\n\n\nAppeal from the United States District Court for the Eastern District of Virginia, at\nAlexandria. Claude M. Hilton, Senior District Judge. (1:07-cv-00960-CMH-JFA)\n\n\nArgued: October 31, 2018 Decided: January 8, 2019\n\n\nBefore MOTZ, KEENAN, and HARRIS, Circuit Judges.\n\fAffirmed by published opinion. Judge Motz wrote the opinion, in which Judge Keenan\nand Judge Harris joined.\n\n\nARGUED: Eric Kenneth Bachman, ZUCKERMAN LAW, Chevy Chase, Maryland, for\nAppellant. George W. Hicks, Jr., KIRKLAND & ELLIS LLP, Washington, D.C., for\nAppellee. ON BRIEF: Jason M. Zuckerman, Washington, D.C., Dallas I. Hammer,\nZUCKERMAN LAW, Tysons Corner, Virginia, for Appellant. Matthew T. Regan,\nChicago, Illinois, Michael A. Glick, Tracie L. Bryant, Michael D. Lieberman,\nKIRKLAND & ELLIS LLP, Washington, D.C.; Daniel B. Huyett, STEVENS & LEE,\nP.C., Reading, Pennsylvania, for Appellee.\n\n\n\n\n 2\n\fDIANA GRIBBON MOTZ, Circuit Judge:\n\n This case returns to us again, this time on appeal from an adverse jury verdict.\n\nDr. Jon Oberg, as relator for the United States, brought this qui tam action against four\n\nstudent loan corporations, including the Pennsylvania Higher Education Assistance\n\nAgency (“PHEAA”). He alleged that the corporations had defrauded the Department of\n\nEducation and so violated the False Claims Act (“FCA”), 31 U.S.C. § 3729 et seq.\n\n Over the course of several appeals, we affirmed the dismissal of one defendant and\n\ntwo of the other defendants settled. See United States ex rel. Oberg v. Pa. Higher Educ.\n\nAssistance Agency, 804 F.3d 646, 650 (4th Cir. 2015); United States ex rel. Oberg v. Pa.\n\nHigher Educ. Assistance Agency, 745 F.3d 131, 145 (4th Cir. 2014); United States ex rel.\n\nOberg v. Ky. Higher Educ. Student Loan Corp., 681 F.3d 575, 579–81 (4th Cir. 2012).\n\nThe case proceeded to trial only against PHEAA. Oberg now appeals the jury’s\n\nunanimous verdict in favor of PHEAA. For the reasons that follow, we affirm.\n\n\n\n I.\n\n Oberg’s claim concerns a Department of Education subsidy program meant to\n\nencourage the issuance of low-interest federal student loans. It did so by offering Special\n\nAllowance Payments (“SAPs”) to certain qualifying lenders. 20 U.S.C. § 1087-1. For\n\none particular category of loans — those financed through tax-exempt bonds — Congress\n\nguaranteed lenders a 9.5 percent return. Id. § 1087-1(b)(2)(B). In the low-interest\n\nenvironment of the mid-2000s, this guaranteed rate made tax-exempt bonds a particularly\n\nattractive investment vehicle.\n\n 3\n\f To take advantage of the favorable return offered by the program, Oberg claims\n\nthat between 2002 and 2006, PHEAA submitted false claims for SAP subsidies by\n\nimproperly transferring student loans from non-tax-exempt bonds into tax-exempt bonds.\n\nIn doing so, PHEAA converted lower-interest floating-rate loans into loans that\n\nguaranteed a 9.5 percent return. This translated into millions of dollars in additional\n\nrevenue for PHEAA.\n\n During a five-day trial, the court admitted more than 100 exhibits and the jury\n\nheard testimony from more than a dozen witnesses. After deliberating for less than three\n\nhours, the jury returned a unanimous verdict in favor of PHEAA.\n\n Oberg timely noted this appeal, asking that we vacate the judgment and remand\n\nfor a new trial. He maintains that the district court substantially impeded his ability to\n\nprove his claims by improperly excluding critical evidence and rejecting Oberg’s\n\nproposed jury instructions.\n\n\n\n II.\n\n Oberg first contends that the district court erred by excluding certain evidence at\n\ntrial. We review a district court’s evidentiary rulings for abuse of discretion. SAS Inst.,\n\nInc. v. World Programming Ltd., 874 F.3d 370, 384 (4th Cir. 2017). “A district court\n\nabuses its discretion if it relies on an error of law or a clearly erroneous factual finding.”\n\nEEOC v. Freeman, 778 F.3d 463, 466 (4th Cir. 2015).\n\n At trial, Oberg sought admission of a 2004–2007 Performance Audit of PHEAA\n\nperformed by the Pennsylvania Auditor General. The Audit “evaluate[d] PHEAA’s\n\n 4\n\fperformance in improving access to higher education for Pennsylvania residents” and\n\nconcluded that PHEAA had largely “failed its mission.” The Audit found that PHEAA\n\npaid excessive salaries and bonuses to its executives and managers. The Audit also\n\ncatalogued and strongly criticized PHEAA’s lavish spending on employee benefits and\n\n“extravagant” expenditures on other unnecessary expenses. It “concluded that PHEAA\n\nwas governed and managed within a culture that sometimes allowed self-reward to\n\nsupersede fiscal prudence.” The district court excluded the Audit as irrelevant under\n\nFederal Rule of Evidence 401.\n\n Oberg contends that the Audit was relevant for several reasons. First, he argues\n\nthat the Audit’s critical findings tended to establish scienter — i.e., that desire for\n\npersonal gain motivated PHEAA officers to submit false claims. This argument fails\n\nbecause unlike the securities fraud cases on which Oberg relies, 1 FCA claims require a\n\nrelator to show only that the defendant had knowledge of the illegality of its actions,\n\nrather than specific intent to defraud. See, e.g., United States ex rel. Harrison v.\n\nWestinghouse Savannah River Co., 352 F.3d 908, 921 (4th Cir. 2003) (“In establishing\n\nliability under the FCA, a plaintiff need not prove the defendant had a financial motive to\n\nmake a false statement relating to a claim seeking government funds.”); United States ex\n\nrel. K & R Ltd. P’ship v. Mass. Hous. Fin. Agency, 530 F.3d 980, 984 (D.C. Cir. 2008)\n\n(finding evidence of defendant’s “motive to submit false claims — the need to bail itself\n\n 1\n Cases requiring proof of specific intent often turn on evidence of motive to prove\nscienter. See, e.g., Tellabs, Inc. v. Makor Issues & Rights, Ltd., 551 U.S. 308, 319, 325\n(2007) (finding motive “a relevant consideration” in measuring a defendant’s intent to\n“deceive, manipulate, or defraud” (internal quotation marks omitted)).\n\n 5\n\fout of financial trouble — could not . . . support a finding of knowledge, be it actual,\n\ndeliberate ignorance, or reckless disregard”). As the district court correctly explained:\n\n“It doesn’t really make any difference whether they were operating well or not well or\n\nwhatever. The only issue in this case is: Did they commit fraud and file a false claim?”\n\n Oberg next maintains that the Audit would have allowed him to rebut PHEAA’s\n\nown improper argument that its management acted with the “benevolent motive” to\n\nbenefit borrowers in carrying out its scheme. Oberg lodged little objection to this\n\nevidence at trial. Indeed, Oberg himself elicited most of the “benevolent motive”\n\ntestimony through his questions to PHEAA’s management. In any event, whether\n\nPHEAA’s management had benevolent motive was a collateral issue of limited relevance,\n\nmaking any error harmless. See Smith v. Balt. City Police Dep’t, 840 F.3d 193, 200–01\n\n(4th Cir. 2016).\n\n Finally, Oberg contends that the Audit would have helped him attack the\n\ncredibility of PHEAA’s executives. He argues that because witness credibility is “always\n\nat issue,” any “evidence concerning a witness’s credibility is always relevant.” United\n\nStates v. Green, 617 F.3d 233, 251 (3d Cir. 2010). This argument also fails, for Oberg\n\nquestioned PHEAA’s executives on the company’s compensation practices and elicited\n\nmuch of the same information contained in the Audit. Moreover, because nothing in the\n\nAudit contradicted the trial testimony of PHEAA executives, its admission would hardly\n\nhave aided Oberg in impeaching the executives’ credibility.\n\n\n\n\n 6\n\f In sum, the district court did not abuse its discretion in excluding the Audit as\n\nirrelevant. 2\n\n\n\n III.\n\n Oberg’s remaining claims center on the district court’s refusal to give several of\n\nhis proposed jury instructions.\n\n A.\n\n Before we consider the merit of his claims, we must first determine our standard\n\nof review.\n\n PHEAA contends that because Oberg did not object to the jury instructions before\n\nthe district court, he has failed to preserve his challenge to them and so we can review\n\nonly for plain error. Oberg counters that the district court rejected his properly requested\n\ninstructions in a “definitive ruling on the record,” and so we must instead review for\n\nabuse of discretion. Fed. R. Civ. P. 51(d)(1)(B); see also BMG Rights Mgmt. (US) LLC\n\nv. Cox Commc’ns, Inc., 881 F.3d 293, 305 (4th Cir. 2018).\n\n To resolve this question, we turn to the language of Federal Rule of Civil\n\nProcedure 51(d)(1)(B), which provides:\n\n A party may assign as error . . . a failure to give an instruction, if that party\n properly requested it and — unless the court rejected the request in a\n definitive ruling on the record — also properly objected.\n\n\n 2\n The parties also quarrel over whether the Audit was more prejudicial than\nprobative under Federal Rule of Evidence 403. Because we hold that the district court\ndid not err in excluding the Audit on relevance grounds, we need not address this issue.\n\n 7\n\fFed. R. Civ. P. 51(d)(1) (emphasis added).\n\n This provision was added to Rule 51 in 2003. See Fed. R. Civ. P. 51 advisory\n\ncommittee’s note to 2003 amendment (hereinafter, 2003 Advisory Committee Note).\n\nThe Advisory Committee explained that the change was motivated by concern over the\n\nmajority view “that a proper request for a jury instruction [was] not alone enough to\n\npreserve the right to appeal failure to give [an] instruction.” Id. The Committee\n\nconcluded that this rule was “appropriate when the court [had not] sufficiently focused on\n\nthe request” or “believe[d] that the request ha[d] been granted in substance although in\n\ndifferent words.” Id. But in other circumstances, the doctrine created “a trap for the\n\nunwary who fail[ed] to add an objection after the court . . . made it clear that the request\n\n[had] been considered and rejected on the merits.” Id. To correct this, the drafters added\n\nthe ruling-on-the-record language to “establish[] authority to review the failure to grant a\n\ntimely request, despite a failure to add an objection, when the court has made a definitive\n\nruling on the record rejecting the request.” Id.\n\n Notwithstanding the 2003 Amendment, some courts have seemed to continue to\n\nfollow a more stringent preservation rule than Rule 51(d)(1)(B) now appears to\n\ncommand. See EEOC v. New Breed Logistics, 783 F.3d 1057, 1075 (6th Cir. 2015); C.B.\n\nv. City of Sonora, 769 F.3d 1005, 1032 (9th Cir. 2014); Consumer Prod. Research &\n\nDesign, Inc. v. Jensen, 572 F.3d 436, 439 (7th Cir. 2009); Colon-Millin v. Sears Roebuck\n\nDe P.R., Inc., 455 F.3d 30, 41 (1st Cir. 2006); Collins v. Alco Parking Corp., 448 F.3d\n\n652, 656 (3d Cir. 2006).\n\n\n\n 8\n\f In our view, the Rule’s text and the Advisory Committee’s direction compel a\n\ndifferent approach. For a court’s rejection of a proposed instruction to constitute “a\n\ndefinitive ruling on the record,” the record must simply provide a reviewing court with a\n\nsufficient basis from which to determine the district court’s rejection was “on the merits”\n\n— in other words, that the court rejected the substance of the proposed instruction, not\n\nmerely the litigant’s choice of words. And, to be “definitive,” this rejection must be final\n\nrather than tentative.\n\n It remains true, of course, that “the mere tendering of a proposed instruction will\n\nnot preserve error for appeal.” Bunn v. Oldendorff Carriers GmbH & Co. KG, 723 F.3d\n\n454, 469 (4th Cir. 2013) (internal quotation marks omitted). But where a litigant\n\nproposes an instruction and the district court’s final ruling on the record demonstrates\n\nthat the court rejected it on the merits, the claim of error is preserved. This approach\n\nhews closely to the language and purpose of Rule 51(d)(1)(B) while remaining cognizant\n\nof the important interests embodied in requiring parties to raise objections in the district\n\ncourt. See Booker v. Mass. Dep’t of Pub. Health, 612 F.3d 34, 41 (1st Cir. 2010).\n\n Applied here, we must conclude that Oberg did not preserve his challenge to the\n\nfailure to give his proposed jury instructions. At the charge conference, the district court\n\noutlined its proposed jury instructions in broad terms, explaining that it would give\n\nstandard instructions on issues like the burden of proof and reasonable doubt, and would\n\nalso instruct the jury on the essential elements of an FCA claim. PHEAA raised several\n\nclarifying questions. Oberg sought only to ensure that the instructions contained a\n\nprovision not at issue on appeal, i.e., that proof of reckless disregard sufficed to establish\n\n 9\n\fan FCA claim. When the court called for any final comments, PHEAA asked whether\n\nthe court would read any of the instructions Oberg had submitted before the charge\n\nconference. The court responded that it was “not reading anybody’s instruction[s]” and it\n\nhad “the areas” it was “going to instruct on.” Oberg did not object. After instructing the\n\njury, the court once again asked whether the parties had any objections to the instructions.\n\nPHEAA raised two; Oberg responded: “[n]o objection from the relator.”\n\n Oberg argues that the district court’s statement that it would “not read anybody’s\n\ninstruction[s]” constitutes a “definitive ruling on the record” rejecting his instructions on\n\nthe merits. Fed. R. Civ. P. 51(d)(1)(B). This argument falls far short. Even assuming\n\nthat the court’s asserted “denial” — a brief response to a question by PHEAA, not Oberg\n\n— constituted a final ruling that foreclosed further discussion of the issue, we cannot\n\ndiscern from the record whether the court considered Oberg’s proposed instructions and\n\nrejected them for their substance, or simply believed that its own instructions were an\n\nadequate substitute. To preserve the issue, Oberg could have sought clarification as to\n\nthe court’s basis for rejecting his instructions, or he could have timely objected. Because\n\nhe did neither, we review only for plain error. 3\n\n\n\n\n 3\n Oberg’s reliance on dicta from Justice Scalia’s concurring opinion in Connick v.\nThompson, 563 U.S. 51, 72 (2011), cannot aid him. In Connick, Justice Scalia found that\na trial court’s response, “No, I’m not giving that,” to an appellant’s request for a jury\ninstruction was sufficient to “preserve a claim of error.” Id. at 75 (citing Fed. Rule Civ.\nP. 51(d)(1)(B)). The trial court in that case, however, had already ruled on the matter in a\nmotion for summary judgment — perhaps the quintessential example of a definitive\nruling on the merits.\n\n 10\n\f We note that the Tenth Circuit also recently addressed the 2003 amendment to\n\nRule 51. There, appellants claimed to have preserved their challenge to jury instructions\n\nby submitting proposed instructions and receiving a responsive email from the district\n\ncourt with the court’s tentative instructions, which did not incorporate their proposals.\n\nFirst Am. Title Ins. Co. v. Nw. Title Ins. Agency, 906 F.3d 884, 894–95 (10th Cir. 2018).\n\nThe Tenth Circuit observed that the district court did not suggest the email included its\n\nfinal instructions and that counsel had ample opportunity to discuss its proposed\n\ninstructions. Id. at 895. It thus held that the email did not constitute a “definitive”\n\nrejection as contemplated by Rule 51(d)(1)(B). Id. 4 Our holding here does not conflict\n\nwith the Tenth Circuit’s opinion, but that case does not provide as clear a parallel as\n\nPHEAA suggests. The district court’s statement that it would not read any party’s\n\ninstruction was arguably more final than that considered by the Tenth Circuit, but we\n\ncannot conclude that it was “on the merits,” and so it fails to satisfy the Rule for that\n\nreason.\n\n B.\n\n Because Oberg failed to preserve his objections to the jury instructions, we review\n\nonly for plain error. Oberg must show that in refusing to give his proposed instructions\n\n(1) the district court erred; “(2) the error is plain; (3) the error affects substantial rights;\n\n 4\n The Tenth Circuit went further to state that for a rejection to be definitive, “the\ndistrict court must expressly reject that specific argument.” Id. (emphasis added). In\nlight of the Advisory Committee’s guidance, we doubt that Rule 51(d)(1)(B) requires\nsuch specificity when a court’s ruling is otherwise final and on the merits. We need not\ndecide this question, however, because we cannot determine that the court’s rejection\nhere was on the merits.\n\n 11\n\fand (4) . . . the error seriously affects the fairness, integrity or public reputation of judicial\n\nproceedings.” Gregg v. Ham, 678 F.3d 333, 338 (4th Cir. 2012) (internal quotation\n\nmarks omitted). Even if his claim had been properly preserved, Oberg “faces a heavy\n\nburden, for we accord the district court much discretion to fashion the charge.” United\n\nStates v. Raza, 876 F.3d 604, 614 (4th Cir. 2017) (internal quotation marks omitted).\n\n Oberg first argues that the district court erred by failing to inform the jury that he\n\ndid not need to prove PHEAA had a “specific intent to defraud” the government for his\n\nFCA claim to succeed. Oberg’s proposed instruction did accurately restate a statutory\n\nelement of the FCA, 31 U.S.C. § 3729(b)(1)(B), but the instructions given by the district\n\ncourt “substantially covered” this issue. United States ex rel. Drakeford v. Tuomey, 792\n\nF.3d 364, 382 (4th Cir. 2015). The court’s instructions correctly listed the three ways in\n\nwhich the jury could find that PHEAA acted with the requisite knowledge, none of which\n\nrequired Oberg to show specific intent to defraud. The court did not err, much less\n\nplainly err, in declining to provide any additional instruction. See Noel v. Artson, 641\n\nF.3d 580, 590 (4th Cir. 2011) (“We have always left the choice between generality versus\n\nspecificity in the charge to the sound discretion of the trial courts.” (internal quotation\n\nmarks and alteration omitted)).\n\n Next, Oberg argues that the district court should have included an instruction\n\nstating that “benevolent motivation . . . is not a defense” to an FCA claim. Much like\n\nOberg’s previous objection, the instructions given by the court substantially covered this\n\ninstruction. Moreover, Oberg’s proposed instruction addresses only a collateral issue —\n\nattempting to “cure” any improper introduction of benevolent motive evidence — that\n\n 12\n\fwould not have affected the outcome in the district court. See Gregg, 678 F.3d at 338\n\n(requiring that proposed instruction must affect substantial rights to establish plain error).\n\n Finally, Oberg contends that the court erred by refusing to instruct the jury on how\n\nit could find PHEAA’s claims fraudulent. He asserts that because the court did not\n\nprovide the jury with the specific statutory language defining whether PHEAA’s claims\n\nwere eligible for the 9.5 percent SAP payments, the jury lacked the necessary tools to\n\ndecide an element of his FCA claim. Had the district court erred in its charge on this\n\nissue, it would have committed the type of error that would usually require reversal, even\n\non plain error review. See United States v. Jennings, 160 F.3d 1006, 1019 (4th Cir. 1998)\n\n(noting that “failure to instruct the jury on any essential element of an offense constitutes\n\nplain error”).\n\n But yet again, the district court’s instructions substantially covered the substance\n\nof Oberg’s proposal. Contrary to Oberg’s assertions, the court’s instructions sufficiently\n\nexplained that the jury had to consider whether PHEAA’s claims were “false or\n\nfraudulent,” and that the crux of Oberg’s argument was that PHEAA “was not entitled to\n\nthe 9.5 percent floor SAP on the claimed loans.” Although the district court did not detail\n\nthe precise steps the jury should follow to determine the eligibility of PHEAA’s SAP\n\nclaims, “where, as here, the instructions accurately covered all the issues in the case, the\n\nfailure to reference specific aspects of a party’s contentions cannot serve as a basis for a\n\nfinding of error.” Noel, 641 F.3d at 590 (internal quotation marks and alterations\n\nomitted).\n\n\n\n 13\n\f In contrast, Oberg’s proposed instruction provided a misleading framework that\n\npresumed his interpretation of the relevant statute and DOE’s regulations was correct,\n\nessentially requiring the jury to find PHEAA’s claims ineligible. See id. (“[W]e cannot\n\nfault the district court for declining to give a wink and a nod to the jury.”).\n\n Armed with extensive testimony and numerous exhibits, it was up to the jury to\n\ndetermine whether PHEAA’s claims were eligible and, if they were not, whether PHEAA\n\nknew so when it submitted its claims. This is precisely what the district court’s jury\n\ninstructions asked of them.\n\n\n\n IV.\n\n For the foregoing reasons, the judgment of the district court is\n\n AFFIRMED.\n\n\n\n\n 14\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES EX REL., Jon H. OBERG, Plaintiff-Appellant, v. PENNSYLVANIA HIGHER EDUCATION ASSISTANCE AGENCY, Defendant-Appellee, and Nelnet, Inc.; Kentucky Higher Education Student Loan Corp. ; SLM Corporation; Panhandle Plains Higher Education Authority ; Brazos Group; Arkansas Student Loan Authority; Education Loans Inc/SD; Southwest Student Services Corporation; Brazos Higher Education Service Corporation; Brazos Higher Education Authority, Inc.; Nelnet Education Loan Funding, Inc.; Panhandle-Plains Management and Servicing Corporation; Student Loan Finance Corporation; Education Loans Inc. ; Vermont Student Assistance Corporation, Defendants.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-08\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1028\\n\\n\\nUNITED STATES EX REL., JON H. OBERG,\\n\\n Plaintiff – Appellant,\\n\\n v.\\n\\nPENNSYLVANIA HIGHER EDUCATION ASSISTANCE AGENCY,\\n\\n Defendant – Appellee,\\n\\n and\\n\\nNELNET, INC.; KENTUCKY HIGHER EDUCATION STUDENT LOAN\\nCORP.; SLM CORPORATION; PANHANDLE PLAINS HIGHER EDUCATION\\nAUTHORITY; BRAZOS GROUP; ARKANSAS STUDENT LOAN\\nAUTHORITY; EDUCATION LOANS INC/SD; SOUTHWEST STUDENT\\nSERVICES CORPORATION; BRAZOS HIGHER EDUCATION SERVICE\\nCORPORATION; BRAZOS HIGHER EDUCATION AUTHORITY, INC.;\\nNELNET EDUCATION LOAN FUNDING, INC.; PANHANDLE-PLAINS\\nMANAGEMENT AND SERVICING CORPORATION; STUDENT LOAN\\nFINANCE CORPORATION; EDUCATION LOANS INC.; VERMONT\\nSTUDENT ASSISTANCE CORPORATION,\\n\\n Defendants.\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. Claude M. Hilton, Senior District Judge. (1:07-cv-00960-CMH-JFA)\\n\\n\\nArgued: October 31, 2018 Decided: January 8, 2019\\n\\n\\nBefore MOTZ, KEENAN, and HARRIS, Circuit Judges.\\n\\fAffirmed by published opinion. Judge Motz wrote the opinion, in which Judge Keenan\\nand Judge Harris joined.\\n\\n\\nARGUED: Eric Kenneth Bachman, ZUCKERMAN LAW, Chevy Chase, Maryland, for\\nAppellant. George W. Hicks, Jr., KIRKLAND & ELLIS LLP, Washington, D.C., for\\nAppellee. ON BRIEF: Jason M. Zuckerman, Washington, D.C., Dallas I. Hammer,\\nZUCKERMAN LAW, Tysons Corner, Virginia, for Appellant. Matthew T. Regan,\\nChicago, Illinois, Michael A. Glick, Tracie L. Bryant, Michael D. Lieberman,\\nKIRKLAND & ELLIS LLP, Washington, D.C.; Daniel B. Huyett, STEVENS & LEE,\\nP.C., Reading, Pennsylvania, for Appellee.\\n\\n\\n\\n\\n 2\\n\\fDIANA GRIBBON MOTZ, Circuit Judge:\\n\\n This case returns to us again, this time on appeal from an adverse jury verdict.\\n\\nDr. Jon Oberg, as relator for the United States, brought this qui tam action against four\\n\\nstudent loan corporations, including the Pennsylvania Higher Education Assistance\\n\\nAgency (“PHEAA”). He alleged that the corporations had defrauded the Department of\\n\\nEducation and so violated the False Claims Act (“FCA”), 31 U.S.C. § 3729 et seq.\\n\\n Over the course of several appeals, we affirmed the dismissal of one defendant and\\n\\ntwo of the other defendants settled. See United States ex rel. Oberg v. Pa. Higher Educ.\\n\\nAssistance Agency, 804 F.3d 646, 650 (4th Cir. 2015); United States ex rel. Oberg v. Pa.\\n\\nHigher Educ. Assistance Agency, 745 F.3d 131, 145 (4th Cir. 2014); United States ex rel.\\n\\nOberg v. Ky. Higher Educ. Student Loan Corp., 681 F.3d 575, 579–81 (4th Cir. 2012).\\n\\nThe case proceeded to trial only against PHEAA. Oberg now appeals the jury’s\\n\\nunanimous verdict in favor of PHEAA. For the reasons that follow, we affirm.\\n\\n\\n\\n I.\\n\\n Oberg’s claim concerns a Department of Education subsidy program meant to\\n\\nencourage the issuance of low-interest federal student loans. It did so by offering Special\\n\\nAllowance Payments (“SAPs”) to certain qualifying lenders. 20 U.S.C. § 1087-1. For\\n\\none particular category of loans — those financed through tax-exempt bonds — Congress\\n\\nguaranteed lenders a 9.5 percent return. Id. § 1087-1(b)(2)(B). In the low-interest\\n\\nenvironment of the mid-2000s, this guaranteed rate made tax-exempt bonds a particularly\\n\\nattractive investment vehicle.\\n\\n 3\\n\\f To take advantage of the favorable return offered by the program, Oberg claims\\n\\nthat between 2002 and 2006, PHEAA submitted false claims for SAP subsidies by\\n\\nimproperly transferring student loans from non-tax-exempt bonds into tax-exempt bonds.\\n\\nIn doing so, PHEAA converted lower-interest floating-rate loans into loans that\\n\\nguaranteed a 9.5 percent return. This translated into millions of dollars in additional\\n\\nrevenue for PHEAA.\\n\\n During a five-day trial, the court admitted more than 100 exhibits and the jury\\n\\nheard testimony from more than a dozen witnesses. After deliberating for less than three\\n\\nhours, the jury returned a unanimous verdict in favor of PHEAA.\\n\\n Oberg timely noted this appeal, asking that we vacate the judgment and remand\\n\\nfor a new trial. He maintains that the district court substantially impeded his ability to\\n\\nprove his claims by improperly excluding critical evidence and rejecting Oberg’s\\n\\nproposed jury instructions.\\n\\n\\n\\n II.\\n\\n Oberg first contends that the district court erred by excluding certain evidence at\\n\\ntrial. We review a district court’s evidentiary rulings for abuse of discretion. SAS Inst.,\\n\\nInc. v. World Programming Ltd., 874 F.3d 370, 384 (4th Cir. 2017). “A district court\\n\\nabuses its discretion if it relies on an error of law or a clearly erroneous factual finding.”\\n\\nEEOC v. Freeman, 778 F.3d 463, 466 (4th Cir. 2015).\\n\\n At trial, Oberg sought admission of a 2004–2007 Performance Audit of PHEAA\\n\\nperformed by the Pennsylvania Auditor General. The Audit “evaluate[d] PHEAA’s\\n\\n 4\\n\\fperformance in improving access to higher education for Pennsylvania residents” and\\n\\nconcluded that PHEAA had largely “failed its mission.” The Audit found that PHEAA\\n\\npaid excessive salaries and bonuses to its executives and managers. The Audit also\\n\\ncatalogued and strongly criticized PHEAA’s lavish spending on employee benefits and\\n\\n“extravagant” expenditures on other unnecessary expenses. It “concluded that PHEAA\\n\\nwas governed and managed within a culture that sometimes allowed self-reward to\\n\\nsupersede fiscal prudence.” The district court excluded the Audit as irrelevant under\\n\\nFederal Rule of Evidence 401.\\n\\n Oberg contends that the Audit was relevant for several reasons. First, he argues\\n\\nthat the Audit’s critical findings tended to establish scienter — i.e., that desire for\\n\\npersonal gain motivated PHEAA officers to submit false claims. This argument fails\\n\\nbecause unlike the securities fraud cases on which Oberg relies, 1 FCA claims require a\\n\\nrelator to show only that the defendant had knowledge of the illegality of its actions,\\n\\nrather than specific intent to defraud. See, e.g., United States ex rel. Harrison v.\\n\\nWestinghouse Savannah River Co., 352 F.3d 908, 921 (4th Cir. 2003) (“In establishing\\n\\nliability under the FCA, a plaintiff need not prove the defendant had a financial motive to\\n\\nmake a false statement relating to a claim seeking government funds.”); United States ex\\n\\nrel. K & R Ltd. P’ship v. Mass. Hous. Fin. Agency, 530 F.3d 980, 984 (D.C. Cir. 2008)\\n\\n(finding evidence of defendant’s “motive to submit false claims — the need to bail itself\\n\\n 1\\n Cases requiring proof of specific intent often turn on evidence of motive to prove\\nscienter. See, e.g., Tellabs, Inc. v. Makor Issues & Rights, Ltd., 551 U.S. 308, 319, 325\\n(2007) (finding motive “a relevant consideration” in measuring a defendant’s intent to\\n“deceive, manipulate, or defraud” (internal quotation marks omitted)).\\n\\n 5\\n\\fout of financial trouble — could not . . . support a finding of knowledge, be it actual,\\n\\ndeliberate ignorance, or reckless disregard”). As the district court correctly explained:\\n\\n“It doesn’t really make any difference whether they were operating well or not well or\\n\\nwhatever. The only issue in this case is: Did they commit fraud and file a false claim?”\\n\\n Oberg next maintains that the Audit would have allowed him to rebut PHEAA’s\\n\\nown improper argument that its management acted with the “benevolent motive” to\\n\\nbenefit borrowers in carrying out its scheme. Oberg lodged little objection to this\\n\\nevidence at trial. Indeed, Oberg himself elicited most of the “benevolent motive”\\n\\ntestimony through his questions to PHEAA’s management. In any event, whether\\n\\nPHEAA’s management had benevolent motive was a collateral issue of limited relevance,\\n\\nmaking any error harmless. See Smith v. Balt. City Police Dep’t, 840 F.3d 193, 200–01\\n\\n(4th Cir. 2016).\\n\\n Finally, Oberg contends that the Audit would have helped him attack the\\n\\ncredibility of PHEAA’s executives. He argues that because witness credibility is “always\\n\\nat issue,” any “evidence concerning a witness’s credibility is always relevant.” United\\n\\nStates v. Green, 617 F.3d 233, 251 (3d Cir. 2010). This argument also fails, for Oberg\\n\\nquestioned PHEAA’s executives on the company’s compensation practices and elicited\\n\\nmuch of the same information contained in the Audit. Moreover, because nothing in the\\n\\nAudit contradicted the trial testimony of PHEAA executives, its admission would hardly\\n\\nhave aided Oberg in impeaching the executives’ credibility.\\n\\n\\n\\n\\n 6\\n\\f In sum, the district court did not abuse its discretion in excluding the Audit as\\n\\nirrelevant. 2\\n\\n\\n\\n III.\\n\\n Oberg’s remaining claims center on the district court’s refusal to give several of\\n\\nhis proposed jury instructions.\\n\\n A.\\n\\n Before we consider the merit of his claims, we must first determine our standard\\n\\nof review.\\n\\n PHEAA contends that because Oberg did not object to the jury instructions before\\n\\nthe district court, he has failed to preserve his challenge to them and so we can review\\n\\nonly for plain error. Oberg counters that the district court rejected his properly requested\\n\\ninstructions in a “definitive ruling on the record,” and so we must instead review for\\n\\nabuse of discretion. Fed. R. Civ. P. 51(d)(1)(B); see also BMG Rights Mgmt. (US) LLC\\n\\nv. Cox Commc’ns, Inc., 881 F.3d 293, 305 (4th Cir. 2018).\\n\\n To resolve this question, we turn to the language of Federal Rule of Civil\\n\\nProcedure 51(d)(1)(B), which provides:\\n\\n A party may assign as error . . . a failure to give an instruction, if that party\\n properly requested it and — unless the court rejected the request in a\\n definitive ruling on the record — also properly objected.\\n\\n\\n 2\\n The parties also quarrel over whether the Audit was more prejudicial than\\nprobative under Federal Rule of Evidence 403. Because we hold that the district court\\ndid not err in excluding the Audit on relevance grounds, we need not address this issue.\\n\\n 7\\n\\fFed. R. Civ. P. 51(d)(1) (emphasis added).\\n\\n This provision was added to Rule 51 in 2003. See Fed. R. Civ. P. 51 advisory\\n\\ncommittee’s note to 2003 amendment (hereinafter, 2003 Advisory Committee Note).\\n\\nThe Advisory Committee explained that the change was motivated by concern over the\\n\\nmajority view “that a proper request for a jury instruction [was] not alone enough to\\n\\npreserve the right to appeal failure to give [an] instruction.” Id. The Committee\\n\\nconcluded that this rule was “appropriate when the court [had not] sufficiently focused on\\n\\nthe request” or “believe[d] that the request ha[d] been granted in substance although in\\n\\ndifferent words.” Id. But in other circumstances, the doctrine created “a trap for the\\n\\nunwary who fail[ed] to add an objection after the court . . . made it clear that the request\\n\\n[had] been considered and rejected on the merits.” Id. To correct this, the drafters added\\n\\nthe ruling-on-the-record language to “establish[] authority to review the failure to grant a\\n\\ntimely request, despite a failure to add an objection, when the court has made a definitive\\n\\nruling on the record rejecting the request.” Id.\\n\\n Notwithstanding the 2003 Amendment, some courts have seemed to continue to\\n\\nfollow a more stringent preservation rule than Rule 51(d)(1)(B) now appears to\\n\\ncommand. See EEOC v. New Breed Logistics, 783 F.3d 1057, 1075 (6th Cir. 2015); C.B.\\n\\nv. City of Sonora, 769 F.3d 1005, 1032 (9th Cir. 2014); Consumer Prod. Research &\\n\\nDesign, Inc. v. Jensen, 572 F.3d 436, 439 (7th Cir. 2009); Colon-Millin v. Sears Roebuck\\n\\nDe P.R., Inc., 455 F.3d 30, 41 (1st Cir. 2006); Collins v. Alco Parking Corp., 448 F.3d\\n\\n652, 656 (3d Cir. 2006).\\n\\n\\n\\n 8\\n\\f In our view, the Rule’s text and the Advisory Committee’s direction compel a\\n\\ndifferent approach. For a court’s rejection of a proposed instruction to constitute “a\\n\\ndefinitive ruling on the record,” the record must simply provide a reviewing court with a\\n\\nsufficient basis from which to determine the district court’s rejection was “on the merits”\\n\\n— in other words, that the court rejected the substance of the proposed instruction, not\\n\\nmerely the litigant’s choice of words. And, to be “definitive,” this rejection must be final\\n\\nrather than tentative.\\n\\n It remains true, of course, that “the mere tendering of a proposed instruction will\\n\\nnot preserve error for appeal.” Bunn v. Oldendorff Carriers GmbH & Co. KG, 723 F.3d\\n\\n454, 469 (4th Cir. 2013) (internal quotation marks omitted). But where a litigant\\n\\nproposes an instruction and the district court’s final ruling on the record demonstrates\\n\\nthat the court rejected it on the merits, the claim of error is preserved. This approach\\n\\nhews closely to the language and purpose of Rule 51(d)(1)(B) while remaining cognizant\\n\\nof the important interests embodied in requiring parties to raise objections in the district\\n\\ncourt. See Booker v. Mass. Dep’t of Pub. Health, 612 F.3d 34, 41 (1st Cir. 2010).\\n\\n Applied here, we must conclude that Oberg did not preserve his challenge to the\\n\\nfailure to give his proposed jury instructions. At the charge conference, the district court\\n\\noutlined its proposed jury instructions in broad terms, explaining that it would give\\n\\nstandard instructions on issues like the burden of proof and reasonable doubt, and would\\n\\nalso instruct the jury on the essential elements of an FCA claim. PHEAA raised several\\n\\nclarifying questions. Oberg sought only to ensure that the instructions contained a\\n\\nprovision not at issue on appeal, i.e., that proof of reckless disregard sufficed to establish\\n\\n 9\\n\\fan FCA claim. When the court called for any final comments, PHEAA asked whether\\n\\nthe court would read any of the instructions Oberg had submitted before the charge\\n\\nconference. The court responded that it was “not reading anybody’s instruction[s]” and it\\n\\nhad “the areas” it was “going to instruct on.” Oberg did not object. After instructing the\\n\\njury, the court once again asked whether the parties had any objections to the instructions.\\n\\nPHEAA raised two; Oberg responded: “[n]o objection from the relator.”\\n\\n Oberg argues that the district court’s statement that it would “not read anybody’s\\n\\ninstruction[s]” constitutes a “definitive ruling on the record” rejecting his instructions on\\n\\nthe merits. Fed. R. Civ. P. 51(d)(1)(B). This argument falls far short. Even assuming\\n\\nthat the court’s asserted “denial” — a brief response to a question by PHEAA, not Oberg\\n\\n— constituted a final ruling that foreclosed further discussion of the issue, we cannot\\n\\ndiscern from the record whether the court considered Oberg’s proposed instructions and\\n\\nrejected them for their substance, or simply believed that its own instructions were an\\n\\nadequate substitute. To preserve the issue, Oberg could have sought clarification as to\\n\\nthe court’s basis for rejecting his instructions, or he could have timely objected. Because\\n\\nhe did neither, we review only for plain error. 3\\n\\n\\n\\n\\n 3\\n Oberg’s reliance on dicta from Justice Scalia’s concurring opinion in Connick v.\\nThompson, 563 U.S. 51, 72 (2011), cannot aid him. In Connick, Justice Scalia found that\\na trial court’s response, “No, I’m not giving that,” to an appellant’s request for a jury\\ninstruction was sufficient to “preserve a claim of error.” Id. at 75 (citing Fed. Rule Civ.\\nP. 51(d)(1)(B)). The trial court in that case, however, had already ruled on the matter in a\\nmotion for summary judgment — perhaps the quintessential example of a definitive\\nruling on the merits.\\n\\n 10\\n\\f We note that the Tenth Circuit also recently addressed the 2003 amendment to\\n\\nRule 51. There, appellants claimed to have preserved their challenge to jury instructions\\n\\nby submitting proposed instructions and receiving a responsive email from the district\\n\\ncourt with the court’s tentative instructions, which did not incorporate their proposals.\\n\\nFirst Am. Title Ins. Co. v. Nw. Title Ins. Agency, 906 F.3d 884, 894–95 (10th Cir. 2018).\\n\\nThe Tenth Circuit observed that the district court did not suggest the email included its\\n\\nfinal instructions and that counsel had ample opportunity to discuss its proposed\\n\\ninstructions. Id. at 895. It thus held that the email did not constitute a “definitive”\\n\\nrejection as contemplated by Rule 51(d)(1)(B). Id. 4 Our holding here does not conflict\\n\\nwith the Tenth Circuit’s opinion, but that case does not provide as clear a parallel as\\n\\nPHEAA suggests. The district court’s statement that it would not read any party’s\\n\\ninstruction was arguably more final than that considered by the Tenth Circuit, but we\\n\\ncannot conclude that it was “on the merits,” and so it fails to satisfy the Rule for that\\n\\nreason.\\n\\n B.\\n\\n Because Oberg failed to preserve his objections to the jury instructions, we review\\n\\nonly for plain error. Oberg must show that in refusing to give his proposed instructions\\n\\n(1) the district court erred; “(2) the error is plain; (3) the error affects substantial rights;\\n\\n 4\\n The Tenth Circuit went further to state that for a rejection to be definitive, “the\\ndistrict court must expressly reject that specific argument.” Id. (emphasis added). In\\nlight of the Advisory Committee’s guidance, we doubt that Rule 51(d)(1)(B) requires\\nsuch specificity when a court’s ruling is otherwise final and on the merits. We need not\\ndecide this question, however, because we cannot determine that the court’s rejection\\nhere was on the merits.\\n\\n 11\\n\\fand (4) . . . the error seriously affects the fairness, integrity or public reputation of judicial\\n\\nproceedings.” Gregg v. Ham, 678 F.3d 333, 338 (4th Cir. 2012) (internal quotation\\n\\nmarks omitted). Even if his claim had been properly preserved, Oberg “faces a heavy\\n\\nburden, for we accord the district court much discretion to fashion the charge.” United\\n\\nStates v. Raza, 876 F.3d 604, 614 (4th Cir. 2017) (internal quotation marks omitted).\\n\\n Oberg first argues that the district court erred by failing to inform the jury that he\\n\\ndid not need to prove PHEAA had a “specific intent to defraud” the government for his\\n\\nFCA claim to succeed. Oberg’s proposed instruction did accurately restate a statutory\\n\\nelement of the FCA, 31 U.S.C. § 3729(b)(1)(B), but the instructions given by the district\\n\\ncourt “substantially covered” this issue. United States ex rel. Drakeford v. Tuomey, 792\\n\\nF.3d 364, 382 (4th Cir. 2015). The court’s instructions correctly listed the three ways in\\n\\nwhich the jury could find that PHEAA acted with the requisite knowledge, none of which\\n\\nrequired Oberg to show specific intent to defraud. The court did not err, much less\\n\\nplainly err, in declining to provide any additional instruction. See Noel v. Artson, 641\\n\\nF.3d 580, 590 (4th Cir. 2011) (“We have always left the choice between generality versus\\n\\nspecificity in the charge to the sound discretion of the trial courts.” (internal quotation\\n\\nmarks and alteration omitted)).\\n\\n Next, Oberg argues that the district court should have included an instruction\\n\\nstating that “benevolent motivation . . . is not a defense” to an FCA claim. Much like\\n\\nOberg’s previous objection, the instructions given by the court substantially covered this\\n\\ninstruction. Moreover, Oberg’s proposed instruction addresses only a collateral issue —\\n\\nattempting to “cure” any improper introduction of benevolent motive evidence — that\\n\\n 12\\n\\fwould not have affected the outcome in the district court. See Gregg, 678 F.3d at 338\\n\\n(requiring that proposed instruction must affect substantial rights to establish plain error).\\n\\n Finally, Oberg contends that the court erred by refusing to instruct the jury on how\\n\\nit could find PHEAA’s claims fraudulent. He asserts that because the court did not\\n\\nprovide the jury with the specific statutory language defining whether PHEAA’s claims\\n\\nwere eligible for the 9.5 percent SAP payments, the jury lacked the necessary tools to\\n\\ndecide an element of his FCA claim. Had the district court erred in its charge on this\\n\\nissue, it would have committed the type of error that would usually require reversal, even\\n\\non plain error review. See United States v. Jennings, 160 F.3d 1006, 1019 (4th Cir. 1998)\\n\\n(noting that “failure to instruct the jury on any essential element of an offense constitutes\\n\\nplain error”).\\n\\n But yet again, the district court’s instructions substantially covered the substance\\n\\nof Oberg’s proposal. Contrary to Oberg’s assertions, the court’s instructions sufficiently\\n\\nexplained that the jury had to consider whether PHEAA’s claims were “false or\\n\\nfraudulent,” and that the crux of Oberg’s argument was that PHEAA “was not entitled to\\n\\nthe 9.5 percent floor SAP on the claimed loans.” Although the district court did not detail\\n\\nthe precise steps the jury should follow to determine the eligibility of PHEAA’s SAP\\n\\nclaims, “where, as here, the instructions accurately covered all the issues in the case, the\\n\\nfailure to reference specific aspects of a party’s contentions cannot serve as a basis for a\\n\\nfinding of error.” Noel, 641 F.3d at 590 (internal quotation marks and alterations\\n\\nomitted).\\n\\n\\n\\n 13\\n\\f In contrast, Oberg’s proposed instruction provided a misleading framework that\\n\\npresumed his interpretation of the relevant statute and DOE’s regulations was correct,\\n\\nessentially requiring the jury to find PHEAA’s claims ineligible. See id. (“[W]e cannot\\n\\nfault the district court for declining to give a wink and a nod to the jury.”).\\n\\n Armed with extensive testimony and numerous exhibits, it was up to the jury to\\n\\ndetermine whether PHEAA’s claims were eligible and, if they were not, whether PHEAA\\n\\nknew so when it submitted its claims. This is precisely what the district court’s jury\\n\\ninstructions asked of them.\\n\\n\\n\\n IV.\\n\\n For the foregoing reasons, the judgment of the district court is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 14\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":88,"cells":{"id":{"kind":"number","value":4579694,"string":"4,579,694"},"name":{"kind":"string","value":"State of SOUTH CAROLINA, Plaintiff - Appellee, v. UNITED STATES of America; United States Department of Energy; Rick Perry, in His Official Capacity as Secretary of Energy; National Nuclear Security Administration; Lisa E. Gordon-Hagerty, in Her Official Capacity as Administrator of the National Nuclear Security Administration and Undersecretary for Nuclear Security, Defendants - Appellants."},"name_abbreviation":{"kind":"string","value":"State of South Carolina v. United States"},"decision_date":{"kind":"string","value":"2019-01-08"},"docket_number":{"kind":"string","value":"18-1684"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Niemeyer, King, Wynn\", \"parties\": \"\", \"opinions\": [{\"author\": \"WYNN, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1684\\n\\n\\nSTATE OF SOUTH CAROLINA,\\n\\n Plaintiff – Appellee,\\n\\nv.\\n\\nUNITED STATES OF AMERICA; UNITED STATES DEPARTMENT OF\\nENERGY; RICK PERRY, in his official capacity as Secretary of Energy;\\nNATIONAL NUCLEAR SECURITY ADMINISTRATION; LISA E. GORDON-\\nHAGERTY, in her official capacity as Administrator of the National Nuclear\\nSecurity Administration and Undersecretary for Nuclear Security,\\n\\n Defendants – Appellants.\\n\\n\\n\\nAppeal from the United States District Court for the District of South Carolina, at Aiken.\\nJ. Michelle Childs, District Judge. (1:18-cv-01431-JMC)\\n\\n\\nArgued: September 27, 2018 Decided: January 8, 2019\\n\\n\\nBefore NIEMEYER, KING, and WYNN, Circuit Judges.\\n\\n\\nVacated and remanded by published opinion. Judge Wynn wrote the opinion, in which\\nJudge Niemeyer and Judge King joined.\\n\\n\\nARGUED: Andrew Alperin Rohrbach, UNITED STATES DEPARTMENT OF\\nJUSTICE, Washington, D.C., for Appellants. Randolph R. Lowell, WILLOUGHBY &\\nHOEFER, PA, Columbia, South Carolina, for Appellee. ON BRIEF: Chad A. Readler,\\nActing Assistant Attorney General, Mark B. Stern, Daniel Tenny, Civil Division,\\n\\fUNITED STATES DEPARTMENT OF JUSTICE, Washington, D.C.; Sherri A. Lydon,\\nUnited States Attorney, OFFICE OF THE UNITED STATES ATTORNEY, Columbia,\\nSouth Carolina, for Appellants.\\n\\n\\n\\n\\n 2\\n\\fWYNN, Circuit Judge:\\n\\n The State of South Carolina brought this action to enjoin the United States of\\n\\nAmerica and other Defendants 1 (collectively, “the United States”) from terminating the\\n\\nconstruction of a mixed-oxide fuel nuclear processing facility located at the Savannah\\n\\nRiver Site in South Carolina. South Carolina alleges that the United States Department\\n\\nof Energy unlawfully failed to (1) prepare a supplemental Environmental Impact\\n\\nStatement analyzing the long-term storage of plutonium in the state; and (2) follow\\n\\nstatutory waiver provisions for terminating construction of the facility. We conclude that\\n\\nSouth Carolina has not established standing to pursue either of these claims.\\n\\nAccordingly, we vacate the preliminary injunction imposed by the district court.\\n\\n I.\\n\\n Following the collapse of the Soviet Union and the end of the Cold War, the\\n\\nUnited States of America and the Russian Federation began a worldwide nuclear\\n\\nnonproliferation effort that included developing plans for the safe disposition of nuclear\\n\\nweapons material. As part of this nonproliferation pact, the Department of Energy began\\n\\nstudying the effects of various nuclear waste storage and disposal strategies. In its initial\\n\\n1996 study, the Department of Energy prepared an Environmental Impact Statement in\\n\\naccordance with Section 4332 of the National Environmental Policy Act (“NEPA”), 42\\n\\n\\n 1\\n The other Defendants are the United States Department of Energy; Rick Perry, in\\nhis official capacity as Secretary of Energy; the National Nuclear Security\\nAdministration; and Lisa E. Gordon-Hagerty, in her official capacity as Administrator of\\nthe National Nuclear Security Administration.\\n\\n\\n 3\\n\\fU.S.C. § 4321 et seq., analyzing the potential environmental consequences associated\\n\\nwith the long-term storage of weapons-grade plutonium and highly enriched uranium\\n\\nprior to disposition. The Environmental Impact Statement addressed storage of these\\n\\nmaterials for a period of up to fifty years.\\n\\n Ultimately, the Department of Energy determined that the best approach to nuclear\\n\\nwaste disposal was a dual strategy involving (1) immobilization of a portion of the\\n\\nsurplus plutonium in glass or ceramic; and (2) irradiation of the remaining plutonium in\\n\\nmixed oxide fuel (the “MOX process”). Both strategies would convert the surplus\\n\\nnuclear material into forms that would meet the National Academy of Science’s Spent\\n\\nFuel Standard, meaning that the material would be “inaccessible and unattractive for\\n\\nweapons” use. J.A. 78.\\n\\n In 1997, the Department of Energy announced its intention to build a new mixed\\n\\noxide fuel fabrication facility (the “MOX facility”) to dispose of some of the nuclear\\n\\nmaterial using the MOX process. Following completion of a supplemental\\n\\nEnvironmental Impact Statement and a Record of Decision in January of 2000, the\\n\\nDepartment of Energy announced that the MOX facility would be located at the\\n\\nSavannah River Site along South Carolina’s border with Georgia. The facility’s original\\n\\nproduction goals included disposition of up to thirty-three metric tons of nuclear material\\n\\nusing the MOX process and immobilization of up to seventeen metric tons of additional\\n\\nnuclear material. As part of its supplemental Environmental Impact Statement, the\\n\\nDepartment of Energy continued to look at the environmental impacts of long-term\\n\\nplutonium storage.\\n\\n 4\\n\\f In 2002, the Department of Energy decided to drop the immobilization portion of\\n\\nthe disposition strategy, leaving the MOX process as the sole plutonium disposal method.\\n\\nThat same year, Congress directed the Secretary of Energy to submit a plan for the\\n\\nconstruction and operation of the MOX facility at the Savannah River site. Pub. L. No.\\n\\n107-314, § 3182 (2002), subsequently codified as 50 U.S.C. § 2566. Congress further\\n\\nauthorized the Secretary to take corrective actions if the construction timetable and\\n\\noperation schedule for the MOX facility were not being met. Additionally, Congress also\\n\\nrequired that in the event the MOX facility failed to achieve its production goals, the\\n\\nDepartment of Energy remove plutonium shipped to South Carolina for processing. See\\n\\n50 U.S.C. § 2566(c), § 2566(e). Finally, as part of its findings, Congress mentioned the\\n\\neconomic benefit that the MOX facility would bring to the State of South Carolina,\\n\\nnoting that the economic benefit would not be fully realized unless the facility was built.\\n\\nSee Pub. L. No. 107-314 at § 3181.\\n\\n Three years later, in 2005, the Department of Energy began transferring plutonium\\n\\nto the Savannah River Site for conversion, and in 2007, construction began on the MOX\\n\\nfacility. The original cost estimate for construction of the facility was $4.8 billion, with\\n\\ncompletion anticipated in 2016. And the original production goal estimate for the facility\\n\\nwas to have thirty-four metric tons of defense plutonium processed no later than January\\n\\n1, 2019. 50 U.S.C. § 2566(a)(2)(B).\\n\\n These original estimates proved grossly inaccurate due to delays and cost overruns\\n\\nin the construction of the MOX facility. The Department of Energy now estimates cost\\n\\n\\n\\n 5\\n\\ffor construction of the facility to be $17.17 billion, with completion now anticipated to be\\n\\nin 2048, over thirty years beyond the original estimated schedule.\\n\\n Since 2014, the Department of Energy has sought to terminate the MOX program\\n\\nand pursue an alternative method of plutonium disposal known as “Dilute and Dispose,”\\n\\nwhich it contends is less costly, faster, and safer. Under the Dilute and Dispose method,\\n\\nnuclear material would be “downblended” with inhibitor materials to reduce the\\n\\nplutonium content to less than ten percent by weight. Upon completion of the\\n\\ndownblending process, the material would then be shipped from the Savannah River Site\\n\\nto the Waste Isolation Pilot Plant near Carlsbad, New Mexico, for permanent disposal.\\n\\n Thus far, Congress has continued to fund construction of the MOX facility and\\n\\nhas, to date, restricted the Department of Energy from utilizing MOX-related\\n\\nappropriations to begin termination of the program. To that end, in 2017, Congress\\n\\nenacted a statute providing that the Secretary of Energy “shall carry out construction and\\n\\nproject support activities relating to the MOX facility.” Pub. L. 115-91, § 3121(a), 131\\n\\nStat. 1283, 1892.\\n\\n However, Section 3121(b) of that statute allows the Secretary of Energy to\\n\\ndiscontinue construction of the MOX facility if certain conditions have been met.\\n\\nSpecifically, the Secretary of Energy must submit to the Congressional defense\\n\\ncommittees:\\n\\n (A) the commitment of the Secretary [of Energy] to remove plutonium\\n intended to be disposed of in the MOX facility from South Carolina\\n and ensure a sustainable future for the Savannah River Site;\\n\\n (B) a certification that―\\n\\n 6\\n\\f (i) an alternative option for carrying out the plutonium disposition\\n program for the same amount of plutonium as the amount of plutonium\\n intended to be disposed of in the MOX facility exists, meeting the\\n requirements of the Business Operating Procedure of the National\\n Nuclear Security Administration entitled “Analysis of Alternatives” and\\n dated March 14, 2016 (BOP-03.07); and\\n\\n (ii) the remaining lifecycle cost, determined in a manner comparable to\\n the cost estimating and assessment best practices of the Government\\n Accountability Office [“GAO”], as found in the document of the\\n Government Accountability Office entitled “GAO Cost Estimating and\\n Assessment Guide” (GAO-09-3SP), for the alternative option would be\\n less than approximately half of the estimated remaining lifecycle costs\\n of the mixed oxide fuel program; and\\n\\n (C) the details of any statutory or regulatory changes necessary to complete\\n the alternative option.\\n\\n§ 3121(b)(1).\\n\\n Additionally, in exercising his authority to discontinue construction of the MOX\\n\\nfacility, the Secretary of Energy\\n\\n (1) shall concurrently submit to the Committees on Appropriations of both\\n Houses of Congress the lifecycle cost estimate used to make the\\n certification under section 3121(b) of such Act; and\\n\\n (2) may not use funds provided for the Project to eliminate such Project\\n until the date that is 30 days after the submission of the lifecycle cost\\n estimate required under paragraph (1).\\n\\nPub. L. No. 115-141, § 309(c), 132 Stat. 348, 530 (2018).\\n\\n Pursuant to these provisions, on May 10, 2018, the Secretary of Energy submitted\\n\\na letter to the Chairman of the House Armed Services Committee that purported to\\n\\nexecute the authority of the Secretary of Energy under Section 3121(b) to discontinue\\n\\nconstruction of the MOX facility. The Secretary of Energy certified, inter alia, that (1)\\n\\n\\n 7\\n\\fthe Department of Energy is committed to removing plutonium from South Carolina; (2)\\n\\nan alternative option for carrying out the plutonium disposition, the Dilute and Dispose\\n\\nmethod, exists and has a lifecycle cost of less than approximately half of the remaining\\n\\nlifecycle cost for the MOX program; (3) the Department of Energy estimated the cost of\\n\\nthe Dilute and Dispose approach in a manner compatible with the best practices of the\\n\\nGAO; and (4) the Department of Energy is committed to ensuring a sustainable future for\\n\\nthe Savannah River Site. The Secretary of Energy further reported that the Department\\n\\nof Energy expected the total cost of disposition via the Dilute and Dispose method to be\\n\\n$19.9 billion, compared to $49.4 billion for the total cost of construction of the MOX\\n\\nfacility and conversion of all the plutonium into MOX fuel.\\n\\n In accordance with the Secretary of Energy’s letter, the Department of Energy and\\n\\nthe National Nuclear Security Administration issued a Partial Stop Work Order on May\\n\\n14, 2018, ending all new contracts and hiring related to the MOX program. The\\n\\nDepartment of Energy further indicated its intent to issue a Full Stop Work Order and\\n\\nbegin winding down the MOX program, including terminating employees currently\\n\\nworking on the project, on or about June 11, 2018.\\n\\n On May 25, 2018, before the Department of Energy issued a full stop work order,\\n\\nSouth Carolina brought this action in the United States District Court for the District of\\n\\nSouth Carolina and moved for a preliminary injunction barring the federal government\\n\\nfrom terminating the MOX program. In its complaint, South Carolina asserted that the\\n\\nUnited States (1) violated NEPA by failing to prepare a supplemental Environmental\\n\\nImpact Statement covering a period of more than fifty years and (2) failed to satisfy\\n\\n 8\\n\\fSection 3121(b) because of the alleged insufficiency of the Secretary of Energy’s\\n\\ncertifications. 2\\n\\n On June 7, 2018, the district court granted South Carolina’s motion for\\n\\npreliminary injunction. The district court first found that South Carolina had standing\\n\\ndue to environmental risks associated with long-term storage at the Savannah River Site,\\n\\nwhich abuts property owned by South Carolina. As to the merits, the district court held,\\n\\nin pertinent part, that South Carolina was likely to succeed on the merits of its NEPA\\n\\nclaim and its claim that the Secretary of Energy’s certifications were insufficient. The\\n\\ndistrict court further found that South Carolina would be irreparably harmed absent a\\n\\npreliminary injunction and that the balance of equities tilted in South Carolina’s favor.\\n\\nThus, the district court enjoined the federal government from ceasing construction of the\\n\\nMOX facility and issuing the full stop work order. The United States timely appealed.\\n\\n After careful review, we dispositively hold that South Carolina failed to establish\\n\\nstanding and therefore we do not reach the district court’s determination on the merits of\\n\\nthis matter.\\n\\n\\n\\n\\n 2\\n South Carolina further claimed that the United States violated 50 U.S.C. § 2567\\nby failing to consult with the governor before deciding to terminate the MOX facility.\\nThe district court held that South Carolina failed to establish that that claim was likely to\\nsucceed on the merits, and therefore that claim is not before this Court.\\n\\n\\n 9\\n\\f II.\\n\\n A.\\n\\n On appeal, the United States contends that the district court erred in concluding\\n\\nthat South Carolina established standing to pursue the two claims that serve as the basis\\n\\nof the district court’s preliminary injunction order—the NEPA claim and the claim\\n\\npremised on the alleged insufficiency of the Secretary’s certifications. The standing\\n\\ndoctrine derives from “the Constitution’s limitation on Article III courts’ power to\\n\\nadjudicate ‘cases and controversies.’” Frank Krasner Enters. v. Montgomery Cty., 401\\n\\nF.3d 230, 234 (4th Cir. 2005) (quoting Allen v. Wright, 468 U.S. 737, 750–51 (1984),\\n\\nabrogated on other grounds by Lexmark Intern., Inc. v. Static Control Components, Inc.,\\n\\n572 U.S. 118 (2014)). Standing implicates the court’s subject matter jurisdiction. Long\\n\\nTerm Care Partners, LLC v. United States, 516 F.3d 225, 230 (4th Cir. 2008).\\n\\n Here, South Carolina, as plaintiff, bears the burden of establishing standing to\\n\\nassert each of its claims. See id.; see also Lewis v. Casey, 518 U.S. 343, 359 n.6 (1996)\\n\\n(“[A] plaintiff who has been subject to injurious conduct of one kind [does not] possess\\n\\nby virtue of that injury the necessary stake in litigating conduct of another kind, although\\n\\nsimilar, to which he has not been subject.” (internal quotation marks omitted)). We\\n\\nreview the question of whether South Carolina possesses standing de novo. Frank\\n\\nKrasner Enters., 401 F.3d at 234.\\n\\n To establish Article III standing, “a plaintiff must show (1) it has suffered an\\n\\n‘injury in fact’ that is (a) concrete and particularized and (b) actual or imminent, not\\n\\nconjectural or hypothetical; (2) the injury is fairly traceable to the challenged action of\\n\\n 10\\n\\fthe defendant; and (3) it is likely, as opposed to merely speculative, that the injury will be\\n\\nredressed by a favorable decision.” Friends of the Earth, Inc. v. Laidlaw Envtl. Servs.\\n\\n(TOC), Inc., 528 U.S. 167, 180–81 (2000). The United States contends South Carolina\\n\\nfailed to show it has suffered an injury-in-fact sufficient to give rise to Article III\\n\\nstanding.\\n\\n To satisfy the injury-in-fact requirement, a plaintiff must establish a “realistic\\n\\ndanger of sustaining a direct injury.” Peterson v. Nat’l Telcoms. & Info. Admin., 478\\n\\nF.3d 626, 632 (4th Cir. 2007) (quoting Babbitt v. United Farm Workers Nat’l Union, 442\\n\\nU.S. 289, 298 (1979)). “[W]hile it is true ‘that threatened rather than actual injury can\\n\\nsatisfy Article III standing requirements,’ . . . not all threatened injuries constitute an\\n\\ninjury-in-fact.” Beck v. McDonald, 848 F.3d 262, 271 (4th Cir. 2017) (quoting Friends of\\n\\nthe Earth, Inc. v. Gaston Copper Recycling Corp., 204 F.3d 149, 160 (4th Cir. 2000) (en\\n\\nbanc)). “Rather, as the Supreme Court has ‘emphasized repeatedly,’ an injury-in-fact\\n\\n‘must be concrete in both a qualitative and temporal sense.’” Id. (quoting Whitmore v.\\n\\nArkansas, 495 U.S. 149, 155 (1990)). The requirement that an alleged injury be palpable\\n\\nand imminent ensures that the injury “is not too speculative for Article III purposes.” Id.\\n\\n(quoting Lujan v. Defenders of Wildlife, 504 U.S. 555, 564–65 n.2 (1992)).\\n\\n On appeal, South Carolina contends that it has suffered an injury-in-fact sufficient\\n\\nto support standing because “[South Carolina] is harmed by being rendered the\\n\\npermanent repository of weapons-grade plutonium as a result of [the Department of\\n\\nEnergy’s] decision to terminate the MOX Facility without first complying with NEPA or\\n\\nfollowing the congressional mandates of § 3121.” Appellee’s Br. at 15–16. According to\\n\\n 11\\n\\fSouth Carolina, this “results in increased radiation exposure to the public, increased risks\\n\\nof nuclear-related accidents, and an increased threat of action by rogue states or terrorists\\n\\nseeking to acquire weapons-grade plutonium.” Id. at 14. But this alleged injury is too\\n\\nspeculative and thus, does not give rise to a concrete injury-in-fact sufficient to support\\n\\neither of South Carolina’s claims.\\n\\n The Supreme Court has repeatedly held that an alleged harm is too “speculative”\\n\\nto support Article III standing when the harm lies at the end of a “highly attenuated chain\\n\\nof possibilities.” Clapper v. Amnesty Int’l USA, 568 U.S. 398, 410 (2013); see also, e.g.,\\n\\nBeck, 848 F.3d at 275 (holding that plaintiffs, who received treatment at a medical center\\n\\nthat suffered a data breach and alleged that they were at risk of experiencing identity\\n\\ntheft, failed to establish standing because their theory of injury rested on an “attenuated\\n\\nchain of possibilities”).\\n\\n Illustratively in Clapper, the Supreme Court considered a challenge to Section 702\\n\\nof the Foreign Intelligence Surveillance Act, which “authoriz[es] the surveillance of\\n\\nindividuals who are not ‘United States persons’ and are reasonably believed to be located\\n\\noutside the United States.” 568 U.S. at 401. The plaintiffs—a group of “attorneys and\\n\\nhuman rights, labor, legal, and media organizations”—alleged that their work demanded\\n\\nthat they “engage in sensitive international communication with individuals who they\\n\\nbelieve are likely targets of surveillance under” Section 702, rendering it reasonably\\n\\nlikely that the government would target and intercept the plaintiffs’ communications. Id.\\n\\nat 401, 406.\\n\\n\\n\\n 12\\n\\f The Supreme Court held that the plaintiffs failed to establish a concrete injury-in-\\n\\nfact based on the possibility that their communications would be intercepted, explaining\\n\\nthat a series of hypothetical events would have to occur before the government would\\n\\nintercept any particular plaintiff’s communications. Id. at 1148–50. The Court held that\\n\\namong other steps, the government would have to decide to invoke its Section 702\\n\\nauthority to target a non-U.S. person with whom a plaintiff communicated, a panel of\\n\\nfederal judges would have to “conclude that the Government’s proposed surveillance\\n\\nprocedures satisfy [the statute’s] many safeguards and are consistent with the Fourth\\n\\nAmendment,” and the government would have to succeed in intercepting one of the\\n\\ntarget’s communications with the plaintiff. Id. Thus, the Court held that that the “highly\\n\\nattenuated chain of possibilities, d[id] not satisfy the requirement that threatened injury\\n\\nmust be certainly impending.” Id. at 1148 (citation omitted).\\n\\n Applying Clapper, this Court reached a similar conclusion in Beck, in which a\\n\\nputative class of veterans who received medical treatment at a veterans’ medical center\\n\\nalleged that they had been injured when two sets of records were stolen from the center.\\n\\n848 F.3d at 262, 267. Although none of the named plaintiffs alleged any actual or\\n\\nattempted misuse of the personal information contained in their stolen records, they\\n\\nalleged that they suffered cognizable injuries-in-fact because they faced “(1) [an]\\n\\nincreased risk of future identity theft, and (2) the costs of protecting against the same.”\\n\\nId. at 273. We concluded that both alleged injuries were too speculative to confer\\n\\nstanding. Id. at 275–77. As to the alleged increased risk of identity theft, in particular,\\n\\nwe explained that plaintiffs’ theory of injury required us to “assume that the thie[ves]\\n\\n 13\\n\\ftargeted the stolen items for the personal information they contained” and that the thieves\\n\\nwould “then select, from thousands of others, the personal information of the named\\n\\nplaintiffs, and attempt successfully to use that information to steal their identities.” Id. at\\n\\n275. “This ‘attenuated chain’ cannot confer standing,” we held. Id. We likewise\\n\\nrejected the plaintiffs’ costs of mitigation theory of standing as a “repackaged” version of\\n\\ntheir first theory of standing, amounting to an effort to recoup “costs they incurred in\\n\\nresponse to a speculative threat.” Id. at 276 (emphasis added) (quoting Clapper, 568\\n\\nU.S. at 416).\\n\\n Here, South Carolina’s theory of standing—that it will become “the permanent\\n\\nrepository of weapons-grade plutonium” and all the environmental, health, and safety\\n\\nrisks that entails, Appellee’s Br. at 15–16—rests on a similarly “highly attenuated chain\\n\\nof possibilities,” Clapper, 568 U.S. at 410. Between now and 2046—when the analysis\\n\\nin the current Environmental Impact Statement governing the risks associated with long-\\n\\nterm storage of weapons-grade nuclear material at the Savannah River Site expires—the\\n\\nDepartment of Energy has twenty-eight years to identify an alternative method for\\n\\ndisposing of the nuclear material or otherwise removing it from South Carolina. The\\n\\nSecretary of Energy already has certified that one potential alternative to the MOX\\n\\nprogram exists, the Dilute and Dispose method. And the Department of Energy may\\n\\nidentify and develop other methods during that twenty-eight-year period. Or the\\n\\nDepartment of Energy may decide to transfer the plutonium out of South Carolina to\\n\\nanother location.\\n\\n\\n\\n 14\\n\\f Furthermore, Congress has put in place contingency plans for the removal of\\n\\nplutonium shipped to the Savannah River Site to forestall the indefinite storage of\\n\\nplutonium in South Carolina. A federal statute requires that, by 2022, all additional\\n\\nplutonium transferred into South Carolina to the MOX facility, but not processed, must\\n\\nbe removed. 50 U.S.C. § 2566(c)(2). Notably, because the Department of Energy\\n\\nalready has failed to meet certain statutory time limits for disposing of nuclear material at\\n\\nthe site, South Carolina has successfully brought suit pursuant to the Administrative\\n\\nProcedure Act to enforce these congressionally mandated deadlines via a mandatory\\n\\ninjunction. See id. § 2566(c)(1) (requiring removal of one metric ton of plutonium no\\n\\nlater than January 1, 2016); South Carolina v. United States, 243 F. Supp. 3d 673 (D.S.C.\\n\\n2017), aff’d, 907 F.3d 742 (4th Cir. 2018) (ordering the Department of Energy to remove\\n\\none metric ton of plutonium within two years).\\n\\n In sum, for South Carolina’s alleged injury—becoming “the permanent repository\\n\\nof weapons-grade plutonium,” Appellee’s Br. at 15–16—to occur: (1) the proposed\\n\\nDilute and Dispose method must fail; (2) the Department of Energy must fail to identify\\n\\nan alternative method for disposing of the nuclear material; and (3) the Department of\\n\\nEnergy must breach its statutory obligation to remove the nuclear material from South\\n\\nCarolina, Congress must repeal that obligation, or the courts must refuse to enforce that\\n\\nobligation. At this juncture, before the Department of Energy has even had an\\n\\nopportunity to finish analyzing the Dilute and Dispose method, this “chain of\\n\\npossibilities” is too speculative to give rise to a sufficiently concrete injury-in-fact.\\n\\n\\n\\n 15\\n\\f That several of the links in this “chain of possibilities” the State’s standing theory\\n\\ncontemplates require our coordinate branches to either breach or abandon their existing\\n\\ncommitments to ensure timely removal of the nuclear material at the Savannah River Site\\n\\nfurther weighs against treating the South Carolina’s alleged injury as conferring standing.\\n\\nAs Clapper recognized, the standing doctrine is “built on separation-of-powers\\n\\nprinciples” and “serves to prevent the judicial process from being used to usurp the\\n\\npowers of the political branches.” 568 U.S. at 408 (citations omitted); see also Allen v.\\n\\nWright, 468 U.S. at 752 (1984) (“[Article] III standing is built on a single basic idea—the\\n\\nidea of separation of powers.”). To confer standing on South Carolina at this juncture\\n\\nbased on an alleged injury—becoming the permanent repository of nuclear material—that\\n\\nthe political branches already have made written and legally binding commitments to\\n\\nforestall would improperly “usurp the powers of the political branches.” Clapper, 568\\n\\nU.S. at 408.\\n\\n The “highly attenuated chain of possibilities” that must occur for South Carolina\\n\\nto become the permanent repository of nuclear material also sets this case apart from this\\n\\nCourt’s decision in Hodges v. Abraham, 300 F.3d 432 (4th Cir. 2002), upon which South\\n\\nCarolina principally relies.\\n\\n Like the instant case, Hodges dealt with the storage of plutonium at the Savannah\\n\\nRiver Site. Id. at 436. In 2002, the Department of Energy issued a Record of Decision\\n\\nauthorizing the immediate shipment of six metric tons of plutonium from a nuclear\\n\\nfacility in Colorado to the Savannah River Site. Id. The Governor of South Carolina\\n\\nsought to enjoin shipment of the plutonium into South Carolina, alleging that the\\n\\n 16\\n\\fDepartment of Energy’s existing Environmental Impact Statement, and its supplemental\\n\\nanalyses to the Environmental Impact Statement, related to storage of plutonium at the\\n\\nSavannah River Site violated NEPA in several ways. Id. at 445. This Court held that the\\n\\nGovernor adequately alleged an injury-in-fact to support his NEPA claims because the\\n\\nSouth Carolina owned property adjacent to the Savannah River Site. Id. “[T]he\\n\\nGovernor, in his official capacity, is essentially a neighboring landowner, whose property\\n\\nis at risk of environmental damage” as a result of the Department of Energy’s shipment\\n\\nof plutonium to the Savannah River Site and storage of that plutonium there, we\\n\\nexplained. Id.\\n\\n Here, unlike in Hodges, South Carolina does not argue that its injury, as a\\n\\nneighboring landowner, is attributable to the current storage of nuclear material at the\\n\\nSavannah River Site or the inadequacy of the Environmental Impact Statement pursuant\\n\\nto which the nuclear material is currently stored—a question that Hodges already\\n\\nresolved in the federal government’s favor. Id. at 446–49. Rather, South Carolina\\n\\ncontends it is injured because the termination of the MOX program renders it the\\n\\npermanent repository of the nuclear material when the Department of Energy has not\\n\\nissued an Environmental Impact Statement analyzing the environmental impact of the\\n\\nstorage of the material at the Savannah River Site beyond the year 2046, the year when\\n\\nthe existing Environmental Impact Statement’s analysis terminates, or, allegedly, satisfies\\n\\nits statutory obligations in terminating the MOX program. There is a meaningful\\n\\ndistinction between the alleged immediate environmental injuries associated with storing\\n\\nplutonium at the Savannah River Site, which were at issue in Hodges, and the alleged\\n\\n 17\\n\\ffuture adverse environmental impacts on South Carolina as a neighboring landowner if\\n\\nthe Department of Energy continues to store the plutonium at the Savannah River Site\\n\\ndecades in the future. That distinction is particularly meaningful because, as explained\\n\\nabove, numerous contingencies must occur in order for the plutonium to remain in South\\n\\nCarolina after 2046, the year when South Carolina’s alleged injury will mature.\\n\\n In sum, the single theory of injury3 that South Carolina relies on to support both of\\n\\nits claims is too speculative at this juncture to support Article III standing. The district\\n\\ncourt, therefore, was without jurisdiction to enter its preliminary injunction premised on\\n\\nthose two claims.\\n\\n B.\\n\\n For reasons similar to those that lead us to find that South Carolina lacks standing,\\n\\nwe also find that the two claims at issue fail on ripeness grounds. Like standing, the\\n\\nripeness doctrine “originates in the ‘case or controversy’ constraint of Article III.”\\n\\nScoggins v. Lee’s Crossing Homeowners Ass’n, 718 F.3d 262, 269 (4th Cir. 2013)\\n\\n(citations omitted). “Analyzing ripeness is similar to determining whether a party has\\n\\nstanding.” Miller v. Brown, 462 F.3d 312, 319 (4th Cir. 2006). “Although the phrasing\\n\\nmakes the questions of who may sue and when they sue seem distinct, in practice there is\\n\\nan obvious overlap between the doctrines of standing and ripeness.” Id. (quoting Erwin\\n\\n 3\\n Because South Carolina has advanced only one theory of injury to support the\\ntwo claims before this Court—that South Carolina is harmed by becoming the permanent\\nrepository of weapons-grade nuclear material—we cannot and do not take any position\\non whether other theories of injury would presently confer standing on South Carolina to\\nsupport either of the two claims before us on appeal.\\n\\n\\n 18\\n\\fChemerinsky, Federal Jurisdiction § 2.4 (4th ed. 2003). As with standing, ripeness is a\\n\\nquestion of subject matter jurisdiction. See Sansotta v. Town of Nags Head, 724 F.3d\\n\\n533, 548 (4th Cir. 2013) (citation omitted).\\n\\n The question of whether a claim is ripe “turns on the ‘fitness of the issues for\\n\\njudicial decision’ and the ‘hardship to the parties of withholding court consideration.’”\\n\\nPac. Gas & Elec. Co. v. State Energy Res. Conservation & Dev. Comm’n, 461 U.S. 190,\\n\\n201 (1983) (citation omitted). In the context of claims challenging agency actions, like\\n\\nthe two at issue, the purpose of the ripeness doctrine is “to prevent the courts, through\\n\\navoidance of premature adjudication, from entangling themselves in abstract\\n\\ndisagreements over administrative policies, and also to protect the agencies from judicial\\n\\ninterference until an administrative decision has been formalized and its effects felt in a\\n\\nconcrete way by the challenging parties.” Abbott Labs. v. Gardner, 387 U.S. 136, 148–\\n\\n49 (1967), abrogated on other grounds by Califano v. Sanders, 430 U.S. 99 (1977).\\n\\n To be fit for judicial review, a controversy should be presented in a “clean-cut and\\n\\nconcrete form.” Miller, 462 F.3d at 319 (citation omitted). This occurs when the action\\n\\nis “final and not dependent on future uncertainties or intervening agency rulings.”\\n\\nFranks v. Ross, 313 F.3d 184, 195 (4th Cir. 2002) (citation omitted). On the other hand,\\n\\njust as a plaintiff cannot assert standing based on an alleged injury that lies at the end of a\\n\\n“highly attenuated chain of possibilities,” Clapper, 568 U.S. at 410, a plaintiff’s claim is\\n\\nnot ripe for judicial review “if it rests upon contingent future events that may not occur as\\n\\nanticipated, or indeed may not occur at all.” Scoggins, 718 F.3d at 270 (quoting Texas v.\\n\\nUnited States, 523 U.S. 296, 300 (1998)).\\n\\n 19\\n\\f The two claims that South Carolina advances before this Court rest on the premise\\n\\nthat South Carolina will be the permanent repository of the weapons-grade nuclear\\n\\nmaterial currently stored at the Savannah River Site. But, numerous “contingent future\\n\\nevents,” id., must occur before South Carolina becomes the permanent repository of the\\n\\nnuclear material, see supra Part II.A. In particular, the Dilute and Dispose method must\\n\\nprove unworkable. The Department of Energy must fail to identify an alternative method\\n\\nof disposal and breach its commitment to dispose of the waste. And Congress or the\\n\\ncourts must set aside or refuse to enforce the statutory mechanisms currently in place to\\n\\nensure timely removal of the nuclear material. All of these “future uncertainties,”\\n\\nFranks, 313 F.3d at 195, lead us to conclude that the two claims at issue are not ripe for\\n\\nreview at this time—at least as presented by South Carolina. Accordingly, the ripeness\\n\\ndoctrine provides an additional basis for our holding that the district court was without\\n\\njurisdiction to enter the preliminary injunction.\\n\\n III.\\n\\n In sum, the only theory of injury advanced by South Carolina—that South\\n\\nCarolina will be the permanent repository of the nuclear material currently stored at the\\n\\nSavannah River Site—rests upon a “highly attenuated chain of possibilities,” Clapper,\\n\\n568 U.S. at 410, and “contingent future events that may not occur as anticipated, or\\n\\nindeed may not occur at all.” Scoggins, 718 F.3d at 270. In such circumstances, we must\\n\\nconclude that South Carolina lacks Article III standing to advance the two claims that\\n\\nserve as the basis of the district court’s injunction and that those two claims are not ripe\\n\\nfor review.\\n\\n 20\\n\\f That the two claims are not currently justiciable does not mean that they never will\\n\\nbe so. If uncertainty as to several links in the chain of possibilities is resolved, then\\n\\nSouth Carolina’s alleged injury may move from the speculative to the concrete, and\\n\\ntherefore the two claims also may become ripe for review. But until that uncertainty is\\n\\nlifted, the Constitution demands that we withhold judicial review.\\n\\n Accordingly, we vacate the preliminary injunction imposed by the district court\\n\\nand remand the case for further proceedings not inconsistent with this opinion.\\n\\n\\n\\n VACATED AND REMANDED\\n\\n\\n\\n\\n 21\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4356947/\", \"author_raw\": \"WYNN, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"NIEMEYER"},"judge2":{"kind":"string","value":"KING"},"judge3":{"kind":"string","value":"WYNN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4579694/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: State of SOUTH CAROLINA, Plaintiff - Appellee, v. UNITED STATES of America; United States Department of Energy; Rick Perry, in His Official Capacity as Secretary of Energy; National Nuclear Security Administration; Lisa E. Gordon-Hagerty, in Her Official Capacity as Administrator of the National Nuclear Security Administration and Undersecretary for Nuclear Security, Defendants - Appellants.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-08\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1684\n\n\nSTATE OF SOUTH CAROLINA,\n\n Plaintiff – Appellee,\n\nv.\n\nUNITED STATES OF AMERICA; UNITED STATES DEPARTMENT OF\nENERGY; RICK PERRY, in his official capacity as Secretary of Energy;\nNATIONAL NUCLEAR SECURITY ADMINISTRATION; LISA E. GORDON-\nHAGERTY, in her official capacity as Administrator of the National Nuclear\nSecurity Administration and Undersecretary for Nuclear Security,\n\n Defendants – Appellants.\n\n\n\nAppeal from the United States District Court for the District of South Carolina, at Aiken.\nJ. Michelle Childs, District Judge. (1:18-cv-01431-JMC)\n\n\nArgued: September 27, 2018 Decided: January 8, 2019\n\n\nBefore NIEMEYER, KING, and WYNN, Circuit Judges.\n\n\nVacated and remanded by published opinion. Judge Wynn wrote the opinion, in which\nJudge Niemeyer and Judge King joined.\n\n\nARGUED: Andrew Alperin Rohrbach, UNITED STATES DEPARTMENT OF\nJUSTICE, Washington, D.C., for Appellants. Randolph R. Lowell, WILLOUGHBY &\nHOEFER, PA, Columbia, South Carolina, for Appellee. ON BRIEF: Chad A. Readler,\nActing Assistant Attorney General, Mark B. Stern, Daniel Tenny, Civil Division,\n\fUNITED STATES DEPARTMENT OF JUSTICE, Washington, D.C.; Sherri A. Lydon,\nUnited States Attorney, OFFICE OF THE UNITED STATES ATTORNEY, Columbia,\nSouth Carolina, for Appellants.\n\n\n\n\n 2\n\fWYNN, Circuit Judge:\n\n The State of South Carolina brought this action to enjoin the United States of\n\nAmerica and other Defendants 1 (collectively, “the United States”) from terminating the\n\nconstruction of a mixed-oxide fuel nuclear processing facility located at the Savannah\n\nRiver Site in South Carolina. South Carolina alleges that the United States Department\n\nof Energy unlawfully failed to (1) prepare a supplemental Environmental Impact\n\nStatement analyzing the long-term storage of plutonium in the state; and (2) follow\n\nstatutory waiver provisions for terminating construction of the facility. We conclude that\n\nSouth Carolina has not established standing to pursue either of these claims.\n\nAccordingly, we vacate the preliminary injunction imposed by the district court.\n\n I.\n\n Following the collapse of the Soviet Union and the end of the Cold War, the\n\nUnited States of America and the Russian Federation began a worldwide nuclear\n\nnonproliferation effort that included developing plans for the safe disposition of nuclear\n\nweapons material. As part of this nonproliferation pact, the Department of Energy began\n\nstudying the effects of various nuclear waste storage and disposal strategies. In its initial\n\n1996 study, the Department of Energy prepared an Environmental Impact Statement in\n\naccordance with Section 4332 of the National Environmental Policy Act (“NEPA”), 42\n\n\n 1\n The other Defendants are the United States Department of Energy; Rick Perry, in\nhis official capacity as Secretary of Energy; the National Nuclear Security\nAdministration; and Lisa E. Gordon-Hagerty, in her official capacity as Administrator of\nthe National Nuclear Security Administration.\n\n\n 3\n\fU.S.C. § 4321 et seq., analyzing the potential environmental consequences associated\n\nwith the long-term storage of weapons-grade plutonium and highly enriched uranium\n\nprior to disposition. The Environmental Impact Statement addressed storage of these\n\nmaterials for a period of up to fifty years.\n\n Ultimately, the Department of Energy determined that the best approach to nuclear\n\nwaste disposal was a dual strategy involving (1) immobilization of a portion of the\n\nsurplus plutonium in glass or ceramic; and (2) irradiation of the remaining plutonium in\n\nmixed oxide fuel (the “MOX process”). Both strategies would convert the surplus\n\nnuclear material into forms that would meet the National Academy of Science’s Spent\n\nFuel Standard, meaning that the material would be “inaccessible and unattractive for\n\nweapons” use. J.A. 78.\n\n In 1997, the Department of Energy announced its intention to build a new mixed\n\noxide fuel fabrication facility (the “MOX facility”) to dispose of some of the nuclear\n\nmaterial using the MOX process. Following completion of a supplemental\n\nEnvironmental Impact Statement and a Record of Decision in January of 2000, the\n\nDepartment of Energy announced that the MOX facility would be located at the\n\nSavannah River Site along South Carolina’s border with Georgia. The facility’s original\n\nproduction goals included disposition of up to thirty-three metric tons of nuclear material\n\nusing the MOX process and immobilization of up to seventeen metric tons of additional\n\nnuclear material. As part of its supplemental Environmental Impact Statement, the\n\nDepartment of Energy continued to look at the environmental impacts of long-term\n\nplutonium storage.\n\n 4\n\f In 2002, the Department of Energy decided to drop the immobilization portion of\n\nthe disposition strategy, leaving the MOX process as the sole plutonium disposal method.\n\nThat same year, Congress directed the Secretary of Energy to submit a plan for the\n\nconstruction and operation of the MOX facility at the Savannah River site. Pub. L. No.\n\n107-314, § 3182 (2002), subsequently codified as 50 U.S.C. § 2566. Congress further\n\nauthorized the Secretary to take corrective actions if the construction timetable and\n\noperation schedule for the MOX facility were not being met. Additionally, Congress also\n\nrequired that in the event the MOX facility failed to achieve its production goals, the\n\nDepartment of Energy remove plutonium shipped to South Carolina for processing. See\n\n50 U.S.C. § 2566(c), § 2566(e). Finally, as part of its findings, Congress mentioned the\n\neconomic benefit that the MOX facility would bring to the State of South Carolina,\n\nnoting that the economic benefit would not be fully realized unless the facility was built.\n\nSee Pub. L. No. 107-314 at § 3181.\n\n Three years later, in 2005, the Department of Energy began transferring plutonium\n\nto the Savannah River Site for conversion, and in 2007, construction began on the MOX\n\nfacility. The original cost estimate for construction of the facility was $4.8 billion, with\n\ncompletion anticipated in 2016. And the original production goal estimate for the facility\n\nwas to have thirty-four metric tons of defense plutonium processed no later than January\n\n1, 2019. 50 U.S.C. § 2566(a)(2)(B).\n\n These original estimates proved grossly inaccurate due to delays and cost overruns\n\nin the construction of the MOX facility. The Department of Energy now estimates cost\n\n\n\n 5\n\ffor construction of the facility to be $17.17 billion, with completion now anticipated to be\n\nin 2048, over thirty years beyond the original estimated schedule.\n\n Since 2014, the Department of Energy has sought to terminate the MOX program\n\nand pursue an alternative method of plutonium disposal known as “Dilute and Dispose,”\n\nwhich it contends is less costly, faster, and safer. Under the Dilute and Dispose method,\n\nnuclear material would be “downblended” with inhibitor materials to reduce the\n\nplutonium content to less than ten percent by weight. Upon completion of the\n\ndownblending process, the material would then be shipped from the Savannah River Site\n\nto the Waste Isolation Pilot Plant near Carlsbad, New Mexico, for permanent disposal.\n\n Thus far, Congress has continued to fund construction of the MOX facility and\n\nhas, to date, restricted the Department of Energy from utilizing MOX-related\n\nappropriations to begin termination of the program. To that end, in 2017, Congress\n\nenacted a statute providing that the Secretary of Energy “shall carry out construction and\n\nproject support activities relating to the MOX facility.” Pub. L. 115-91, § 3121(a), 131\n\nStat. 1283, 1892.\n\n However, Section 3121(b) of that statute allows the Secretary of Energy to\n\ndiscontinue construction of the MOX facility if certain conditions have been met.\n\nSpecifically, the Secretary of Energy must submit to the Congressional defense\n\ncommittees:\n\n (A) the commitment of the Secretary [of Energy] to remove plutonium\n intended to be disposed of in the MOX facility from South Carolina\n and ensure a sustainable future for the Savannah River Site;\n\n (B) a certification that―\n\n 6\n\f (i) an alternative option for carrying out the plutonium disposition\n program for the same amount of plutonium as the amount of plutonium\n intended to be disposed of in the MOX facility exists, meeting the\n requirements of the Business Operating Procedure of the National\n Nuclear Security Administration entitled “Analysis of Alternatives” and\n dated March 14, 2016 (BOP-03.07); and\n\n (ii) the remaining lifecycle cost, determined in a manner comparable to\n the cost estimating and assessment best practices of the Government\n Accountability Office [“GAO”], as found in the document of the\n Government Accountability Office entitled “GAO Cost Estimating and\n Assessment Guide” (GAO-09-3SP), for the alternative option would be\n less than approximately half of the estimated remaining lifecycle costs\n of the mixed oxide fuel program; and\n\n (C) the details of any statutory or regulatory changes necessary to complete\n the alternative option.\n\n§ 3121(b)(1).\n\n Additionally, in exercising his authority to discontinue construction of the MOX\n\nfacility, the Secretary of Energy\n\n (1) shall concurrently submit to the Committees on Appropriations of both\n Houses of Congress the lifecycle cost estimate used to make the\n certification under section 3121(b) of such Act; and\n\n (2) may not use funds provided for the Project to eliminate such Project\n until the date that is 30 days after the submission of the lifecycle cost\n estimate required under paragraph (1).\n\nPub. L. No. 115-141, § 309(c), 132 Stat. 348, 530 (2018).\n\n Pursuant to these provisions, on May 10, 2018, the Secretary of Energy submitted\n\na letter to the Chairman of the House Armed Services Committee that purported to\n\nexecute the authority of the Secretary of Energy under Section 3121(b) to discontinue\n\nconstruction of the MOX facility. The Secretary of Energy certified, inter alia, that (1)\n\n\n 7\n\fthe Department of Energy is committed to removing plutonium from South Carolina; (2)\n\nan alternative option for carrying out the plutonium disposition, the Dilute and Dispose\n\nmethod, exists and has a lifecycle cost of less than approximately half of the remaining\n\nlifecycle cost for the MOX program; (3) the Department of Energy estimated the cost of\n\nthe Dilute and Dispose approach in a manner compatible with the best practices of the\n\nGAO; and (4) the Department of Energy is committed to ensuring a sustainable future for\n\nthe Savannah River Site. The Secretary of Energy further reported that the Department\n\nof Energy expected the total cost of disposition via the Dilute and Dispose method to be\n\n$19.9 billion, compared to $49.4 billion for the total cost of construction of the MOX\n\nfacility and conversion of all the plutonium into MOX fuel.\n\n In accordance with the Secretary of Energy’s letter, the Department of Energy and\n\nthe National Nuclear Security Administration issued a Partial Stop Work Order on May\n\n14, 2018, ending all new contracts and hiring related to the MOX program. The\n\nDepartment of Energy further indicated its intent to issue a Full Stop Work Order and\n\nbegin winding down the MOX program, including terminating employees currently\n\nworking on the project, on or about June 11, 2018.\n\n On May 25, 2018, before the Department of Energy issued a full stop work order,\n\nSouth Carolina brought this action in the United States District Court for the District of\n\nSouth Carolina and moved for a preliminary injunction barring the federal government\n\nfrom terminating the MOX program. In its complaint, South Carolina asserted that the\n\nUnited States (1) violated NEPA by failing to prepare a supplemental Environmental\n\nImpact Statement covering a period of more than fifty years and (2) failed to satisfy\n\n 8\n\fSection 3121(b) because of the alleged insufficiency of the Secretary of Energy’s\n\ncertifications. 2\n\n On June 7, 2018, the district court granted South Carolina’s motion for\n\npreliminary injunction. The district court first found that South Carolina had standing\n\ndue to environmental risks associated with long-term storage at the Savannah River Site,\n\nwhich abuts property owned by South Carolina. As to the merits, the district court held,\n\nin pertinent part, that South Carolina was likely to succeed on the merits of its NEPA\n\nclaim and its claim that the Secretary of Energy’s certifications were insufficient. The\n\ndistrict court further found that South Carolina would be irreparably harmed absent a\n\npreliminary injunction and that the balance of equities tilted in South Carolina’s favor.\n\nThus, the district court enjoined the federal government from ceasing construction of the\n\nMOX facility and issuing the full stop work order. The United States timely appealed.\n\n After careful review, we dispositively hold that South Carolina failed to establish\n\nstanding and therefore we do not reach the district court’s determination on the merits of\n\nthis matter.\n\n\n\n\n 2\n South Carolina further claimed that the United States violated 50 U.S.C. § 2567\nby failing to consult with the governor before deciding to terminate the MOX facility.\nThe district court held that South Carolina failed to establish that that claim was likely to\nsucceed on the merits, and therefore that claim is not before this Court.\n\n\n 9\n\f II.\n\n A.\n\n On appeal, the United States contends that the district court erred in concluding\n\nthat South Carolina established standing to pursue the two claims that serve as the basis\n\nof the district court’s preliminary injunction order—the NEPA claim and the claim\n\npremised on the alleged insufficiency of the Secretary’s certifications. The standing\n\ndoctrine derives from “the Constitution’s limitation on Article III courts’ power to\n\nadjudicate ‘cases and controversies.’” Frank Krasner Enters. v. Montgomery Cty., 401\n\nF.3d 230, 234 (4th Cir. 2005) (quoting Allen v. Wright, 468 U.S. 737, 750–51 (1984),\n\nabrogated on other grounds by Lexmark Intern., Inc. v. Static Control Components, Inc.,\n\n572 U.S. 118 (2014)). Standing implicates the court’s subject matter jurisdiction. Long\n\nTerm Care Partners, LLC v. United States, 516 F.3d 225, 230 (4th Cir. 2008).\n\n Here, South Carolina, as plaintiff, bears the burden of establishing standing to\n\nassert each of its claims. See id.; see also Lewis v. Casey, 518 U.S. 343, 359 n.6 (1996)\n\n(“[A] plaintiff who has been subject to injurious conduct of one kind [does not] possess\n\nby virtue of that injury the necessary stake in litigating conduct of another kind, although\n\nsimilar, to which he has not been subject.” (internal quotation marks omitted)). We\n\nreview the question of whether South Carolina possesses standing de novo. Frank\n\nKrasner Enters., 401 F.3d at 234.\n\n To establish Article III standing, “a plaintiff must show (1) it has suffered an\n\n‘injury in fact’ that is (a) concrete and particularized and (b) actual or imminent, not\n\nconjectural or hypothetical; (2) the injury is fairly traceable to the challenged action of\n\n 10\n\fthe defendant; and (3) it is likely, as opposed to merely speculative, that the injury will be\n\nredressed by a favorable decision.” Friends of the Earth, Inc. v. Laidlaw Envtl. Servs.\n\n(TOC), Inc., 528 U.S. 167, 180–81 (2000). The United States contends South Carolina\n\nfailed to show it has suffered an injury-in-fact sufficient to give rise to Article III\n\nstanding.\n\n To satisfy the injury-in-fact requirement, a plaintiff must establish a “realistic\n\ndanger of sustaining a direct injury.” Peterson v. Nat’l Telcoms. & Info. Admin., 478\n\nF.3d 626, 632 (4th Cir. 2007) (quoting Babbitt v. United Farm Workers Nat’l Union, 442\n\nU.S. 289, 298 (1979)). “[W]hile it is true ‘that threatened rather than actual injury can\n\nsatisfy Article III standing requirements,’ . . . not all threatened injuries constitute an\n\ninjury-in-fact.” Beck v. McDonald, 848 F.3d 262, 271 (4th Cir. 2017) (quoting Friends of\n\nthe Earth, Inc. v. Gaston Copper Recycling Corp., 204 F.3d 149, 160 (4th Cir. 2000) (en\n\nbanc)). “Rather, as the Supreme Court has ‘emphasized repeatedly,’ an injury-in-fact\n\n‘must be concrete in both a qualitative and temporal sense.’” Id. (quoting Whitmore v.\n\nArkansas, 495 U.S. 149, 155 (1990)). The requirement that an alleged injury be palpable\n\nand imminent ensures that the injury “is not too speculative for Article III purposes.” Id.\n\n(quoting Lujan v. Defenders of Wildlife, 504 U.S. 555, 564–65 n.2 (1992)).\n\n On appeal, South Carolina contends that it has suffered an injury-in-fact sufficient\n\nto support standing because “[South Carolina] is harmed by being rendered the\n\npermanent repository of weapons-grade plutonium as a result of [the Department of\n\nEnergy’s] decision to terminate the MOX Facility without first complying with NEPA or\n\nfollowing the congressional mandates of § 3121.” Appellee’s Br. at 15–16. According to\n\n 11\n\fSouth Carolina, this “results in increased radiation exposure to the public, increased risks\n\nof nuclear-related accidents, and an increased threat of action by rogue states or terrorists\n\nseeking to acquire weapons-grade plutonium.” Id. at 14. But this alleged injury is too\n\nspeculative and thus, does not give rise to a concrete injury-in-fact sufficient to support\n\neither of South Carolina’s claims.\n\n The Supreme Court has repeatedly held that an alleged harm is too “speculative”\n\nto support Article III standing when the harm lies at the end of a “highly attenuated chain\n\nof possibilities.” Clapper v. Amnesty Int’l USA, 568 U.S. 398, 410 (2013); see also, e.g.,\n\nBeck, 848 F.3d at 275 (holding that plaintiffs, who received treatment at a medical center\n\nthat suffered a data breach and alleged that they were at risk of experiencing identity\n\ntheft, failed to establish standing because their theory of injury rested on an “attenuated\n\nchain of possibilities”).\n\n Illustratively in Clapper, the Supreme Court considered a challenge to Section 702\n\nof the Foreign Intelligence Surveillance Act, which “authoriz[es] the surveillance of\n\nindividuals who are not ‘United States persons’ and are reasonably believed to be located\n\noutside the United States.” 568 U.S. at 401. The plaintiffs—a group of “attorneys and\n\nhuman rights, labor, legal, and media organizations”—alleged that their work demanded\n\nthat they “engage in sensitive international communication with individuals who they\n\nbelieve are likely targets of surveillance under” Section 702, rendering it reasonably\n\nlikely that the government would target and intercept the plaintiffs’ communications. Id.\n\nat 401, 406.\n\n\n\n 12\n\f The Supreme Court held that the plaintiffs failed to establish a concrete injury-in-\n\nfact based on the possibility that their communications would be intercepted, explaining\n\nthat a series of hypothetical events would have to occur before the government would\n\nintercept any particular plaintiff’s communications. Id. at 1148–50. The Court held that\n\namong other steps, the government would have to decide to invoke its Section 702\n\nauthority to target a non-U.S. person with whom a plaintiff communicated, a panel of\n\nfederal judges would have to “conclude that the Government’s proposed surveillance\n\nprocedures satisfy [the statute’s] many safeguards and are consistent with the Fourth\n\nAmendment,” and the government would have to succeed in intercepting one of the\n\ntarget’s communications with the plaintiff. Id. Thus, the Court held that that the “highly\n\nattenuated chain of possibilities, d[id] not satisfy the requirement that threatened injury\n\nmust be certainly impending.” Id. at 1148 (citation omitted).\n\n Applying Clapper, this Court reached a similar conclusion in Beck, in which a\n\nputative class of veterans who received medical treatment at a veterans’ medical center\n\nalleged that they had been injured when two sets of records were stolen from the center.\n\n848 F.3d at 262, 267. Although none of the named plaintiffs alleged any actual or\n\nattempted misuse of the personal information contained in their stolen records, they\n\nalleged that they suffered cognizable injuries-in-fact because they faced “(1) [an]\n\nincreased risk of future identity theft, and (2) the costs of protecting against the same.”\n\nId. at 273. We concluded that both alleged injuries were too speculative to confer\n\nstanding. Id. at 275–77. As to the alleged increased risk of identity theft, in particular,\n\nwe explained that plaintiffs’ theory of injury required us to “assume that the thie[ves]\n\n 13\n\ftargeted the stolen items for the personal information they contained” and that the thieves\n\nwould “then select, from thousands of others, the personal information of the named\n\nplaintiffs, and attempt successfully to use that information to steal their identities.” Id. at\n\n275. “This ‘attenuated chain’ cannot confer standing,” we held. Id. We likewise\n\nrejected the plaintiffs’ costs of mitigation theory of standing as a “repackaged” version of\n\ntheir first theory of standing, amounting to an effort to recoup “costs they incurred in\n\nresponse to a speculative threat.” Id. at 276 (emphasis added) (quoting Clapper, 568\n\nU.S. at 416).\n\n Here, South Carolina’s theory of standing—that it will become “the permanent\n\nrepository of weapons-grade plutonium” and all the environmental, health, and safety\n\nrisks that entails, Appellee’s Br. at 15–16—rests on a similarly “highly attenuated chain\n\nof possibilities,” Clapper, 568 U.S. at 410. Between now and 2046—when the analysis\n\nin the current Environmental Impact Statement governing the risks associated with long-\n\nterm storage of weapons-grade nuclear material at the Savannah River Site expires—the\n\nDepartment of Energy has twenty-eight years to identify an alternative method for\n\ndisposing of the nuclear material or otherwise removing it from South Carolina. The\n\nSecretary of Energy already has certified that one potential alternative to the MOX\n\nprogram exists, the Dilute and Dispose method. And the Department of Energy may\n\nidentify and develop other methods during that twenty-eight-year period. Or the\n\nDepartment of Energy may decide to transfer the plutonium out of South Carolina to\n\nanother location.\n\n\n\n 14\n\f Furthermore, Congress has put in place contingency plans for the removal of\n\nplutonium shipped to the Savannah River Site to forestall the indefinite storage of\n\nplutonium in South Carolina. A federal statute requires that, by 2022, all additional\n\nplutonium transferred into South Carolina to the MOX facility, but not processed, must\n\nbe removed. 50 U.S.C. § 2566(c)(2). Notably, because the Department of Energy\n\nalready has failed to meet certain statutory time limits for disposing of nuclear material at\n\nthe site, South Carolina has successfully brought suit pursuant to the Administrative\n\nProcedure Act to enforce these congressionally mandated deadlines via a mandatory\n\ninjunction. See id. § 2566(c)(1) (requiring removal of one metric ton of plutonium no\n\nlater than January 1, 2016); South Carolina v. United States, 243 F. Supp. 3d 673 (D.S.C.\n\n2017), aff’d, 907 F.3d 742 (4th Cir. 2018) (ordering the Department of Energy to remove\n\none metric ton of plutonium within two years).\n\n In sum, for South Carolina’s alleged injury—becoming “the permanent repository\n\nof weapons-grade plutonium,” Appellee’s Br. at 15–16—to occur: (1) the proposed\n\nDilute and Dispose method must fail; (2) the Department of Energy must fail to identify\n\nan alternative method for disposing of the nuclear material; and (3) the Department of\n\nEnergy must breach its statutory obligation to remove the nuclear material from South\n\nCarolina, Congress must repeal that obligation, or the courts must refuse to enforce that\n\nobligation. At this juncture, before the Department of Energy has even had an\n\nopportunity to finish analyzing the Dilute and Dispose method, this “chain of\n\npossibilities” is too speculative to give rise to a sufficiently concrete injury-in-fact.\n\n\n\n 15\n\f That several of the links in this “chain of possibilities” the State’s standing theory\n\ncontemplates require our coordinate branches to either breach or abandon their existing\n\ncommitments to ensure timely removal of the nuclear material at the Savannah River Site\n\nfurther weighs against treating the South Carolina’s alleged injury as conferring standing.\n\nAs Clapper recognized, the standing doctrine is “built on separation-of-powers\n\nprinciples” and “serves to prevent the judicial process from being used to usurp the\n\npowers of the political branches.” 568 U.S. at 408 (citations omitted); see also Allen v.\n\nWright, 468 U.S. at 752 (1984) (“[Article] III standing is built on a single basic idea—the\n\nidea of separation of powers.”). To confer standing on South Carolina at this juncture\n\nbased on an alleged injury—becoming the permanent repository of nuclear material—that\n\nthe political branches already have made written and legally binding commitments to\n\nforestall would improperly “usurp the powers of the political branches.” Clapper, 568\n\nU.S. at 408.\n\n The “highly attenuated chain of possibilities” that must occur for South Carolina\n\nto become the permanent repository of nuclear material also sets this case apart from this\n\nCourt’s decision in Hodges v. Abraham, 300 F.3d 432 (4th Cir. 2002), upon which South\n\nCarolina principally relies.\n\n Like the instant case, Hodges dealt with the storage of plutonium at the Savannah\n\nRiver Site. Id. at 436. In 2002, the Department of Energy issued a Record of Decision\n\nauthorizing the immediate shipment of six metric tons of plutonium from a nuclear\n\nfacility in Colorado to the Savannah River Site. Id. The Governor of South Carolina\n\nsought to enjoin shipment of the plutonium into South Carolina, alleging that the\n\n 16\n\fDepartment of Energy’s existing Environmental Impact Statement, and its supplemental\n\nanalyses to the Environmental Impact Statement, related to storage of plutonium at the\n\nSavannah River Site violated NEPA in several ways. Id. at 445. This Court held that the\n\nGovernor adequately alleged an injury-in-fact to support his NEPA claims because the\n\nSouth Carolina owned property adjacent to the Savannah River Site. Id. “[T]he\n\nGovernor, in his official capacity, is essentially a neighboring landowner, whose property\n\nis at risk of environmental damage” as a result of the Department of Energy’s shipment\n\nof plutonium to the Savannah River Site and storage of that plutonium there, we\n\nexplained. Id.\n\n Here, unlike in Hodges, South Carolina does not argue that its injury, as a\n\nneighboring landowner, is attributable to the current storage of nuclear material at the\n\nSavannah River Site or the inadequacy of the Environmental Impact Statement pursuant\n\nto which the nuclear material is currently stored—a question that Hodges already\n\nresolved in the federal government’s favor. Id. at 446–49. Rather, South Carolina\n\ncontends it is injured because the termination of the MOX program renders it the\n\npermanent repository of the nuclear material when the Department of Energy has not\n\nissued an Environmental Impact Statement analyzing the environmental impact of the\n\nstorage of the material at the Savannah River Site beyond the year 2046, the year when\n\nthe existing Environmental Impact Statement’s analysis terminates, or, allegedly, satisfies\n\nits statutory obligations in terminating the MOX program. There is a meaningful\n\ndistinction between the alleged immediate environmental injuries associated with storing\n\nplutonium at the Savannah River Site, which were at issue in Hodges, and the alleged\n\n 17\n\ffuture adverse environmental impacts on South Carolina as a neighboring landowner if\n\nthe Department of Energy continues to store the plutonium at the Savannah River Site\n\ndecades in the future. That distinction is particularly meaningful because, as explained\n\nabove, numerous contingencies must occur in order for the plutonium to remain in South\n\nCarolina after 2046, the year when South Carolina’s alleged injury will mature.\n\n In sum, the single theory of injury3 that South Carolina relies on to support both of\n\nits claims is too speculative at this juncture to support Article III standing. The district\n\ncourt, therefore, was without jurisdiction to enter its preliminary injunction premised on\n\nthose two claims.\n\n B.\n\n For reasons similar to those that lead us to find that South Carolina lacks standing,\n\nwe also find that the two claims at issue fail on ripeness grounds. Like standing, the\n\nripeness doctrine “originates in the ‘case or controversy’ constraint of Article III.”\n\nScoggins v. Lee’s Crossing Homeowners Ass’n, 718 F.3d 262, 269 (4th Cir. 2013)\n\n(citations omitted). “Analyzing ripeness is similar to determining whether a party has\n\nstanding.” Miller v. Brown, 462 F.3d 312, 319 (4th Cir. 2006). “Although the phrasing\n\nmakes the questions of who may sue and when they sue seem distinct, in practice there is\n\nan obvious overlap between the doctrines of standing and ripeness.” Id. (quoting Erwin\n\n 3\n Because South Carolina has advanced only one theory of injury to support the\ntwo claims before this Court—that South Carolina is harmed by becoming the permanent\nrepository of weapons-grade nuclear material—we cannot and do not take any position\non whether other theories of injury would presently confer standing on South Carolina to\nsupport either of the two claims before us on appeal.\n\n\n 18\n\fChemerinsky, Federal Jurisdiction § 2.4 (4th ed. 2003). As with standing, ripeness is a\n\nquestion of subject matter jurisdiction. See Sansotta v. Town of Nags Head, 724 F.3d\n\n533, 548 (4th Cir. 2013) (citation omitted).\n\n The question of whether a claim is ripe “turns on the ‘fitness of the issues for\n\njudicial decision’ and the ‘hardship to the parties of withholding court consideration.’”\n\nPac. Gas & Elec. Co. v. State Energy Res. Conservation & Dev. Comm’n, 461 U.S. 190,\n\n201 (1983) (citation omitted). In the context of claims challenging agency actions, like\n\nthe two at issue, the purpose of the ripeness doctrine is “to prevent the courts, through\n\navoidance of premature adjudication, from entangling themselves in abstract\n\ndisagreements over administrative policies, and also to protect the agencies from judicial\n\ninterference until an administrative decision has been formalized and its effects felt in a\n\nconcrete way by the challenging parties.” Abbott Labs. v. Gardner, 387 U.S. 136, 148–\n\n49 (1967), abrogated on other grounds by Califano v. Sanders, 430 U.S. 99 (1977).\n\n To be fit for judicial review, a controversy should be presented in a “clean-cut and\n\nconcrete form.” Miller, 462 F.3d at 319 (citation omitted). This occurs when the action\n\nis “final and not dependent on future uncertainties or intervening agency rulings.”\n\nFranks v. Ross, 313 F.3d 184, 195 (4th Cir. 2002) (citation omitted). On the other hand,\n\njust as a plaintiff cannot assert standing based on an alleged injury that lies at the end of a\n\n“highly attenuated chain of possibilities,” Clapper, 568 U.S. at 410, a plaintiff’s claim is\n\nnot ripe for judicial review “if it rests upon contingent future events that may not occur as\n\nanticipated, or indeed may not occur at all.” Scoggins, 718 F.3d at 270 (quoting Texas v.\n\nUnited States, 523 U.S. 296, 300 (1998)).\n\n 19\n\f The two claims that South Carolina advances before this Court rest on the premise\n\nthat South Carolina will be the permanent repository of the weapons-grade nuclear\n\nmaterial currently stored at the Savannah River Site. But, numerous “contingent future\n\nevents,” id., must occur before South Carolina becomes the permanent repository of the\n\nnuclear material, see supra Part II.A. In particular, the Dilute and Dispose method must\n\nprove unworkable. The Department of Energy must fail to identify an alternative method\n\nof disposal and breach its commitment to dispose of the waste. And Congress or the\n\ncourts must set aside or refuse to enforce the statutory mechanisms currently in place to\n\nensure timely removal of the nuclear material. All of these “future uncertainties,”\n\nFranks, 313 F.3d at 195, lead us to conclude that the two claims at issue are not ripe for\n\nreview at this time—at least as presented by South Carolina. Accordingly, the ripeness\n\ndoctrine provides an additional basis for our holding that the district court was without\n\njurisdiction to enter the preliminary injunction.\n\n III.\n\n In sum, the only theory of injury advanced by South Carolina—that South\n\nCarolina will be the permanent repository of the nuclear material currently stored at the\n\nSavannah River Site—rests upon a “highly attenuated chain of possibilities,” Clapper,\n\n568 U.S. at 410, and “contingent future events that may not occur as anticipated, or\n\nindeed may not occur at all.” Scoggins, 718 F.3d at 270. In such circumstances, we must\n\nconclude that South Carolina lacks Article III standing to advance the two claims that\n\nserve as the basis of the district court’s injunction and that those two claims are not ripe\n\nfor review.\n\n 20\n\f That the two claims are not currently justiciable does not mean that they never will\n\nbe so. If uncertainty as to several links in the chain of possibilities is resolved, then\n\nSouth Carolina’s alleged injury may move from the speculative to the concrete, and\n\ntherefore the two claims also may become ripe for review. But until that uncertainty is\n\nlifted, the Constitution demands that we withhold judicial review.\n\n Accordingly, we vacate the preliminary injunction imposed by the district court\n\nand remand the case for further proceedings not inconsistent with this opinion.\n\n\n\n VACATED AND REMANDED\n\n\n\n\n 21\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: State of SOUTH CAROLINA, Plaintiff - Appellee, v. UNITED STATES of America; United States Department of Energy; Rick Perry, in His Official Capacity as Secretary of Energy; National Nuclear Security Administration; Lisa E. Gordon-Hagerty, in Her Official Capacity as Administrator of the National Nuclear Security Administration and Undersecretary for Nuclear Security, Defendants - Appellants.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-08\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1684\\n\\n\\nSTATE OF SOUTH CAROLINA,\\n\\n Plaintiff – Appellee,\\n\\nv.\\n\\nUNITED STATES OF AMERICA; UNITED STATES DEPARTMENT OF\\nENERGY; RICK PERRY, in his official capacity as Secretary of Energy;\\nNATIONAL NUCLEAR SECURITY ADMINISTRATION; LISA E. GORDON-\\nHAGERTY, in her official capacity as Administrator of the National Nuclear\\nSecurity Administration and Undersecretary for Nuclear Security,\\n\\n Defendants – Appellants.\\n\\n\\n\\nAppeal from the United States District Court for the District of South Carolina, at Aiken.\\nJ. Michelle Childs, District Judge. (1:18-cv-01431-JMC)\\n\\n\\nArgued: September 27, 2018 Decided: January 8, 2019\\n\\n\\nBefore NIEMEYER, KING, and WYNN, Circuit Judges.\\n\\n\\nVacated and remanded by published opinion. Judge Wynn wrote the opinion, in which\\nJudge Niemeyer and Judge King joined.\\n\\n\\nARGUED: Andrew Alperin Rohrbach, UNITED STATES DEPARTMENT OF\\nJUSTICE, Washington, D.C., for Appellants. Randolph R. Lowell, WILLOUGHBY &\\nHOEFER, PA, Columbia, South Carolina, for Appellee. ON BRIEF: Chad A. Readler,\\nActing Assistant Attorney General, Mark B. Stern, Daniel Tenny, Civil Division,\\n\\fUNITED STATES DEPARTMENT OF JUSTICE, Washington, D.C.; Sherri A. Lydon,\\nUnited States Attorney, OFFICE OF THE UNITED STATES ATTORNEY, Columbia,\\nSouth Carolina, for Appellants.\\n\\n\\n\\n\\n 2\\n\\fWYNN, Circuit Judge:\\n\\n The State of South Carolina brought this action to enjoin the United States of\\n\\nAmerica and other Defendants 1 (collectively, “the United States”) from terminating the\\n\\nconstruction of a mixed-oxide fuel nuclear processing facility located at the Savannah\\n\\nRiver Site in South Carolina. South Carolina alleges that the United States Department\\n\\nof Energy unlawfully failed to (1) prepare a supplemental Environmental Impact\\n\\nStatement analyzing the long-term storage of plutonium in the state; and (2) follow\\n\\nstatutory waiver provisions for terminating construction of the facility. We conclude that\\n\\nSouth Carolina has not established standing to pursue either of these claims.\\n\\nAccordingly, we vacate the preliminary injunction imposed by the district court.\\n\\n I.\\n\\n Following the collapse of the Soviet Union and the end of the Cold War, the\\n\\nUnited States of America and the Russian Federation began a worldwide nuclear\\n\\nnonproliferation effort that included developing plans for the safe disposition of nuclear\\n\\nweapons material. As part of this nonproliferation pact, the Department of Energy began\\n\\nstudying the effects of various nuclear waste storage and disposal strategies. In its initial\\n\\n1996 study, the Department of Energy prepared an Environmental Impact Statement in\\n\\naccordance with Section 4332 of the National Environmental Policy Act (“NEPA”), 42\\n\\n\\n 1\\n The other Defendants are the United States Department of Energy; Rick Perry, in\\nhis official capacity as Secretary of Energy; the National Nuclear Security\\nAdministration; and Lisa E. Gordon-Hagerty, in her official capacity as Administrator of\\nthe National Nuclear Security Administration.\\n\\n\\n 3\\n\\fU.S.C. § 4321 et seq., analyzing the potential environmental consequences associated\\n\\nwith the long-term storage of weapons-grade plutonium and highly enriched uranium\\n\\nprior to disposition. The Environmental Impact Statement addressed storage of these\\n\\nmaterials for a period of up to fifty years.\\n\\n Ultimately, the Department of Energy determined that the best approach to nuclear\\n\\nwaste disposal was a dual strategy involving (1) immobilization of a portion of the\\n\\nsurplus plutonium in glass or ceramic; and (2) irradiation of the remaining plutonium in\\n\\nmixed oxide fuel (the “MOX process”). Both strategies would convert the surplus\\n\\nnuclear material into forms that would meet the National Academy of Science’s Spent\\n\\nFuel Standard, meaning that the material would be “inaccessible and unattractive for\\n\\nweapons” use. J.A. 78.\\n\\n In 1997, the Department of Energy announced its intention to build a new mixed\\n\\noxide fuel fabrication facility (the “MOX facility”) to dispose of some of the nuclear\\n\\nmaterial using the MOX process. Following completion of a supplemental\\n\\nEnvironmental Impact Statement and a Record of Decision in January of 2000, the\\n\\nDepartment of Energy announced that the MOX facility would be located at the\\n\\nSavannah River Site along South Carolina’s border with Georgia. The facility’s original\\n\\nproduction goals included disposition of up to thirty-three metric tons of nuclear material\\n\\nusing the MOX process and immobilization of up to seventeen metric tons of additional\\n\\nnuclear material. As part of its supplemental Environmental Impact Statement, the\\n\\nDepartment of Energy continued to look at the environmental impacts of long-term\\n\\nplutonium storage.\\n\\n 4\\n\\f In 2002, the Department of Energy decided to drop the immobilization portion of\\n\\nthe disposition strategy, leaving the MOX process as the sole plutonium disposal method.\\n\\nThat same year, Congress directed the Secretary of Energy to submit a plan for the\\n\\nconstruction and operation of the MOX facility at the Savannah River site. Pub. L. No.\\n\\n107-314, § 3182 (2002), subsequently codified as 50 U.S.C. § 2566. Congress further\\n\\nauthorized the Secretary to take corrective actions if the construction timetable and\\n\\noperation schedule for the MOX facility were not being met. Additionally, Congress also\\n\\nrequired that in the event the MOX facility failed to achieve its production goals, the\\n\\nDepartment of Energy remove plutonium shipped to South Carolina for processing. See\\n\\n50 U.S.C. § 2566(c), § 2566(e). Finally, as part of its findings, Congress mentioned the\\n\\neconomic benefit that the MOX facility would bring to the State of South Carolina,\\n\\nnoting that the economic benefit would not be fully realized unless the facility was built.\\n\\nSee Pub. L. No. 107-314 at § 3181.\\n\\n Three years later, in 2005, the Department of Energy began transferring plutonium\\n\\nto the Savannah River Site for conversion, and in 2007, construction began on the MOX\\n\\nfacility. The original cost estimate for construction of the facility was $4.8 billion, with\\n\\ncompletion anticipated in 2016. And the original production goal estimate for the facility\\n\\nwas to have thirty-four metric tons of defense plutonium processed no later than January\\n\\n1, 2019. 50 U.S.C. § 2566(a)(2)(B).\\n\\n These original estimates proved grossly inaccurate due to delays and cost overruns\\n\\nin the construction of the MOX facility. The Department of Energy now estimates cost\\n\\n\\n\\n 5\\n\\ffor construction of the facility to be $17.17 billion, with completion now anticipated to be\\n\\nin 2048, over thirty years beyond the original estimated schedule.\\n\\n Since 2014, the Department of Energy has sought to terminate the MOX program\\n\\nand pursue an alternative method of plutonium disposal known as “Dilute and Dispose,”\\n\\nwhich it contends is less costly, faster, and safer. Under the Dilute and Dispose method,\\n\\nnuclear material would be “downblended” with inhibitor materials to reduce the\\n\\nplutonium content to less than ten percent by weight. Upon completion of the\\n\\ndownblending process, the material would then be shipped from the Savannah River Site\\n\\nto the Waste Isolation Pilot Plant near Carlsbad, New Mexico, for permanent disposal.\\n\\n Thus far, Congress has continued to fund construction of the MOX facility and\\n\\nhas, to date, restricted the Department of Energy from utilizing MOX-related\\n\\nappropriations to begin termination of the program. To that end, in 2017, Congress\\n\\nenacted a statute providing that the Secretary of Energy “shall carry out construction and\\n\\nproject support activities relating to the MOX facility.” Pub. L. 115-91, § 3121(a), 131\\n\\nStat. 1283, 1892.\\n\\n However, Section 3121(b) of that statute allows the Secretary of Energy to\\n\\ndiscontinue construction of the MOX facility if certain conditions have been met.\\n\\nSpecifically, the Secretary of Energy must submit to the Congressional defense\\n\\ncommittees:\\n\\n (A) the commitment of the Secretary [of Energy] to remove plutonium\\n intended to be disposed of in the MOX facility from South Carolina\\n and ensure a sustainable future for the Savannah River Site;\\n\\n (B) a certification that―\\n\\n 6\\n\\f (i) an alternative option for carrying out the plutonium disposition\\n program for the same amount of plutonium as the amount of plutonium\\n intended to be disposed of in the MOX facility exists, meeting the\\n requirements of the Business Operating Procedure of the National\\n Nuclear Security Administration entitled “Analysis of Alternatives” and\\n dated March 14, 2016 (BOP-03.07); and\\n\\n (ii) the remaining lifecycle cost, determined in a manner comparable to\\n the cost estimating and assessment best practices of the Government\\n Accountability Office [“GAO”], as found in the document of the\\n Government Accountability Office entitled “GAO Cost Estimating and\\n Assessment Guide” (GAO-09-3SP), for the alternative option would be\\n less than approximately half of the estimated remaining lifecycle costs\\n of the mixed oxide fuel program; and\\n\\n (C) the details of any statutory or regulatory changes necessary to complete\\n the alternative option.\\n\\n§ 3121(b)(1).\\n\\n Additionally, in exercising his authority to discontinue construction of the MOX\\n\\nfacility, the Secretary of Energy\\n\\n (1) shall concurrently submit to the Committees on Appropriations of both\\n Houses of Congress the lifecycle cost estimate used to make the\\n certification under section 3121(b) of such Act; and\\n\\n (2) may not use funds provided for the Project to eliminate such Project\\n until the date that is 30 days after the submission of the lifecycle cost\\n estimate required under paragraph (1).\\n\\nPub. L. No. 115-141, § 309(c), 132 Stat. 348, 530 (2018).\\n\\n Pursuant to these provisions, on May 10, 2018, the Secretary of Energy submitted\\n\\na letter to the Chairman of the House Armed Services Committee that purported to\\n\\nexecute the authority of the Secretary of Energy under Section 3121(b) to discontinue\\n\\nconstruction of the MOX facility. The Secretary of Energy certified, inter alia, that (1)\\n\\n\\n 7\\n\\fthe Department of Energy is committed to removing plutonium from South Carolina; (2)\\n\\nan alternative option for carrying out the plutonium disposition, the Dilute and Dispose\\n\\nmethod, exists and has a lifecycle cost of less than approximately half of the remaining\\n\\nlifecycle cost for the MOX program; (3) the Department of Energy estimated the cost of\\n\\nthe Dilute and Dispose approach in a manner compatible with the best practices of the\\n\\nGAO; and (4) the Department of Energy is committed to ensuring a sustainable future for\\n\\nthe Savannah River Site. The Secretary of Energy further reported that the Department\\n\\nof Energy expected the total cost of disposition via the Dilute and Dispose method to be\\n\\n$19.9 billion, compared to $49.4 billion for the total cost of construction of the MOX\\n\\nfacility and conversion of all the plutonium into MOX fuel.\\n\\n In accordance with the Secretary of Energy’s letter, the Department of Energy and\\n\\nthe National Nuclear Security Administration issued a Partial Stop Work Order on May\\n\\n14, 2018, ending all new contracts and hiring related to the MOX program. The\\n\\nDepartment of Energy further indicated its intent to issue a Full Stop Work Order and\\n\\nbegin winding down the MOX program, including terminating employees currently\\n\\nworking on the project, on or about June 11, 2018.\\n\\n On May 25, 2018, before the Department of Energy issued a full stop work order,\\n\\nSouth Carolina brought this action in the United States District Court for the District of\\n\\nSouth Carolina and moved for a preliminary injunction barring the federal government\\n\\nfrom terminating the MOX program. In its complaint, South Carolina asserted that the\\n\\nUnited States (1) violated NEPA by failing to prepare a supplemental Environmental\\n\\nImpact Statement covering a period of more than fifty years and (2) failed to satisfy\\n\\n 8\\n\\fSection 3121(b) because of the alleged insufficiency of the Secretary of Energy’s\\n\\ncertifications. 2\\n\\n On June 7, 2018, the district court granted South Carolina’s motion for\\n\\npreliminary injunction. The district court first found that South Carolina had standing\\n\\ndue to environmental risks associated with long-term storage at the Savannah River Site,\\n\\nwhich abuts property owned by South Carolina. As to the merits, the district court held,\\n\\nin pertinent part, that South Carolina was likely to succeed on the merits of its NEPA\\n\\nclaim and its claim that the Secretary of Energy’s certifications were insufficient. The\\n\\ndistrict court further found that South Carolina would be irreparably harmed absent a\\n\\npreliminary injunction and that the balance of equities tilted in South Carolina’s favor.\\n\\nThus, the district court enjoined the federal government from ceasing construction of the\\n\\nMOX facility and issuing the full stop work order. The United States timely appealed.\\n\\n After careful review, we dispositively hold that South Carolina failed to establish\\n\\nstanding and therefore we do not reach the district court’s determination on the merits of\\n\\nthis matter.\\n\\n\\n\\n\\n 2\\n South Carolina further claimed that the United States violated 50 U.S.C. § 2567\\nby failing to consult with the governor before deciding to terminate the MOX facility.\\nThe district court held that South Carolina failed to establish that that claim was likely to\\nsucceed on the merits, and therefore that claim is not before this Court.\\n\\n\\n 9\\n\\f II.\\n\\n A.\\n\\n On appeal, the United States contends that the district court erred in concluding\\n\\nthat South Carolina established standing to pursue the two claims that serve as the basis\\n\\nof the district court’s preliminary injunction order—the NEPA claim and the claim\\n\\npremised on the alleged insufficiency of the Secretary’s certifications. The standing\\n\\ndoctrine derives from “the Constitution’s limitation on Article III courts’ power to\\n\\nadjudicate ‘cases and controversies.’” Frank Krasner Enters. v. Montgomery Cty., 401\\n\\nF.3d 230, 234 (4th Cir. 2005) (quoting Allen v. Wright, 468 U.S. 737, 750–51 (1984),\\n\\nabrogated on other grounds by Lexmark Intern., Inc. v. Static Control Components, Inc.,\\n\\n572 U.S. 118 (2014)). Standing implicates the court’s subject matter jurisdiction. Long\\n\\nTerm Care Partners, LLC v. United States, 516 F.3d 225, 230 (4th Cir. 2008).\\n\\n Here, South Carolina, as plaintiff, bears the burden of establishing standing to\\n\\nassert each of its claims. See id.; see also Lewis v. Casey, 518 U.S. 343, 359 n.6 (1996)\\n\\n(“[A] plaintiff who has been subject to injurious conduct of one kind [does not] possess\\n\\nby virtue of that injury the necessary stake in litigating conduct of another kind, although\\n\\nsimilar, to which he has not been subject.” (internal quotation marks omitted)). We\\n\\nreview the question of whether South Carolina possesses standing de novo. Frank\\n\\nKrasner Enters., 401 F.3d at 234.\\n\\n To establish Article III standing, “a plaintiff must show (1) it has suffered an\\n\\n‘injury in fact’ that is (a) concrete and particularized and (b) actual or imminent, not\\n\\nconjectural or hypothetical; (2) the injury is fairly traceable to the challenged action of\\n\\n 10\\n\\fthe defendant; and (3) it is likely, as opposed to merely speculative, that the injury will be\\n\\nredressed by a favorable decision.” Friends of the Earth, Inc. v. Laidlaw Envtl. Servs.\\n\\n(TOC), Inc., 528 U.S. 167, 180–81 (2000). The United States contends South Carolina\\n\\nfailed to show it has suffered an injury-in-fact sufficient to give rise to Article III\\n\\nstanding.\\n\\n To satisfy the injury-in-fact requirement, a plaintiff must establish a “realistic\\n\\ndanger of sustaining a direct injury.” Peterson v. Nat’l Telcoms. & Info. Admin., 478\\n\\nF.3d 626, 632 (4th Cir. 2007) (quoting Babbitt v. United Farm Workers Nat’l Union, 442\\n\\nU.S. 289, 298 (1979)). “[W]hile it is true ‘that threatened rather than actual injury can\\n\\nsatisfy Article III standing requirements,’ . . . not all threatened injuries constitute an\\n\\ninjury-in-fact.” Beck v. McDonald, 848 F.3d 262, 271 (4th Cir. 2017) (quoting Friends of\\n\\nthe Earth, Inc. v. Gaston Copper Recycling Corp., 204 F.3d 149, 160 (4th Cir. 2000) (en\\n\\nbanc)). “Rather, as the Supreme Court has ‘emphasized repeatedly,’ an injury-in-fact\\n\\n‘must be concrete in both a qualitative and temporal sense.’” Id. (quoting Whitmore v.\\n\\nArkansas, 495 U.S. 149, 155 (1990)). The requirement that an alleged injury be palpable\\n\\nand imminent ensures that the injury “is not too speculative for Article III purposes.” Id.\\n\\n(quoting Lujan v. Defenders of Wildlife, 504 U.S. 555, 564–65 n.2 (1992)).\\n\\n On appeal, South Carolina contends that it has suffered an injury-in-fact sufficient\\n\\nto support standing because “[South Carolina] is harmed by being rendered the\\n\\npermanent repository of weapons-grade plutonium as a result of [the Department of\\n\\nEnergy’s] decision to terminate the MOX Facility without first complying with NEPA or\\n\\nfollowing the congressional mandates of § 3121.” Appellee’s Br. at 15–16. According to\\n\\n 11\\n\\fSouth Carolina, this “results in increased radiation exposure to the public, increased risks\\n\\nof nuclear-related accidents, and an increased threat of action by rogue states or terrorists\\n\\nseeking to acquire weapons-grade plutonium.” Id. at 14. But this alleged injury is too\\n\\nspeculative and thus, does not give rise to a concrete injury-in-fact sufficient to support\\n\\neither of South Carolina’s claims.\\n\\n The Supreme Court has repeatedly held that an alleged harm is too “speculative”\\n\\nto support Article III standing when the harm lies at the end of a “highly attenuated chain\\n\\nof possibilities.” Clapper v. Amnesty Int’l USA, 568 U.S. 398, 410 (2013); see also, e.g.,\\n\\nBeck, 848 F.3d at 275 (holding that plaintiffs, who received treatment at a medical center\\n\\nthat suffered a data breach and alleged that they were at risk of experiencing identity\\n\\ntheft, failed to establish standing because their theory of injury rested on an “attenuated\\n\\nchain of possibilities”).\\n\\n Illustratively in Clapper, the Supreme Court considered a challenge to Section 702\\n\\nof the Foreign Intelligence Surveillance Act, which “authoriz[es] the surveillance of\\n\\nindividuals who are not ‘United States persons’ and are reasonably believed to be located\\n\\noutside the United States.” 568 U.S. at 401. The plaintiffs—a group of “attorneys and\\n\\nhuman rights, labor, legal, and media organizations”—alleged that their work demanded\\n\\nthat they “engage in sensitive international communication with individuals who they\\n\\nbelieve are likely targets of surveillance under” Section 702, rendering it reasonably\\n\\nlikely that the government would target and intercept the plaintiffs’ communications. Id.\\n\\nat 401, 406.\\n\\n\\n\\n 12\\n\\f The Supreme Court held that the plaintiffs failed to establish a concrete injury-in-\\n\\nfact based on the possibility that their communications would be intercepted, explaining\\n\\nthat a series of hypothetical events would have to occur before the government would\\n\\nintercept any particular plaintiff’s communications. Id. at 1148–50. The Court held that\\n\\namong other steps, the government would have to decide to invoke its Section 702\\n\\nauthority to target a non-U.S. person with whom a plaintiff communicated, a panel of\\n\\nfederal judges would have to “conclude that the Government’s proposed surveillance\\n\\nprocedures satisfy [the statute’s] many safeguards and are consistent with the Fourth\\n\\nAmendment,” and the government would have to succeed in intercepting one of the\\n\\ntarget’s communications with the plaintiff. Id. Thus, the Court held that that the “highly\\n\\nattenuated chain of possibilities, d[id] not satisfy the requirement that threatened injury\\n\\nmust be certainly impending.” Id. at 1148 (citation omitted).\\n\\n Applying Clapper, this Court reached a similar conclusion in Beck, in which a\\n\\nputative class of veterans who received medical treatment at a veterans’ medical center\\n\\nalleged that they had been injured when two sets of records were stolen from the center.\\n\\n848 F.3d at 262, 267. Although none of the named plaintiffs alleged any actual or\\n\\nattempted misuse of the personal information contained in their stolen records, they\\n\\nalleged that they suffered cognizable injuries-in-fact because they faced “(1) [an]\\n\\nincreased risk of future identity theft, and (2) the costs of protecting against the same.”\\n\\nId. at 273. We concluded that both alleged injuries were too speculative to confer\\n\\nstanding. Id. at 275–77. As to the alleged increased risk of identity theft, in particular,\\n\\nwe explained that plaintiffs’ theory of injury required us to “assume that the thie[ves]\\n\\n 13\\n\\ftargeted the stolen items for the personal information they contained” and that the thieves\\n\\nwould “then select, from thousands of others, the personal information of the named\\n\\nplaintiffs, and attempt successfully to use that information to steal their identities.” Id. at\\n\\n275. “This ‘attenuated chain’ cannot confer standing,” we held. Id. We likewise\\n\\nrejected the plaintiffs’ costs of mitigation theory of standing as a “repackaged” version of\\n\\ntheir first theory of standing, amounting to an effort to recoup “costs they incurred in\\n\\nresponse to a speculative threat.” Id. at 276 (emphasis added) (quoting Clapper, 568\\n\\nU.S. at 416).\\n\\n Here, South Carolina’s theory of standing—that it will become “the permanent\\n\\nrepository of weapons-grade plutonium” and all the environmental, health, and safety\\n\\nrisks that entails, Appellee’s Br. at 15–16—rests on a similarly “highly attenuated chain\\n\\nof possibilities,” Clapper, 568 U.S. at 410. Between now and 2046—when the analysis\\n\\nin the current Environmental Impact Statement governing the risks associated with long-\\n\\nterm storage of weapons-grade nuclear material at the Savannah River Site expires—the\\n\\nDepartment of Energy has twenty-eight years to identify an alternative method for\\n\\ndisposing of the nuclear material or otherwise removing it from South Carolina. The\\n\\nSecretary of Energy already has certified that one potential alternative to the MOX\\n\\nprogram exists, the Dilute and Dispose method. And the Department of Energy may\\n\\nidentify and develop other methods during that twenty-eight-year period. Or the\\n\\nDepartment of Energy may decide to transfer the plutonium out of South Carolina to\\n\\nanother location.\\n\\n\\n\\n 14\\n\\f Furthermore, Congress has put in place contingency plans for the removal of\\n\\nplutonium shipped to the Savannah River Site to forestall the indefinite storage of\\n\\nplutonium in South Carolina. A federal statute requires that, by 2022, all additional\\n\\nplutonium transferred into South Carolina to the MOX facility, but not processed, must\\n\\nbe removed. 50 U.S.C. § 2566(c)(2). Notably, because the Department of Energy\\n\\nalready has failed to meet certain statutory time limits for disposing of nuclear material at\\n\\nthe site, South Carolina has successfully brought suit pursuant to the Administrative\\n\\nProcedure Act to enforce these congressionally mandated deadlines via a mandatory\\n\\ninjunction. See id. § 2566(c)(1) (requiring removal of one metric ton of plutonium no\\n\\nlater than January 1, 2016); South Carolina v. United States, 243 F. Supp. 3d 673 (D.S.C.\\n\\n2017), aff’d, 907 F.3d 742 (4th Cir. 2018) (ordering the Department of Energy to remove\\n\\none metric ton of plutonium within two years).\\n\\n In sum, for South Carolina’s alleged injury—becoming “the permanent repository\\n\\nof weapons-grade plutonium,” Appellee’s Br. at 15–16—to occur: (1) the proposed\\n\\nDilute and Dispose method must fail; (2) the Department of Energy must fail to identify\\n\\nan alternative method for disposing of the nuclear material; and (3) the Department of\\n\\nEnergy must breach its statutory obligation to remove the nuclear material from South\\n\\nCarolina, Congress must repeal that obligation, or the courts must refuse to enforce that\\n\\nobligation. At this juncture, before the Department of Energy has even had an\\n\\nopportunity to finish analyzing the Dilute and Dispose method, this “chain of\\n\\npossibilities” is too speculative to give rise to a sufficiently concrete injury-in-fact.\\n\\n\\n\\n 15\\n\\f That several of the links in this “chain of possibilities” the State’s standing theory\\n\\ncontemplates require our coordinate branches to either breach or abandon their existing\\n\\ncommitments to ensure timely removal of the nuclear material at the Savannah River Site\\n\\nfurther weighs against treating the South Carolina’s alleged injury as conferring standing.\\n\\nAs Clapper recognized, the standing doctrine is “built on separation-of-powers\\n\\nprinciples” and “serves to prevent the judicial process from being used to usurp the\\n\\npowers of the political branches.” 568 U.S. at 408 (citations omitted); see also Allen v.\\n\\nWright, 468 U.S. at 752 (1984) (“[Article] III standing is built on a single basic idea—the\\n\\nidea of separation of powers.”). To confer standing on South Carolina at this juncture\\n\\nbased on an alleged injury—becoming the permanent repository of nuclear material—that\\n\\nthe political branches already have made written and legally binding commitments to\\n\\nforestall would improperly “usurp the powers of the political branches.” Clapper, 568\\n\\nU.S. at 408.\\n\\n The “highly attenuated chain of possibilities” that must occur for South Carolina\\n\\nto become the permanent repository of nuclear material also sets this case apart from this\\n\\nCourt’s decision in Hodges v. Abraham, 300 F.3d 432 (4th Cir. 2002), upon which South\\n\\nCarolina principally relies.\\n\\n Like the instant case, Hodges dealt with the storage of plutonium at the Savannah\\n\\nRiver Site. Id. at 436. In 2002, the Department of Energy issued a Record of Decision\\n\\nauthorizing the immediate shipment of six metric tons of plutonium from a nuclear\\n\\nfacility in Colorado to the Savannah River Site. Id. The Governor of South Carolina\\n\\nsought to enjoin shipment of the plutonium into South Carolina, alleging that the\\n\\n 16\\n\\fDepartment of Energy’s existing Environmental Impact Statement, and its supplemental\\n\\nanalyses to the Environmental Impact Statement, related to storage of plutonium at the\\n\\nSavannah River Site violated NEPA in several ways. Id. at 445. This Court held that the\\n\\nGovernor adequately alleged an injury-in-fact to support his NEPA claims because the\\n\\nSouth Carolina owned property adjacent to the Savannah River Site. Id. “[T]he\\n\\nGovernor, in his official capacity, is essentially a neighboring landowner, whose property\\n\\nis at risk of environmental damage” as a result of the Department of Energy’s shipment\\n\\nof plutonium to the Savannah River Site and storage of that plutonium there, we\\n\\nexplained. Id.\\n\\n Here, unlike in Hodges, South Carolina does not argue that its injury, as a\\n\\nneighboring landowner, is attributable to the current storage of nuclear material at the\\n\\nSavannah River Site or the inadequacy of the Environmental Impact Statement pursuant\\n\\nto which the nuclear material is currently stored—a question that Hodges already\\n\\nresolved in the federal government’s favor. Id. at 446–49. Rather, South Carolina\\n\\ncontends it is injured because the termination of the MOX program renders it the\\n\\npermanent repository of the nuclear material when the Department of Energy has not\\n\\nissued an Environmental Impact Statement analyzing the environmental impact of the\\n\\nstorage of the material at the Savannah River Site beyond the year 2046, the year when\\n\\nthe existing Environmental Impact Statement’s analysis terminates, or, allegedly, satisfies\\n\\nits statutory obligations in terminating the MOX program. There is a meaningful\\n\\ndistinction between the alleged immediate environmental injuries associated with storing\\n\\nplutonium at the Savannah River Site, which were at issue in Hodges, and the alleged\\n\\n 17\\n\\ffuture adverse environmental impacts on South Carolina as a neighboring landowner if\\n\\nthe Department of Energy continues to store the plutonium at the Savannah River Site\\n\\ndecades in the future. That distinction is particularly meaningful because, as explained\\n\\nabove, numerous contingencies must occur in order for the plutonium to remain in South\\n\\nCarolina after 2046, the year when South Carolina’s alleged injury will mature.\\n\\n In sum, the single theory of injury3 that South Carolina relies on to support both of\\n\\nits claims is too speculative at this juncture to support Article III standing. The district\\n\\ncourt, therefore, was without jurisdiction to enter its preliminary injunction premised on\\n\\nthose two claims.\\n\\n B.\\n\\n For reasons similar to those that lead us to find that South Carolina lacks standing,\\n\\nwe also find that the two claims at issue fail on ripeness grounds. Like standing, the\\n\\nripeness doctrine “originates in the ‘case or controversy’ constraint of Article III.”\\n\\nScoggins v. Lee’s Crossing Homeowners Ass’n, 718 F.3d 262, 269 (4th Cir. 2013)\\n\\n(citations omitted). “Analyzing ripeness is similar to determining whether a party has\\n\\nstanding.” Miller v. Brown, 462 F.3d 312, 319 (4th Cir. 2006). “Although the phrasing\\n\\nmakes the questions of who may sue and when they sue seem distinct, in practice there is\\n\\nan obvious overlap between the doctrines of standing and ripeness.” Id. (quoting Erwin\\n\\n 3\\n Because South Carolina has advanced only one theory of injury to support the\\ntwo claims before this Court—that South Carolina is harmed by becoming the permanent\\nrepository of weapons-grade nuclear material—we cannot and do not take any position\\non whether other theories of injury would presently confer standing on South Carolina to\\nsupport either of the two claims before us on appeal.\\n\\n\\n 18\\n\\fChemerinsky, Federal Jurisdiction § 2.4 (4th ed. 2003). As with standing, ripeness is a\\n\\nquestion of subject matter jurisdiction. See Sansotta v. Town of Nags Head, 724 F.3d\\n\\n533, 548 (4th Cir. 2013) (citation omitted).\\n\\n The question of whether a claim is ripe “turns on the ‘fitness of the issues for\\n\\njudicial decision’ and the ‘hardship to the parties of withholding court consideration.’”\\n\\nPac. Gas & Elec. Co. v. State Energy Res. Conservation & Dev. Comm’n, 461 U.S. 190,\\n\\n201 (1983) (citation omitted). In the context of claims challenging agency actions, like\\n\\nthe two at issue, the purpose of the ripeness doctrine is “to prevent the courts, through\\n\\navoidance of premature adjudication, from entangling themselves in abstract\\n\\ndisagreements over administrative policies, and also to protect the agencies from judicial\\n\\ninterference until an administrative decision has been formalized and its effects felt in a\\n\\nconcrete way by the challenging parties.” Abbott Labs. v. Gardner, 387 U.S. 136, 148–\\n\\n49 (1967), abrogated on other grounds by Califano v. Sanders, 430 U.S. 99 (1977).\\n\\n To be fit for judicial review, a controversy should be presented in a “clean-cut and\\n\\nconcrete form.” Miller, 462 F.3d at 319 (citation omitted). This occurs when the action\\n\\nis “final and not dependent on future uncertainties or intervening agency rulings.”\\n\\nFranks v. Ross, 313 F.3d 184, 195 (4th Cir. 2002) (citation omitted). On the other hand,\\n\\njust as a plaintiff cannot assert standing based on an alleged injury that lies at the end of a\\n\\n“highly attenuated chain of possibilities,” Clapper, 568 U.S. at 410, a plaintiff’s claim is\\n\\nnot ripe for judicial review “if it rests upon contingent future events that may not occur as\\n\\nanticipated, or indeed may not occur at all.” Scoggins, 718 F.3d at 270 (quoting Texas v.\\n\\nUnited States, 523 U.S. 296, 300 (1998)).\\n\\n 19\\n\\f The two claims that South Carolina advances before this Court rest on the premise\\n\\nthat South Carolina will be the permanent repository of the weapons-grade nuclear\\n\\nmaterial currently stored at the Savannah River Site. But, numerous “contingent future\\n\\nevents,” id., must occur before South Carolina becomes the permanent repository of the\\n\\nnuclear material, see supra Part II.A. In particular, the Dilute and Dispose method must\\n\\nprove unworkable. The Department of Energy must fail to identify an alternative method\\n\\nof disposal and breach its commitment to dispose of the waste. And Congress or the\\n\\ncourts must set aside or refuse to enforce the statutory mechanisms currently in place to\\n\\nensure timely removal of the nuclear material. All of these “future uncertainties,”\\n\\nFranks, 313 F.3d at 195, lead us to conclude that the two claims at issue are not ripe for\\n\\nreview at this time—at least as presented by South Carolina. Accordingly, the ripeness\\n\\ndoctrine provides an additional basis for our holding that the district court was without\\n\\njurisdiction to enter the preliminary injunction.\\n\\n III.\\n\\n In sum, the only theory of injury advanced by South Carolina—that South\\n\\nCarolina will be the permanent repository of the nuclear material currently stored at the\\n\\nSavannah River Site—rests upon a “highly attenuated chain of possibilities,” Clapper,\\n\\n568 U.S. at 410, and “contingent future events that may not occur as anticipated, or\\n\\nindeed may not occur at all.” Scoggins, 718 F.3d at 270. In such circumstances, we must\\n\\nconclude that South Carolina lacks Article III standing to advance the two claims that\\n\\nserve as the basis of the district court’s injunction and that those two claims are not ripe\\n\\nfor review.\\n\\n 20\\n\\f That the two claims are not currently justiciable does not mean that they never will\\n\\nbe so. If uncertainty as to several links in the chain of possibilities is resolved, then\\n\\nSouth Carolina’s alleged injury may move from the speculative to the concrete, and\\n\\ntherefore the two claims also may become ripe for review. But until that uncertainty is\\n\\nlifted, the Constitution demands that we withhold judicial review.\\n\\n Accordingly, we vacate the preliminary injunction imposed by the district court\\n\\nand remand the case for further proceedings not inconsistent with this opinion.\\n\\n\\n\\n VACATED AND REMANDED\\n\\n\\n\\n\\n 21\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":89,"cells":{"id":{"kind":"number","value":4579697,"string":"4,579,697"},"name":{"kind":"string","value":"Fenyang Ajamu STEWART, Plaintiff - Appellant, v. Andrei IANCU, Defendant - Appellee."},"name_abbreviation":{"kind":"string","value":"Fenyang Stewart v. Andrei Iancu"},"decision_date":{"kind":"string","value":"2019-01-08"},"docket_number":{"kind":"string","value":"17-1815"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Gregory, Motz, Wynn\", \"parties\": \"\", \"opinions\": [{\"author\": \"WYNN, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-1815\\n\\n\\nFENYANG AJAMU STEWART,\\n\\n Plaintiff - Appellant,\\n\\n v.\\n\\nANDREI IANCU,\\n\\n Defendant - Appellee.\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. Leonie M. Brinkema, District Judge. (1:16-cv-00213-LMB-JFA)\\n\\n\\nArgued: October 30, 2018 Decided: January 8, 2019\\n\\n\\nBefore GREGORY, Chief Judge, MOTZ and WYNN, Circuit Judges.\\n\\n\\nReversed and remanded by published opinion. Judge Wynn wrote the opinion, in which\\nChief Judge Gregory and Judge Motz joined.\\n\\n\\nARGUED: Kevin Spencer Elliker, HUNTON ANDREWS KURTH LLP, Richmond,\\nVirginia, for Appellant. Dennis Carl Barghaan, Jr., OFFICE OF THE UNITED STATES\\nATTORNEY, Alexandria, Virginia, for Appellee. ON BRIEF: G. Zachary Terwilliger,\\nUnited States Attorney, OFFICE OF THE UNITED STATES ATTORNEY, Alexandria,\\nVirginia, for Appellee.\\n\\fWYNN, Circuit Judge:\\n\\n This appeal arises from the district court’s determination that Fenyang Ajamu\\n\\nStewart (“Stewart”) is required to wait longer than 180 days to commence a civil action\\n\\nunder Title VII and the Rehabilitation Act after amending his initial administrative\\n\\ncomplaint before the relevant agency. But the text of Title VII, as well as the legislative\\n\\ncontext and purpose, plainly states that a claimant may commence a civil action 180 days\\n\\nfrom “the filing of the initial charge.” 42 U.S.C. § 2000e-16(c) (emphasis added). We,\\n\\ntherefore, reverse the district court and remand for further proceedings.\\n\\n I.\\n\\n Stewart worked as a patent examiner for the U.S. Patent and Trademark Office\\n\\n(“PTO”). He suffers from bulging discs in his lower back and radiculopathy, resulting\\n\\nfrom compression of his sciatic nerve, as well as post- and continuous-traumatic stress\\n\\ndisorder. Because of these medical conditions, Stewart filed a reasonable\\n\\naccommodation request with the PTO in April 2014. Specifically, he requested that he\\n\\nnot be required to (1) come into work at a specified, mandatory time; (2) report his work\\n\\nschedule to his supervisor; and (3) schedule his meetings before 12:00 p.m., as his pain\\n\\nmedications caused morning grogginess. In addition, Stewart requested an ergonomic\\n\\nchair and keyboard, a standing desk, and a foot stool.\\n\\n On September 19, 2014, the PTO granted Stewart’s requests for the keyboard,\\n\\nstanding desk, and foot stool. Stewart had already received an ergonomic chair by that\\n\\npoint. Regarding his work schedule, the PTO determined that Stewart was already on the\\n\\nIncreased Flexitime Program work schedule, which permitted him sufficient flexibility to\\n\\n\\n 2\\n\\f“work around any difficulties” and that Stewart’s supervisor, when possible, would\\n\\nschedule meetings specifically designed for Stewart after 12:00 pm. However, the PTO\\n\\ndenied Stewart’s request not to report his work schedule to his supervisor, as such a\\n\\nrequest would unduly burden his supervisor and the agency’s ability to oversee and\\n\\nadminister Stewart’s work.\\n\\n Stewart filed a formal complaint with the PTO’s Office of Equal Employment\\n\\nOpportunity and Diversity on July 14, 2015, challenging the PTO’s denial of his request\\n\\nfor accommodations, asserting a hostile work environment and discrimination, and\\n\\nalleging various claims of retaliation. Stewart amended this administrative complaint\\n\\neight times. After each of these amendments, the PTO’s Office of Equal Employment\\n\\nOpportunity and Diversity responded with a notice advising Stewart that (1) he may\\n\\namend his formal complaint at any time before the investigation is complete, and any\\n\\nnew claims “must be like or related to the claims raised” in the original complaint; and\\n\\n(2) he may “file a civil action in an appropriate United States District Court at any time\\n\\nafter 180 days have passed from the date [he] filed [his] original complaint. 29 C.F.R. §\\n\\n1614.407(b).” J.A. 114.\\n\\n On February 29, 2016—more than 180 days after the filing of his original\\n\\nadministrative complaint, but less than 180 days after the filing of several of the\\n\\namendments—Stewart filed pro se a civil action in the District Court for the Eastern\\n\\nDistrict of Virginia, alleging numerous violations of the Rehabilitation Act of 1973, 29\\n\\nU.S.C. § 701 et seq., and Title VII of the Civil Rights Act of 1964, 42 U.S.C. § 2000e et\\n\\nseq. Stewart’s claims rested on the PTO’s alleged failure to accommodate his\\n\\n\\n 3\\n\\fdisabilities; a hostile work environment; reprisal for participating in protected Equal\\n\\nEmployment Opportunity activity; disparate treatment discrimination on the basis of\\n\\ndisability and failure to accommodate; and retaliation for requesting reasonable\\n\\naccommodation. Stewart later amended the complaint in April 2016, adding two counts.\\n\\n The PTO filed a motion to dismiss, arguing that Stewart’s suit was premature\\n\\nunder both 42 U.S.C. § 2000e-16(c) and 29 C.F.R. § 1614.407(b) because he had not\\n\\nexhausted his administrative remedies. According to the PTO, Stewart was required to\\n\\nwait to file a civil action until the conclusion of the agency’s investigation period. That\\n\\ninvestigation period is extended when employees amend their administrative complaint to\\n\\nthe earlier of 180 days after the last amendment or 360 days after the filing of the initial\\n\\ncomplaint. 29 C.F.R. §§ 1614.106(e)(2); 1614.108(f).\\n\\n On March 17, 2017, the district court dismissed Stewart’s case without prejudice\\n\\nfor lack of subject matter jurisdiction. The district court held that Stewart had failed to\\n\\nexhaust his administrative remedies because under Section 1614.407(b), he was required\\n\\nto wait until July 8, 2016, the earlier of 180 days after Stewart’s last amendment or 360\\n\\ndays after the filing of his initial complaint, to file a civil action in federal court. Stewart\\n\\ntimely appealed the district court’s decision.\\n\\n II.\\n\\n A.\\n\\n Stewart alleges violations of both the Rehabilitation Act and Title VII.\\n\\nRehabilitation Act claims “must comply with the same administrative procedures that\\n\\ngovern federal employee Title VII claims.” Wilkinson v. Rumsfeld, 100 F. App’x 155,\\n\\n\\n 4\\n\\f157 (4th Cir. 2004). Section 717, codified at 42 U.S.C. § 2000e-16, amended Title VII to\\n\\npermit federal employees to file a civil action for employment discrimination under\\n\\ncertain circumstances. Federal employees may file a civil action based upon their\\n\\nadministrative complaint (1) within 90 days of receipt of notice of final agency action or\\n\\n(2) after 180 days from “the filing of the initial charge” with the agency, if there has been\\n\\nno final agency action on the complaint.\\n\\n In addition to 42 U.S.C. § 2000e-16, federal regulations govern the process for\\n\\nfiling a civil action based on employment discrimination. Congress has delegated to the\\n\\nEqual Employment Opportunity Commission (“EEOC”) the authority to promulgate\\n\\nregulations to implement Title VII. E.E.O.C. v. Randstad, 685 F.3d 433, 444 (4th Cir.\\n\\n2012). Accordingly, the EEOC has enacted regulations regarding individuals’ ability to\\n\\n(1) amend their administrative complaint and (2) file suit in federal court under Title VII.\\n\\nThese regulations reinforce Section 2000e-16. A federal employee may amend a\\n\\ncomplaint “at any time prior to the conclusion of the investigation to include issues or\\n\\nclaims like or related to those raised in the complaint.” 29 C.F.R. § 1614.106(d).\\n\\nEchoing the language of 42 U.S.C. § 2000e-16(c), the EEOC’s regulations also state that\\n\\nfederal employees seeking relief under Title VII and the Rehabilitation Act may file a\\n\\ncivil action in federal district court “[a]fter 180 days from the date of filing an individual\\n\\nor class complaint if an appeal has not been filed and final action has not been taken.” 29\\n\\nC.F.R. § 1614.407(b).\\n\\n\\n\\n\\n 5\\n\\f B.\\n\\n We begin with the threshold question of whether Title VII’s 180-day waiting\\n\\nperiod found in Section 2000e-16(c) is a jurisdictional bar, a question of first impression\\n\\nin this circuit. 1 Although the PTO filed its motion to dismiss under Fed. R. Civ. P.\\n\\n12(b)(6), the district court dismissed Stewart’s case under Fed. R. Civ. P. 12(b)(1) for\\n\\nlack of subject-matter jurisdiction, stating that the “administrative exhaustion\\n\\nrequirements for the Rehabilitation Act and Title VII claims are jurisdictional,” and\\n\\nStewart failed to exhaust his administrative remedies. J.A. 234 n.4. For the following\\n\\nreasons, we conclude that the district court incorrectly held that Section 2000e-16(c)’s\\n\\n180-day waiting period is jurisdictional.\\n\\n Title VII directs federal employees to exhaust administrative remedies before\\n\\nfiling suit. Pueschel v. United States, 369 F.3d 345, 353 (4th Cir. 2004). Requiring\\n\\nexhaustion of administrative remedies serves twin objectives: protecting agency authority\\n\\n\\n 1\\n We have previously treated certain Title VII exhaustion requirements as\\njurisdictional—for example, filing a charge of discrimination with the EEOC, see Jones\\nv. Calvert Grp., Ltd., 551 F.3d 297, 300 (4th Cir. 2009)—but have never considered\\nwhether the 180-day waiting period in Section 2000e-16(c) is a jurisdictional\\nprerequisite. We also recognize that circuits have split on whether the failure to exhaust\\nadministrative remedies under Title VII, broadly conceived, is a jurisdictional\\nrequirement. Again, however, none of these cases implicate the mandatory 180-day\\nwaiting period in Section 2000e-16(c) that is before us in this case. Compare Peppers v.\\nCobb Cty., 835 F.3d 1289, 1296–97 (11th Cir. 2016) (treating the administrative\\nexhaustion requirement as a jurisdictional prerequisite to filing a Title VII action), with\\nFowlkes v. Ironworkers Local 40, 790 F.3d 378, 385 (2d Cir. 2015) (holding that the\\nfailure to exhaust administrative remedies does not raise a jurisdictional bar); Artis v.\\nBernanke, 630 F.3d 1031, 1034 n.4 (D.C. Cir. 2011) (same); Frederique-Alexandre v.\\nDep’t of Nat. & Envtl. Res. of Puerto Rico, 478 F.3d 433, 440 (1st Cir. 2007) (same).\\n\\n\\n\\n 6\\n\\fin the administrative process and “promot[ing] efficiency” in the resolution of claims.\\n\\nWoodford v. Ngo, 548 U.S. 81, 89 (2006). By avoiding the “premature interruption of the\\n\\nadministrative process,” exhaustion requirements ensure that agencies are provided the\\n\\nfirst opportunity to “exercise [] discretion” or “apply [] expertise.” McKart v. United\\n\\nStates, 395 U.S. 185, 193–94 (1969). The 180-day waiting period serves these purposes:\\n\\nit ensures that the employer is “put on notice of the alleged violations” to facilitate out-\\n\\nof-court resolution and permits sufficient, but finite, time for the agency to address the\\n\\ndiscrimination charges in the first instance. Miles v. Dell, Inc., 429 F.3d 480, 491 (4th\\n\\nCir. 2005). Indeed, courts have regularly characterized Section 2000e-16(c)’s 180-day\\n\\nwaiting period as an exhaustion requirement. See Murthy v. Vilsack, 609 F.3d 460, 465\\n\\n(D.C. Cir. 2010); Brown v. Snow, 440 F.3d 1259, 1263 (11th Cir. 2006).\\n\\n However, it bears noting that the 180-day waiting period also is not a paradigmatic\\n\\nexhaustion requirement. Unlike most administrative exhaustion requirements premised\\n\\non agency action, after which injured parties may “seek review of an adverse decision\\n\\nand obtain a remedy” if warranted, the 180-day waiting period is satisfied by agency\\n\\ninaction. Darby v. Cisneros, 509 U.S. 137, 144 (1993) (citation omitted). Indeed,\\n\\nCongress passed Section 2000e-16(c) of Title VII in 1972 precisely because of its\\n\\nrecognition that federal employees frequently encountered an “administrative quagmire”\\n\\nin filing charges of discrimination. H.R. Rep. 92–238, at 12 (June 2, 1971). The 180-day\\n\\nwaiting period therefore “confines agencies and the EEOC to a tight schedule” and\\n\\nsignals congressional recognition that “the doctrine of exhaustion of remedies . . . had\\n\\nbecome [a] barrier to meaningful court review.” Wilson v. Pena, 79 F.3d 154, 167 (D.C.\\n\\n\\n 7\\n\\fCir. 1996) (quoting Grubbs v. Butz, 514 F.2d 1323, 1328 (D.C. Cir. 1975)). In light of\\n\\nthis legislative context, the 180-day waiting period functions more like a mandatory\\n\\nprocedural hurdle for litigants than an affirmative agency step potentially giving rise to a\\n\\nremedy on review.\\n\\n This distinction informs our consideration of whether Section 2000e-16(c)’s 180-\\n\\nday waiting period requirement is also a jurisdictional requirement. Not all exhaustion\\n\\nrequirements are jurisdictional. Rather, we have recognized that certain exhaustion\\n\\nrequirements may be jurisdictional while others are not. For example, in Davis v. North\\n\\nCarolina Department of Correction, we specifically distinguished one exhaustion\\n\\nrequirement as jurisdictional—the entitlement to a right-to-sue letter from the EEOC—\\n\\nfrom Title VII’s “timely filing requirements,” which the Supreme Court has held are not\\n\\njurisdictional. 48 F.3d 134, 140 (4th Cir. 1995) (citing Zipes v. Trans World Airlines,\\n\\nInc., 455 U.S. 385, 393 (1982)); see also Laber v. Harvey, 438 F.3d 404, 429 n.25 (4th\\n\\nCir. 2006) (concluding that the 90-day time limit set forth in 42 U.S.C. § 2000e–16(c) is\\n\\nnot a jurisdictional requirement).\\n\\n In recent years, the Supreme Court repeatedly has cautioned courts not to\\n\\n“confuse[] or conflate[]” subject-matter jurisdiction, on the one hand, with the “essential\\n\\ningredients of a federal claim for relief,” on the other. Arbaugh v. Y & H Corp., 546 U.S.\\n\\n500, 503 (2006). Applying this distinction, the Supreme Court has differentiated between\\n\\nnon-jurisdictional “claim-processing” rules and jurisdictional rules that govern a court’s\\n\\nadjudicatory authority. Kontrick v. Ryan, 540 U.S. 443, 456 (2004); see also Gonzalez v.\\n\\nThaler, 565 U.S. 134, 141 (2012) (pressing a “stricter distinction” between these two\\n\\n\\n 8\\n\\fcategories of rules). In particular, the Supreme Court has clarified that most time bars are\\n\\n“quintessential claim-processing rules,” which “promote the orderly progress of litigation\\n\\nby requiring that the parties take certain procedural steps at certain specified times.”\\n\\nHenderson v. Shinseki, 562 U.S. 428, 435 (2011) (holding that a statute requiring filing of\\n\\nnotice of appeal within 180 days of administrative decision constituted a “claim-\\n\\nprocessing rule” and therefore was not jurisdictional). Such rules do not strip a court of\\n\\njudicial authority to hear a case, even when the time limits are “framed in mandatory\\n\\nterms.” United States v. Kwai Fun Wong, 135 S. Ct. 1625, 1632 (2015) (holding that\\n\\ncertain timely filing provisions in the Federal Torts Claims Act were not jurisdictional).\\n\\n Instead, the Supreme Court has established a clear statement rule for\\n\\ndetermining whether procedural rules, including time bars, are jurisdictional. Only if the\\n\\nstatutory text “plainly show[s] that Congress imbued a procedural bar with jurisdictional\\n\\nconsequences” should a court treat a rule as jurisdictional. Id. Put otherwise, Congress\\n\\nmust explicitly “tag” a procedural bar “as jurisdictional.” Id. In conducting this clear\\n\\nstatement inquiry, the Supreme Court has looked to several factors, including the\\n\\nstatutory text (if it speaks in “jurisdictional terms”); the placement of the rule (if it is\\n\\nlocated in the jurisdiction-granting provision of the statute); and legislative context.\\n\\nHenderson, 562 U.S. at 438.\\n\\n Here, Congress has done nothing to “tag” as jurisdictional the 180-day waiting\\n\\nperiod. The text of Section 2000e-16(c) addresses only the timeliness of claims; it does\\n\\nnot refer to the district courts’ “authority to hear untimely suits.” Kwai Fun Wong, 135 S.\\n\\nCt. 1625, 1628 (2015). Much like the filing deadline at issue in Henderson, Section\\n\\n\\n 9\\n\\f2000e-16(c) does not contain “jurisdictional language”—language dictating that judicial\\n\\nreview be obtained within a prescribed time and manner before a particular court.\\n\\nHenderson, 562 U.S. at 438. Simply because the 180-day waiting period is “cast in\\n\\nmandatory language” does not render it jurisdictional. Id. at 439.\\n\\n In addition, Section 2000e-16(c)’s placement within Title VII is distinct from\\n\\nthose provisions pertaining to jurisdiction. Section 2000e-16(c), titled “Employment by\\n\\nFederal Government,” lays out the respective 90-day filing period and 180-day waiting\\n\\nperiods before stating that the federal employee “may file a civil action as provided in\\n\\nsection 2000e-5.” 42 U.S.C. § 2000e-16(c) (emphasis added). Section 2000e-5, titled\\n\\n“Enforcement provisions,” mandates that federal district courts “shall have jurisdiction of\\n\\nactions brought under this subchapter.” 42 U.S.C. § 2000e-5(f)(3). These statutory\\n\\nsections serve different functions: on the one hand, Section 2000e-16(c) extends Title VII\\n\\nprotections to federal employees, and on the other, Section 2000e-5, as the enforcement\\n\\nprovision, prescribes jurisdictional requirements. Nothing “conditions the jurisdictional\\n\\ngrant [in Section 2000e-5(f)(3)] on the limitations periods [in Section 2000e-16(c)], or\\n\\notherwise links those separate provisions.” Kwai Fun Wong, 135 S. Ct. at 1633; see also\\n\\nGad v. Kansas State Univ., 787 F.3d 1032, 1038 (10th Cir. 2015) (noting that “a Title VII\\n\\nstatutory requirement’s classification as jurisdictional or non-jurisdictional turns in large\\n\\npart on whether it is located in Title VII’s jurisdictional subsection—42 U.S.C. § 2000e-\\n\\n5(f)(3)). This division further supports a conclusion that the 180-day waiting period is\\n\\nnot a jurisdictional requirement but rather a “prudential prerequisite to suit,” Davis v.\\n\\n\\n\\n\\n 10\\n\\fFort Bend Cty., 893 F.3d 300, 305 (5th Cir. 2018), or “statutory precondition,” Vinieratos\\n\\nv. U.S. Dep’t of Air Force, 939 F.2d 762, 768 n.5 (9th Cir. 1991).\\n\\n In considering this issue, we emphasize the subtle, but important, distinction\\n\\nbetween those exhaustion requirements that operate as a jurisdictional bar and those that\\n\\nmerely function as a statutory prerequisite to filing suit under Title VII. See Vinieratos,\\n\\n939 F.2d at 768 n.5 (9th Cir. 1991). Because we conclude that Section 2000e-16(c)’s\\n\\n180-day waiting period is akin to a “claim-processing” rule that imposes procedural\\n\\nobligations on litigants, rather than implicates judicial authority to hear a class of cases,\\n\\nwe hold that the 180-day waiting period is not jurisdictional.\\n\\n Our holding also prevents the “drastic” consequences of treating a procedural rule\\n\\nas jurisdictional—consequences that “alter[] the normal operation of our adversarial\\n\\nsystem.” Henderson, 562 U.S. at 434. Jurisdictional defects can be raised at any time by\\n\\nthe parties or sua sponte by the courts, even post-judgment, which may result in the\\n\\n“waste of judicial resources and may unfairly prejudice litigants.” Id. Because of the\\n\\ngravity of a jurisdictional label, the Supreme Court has repeatedly and explicitly\\n\\ndemanded “discipline” in this inquiry. Id. at 435.\\n\\n To be clear, we do not hold that all exhaustion requirements set forth in Title VII\\n\\nare non-jurisdictional. Rather, whether a particular exhaustion requirement—in Title VII\\n\\nor any other statute—is jurisdictional turns on the statutory language and purpose of the\\n\\nexhaustion provision at issue. Here, Section 2000e-16(c) includes no language clearly\\n\\nindicating that Congress intended for the provision to serve as a jurisdictional bar.\\n\\nFurther, in practice, Section 2000e-16(c)’s 180-day waiting period functions more closely\\n\\n\\n 11\\n\\fas a “time prescription,” which imposes a mandatory obligation on litigants but does not\\n\\ngovern a court’s jurisdiction. Arbaugh, 546 U.S. at 510; see also Stroy v. Gibson, 896\\n\\nF.3d 693, 698 (5th Cir. 2018) (treating Section 2000e-16(c)’s 180-day waiting period as a\\n\\n“precondition to filing suit,” not a jurisdictional requirement).\\n\\n Accordingly, the district court erred in dismissing this case under Federal Rule of\\n\\nCivil Procedure 12(b)(1). Instead, it should have considered the 180-day waiting period\\n\\nas a non-jurisdictional rule and decided the case under Federal Rule of Civil Procedure\\n\\n12(b)(6).\\n\\n III.\\n\\n A.\\n\\n Having determined that Section 2000e-16(c)’s 180-day waiting period is not\\n\\njurisdictional, we now turn to whether the district court erred in dismissing Stewart’s\\n\\naction under that provision. “We review de novo the grant of a motion to dismiss for\\n\\nfailure to state a claim [under Rule 12(b)(6)]. In so doing, we must accept as true all of\\n\\nthe factual allegations contained in the complaint.” Gerner v. Cty. of Chesterfield, Va.,\\n\\n674 F.3d 264, 266 (4th Cir. 2012) (citation omitted).\\n\\n Stewart’s appeal requires us to construe the statutory language of Section 2000e-\\n\\n16(c), and that provision’s 180-day waiting period, in particular. When construing a\\n\\nstatute, we “first and foremost strive to implement congressional intent by examining the\\n\\nplain language.” Minor v. Bostwick Laboratories, Inc., 669 F.3d 428 (4th Cir. 2012)\\n\\n(citation omitted). “[U]nless otherwise defined, words will be interpreted as taking their\\n\\nordinary, contemporary, common meaning.” Kennedy v. St. Joseph’s Ministries, Inc.,\\n\\n\\n 12\\n\\f657 F.3d 189, 192 (4th Cir. 2011) (citation omitted). In interpreting the plain language of\\n\\nthe statute, we also look to “the specific context in which the language is used, and the\\n\\nbroader context of the statute as a whole,” Minor, 669 F.3d at 434–35 (citations omitted),\\n\\nas well as a statute’s legislative history as additional evidence of congressional intent,\\n\\nElm Grove Coal Co. v. Director, O.W.C.P., 480 F.3d 278, 293 (4th Cir. 2007). Here,\\n\\neach of these factors indicates that Stewart’s amendments of his complaint did not restart\\n\\nthe 180-day clock.\\n\\n We begin with the plain language of the statute. In relevant part, Section 2000e-\\n\\n16(c) permits aggrieved federal employees to file a civil action 180 days “from the filing\\n\\nof the initial charge with the department, agency, or unit” if the agency has “fail[ed] to\\n\\ntake final action on his complaint.” 42 U.S.C. § 2000e-16(c) (emphasis added). Given\\n\\nthe ordinary meaning of the word “initial,” Section 2000e-16(c) requires that the 180-day\\n\\nwaiting period begin upon the filing of the first, original charge. See Webster’s Third\\n\\nNew Int’l Dictionary 1163 (3d ed. 1976) (defining “initial” as “of or relating to the\\n\\nbeginning; marking the commencement”); American Heritage Dictionary of the English\\n\\nLanguage 902 (4th ed. 2009) (defining “initial” as “of, relating to, or occurring at the\\n\\nbeginning; first”). Therefore, in Stewart’s case, the 180-day waiting period began on July\\n\\n14, 2015, the date he filed his “initial,” formal administrative complaint of discrimination\\n\\nand retaliation before the PTO’s Office of Equal Employment and Diversity.\\n\\n The statute’s use of the modifier “initial” also implicitly allows for the possibility\\n\\nof subsequent amendments—that there may well be additional “charge[s]” that follow the\\n\\n“initial charge.” Accordingly, the 180-day waiting period does not reset upon subsequent\\n\\n\\n 13\\n\\famendments to the administrative complaint. Had Congress not contemplated the\\n\\npossibility of amendments to the complaint, there would have been no reason to use the\\n\\nword “initial.” See Alaska Dep’t of Envtl. Conservation v. E.P.A., 540 U.S. 461, 489 n.13\\n\\n(2004) (observing it is “a cardinal principle of statutory construction that a statute ought,\\n\\nupon the whole, to be so construed that, if it can be prevented, no clause, sentence, or\\n\\nword shall be superfluous, void, or insignificant”) (citations and alterations omitted).\\n\\nTherefore, we hold that upon the passage of 180 days from the filing of the original\\n\\ncomplaint, and absent agency final action on the complaint, federal employees may file a\\n\\ncivil action, regardless of subsequent amendments to that complaint. 2\\n\\n Turning to the legislative context, Congress passed Section 2000e-16(c) of Title\\n\\nVII in 1972 because of its recognition that aggrieved federal employees did not have\\n\\nsufficient access to the courts under Title VII. S. Rep. 92–415 at 16 (1971). Before the\\n\\n1972 Act, the “effective availability of either administrative or judicial relief” for federal\\n\\nemployees was uncertain. Brown v. General Servs. Admin., 425 U.S. 820, 825 (1976).\\n\\nFederal employees often faced an “administrative quagmire” in which parties had to wait\\n\\nseveral years in the overburdened administrative process. H.R. Rep. 92–238, at 12 (June\\n\\n\\n 2\\n In an unpublished per curiam opinion, we summarily affirmed a district court’s\\nholding that federal employees must wait beyond the 180-day period when they amend\\ntheir complaints. Laber v. Harvey, No. 1:05-cv-00803-CMH, 2005 WL 3008510, at *1\\n(E.D. Va. Nov. 7, 2005), aff’d, 204 F. App’x 332 (4th Cir. 2006). We are not bound by\\nthat opinion, which is devoid of reasoning. See Collins v. Pond Creek Mining Co., 468\\nF.3d 213, 219 (4th Cir. 2006) (noting that “we ordinarily do not accord precedential value\\nto our unpublished decisions” and they are “entitled only to the weight they generate by\\nthe persuasiveness of their reasoning”) (citation omitted).\\n\\n\\n\\n 14\\n\\f2, 1971). Ensuring that federal employees had “access to the courts” therefore drove the\\n\\npassage of Section 2000e-16(c). S. Rep. No. 92–415, at 16 (1971). The 180-day waiting\\n\\nperiod directly serves that end. In discussing Section 2000e-16(c)’s 180-day waiting\\n\\nprovision in the context of EEOC inaction, the D.C. Circuit observed that:\\n\\n The 180 day [waiting period] provision represents a Congressional\\n determination that providing prompt access to the courts in discrimination\\n disputes is so important that the administrative process will be given only a\\n finite time to deal alone with a given dispute. Indeed, the Act is in part a\\n response to Congressional realization that “the doctrine of exhaustion of\\n remedies . . . had become [a] barrier to meaningful court review.”\\n\\nWilson, 79 F.3d at 167 (quoting Grubbs, 514 F.2d at 1328). Allowing agencies to\\n\\nrepeatedly delay individuals’ ability to go to court, simply because they have amended\\n\\ntheir administrative complaints, would frustrate a “congressional policy to make the\\n\\ncourts the final tribunal for the resolution of controversies over charges of discrimination\\n\\nafter all administrative remedies have been exhausted.” Koger v. Ball, 497 F.2d 702, 706\\n\\n(4th Cir. 1974). Although Section 2000e-16(c) “provides for a careful blend of\\n\\nadministrative and judicial enforcement powers,” we cannot overlook that, in passing the\\n\\nprovision, Congress intended federal employees to have a robust judicial remedy, and\\n\\nready access to the courts, for employment discrimination claims. Brown, 425 U.S. at\\n\\n833\\n\\n Our conclusion also comports with the broader purpose of Title VII as a “remedial\\n\\nscheme in which laypersons, rather than lawyers, are expected to initiate the process.”\\n\\nSydnor, 681 F.3d at 594 (citation omitted); see also Alvarado v. Board of Trustees of\\n\\nMontgomery Community College, 848 F.2d 457, 460 (4th Cir. 1988) (“Title VII does not\\n\\n\\n\\n 15\\n\\frequire procedural exactness from lay complainants.”). We must be wary of “overly\\n\\ntechnical concerns” laying a “tripwire for hapless plaintiffs.” Syndor, 681 F.3d at 594.\\n\\nHere, for example, the PTO repeatedly informed Stewart, after each of his amendments—\\n\\nand in accordance with the statute’s plain language—that he could file a civil action “at\\n\\nany time after 180 days have passed from the date [he] filed [his] original complaint.”\\n\\nJ.A. 114. Permitting the agency to repeatedly confuse litigants in this manner would only\\n\\nfurther pervert Title VII’s remedial purpose.\\n\\n B.\\n\\n In support of its position that Stewart was required to wait beyond the initial 180-\\n\\nday waiting period, the PTO makes several arguments. First, the PTO argues that Section\\n\\n2000e-16(c)’s statutory text is “ambiguous” because it uses two different terms,\\n\\n“complaint” and “charge.” Second, the PTO argues that the EEOC’s regulations support\\n\\ntethering the 180-day waiting period to the agency’s extended investigation period for\\n\\namended complaints. Third, the PTO argues that should we reverse the district court’s\\n\\nholding, we would incentivize gamesmanship in Title VII claims. Each of these\\n\\narguments is unavailing.\\n\\n In support of its first argument—that Section 2000e-16(c)’s statutory text is\\n\\nambiguous 3—the PTO emphasizes Congress’s use of two terms within the statute:\\n\\n\\n 3\\n In repeatedly referring to Section 2000e-16(c)’s purported “ambiguity,” the PTO\\nappears to be implicitly invoking, or at least evoking, Chevron deference to its\\ninterpretation of the statute. However, the statute is not ambiguous. Further, we only\\ngrant Chevron deference to “an agency’s construction of the statute which it\\nadministers.” Chevron, U.S.A., Inc. v. Nat. Res. Def. Council, Inc., 467 U.S. 837, 842\\n(Continued)\\n\\n 16\\n\\f“complaint” and “charge.” The PTO argues that the term “complaint” in Section 2000e-\\n\\n16(c) references “an employee’s general use of the administrative process” to allege\\n\\nunlawful discrimination, while the phrase “initial charge” is “the first ‘statement’”\\n\\nthrough which an employee identifies this discrimination. Appellee’s Br. at 25–26. To\\n\\nthe PTO, it bears significance that Congress did not use the phrase “initial complaint” in\\n\\nSection 2000e-16(c) but rather “initial charge,” thus indicating that “Congress did not\\n\\nseek to trigger the 180-day period upon the commencement of the EEO process\\n\\ngenerally.” Appellee’s Br. at 26 (emphasis in original).\\n\\n Even if we were to accept the PTO’s proposed distinction between these two\\n\\nterms, such a distinction does not aid the PTO’s position. If we treat “initial charge” as\\n\\nthe first, informal “statement” through which an employee alleges unlawful\\n\\ndiscrimination, then the 180-day waiting period would be satisfied at the same time or\\n\\nearlier than under the reading we adopt because a “charge,” so conceived, never\\n\\ntemporally follows a “complaint.” Under the PTO’s construction, Stewart’s “initial\\n\\ncharge” occurred on April 30, 2015, when he submitted a document to the PTO’s Office\\n\\nof Equal Employment Opportunity and Diversity alleging harassment and discrimination\\n\\non the basis of disability. Accepting the PTO’s position, then, would only hasten the date\\n\\nupon which Stewart could file a civil action. More significantly, PTO’s position in no\\n\\n\\n\\n\\n(1984). The EEOC, not the PTO, administers Title VII, so even if Chevron deference\\nwere implicated here, the PTO is entitled to no such deference. The record includes no\\nindication that the EEOC concurs in the PTO’s construction of Section 2000e-16(c).\\n\\n\\n\\n 17\\n\\fway explains Congress’s express use of the word “initial,” which serves as the crux of\\n\\nour construction of Section 2000e-16(c)’s 180-day waiting period. The term “initial”\\n\\nmakes clear that Congress intended to begin the 180-day waiting period from the filing of\\n\\nthe original complaint, regardless of whether subsequent amendments to that complaint\\n\\nare filed. See United States v. Blannon, 836 F.2d 843, 854 (4th Cir. 1988) (“[A] court\\n\\nmay not manufacture an ambiguity in order to defeat Congress’ intent.”).\\n\\n Next, the PTO argues that the EEOC’s relevant regulations support its position\\n\\nthat Stewart was required to wait longer than 180 days before filing suit. However, we\\n\\nconclude that these regulations only reinforce our interpretation of Section 2000e-16(c).\\n\\n29 C.F.R. § 1614.407(b) mirrors the language found in Section 2000e-16(c), providing in\\n\\nrelevant part that a complainant is authorized under Title VII and the Rehabilitation Act\\n\\nto file a civil action in federal district court “[a]fter 180 days from the date of filing an\\n\\nindividual or class complaint if an appeal has not been filed and final action has not been\\n\\ntaken.” Given the regulation’s use of the term “individual . . . complaint,” the PTO\\n\\ncannot dispute that the 180-day waiting period begins upon filing of the individual\\n\\ncomplaint. Instead, the PTO attempts to wave away the regulation as a “generic rule,”\\n\\nbut this perfunctory argument is not persuasive. Appellee’s Br. at 29.\\n\\n The district court, and the PTO, wrongly tether Section 1614.407(b)’s 180-day\\n\\nwaiting period to other EEOC regulations extending the agency investigation period\\n\\nwhen a complaint has been amended to “within the earlier of 180 days after the last\\n\\namendment to the complaint or 360 days after the filing of the original complaint.” 29\\n\\nC.F.R. §§ 1614.106(e)(2), 1614.108(f). The district court reasoned that otherwise, the\\n\\n\\n 18\\n\\fcourt “would be adjudicating claims that the [PTO] has not yet had the opportunity to\\n\\ninvestigate, let alone adjudicate.” J.A. 236. We disagree for two reasons.\\n\\n First, as discussed above, the district court’s holding is contrary to the plain\\n\\nlanguage of both Section 2000e-16(c) of Title VII and 29 C.F.R. § 1614.407(b). Further,\\n\\nSection 1614.407(b) lacks any textual distinction between filing an initial complaint and\\n\\nfiling an amendment, which is particularly telling given that other regulations in the same\\n\\npart, such as those governing the agency investigation period, do make such a distinction.\\n\\nSee 29 C.F.R. §§ 1614.106(e)(2), 1614.108(f). Section 1614.407(b) does not hinge\\n\\nemployees’ ability to file a civil action on the conclusion of the agency investigation;\\n\\nrather, it establishes a bright-line 180-day waiting period after which the employee can be\\n\\n“assured of having reasonably prompt access to the courts.” Wilson, 79 F.3d at 167 (D.C.\\n\\nCir. 1996).\\n\\n Additionally, the district court neglected an important facet of Title VII claims: we\\n\\nhave long held that courts may in fact adjudicate claims not raised before the agency, if\\n\\ncertain requirements are met. In Hill v. Western Electric Company, Inc., we recognized\\n\\nthe “generally accepted principle” that the “scope of a Title VII lawsuit may extend to\\n\\n‘any kind of discrimination like or related to allegations contained in the charge and\\n\\ngrowing out of such allegations during the pendency of the case’” before the agency. 672\\n\\nF.2d 381, 390 n.6 (4th Cir. 1982). Put otherwise, an “administrative charge of\\n\\ndiscrimination does not strictly limit a Title VII suit which may follow,” and federal\\n\\ncourts may still hear claims that the employee did not raise before the agency, as long as\\n\\nthey are “like or related” and grow out of the allegations during the pendency of the case\\n\\n\\n 19\\n\\fbefore the agency. Sydnor, 681 F.3d at 594. Only “those discrimination claims stated in\\n\\nthe initial charge, those reasonably related to the original complaint, and those developed\\n\\nby reasonable investigation of the original complaint may be maintained in a subsequent\\n\\nTitle VII lawsuit.” Chacko v. Patuxent Institution, 429 F. 3d 505, 506 (4th Cir. 2005)\\n\\n(citation omitted); see also Smith v. First Union Nat. Bank, 202 F.3d 234, 247 (4th Cir.\\n\\n2000) (“If a plaintiff’s claims in her judicial complaint are reasonably related to her\\n\\nEEOC charge and can be expected to follow from a reasonable administrative\\n\\ninvestigation, the plaintiff may advance such claims in her subsequent civil suit.”). Our\\n\\nprecedent makes clear that plaintiffs, although circumscribed by their administrative\\n\\ncomplaints, are not wholly banned from raising claims for the first time before the district\\n\\ncourt, so long as they meet the requirements articulated in Hill and Chacko.\\n\\n Nor is a plaintiff’s ability to raise new claims before the district court cabined to\\n\\nthe context of retaliation claims, as the PTO appeared to briefly suggest at oral argument.\\n\\nOral Argument at 27:53–28:25 (“I don’t think he can amend his complaint, [] unless it\\n\\nwas for retaliation . . . because this Court’s jurisprudence provides that in cases of\\n\\nretaliation, the exhaustion procedures and principles are a little bit different.”). It is true\\n\\nthat we have often addressed a plaintiff’s ability to do so in the specific context of\\n\\nretaliation claims. See Nealon v. Stone, 958 F.2d 584, 590 (4th Cir. 1992). Importantly,\\n\\nhowever, we have never held that the rule applies exclusively in the context of retaliation\\n\\nclaims but rather that retaliation claims “receive extended flexibility” when being\\n\\nconsidered under the general rule referenced in Hill. Clarke v. Richmond Behavioral\\n\\nHealth Auth., No. 3:09CV743, 2011 WL 13274273, at *4 (E.D. Va. Aug. 10, 2011); see\\n\\n\\n 20\\n\\falso Brown v. Runyon, 139 F.3d 888 (4th Cir. 1988) (unpublished opinion) (noting that\\n\\nour precedent “presupposes both that a retaliation count in a Title VII lawsuit be ‘related\\n\\nto’ and have ‘grown out’ of the EEO charge while the administrative charge remained\\n\\npending”). We have reasoned that retaliation claims constitute a subset of the general\\n\\nrule noted in Hill, because “retaliation claims almost always relate back to previously\\n\\nfiled EEO charges, and, therefore, may be raised for the first time in district court without\\n\\nthe requirement that a plaintiff have exhausted his administrative remedies.” Brown, 139\\n\\nF.3d at 888. Accordingly, retaliation claims represent the “inevitable corollary,” but not\\n\\nthe exclusive application, of the “generally accepted principle” articulated in Hill. Id.\\n\\n(quoting Nealon, 958 F.2d at 590). We have therefore left open the possibility that\\n\\ndistrict courts may hear claims for the first time, beyond just retaliation claims, if they are\\n\\n“reasonably related to the original complaint” and “developed by reasonable investigation\\n\\nof the original complaint.” Chacko, 429 F.3d at 506.\\n\\n Indeed, other circuits have recognized the need to grant Title VII plaintiffs\\n\\n“significant leeway” in drafting administrative complaints, given their lack of technical\\n\\nexpertise. Cheek v. W. & S. Life Ins. Co., 31 F.3d 497, 500 (7th Cir. 1994) (citation\\n\\nomitted). Applying this principle of liberal construction, other circuits permit litigants to\\n\\nbring claims not specifically pressed before the agency if they are “like or reasonably\\n\\nrelated to those contained in the [agency] complaint” and if they “reasonably could have\\n\\ndeveloped from the [agency’s] investigation of the charges before it.” Sommerfield v.\\n\\nCity of Chicago, 863 F.3d 645, 648 (7th Cir. 2017); see also Foster v. BNSF Ry. Co., 866\\n\\nF.3d 962, 966 (8th Cir. 2017) (holding same); Freeman v. Oakland Unified Sch. Dist.,\\n\\n\\n 21\\n\\f291 F.3d 632, 636 (9th Cir. 2002) (same). We join these circuits today in reiterating our\\n\\ndecision in Hill and Chacko that plaintiffs may bring Title VII claims for the first time\\n\\nbefore a district court, so long as they are like or reasonably related to charges in the\\n\\noriginal administrative complaint, and if they reasonably could have developed from the\\n\\nagency’s investigation of the original complaint. See Hill, 672 F.2d at 390 n.6; Chacko,\\n\\n429 F.3d at 506.\\n\\n Crucially, this “like or related” limitation also allays the PTO’s third argument\\n\\nregarding gamesmanship. The PTO argues that should we reverse the district court, a\\n\\nfederal employee could file a “perfunctory initial ‘charge,’ seek to add new claims\\n\\nimmediately before the 180-day ‘mark,’ and then file a civil action immediately\\n\\nfollowing that same ‘mark.’” Appellee’s Br. at 28. First, as discussed above, we already\\n\\npermit courts to adjudicate reasonably related claims not heard in the first instance by\\n\\nagencies. The “like or related” limitation limits the universe of charges that the litigant\\n\\nmay bring and guards against the gamesmanship concern that litigants will raise wholly\\n\\nunrelated claims for the first time before a district court.\\n\\n Second, as Stewart correctly points out, existing procedural guardrails further\\n\\nprotect against such gamesmanship. When amending a complaint before the agency, the\\n\\nemployee must file a letter with the agency’s Office of Equal Employment Director\\n\\n“describing the new incident(s) and stating that s/he wishes to amend his/her complaint to\\n\\ninclude the new incident(s).” EEOC Mgmt. Directive 110, Ch. 5.B. The Director must\\n\\nthen review this request to determine if the claims are like or related, and “whether a fair\\n\\nand impartial investigation of the new claims can be accomplished within 360 days of the\\n\\n\\n 22\\n\\foriginal filed complaint.” Id. If not, then the individual must start a new administrative\\n\\nprocess with respect to the new claim. Accordingly, employees cannot game the\\n\\nadministrative process in the way suggested by the PTO. Indeed, if we were to accept the\\n\\ndistrict court’s holding, we may even risk disincentivizing plaintiffs from bringing a “like\\n\\nor related” claim before the agency, as each amendment would only further delay the\\n\\nplaintiff’s access to court. Under the district court’s reading of 42 U.S.C. § 2000e-16(c)\\n\\nand 29 C.F.R. § 1614.407(b), a plaintiff might be better served by holding onto their “like\\n\\nor related” claims until the filing of a civil action. But this outcome would undermine the\\n\\npolicy goals underlying Title VII’s administrative framework to encourage “quicker, less\\n\\nformal, and less expensive resolution of disputes.” Sydnor, 681 F.3d at 593 (quoting\\n\\nChris v. Tenet, 221 F.3d 648, 653 (4th Cir. 2000)).\\n\\n Our holding maintains the careful balance between the Title VII’s administrative\\n\\nframework and judicial remedies, between “providing notice to employers and the\\n\\n[agency] on the one hand and ensuring plaintiffs are not tripped up over technicalities on\\n\\nthe other.” Id. at 594. We recognize the “substantial role” played by the administrative\\n\\nprocess in narrowing “formal litigation.” Chacko, 429 F.3d at 509. But it is equally\\n\\nwell-established that if the claim raised for the first time before the district court contains\\n\\nfactual allegations that “are reasonably related to the factual allegations in the formal\\n\\nlitigation, the connection between the charge and the claim is sufficient.” Id. (citation\\n\\nomitted); see also Kersting v. Wal-Mart Stores, Inc., 250 F.3d 1109, 1118 (7th Cir. 2001)\\n\\n(noting that a plaintiff may pursue a claim not explicitly included in an administrative\\n\\ncomplaint if the allegations are “like or reasonably related to” those in the charge).\\n\\n\\n 23\\n\\f *****\\n\\n The plain text of 42 U.S.C. § 2000e-16(c) and 29 C.F.R. 1614.407(b), as well as\\n\\nthe legislative context and purpose of Title VII, dictate the outcome of this case.\\n\\nContrary to the district court’s holding, Section 2000e-16(c)’s 180-day waiting period\\n\\noperates independently of the agency’s extended investigation window for amended\\n\\ncomplaints. Instead, the 180-day waiting period “gives great weight to the complainant’s\\n\\ninterest in obtaining speedy resolution of the complaint” and ensures ready access to the\\n\\ncourts. Wilson, 79 F.3d at 167. Accordingly, we hold that Section 2000e-16(c)’s 180-\\n\\nday waiting period for filing a civil action, absent agency final action, commences with\\n\\nthe filing of the initial administrative complaint, regardless of subsequent amendments to\\n\\nthat complaint.\\n\\n IV.\\n\\n For the foregoing reasons, we reverse the district court’s dismissal of Stewart’s\\n\\namended complaint and remand for further proceedings.\\n\\n REVERSED AND REMANDED\\n\\n\\n\\n\\n 24\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4356950/\", \"author_raw\": \"WYNN, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"GREGORY"},"judge2":{"kind":"string","value":"MOTZ"},"judge3":{"kind":"string","value":"WYNN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4579697/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Fenyang Ajamu STEWART, Plaintiff - Appellant, v. Andrei IANCU, Defendant - Appellee.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-08\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-1815\n\n\nFENYANG AJAMU STEWART,\n\n Plaintiff - Appellant,\n\n v.\n\nANDREI IANCU,\n\n Defendant - Appellee.\n\n\nAppeal from the United States District Court for the Eastern District of Virginia, at\nAlexandria. Leonie M. Brinkema, District Judge. (1:16-cv-00213-LMB-JFA)\n\n\nArgued: October 30, 2018 Decided: January 8, 2019\n\n\nBefore GREGORY, Chief Judge, MOTZ and WYNN, Circuit Judges.\n\n\nReversed and remanded by published opinion. Judge Wynn wrote the opinion, in which\nChief Judge Gregory and Judge Motz joined.\n\n\nARGUED: Kevin Spencer Elliker, HUNTON ANDREWS KURTH LLP, Richmond,\nVirginia, for Appellant. Dennis Carl Barghaan, Jr., OFFICE OF THE UNITED STATES\nATTORNEY, Alexandria, Virginia, for Appellee. ON BRIEF: G. Zachary Terwilliger,\nUnited States Attorney, OFFICE OF THE UNITED STATES ATTORNEY, Alexandria,\nVirginia, for Appellee.\n\fWYNN, Circuit Judge:\n\n This appeal arises from the district court’s determination that Fenyang Ajamu\n\nStewart (“Stewart”) is required to wait longer than 180 days to commence a civil action\n\nunder Title VII and the Rehabilitation Act after amending his initial administrative\n\ncomplaint before the relevant agency. But the text of Title VII, as well as the legislative\n\ncontext and purpose, plainly states that a claimant may commence a civil action 180 days\n\nfrom “the filing of the initial charge.” 42 U.S.C. § 2000e-16(c) (emphasis added). We,\n\ntherefore, reverse the district court and remand for further proceedings.\n\n I.\n\n Stewart worked as a patent examiner for the U.S. Patent and Trademark Office\n\n(“PTO”). He suffers from bulging discs in his lower back and radiculopathy, resulting\n\nfrom compression of his sciatic nerve, as well as post- and continuous-traumatic stress\n\ndisorder. Because of these medical conditions, Stewart filed a reasonable\n\naccommodation request with the PTO in April 2014. Specifically, he requested that he\n\nnot be required to (1) come into work at a specified, mandatory time; (2) report his work\n\nschedule to his supervisor; and (3) schedule his meetings before 12:00 p.m., as his pain\n\nmedications caused morning grogginess. In addition, Stewart requested an ergonomic\n\nchair and keyboard, a standing desk, and a foot stool.\n\n On September 19, 2014, the PTO granted Stewart’s requests for the keyboard,\n\nstanding desk, and foot stool. Stewart had already received an ergonomic chair by that\n\npoint. Regarding his work schedule, the PTO determined that Stewart was already on the\n\nIncreased Flexitime Program work schedule, which permitted him sufficient flexibility to\n\n\n 2\n\f“work around any difficulties” and that Stewart’s supervisor, when possible, would\n\nschedule meetings specifically designed for Stewart after 12:00 pm. However, the PTO\n\ndenied Stewart’s request not to report his work schedule to his supervisor, as such a\n\nrequest would unduly burden his supervisor and the agency’s ability to oversee and\n\nadminister Stewart’s work.\n\n Stewart filed a formal complaint with the PTO’s Office of Equal Employment\n\nOpportunity and Diversity on July 14, 2015, challenging the PTO’s denial of his request\n\nfor accommodations, asserting a hostile work environment and discrimination, and\n\nalleging various claims of retaliation. Stewart amended this administrative complaint\n\neight times. After each of these amendments, the PTO’s Office of Equal Employment\n\nOpportunity and Diversity responded with a notice advising Stewart that (1) he may\n\namend his formal complaint at any time before the investigation is complete, and any\n\nnew claims “must be like or related to the claims raised” in the original complaint; and\n\n(2) he may “file a civil action in an appropriate United States District Court at any time\n\nafter 180 days have passed from the date [he] filed [his] original complaint. 29 C.F.R. §\n\n1614.407(b).” J.A. 114.\n\n On February 29, 2016—more than 180 days after the filing of his original\n\nadministrative complaint, but less than 180 days after the filing of several of the\n\namendments—Stewart filed pro se a civil action in the District Court for the Eastern\n\nDistrict of Virginia, alleging numerous violations of the Rehabilitation Act of 1973, 29\n\nU.S.C. § 701 et seq., and Title VII of the Civil Rights Act of 1964, 42 U.S.C. § 2000e et\n\nseq. Stewart’s claims rested on the PTO’s alleged failure to accommodate his\n\n\n 3\n\fdisabilities; a hostile work environment; reprisal for participating in protected Equal\n\nEmployment Opportunity activity; disparate treatment discrimination on the basis of\n\ndisability and failure to accommodate; and retaliation for requesting reasonable\n\naccommodation. Stewart later amended the complaint in April 2016, adding two counts.\n\n The PTO filed a motion to dismiss, arguing that Stewart’s suit was premature\n\nunder both 42 U.S.C. § 2000e-16(c) and 29 C.F.R. § 1614.407(b) because he had not\n\nexhausted his administrative remedies. According to the PTO, Stewart was required to\n\nwait to file a civil action until the conclusion of the agency’s investigation period. That\n\ninvestigation period is extended when employees amend their administrative complaint to\n\nthe earlier of 180 days after the last amendment or 360 days after the filing of the initial\n\ncomplaint. 29 C.F.R. §§ 1614.106(e)(2); 1614.108(f).\n\n On March 17, 2017, the district court dismissed Stewart’s case without prejudice\n\nfor lack of subject matter jurisdiction. The district court held that Stewart had failed to\n\nexhaust his administrative remedies because under Section 1614.407(b), he was required\n\nto wait until July 8, 2016, the earlier of 180 days after Stewart’s last amendment or 360\n\ndays after the filing of his initial complaint, to file a civil action in federal court. Stewart\n\ntimely appealed the district court’s decision.\n\n II.\n\n A.\n\n Stewart alleges violations of both the Rehabilitation Act and Title VII.\n\nRehabilitation Act claims “must comply with the same administrative procedures that\n\ngovern federal employee Title VII claims.” Wilkinson v. Rumsfeld, 100 F. App’x 155,\n\n\n 4\n\f157 (4th Cir. 2004). Section 717, codified at 42 U.S.C. § 2000e-16, amended Title VII to\n\npermit federal employees to file a civil action for employment discrimination under\n\ncertain circumstances. Federal employees may file a civil action based upon their\n\nadministrative complaint (1) within 90 days of receipt of notice of final agency action or\n\n(2) after 180 days from “the filing of the initial charge” with the agency, if there has been\n\nno final agency action on the complaint.\n\n In addition to 42 U.S.C. § 2000e-16, federal regulations govern the process for\n\nfiling a civil action based on employment discrimination. Congress has delegated to the\n\nEqual Employment Opportunity Commission (“EEOC”) the authority to promulgate\n\nregulations to implement Title VII. E.E.O.C. v. Randstad, 685 F.3d 433, 444 (4th Cir.\n\n2012). Accordingly, the EEOC has enacted regulations regarding individuals’ ability to\n\n(1) amend their administrative complaint and (2) file suit in federal court under Title VII.\n\nThese regulations reinforce Section 2000e-16. A federal employee may amend a\n\ncomplaint “at any time prior to the conclusion of the investigation to include issues or\n\nclaims like or related to those raised in the complaint.” 29 C.F.R. § 1614.106(d).\n\nEchoing the language of 42 U.S.C. § 2000e-16(c), the EEOC’s regulations also state that\n\nfederal employees seeking relief under Title VII and the Rehabilitation Act may file a\n\ncivil action in federal district court “[a]fter 180 days from the date of filing an individual\n\nor class complaint if an appeal has not been filed and final action has not been taken.” 29\n\nC.F.R. § 1614.407(b).\n\n\n\n\n 5\n\f B.\n\n We begin with the threshold question of whether Title VII’s 180-day waiting\n\nperiod found in Section 2000e-16(c) is a jurisdictional bar, a question of first impression\n\nin this circuit. 1 Although the PTO filed its motion to dismiss under Fed. R. Civ. P.\n\n12(b)(6), the district court dismissed Stewart’s case under Fed. R. Civ. P. 12(b)(1) for\n\nlack of subject-matter jurisdiction, stating that the “administrative exhaustion\n\nrequirements for the Rehabilitation Act and Title VII claims are jurisdictional,” and\n\nStewart failed to exhaust his administrative remedies. J.A. 234 n.4. For the following\n\nreasons, we conclude that the district court incorrectly held that Section 2000e-16(c)’s\n\n180-day waiting period is jurisdictional.\n\n Title VII directs federal employees to exhaust administrative remedies before\n\nfiling suit. Pueschel v. United States, 369 F.3d 345, 353 (4th Cir. 2004). Requiring\n\nexhaustion of administrative remedies serves twin objectives: protecting agency authority\n\n\n 1\n We have previously treated certain Title VII exhaustion requirements as\njurisdictional—for example, filing a charge of discrimination with the EEOC, see Jones\nv. Calvert Grp., Ltd., 551 F.3d 297, 300 (4th Cir. 2009)—but have never considered\nwhether the 180-day waiting period in Section 2000e-16(c) is a jurisdictional\nprerequisite. We also recognize that circuits have split on whether the failure to exhaust\nadministrative remedies under Title VII, broadly conceived, is a jurisdictional\nrequirement. Again, however, none of these cases implicate the mandatory 180-day\nwaiting period in Section 2000e-16(c) that is before us in this case. Compare Peppers v.\nCobb Cty., 835 F.3d 1289, 1296–97 (11th Cir. 2016) (treating the administrative\nexhaustion requirement as a jurisdictional prerequisite to filing a Title VII action), with\nFowlkes v. Ironworkers Local 40, 790 F.3d 378, 385 (2d Cir. 2015) (holding that the\nfailure to exhaust administrative remedies does not raise a jurisdictional bar); Artis v.\nBernanke, 630 F.3d 1031, 1034 n.4 (D.C. Cir. 2011) (same); Frederique-Alexandre v.\nDep’t of Nat. & Envtl. Res. of Puerto Rico, 478 F.3d 433, 440 (1st Cir. 2007) (same).\n\n\n\n 6\n\fin the administrative process and “promot[ing] efficiency” in the resolution of claims.\n\nWoodford v. Ngo, 548 U.S. 81, 89 (2006). By avoiding the “premature interruption of the\n\nadministrative process,” exhaustion requirements ensure that agencies are provided the\n\nfirst opportunity to “exercise [] discretion” or “apply [] expertise.” McKart v. United\n\nStates, 395 U.S. 185, 193–94 (1969). The 180-day waiting period serves these purposes:\n\nit ensures that the employer is “put on notice of the alleged violations” to facilitate out-\n\nof-court resolution and permits sufficient, but finite, time for the agency to address the\n\ndiscrimination charges in the first instance. Miles v. Dell, Inc., 429 F.3d 480, 491 (4th\n\nCir. 2005). Indeed, courts have regularly characterized Section 2000e-16(c)’s 180-day\n\nwaiting period as an exhaustion requirement. See Murthy v. Vilsack, 609 F.3d 460, 465\n\n(D.C. Cir. 2010); Brown v. Snow, 440 F.3d 1259, 1263 (11th Cir. 2006).\n\n However, it bears noting that the 180-day waiting period also is not a paradigmatic\n\nexhaustion requirement. Unlike most administrative exhaustion requirements premised\n\non agency action, after which injured parties may “seek review of an adverse decision\n\nand obtain a remedy” if warranted, the 180-day waiting period is satisfied by agency\n\ninaction. Darby v. Cisneros, 509 U.S. 137, 144 (1993) (citation omitted). Indeed,\n\nCongress passed Section 2000e-16(c) of Title VII in 1972 precisely because of its\n\nrecognition that federal employees frequently encountered an “administrative quagmire”\n\nin filing charges of discrimination. H.R. Rep. 92–238, at 12 (June 2, 1971). The 180-day\n\nwaiting period therefore “confines agencies and the EEOC to a tight schedule” and\n\nsignals congressional recognition that “the doctrine of exhaustion of remedies . . . had\n\nbecome [a] barrier to meaningful court review.” Wilson v. Pena, 79 F.3d 154, 167 (D.C.\n\n\n 7\n\fCir. 1996) (quoting Grubbs v. Butz, 514 F.2d 1323, 1328 (D.C. Cir. 1975)). In light of\n\nthis legislative context, the 180-day waiting period functions more like a mandatory\n\nprocedural hurdle for litigants than an affirmative agency step potentially giving rise to a\n\nremedy on review.\n\n This distinction informs our consideration of whether Section 2000e-16(c)’s 180-\n\nday waiting period requirement is also a jurisdictional requirement. Not all exhaustion\n\nrequirements are jurisdictional. Rather, we have recognized that certain exhaustion\n\nrequirements may be jurisdictional while others are not. For example, in Davis v. North\n\nCarolina Department of Correction, we specifically distinguished one exhaustion\n\nrequirement as jurisdictional—the entitlement to a right-to-sue letter from the EEOC—\n\nfrom Title VII’s “timely filing requirements,” which the Supreme Court has held are not\n\njurisdictional. 48 F.3d 134, 140 (4th Cir. 1995) (citing Zipes v. Trans World Airlines,\n\nInc., 455 U.S. 385, 393 (1982)); see also Laber v. Harvey, 438 F.3d 404, 429 n.25 (4th\n\nCir. 2006) (concluding that the 90-day time limit set forth in 42 U.S.C. § 2000e–16(c) is\n\nnot a jurisdictional requirement).\n\n In recent years, the Supreme Court repeatedly has cautioned courts not to\n\n“confuse[] or conflate[]” subject-matter jurisdiction, on the one hand, with the “essential\n\ningredients of a federal claim for relief,” on the other. Arbaugh v. Y & H Corp., 546 U.S.\n\n500, 503 (2006). Applying this distinction, the Supreme Court has differentiated between\n\nnon-jurisdictional “claim-processing” rules and jurisdictional rules that govern a court’s\n\nadjudicatory authority. Kontrick v. Ryan, 540 U.S. 443, 456 (2004); see also Gonzalez v.\n\nThaler, 565 U.S. 134, 141 (2012) (pressing a “stricter distinction” between these two\n\n\n 8\n\fcategories of rules). In particular, the Supreme Court has clarified that most time bars are\n\n“quintessential claim-processing rules,” which “promote the orderly progress of litigation\n\nby requiring that the parties take certain procedural steps at certain specified times.”\n\nHenderson v. Shinseki, 562 U.S. 428, 435 (2011) (holding that a statute requiring filing of\n\nnotice of appeal within 180 days of administrative decision constituted a “claim-\n\nprocessing rule” and therefore was not jurisdictional). Such rules do not strip a court of\n\njudicial authority to hear a case, even when the time limits are “framed in mandatory\n\nterms.” United States v. Kwai Fun Wong, 135 S. Ct. 1625, 1632 (2015) (holding that\n\ncertain timely filing provisions in the Federal Torts Claims Act were not jurisdictional).\n\n Instead, the Supreme Court has established a clear statement rule for\n\ndetermining whether procedural rules, including time bars, are jurisdictional. Only if the\n\nstatutory text “plainly show[s] that Congress imbued a procedural bar with jurisdictional\n\nconsequences” should a court treat a rule as jurisdictional. Id. Put otherwise, Congress\n\nmust explicitly “tag” a procedural bar “as jurisdictional.” Id. In conducting this clear\n\nstatement inquiry, the Supreme Court has looked to several factors, including the\n\nstatutory text (if it speaks in “jurisdictional terms”); the placement of the rule (if it is\n\nlocated in the jurisdiction-granting provision of the statute); and legislative context.\n\nHenderson, 562 U.S. at 438.\n\n Here, Congress has done nothing to “tag” as jurisdictional the 180-day waiting\n\nperiod. The text of Section 2000e-16(c) addresses only the timeliness of claims; it does\n\nnot refer to the district courts’ “authority to hear untimely suits.” Kwai Fun Wong, 135 S.\n\nCt. 1625, 1628 (2015). Much like the filing deadline at issue in Henderson, Section\n\n\n 9\n\f2000e-16(c) does not contain “jurisdictional language”—language dictating that judicial\n\nreview be obtained within a prescribed time and manner before a particular court.\n\nHenderson, 562 U.S. at 438. Simply because the 180-day waiting period is “cast in\n\nmandatory language” does not render it jurisdictional. Id. at 439.\n\n In addition, Section 2000e-16(c)’s placement within Title VII is distinct from\n\nthose provisions pertaining to jurisdiction. Section 2000e-16(c), titled “Employment by\n\nFederal Government,” lays out the respective 90-day filing period and 180-day waiting\n\nperiods before stating that the federal employee “may file a civil action as provided in\n\nsection 2000e-5.” 42 U.S.C. § 2000e-16(c) (emphasis added). Section 2000e-5, titled\n\n“Enforcement provisions,” mandates that federal district courts “shall have jurisdiction of\n\nactions brought under this subchapter.” 42 U.S.C. § 2000e-5(f)(3). These statutory\n\nsections serve different functions: on the one hand, Section 2000e-16(c) extends Title VII\n\nprotections to federal employees, and on the other, Section 2000e-5, as the enforcement\n\nprovision, prescribes jurisdictional requirements. Nothing “conditions the jurisdictional\n\ngrant [in Section 2000e-5(f)(3)] on the limitations periods [in Section 2000e-16(c)], or\n\notherwise links those separate provisions.” Kwai Fun Wong, 135 S. Ct. at 1633; see also\n\nGad v. Kansas State Univ., 787 F.3d 1032, 1038 (10th Cir. 2015) (noting that “a Title VII\n\nstatutory requirement’s classification as jurisdictional or non-jurisdictional turns in large\n\npart on whether it is located in Title VII’s jurisdictional subsection—42 U.S.C. § 2000e-\n\n5(f)(3)). This division further supports a conclusion that the 180-day waiting period is\n\nnot a jurisdictional requirement but rather a “prudential prerequisite to suit,” Davis v.\n\n\n\n\n 10\n\fFort Bend Cty., 893 F.3d 300, 305 (5th Cir. 2018), or “statutory precondition,” Vinieratos\n\nv. U.S. Dep’t of Air Force, 939 F.2d 762, 768 n.5 (9th Cir. 1991).\n\n In considering this issue, we emphasize the subtle, but important, distinction\n\nbetween those exhaustion requirements that operate as a jurisdictional bar and those that\n\nmerely function as a statutory prerequisite to filing suit under Title VII. See Vinieratos,\n\n939 F.2d at 768 n.5 (9th Cir. 1991). Because we conclude that Section 2000e-16(c)’s\n\n180-day waiting period is akin to a “claim-processing” rule that imposes procedural\n\nobligations on litigants, rather than implicates judicial authority to hear a class of cases,\n\nwe hold that the 180-day waiting period is not jurisdictional.\n\n Our holding also prevents the “drastic” consequences of treating a procedural rule\n\nas jurisdictional—consequences that “alter[] the normal operation of our adversarial\n\nsystem.” Henderson, 562 U.S. at 434. Jurisdictional defects can be raised at any time by\n\nthe parties or sua sponte by the courts, even post-judgment, which may result in the\n\n“waste of judicial resources and may unfairly prejudice litigants.” Id. Because of the\n\ngravity of a jurisdictional label, the Supreme Court has repeatedly and explicitly\n\ndemanded “discipline” in this inquiry. Id. at 435.\n\n To be clear, we do not hold that all exhaustion requirements set forth in Title VII\n\nare non-jurisdictional. Rather, whether a particular exhaustion requirement—in Title VII\n\nor any other statute—is jurisdictional turns on the statutory language and purpose of the\n\nexhaustion provision at issue. Here, Section 2000e-16(c) includes no language clearly\n\nindicating that Congress intended for the provision to serve as a jurisdictional bar.\n\nFurther, in practice, Section 2000e-16(c)’s 180-day waiting period functions more closely\n\n\n 11\n\fas a “time prescription,” which imposes a mandatory obligation on litigants but does not\n\ngovern a court’s jurisdiction. Arbaugh, 546 U.S. at 510; see also Stroy v. Gibson, 896\n\nF.3d 693, 698 (5th Cir. 2018) (treating Section 2000e-16(c)’s 180-day waiting period as a\n\n“precondition to filing suit,” not a jurisdictional requirement).\n\n Accordingly, the district court erred in dismissing this case under Federal Rule of\n\nCivil Procedure 12(b)(1). Instead, it should have considered the 180-day waiting period\n\nas a non-jurisdictional rule and decided the case under Federal Rule of Civil Procedure\n\n12(b)(6).\n\n III.\n\n A.\n\n Having determined that Section 2000e-16(c)’s 180-day waiting period is not\n\njurisdictional, we now turn to whether the district court erred in dismissing Stewart’s\n\naction under that provision. “We review de novo the grant of a motion to dismiss for\n\nfailure to state a claim [under Rule 12(b)(6)]. In so doing, we must accept as true all of\n\nthe factual allegations contained in the complaint.” Gerner v. Cty. of Chesterfield, Va.,\n\n674 F.3d 264, 266 (4th Cir. 2012) (citation omitted).\n\n Stewart’s appeal requires us to construe the statutory language of Section 2000e-\n\n16(c), and that provision’s 180-day waiting period, in particular. When construing a\n\nstatute, we “first and foremost strive to implement congressional intent by examining the\n\nplain language.” Minor v. Bostwick Laboratories, Inc., 669 F.3d 428 (4th Cir. 2012)\n\n(citation omitted). “[U]nless otherwise defined, words will be interpreted as taking their\n\nordinary, contemporary, common meaning.” Kennedy v. St. Joseph’s Ministries, Inc.,\n\n\n 12\n\f657 F.3d 189, 192 (4th Cir. 2011) (citation omitted). In interpreting the plain language of\n\nthe statute, we also look to “the specific context in which the language is used, and the\n\nbroader context of the statute as a whole,” Minor, 669 F.3d at 434–35 (citations omitted),\n\nas well as a statute’s legislative history as additional evidence of congressional intent,\n\nElm Grove Coal Co. v. Director, O.W.C.P., 480 F.3d 278, 293 (4th Cir. 2007). Here,\n\neach of these factors indicates that Stewart’s amendments of his complaint did not restart\n\nthe 180-day clock.\n\n We begin with the plain language of the statute. In relevant part, Section 2000e-\n\n16(c) permits aggrieved federal employees to file a civil action 180 days “from the filing\n\nof the initial charge with the department, agency, or unit” if the agency has “fail[ed] to\n\ntake final action on his complaint.” 42 U.S.C. § 2000e-16(c) (emphasis added). Given\n\nthe ordinary meaning of the word “initial,” Section 2000e-16(c) requires that the 180-day\n\nwaiting period begin upon the filing of the first, original charge. See Webster’s Third\n\nNew Int’l Dictionary 1163 (3d ed. 1976) (defining “initial” as “of or relating to the\n\nbeginning; marking the commencement”); American Heritage Dictionary of the English\n\nLanguage 902 (4th ed. 2009) (defining “initial” as “of, relating to, or occurring at the\n\nbeginning; first”). Therefore, in Stewart’s case, the 180-day waiting period began on July\n\n14, 2015, the date he filed his “initial,” formal administrative complaint of discrimination\n\nand retaliation before the PTO’s Office of Equal Employment and Diversity.\n\n The statute’s use of the modifier “initial” also implicitly allows for the possibility\n\nof subsequent amendments—that there may well be additional “charge[s]” that follow the\n\n“initial charge.” Accordingly, the 180-day waiting period does not reset upon subsequent\n\n\n 13\n\famendments to the administrative complaint. Had Congress not contemplated the\n\npossibility of amendments to the complaint, there would have been no reason to use the\n\nword “initial.” See Alaska Dep’t of Envtl. Conservation v. E.P.A., 540 U.S. 461, 489 n.13\n\n(2004) (observing it is “a cardinal principle of statutory construction that a statute ought,\n\nupon the whole, to be so construed that, if it can be prevented, no clause, sentence, or\n\nword shall be superfluous, void, or insignificant”) (citations and alterations omitted).\n\nTherefore, we hold that upon the passage of 180 days from the filing of the original\n\ncomplaint, and absent agency final action on the complaint, federal employees may file a\n\ncivil action, regardless of subsequent amendments to that complaint. 2\n\n Turning to the legislative context, Congress passed Section 2000e-16(c) of Title\n\nVII in 1972 because of its recognition that aggrieved federal employees did not have\n\nsufficient access to the courts under Title VII. S. Rep. 92–415 at 16 (1971). Before the\n\n1972 Act, the “effective availability of either administrative or judicial relief” for federal\n\nemployees was uncertain. Brown v. General Servs. Admin., 425 U.S. 820, 825 (1976).\n\nFederal employees often faced an “administrative quagmire” in which parties had to wait\n\nseveral years in the overburdened administrative process. H.R. Rep. 92–238, at 12 (June\n\n\n 2\n In an unpublished per curiam opinion, we summarily affirmed a district court’s\nholding that federal employees must wait beyond the 180-day period when they amend\ntheir complaints. Laber v. Harvey, No. 1:05-cv-00803-CMH, 2005 WL 3008510, at *1\n(E.D. Va. Nov. 7, 2005), aff’d, 204 F. App’x 332 (4th Cir. 2006). We are not bound by\nthat opinion, which is devoid of reasoning. See Collins v. Pond Creek Mining Co., 468\nF.3d 213, 219 (4th Cir. 2006) (noting that “we ordinarily do not accord precedential value\nto our unpublished decisions” and they are “entitled only to the weight they generate by\nthe persuasiveness of their reasoning”) (citation omitted).\n\n\n\n 14\n\f2, 1971). Ensuring that federal employees had “access to the courts” therefore drove the\n\npassage of Section 2000e-16(c). S. Rep. No. 92–415, at 16 (1971). The 180-day waiting\n\nperiod directly serves that end. In discussing Section 2000e-16(c)’s 180-day waiting\n\nprovision in the context of EEOC inaction, the D.C. Circuit observed that:\n\n The 180 day [waiting period] provision represents a Congressional\n determination that providing prompt access to the courts in discrimination\n disputes is so important that the administrative process will be given only a\n finite time to deal alone with a given dispute. Indeed, the Act is in part a\n response to Congressional realization that “the doctrine of exhaustion of\n remedies . . . had become [a] barrier to meaningful court review.”\n\nWilson, 79 F.3d at 167 (quoting Grubbs, 514 F.2d at 1328). Allowing agencies to\n\nrepeatedly delay individuals’ ability to go to court, simply because they have amended\n\ntheir administrative complaints, would frustrate a “congressional policy to make the\n\ncourts the final tribunal for the resolution of controversies over charges of discrimination\n\nafter all administrative remedies have been exhausted.” Koger v. Ball, 497 F.2d 702, 706\n\n(4th Cir. 1974). Although Section 2000e-16(c) “provides for a careful blend of\n\nadministrative and judicial enforcement powers,” we cannot overlook that, in passing the\n\nprovision, Congress intended federal employees to have a robust judicial remedy, and\n\nready access to the courts, for employment discrimination claims. Brown, 425 U.S. at\n\n833\n\n Our conclusion also comports with the broader purpose of Title VII as a “remedial\n\nscheme in which laypersons, rather than lawyers, are expected to initiate the process.”\n\nSydnor, 681 F.3d at 594 (citation omitted); see also Alvarado v. Board of Trustees of\n\nMontgomery Community College, 848 F.2d 457, 460 (4th Cir. 1988) (“Title VII does not\n\n\n\n 15\n\frequire procedural exactness from lay complainants.”). We must be wary of “overly\n\ntechnical concerns” laying a “tripwire for hapless plaintiffs.” Syndor, 681 F.3d at 594.\n\nHere, for example, the PTO repeatedly informed Stewart, after each of his amendments—\n\nand in accordance with the statute’s plain language—that he could file a civil action “at\n\nany time after 180 days have passed from the date [he] filed [his] original complaint.”\n\nJ.A. 114. Permitting the agency to repeatedly confuse litigants in this manner would only\n\nfurther pervert Title VII’s remedial purpose.\n\n B.\n\n In support of its position that Stewart was required to wait beyond the initial 180-\n\nday waiting period, the PTO makes several arguments. First, the PTO argues that Section\n\n2000e-16(c)’s statutory text is “ambiguous” because it uses two different terms,\n\n“complaint” and “charge.” Second, the PTO argues that the EEOC’s regulations support\n\ntethering the 180-day waiting period to the agency’s extended investigation period for\n\namended complaints. Third, the PTO argues that should we reverse the district court’s\n\nholding, we would incentivize gamesmanship in Title VII claims. Each of these\n\narguments is unavailing.\n\n In support of its first argument—that Section 2000e-16(c)’s statutory text is\n\nambiguous 3—the PTO emphasizes Congress’s use of two terms within the statute:\n\n\n 3\n In repeatedly referring to Section 2000e-16(c)’s purported “ambiguity,” the PTO\nappears to be implicitly invoking, or at least evoking, Chevron deference to its\ninterpretation of the statute. However, the statute is not ambiguous. Further, we only\ngrant Chevron deference to “an agency’s construction of the statute which it\nadministers.” Chevron, U.S.A., Inc. v. Nat. Res. Def. Council, Inc., 467 U.S. 837, 842\n(Continued)\n\n 16\n\f“complaint” and “charge.” The PTO argues that the term “complaint” in Section 2000e-\n\n16(c) references “an employee’s general use of the administrative process” to allege\n\nunlawful discrimination, while the phrase “initial charge” is “the first ‘statement’”\n\nthrough which an employee identifies this discrimination. Appellee’s Br. at 25–26. To\n\nthe PTO, it bears significance that Congress did not use the phrase “initial complaint” in\n\nSection 2000e-16(c) but rather “initial charge,” thus indicating that “Congress did not\n\nseek to trigger the 180-day period upon the commencement of the EEO process\n\ngenerally.” Appellee’s Br. at 26 (emphasis in original).\n\n Even if we were to accept the PTO’s proposed distinction between these two\n\nterms, such a distinction does not aid the PTO’s position. If we treat “initial charge” as\n\nthe first, informal “statement” through which an employee alleges unlawful\n\ndiscrimination, then the 180-day waiting period would be satisfied at the same time or\n\nearlier than under the reading we adopt because a “charge,” so conceived, never\n\ntemporally follows a “complaint.” Under the PTO’s construction, Stewart’s “initial\n\ncharge” occurred on April 30, 2015, when he submitted a document to the PTO’s Office\n\nof Equal Employment Opportunity and Diversity alleging harassment and discrimination\n\non the basis of disability. Accepting the PTO’s position, then, would only hasten the date\n\nupon which Stewart could file a civil action. More significantly, PTO’s position in no\n\n\n\n\n(1984). The EEOC, not the PTO, administers Title VII, so even if Chevron deference\nwere implicated here, the PTO is entitled to no such deference. The record includes no\nindication that the EEOC concurs in the PTO’s construction of Section 2000e-16(c).\n\n\n\n 17\n\fway explains Congress’s express use of the word “initial,” which serves as the crux of\n\nour construction of Section 2000e-16(c)’s 180-day waiting period. The term “initial”\n\nmakes clear that Congress intended to begin the 180-day waiting period from the filing of\n\nthe original complaint, regardless of whether subsequent amendments to that complaint\n\nare filed. See United States v. Blannon, 836 F.2d 843, 854 (4th Cir. 1988) (“[A] court\n\nmay not manufacture an ambiguity in order to defeat Congress’ intent.”).\n\n Next, the PTO argues that the EEOC’s relevant regulations support its position\n\nthat Stewart was required to wait longer than 180 days before filing suit. However, we\n\nconclude that these regulations only reinforce our interpretation of Section 2000e-16(c).\n\n29 C.F.R. § 1614.407(b) mirrors the language found in Section 2000e-16(c), providing in\n\nrelevant part that a complainant is authorized under Title VII and the Rehabilitation Act\n\nto file a civil action in federal district court “[a]fter 180 days from the date of filing an\n\nindividual or class complaint if an appeal has not been filed and final action has not been\n\ntaken.” Given the regulation’s use of the term “individual . . . complaint,” the PTO\n\ncannot dispute that the 180-day waiting period begins upon filing of the individual\n\ncomplaint. Instead, the PTO attempts to wave away the regulation as a “generic rule,”\n\nbut this perfunctory argument is not persuasive. Appellee’s Br. at 29.\n\n The district court, and the PTO, wrongly tether Section 1614.407(b)’s 180-day\n\nwaiting period to other EEOC regulations extending the agency investigation period\n\nwhen a complaint has been amended to “within the earlier of 180 days after the last\n\namendment to the complaint or 360 days after the filing of the original complaint.” 29\n\nC.F.R. §§ 1614.106(e)(2), 1614.108(f). The district court reasoned that otherwise, the\n\n\n 18\n\fcourt “would be adjudicating claims that the [PTO] has not yet had the opportunity to\n\ninvestigate, let alone adjudicate.” J.A. 236. We disagree for two reasons.\n\n First, as discussed above, the district court’s holding is contrary to the plain\n\nlanguage of both Section 2000e-16(c) of Title VII and 29 C.F.R. § 1614.407(b). Further,\n\nSection 1614.407(b) lacks any textual distinction between filing an initial complaint and\n\nfiling an amendment, which is particularly telling given that other regulations in the same\n\npart, such as those governing the agency investigation period, do make such a distinction.\n\nSee 29 C.F.R. §§ 1614.106(e)(2), 1614.108(f). Section 1614.407(b) does not hinge\n\nemployees’ ability to file a civil action on the conclusion of the agency investigation;\n\nrather, it establishes a bright-line 180-day waiting period after which the employee can be\n\n“assured of having reasonably prompt access to the courts.” Wilson, 79 F.3d at 167 (D.C.\n\nCir. 1996).\n\n Additionally, the district court neglected an important facet of Title VII claims: we\n\nhave long held that courts may in fact adjudicate claims not raised before the agency, if\n\ncertain requirements are met. In Hill v. Western Electric Company, Inc., we recognized\n\nthe “generally accepted principle” that the “scope of a Title VII lawsuit may extend to\n\n‘any kind of discrimination like or related to allegations contained in the charge and\n\ngrowing out of such allegations during the pendency of the case’” before the agency. 672\n\nF.2d 381, 390 n.6 (4th Cir. 1982). Put otherwise, an “administrative charge of\n\ndiscrimination does not strictly limit a Title VII suit which may follow,” and federal\n\ncourts may still hear claims that the employee did not raise before the agency, as long as\n\nthey are “like or related” and grow out of the allegations during the pendency of the case\n\n\n 19\n\fbefore the agency. Sydnor, 681 F.3d at 594. Only “those discrimination claims stated in\n\nthe initial charge, those reasonably related to the original complaint, and those developed\n\nby reasonable investigation of the original complaint may be maintained in a subsequent\n\nTitle VII lawsuit.” Chacko v. Patuxent Institution, 429 F. 3d 505, 506 (4th Cir. 2005)\n\n(citation omitted); see also Smith v. First Union Nat. Bank, 202 F.3d 234, 247 (4th Cir.\n\n2000) (“If a plaintiff’s claims in her judicial complaint are reasonably related to her\n\nEEOC charge and can be expected to follow from a reasonable administrative\n\ninvestigation, the plaintiff may advance such claims in her subsequent civil suit.”). Our\n\nprecedent makes clear that plaintiffs, although circumscribed by their administrative\n\ncomplaints, are not wholly banned from raising claims for the first time before the district\n\ncourt, so long as they meet the requirements articulated in Hill and Chacko.\n\n Nor is a plaintiff’s ability to raise new claims before the district court cabined to\n\nthe context of retaliation claims, as the PTO appeared to briefly suggest at oral argument.\n\nOral Argument at 27:53–28:25 (“I don’t think he can amend his complaint, [] unless it\n\nwas for retaliation . . . because this Court’s jurisprudence provides that in cases of\n\nretaliation, the exhaustion procedures and principles are a little bit different.”). It is true\n\nthat we have often addressed a plaintiff’s ability to do so in the specific context of\n\nretaliation claims. See Nealon v. Stone, 958 F.2d 584, 590 (4th Cir. 1992). Importantly,\n\nhowever, we have never held that the rule applies exclusively in the context of retaliation\n\nclaims but rather that retaliation claims “receive extended flexibility” when being\n\nconsidered under the general rule referenced in Hill. Clarke v. Richmond Behavioral\n\nHealth Auth., No. 3:09CV743, 2011 WL 13274273, at *4 (E.D. Va. Aug. 10, 2011); see\n\n\n 20\n\falso Brown v. Runyon, 139 F.3d 888 (4th Cir. 1988) (unpublished opinion) (noting that\n\nour precedent “presupposes both that a retaliation count in a Title VII lawsuit be ‘related\n\nto’ and have ‘grown out’ of the EEO charge while the administrative charge remained\n\npending”). We have reasoned that retaliation claims constitute a subset of the general\n\nrule noted in Hill, because “retaliation claims almost always relate back to previously\n\nfiled EEO charges, and, therefore, may be raised for the first time in district court without\n\nthe requirement that a plaintiff have exhausted his administrative remedies.” Brown, 139\n\nF.3d at 888. Accordingly, retaliation claims represent the “inevitable corollary,” but not\n\nthe exclusive application, of the “generally accepted principle” articulated in Hill. Id.\n\n(quoting Nealon, 958 F.2d at 590). We have therefore left open the possibility that\n\ndistrict courts may hear claims for the first time, beyond just retaliation claims, if they are\n\n“reasonably related to the original complaint” and “developed by reasonable investigation\n\nof the original complaint.” Chacko, 429 F.3d at 506.\n\n Indeed, other circuits have recognized the need to grant Title VII plaintiffs\n\n“significant leeway” in drafting administrative complaints, given their lack of technical\n\nexpertise. Cheek v. W. & S. Life Ins. Co., 31 F.3d 497, 500 (7th Cir. 1994) (citation\n\nomitted). Applying this principle of liberal construction, other circuits permit litigants to\n\nbring claims not specifically pressed before the agency if they are “like or reasonably\n\nrelated to those contained in the [agency] complaint” and if they “reasonably could have\n\ndeveloped from the [agency’s] investigation of the charges before it.” Sommerfield v.\n\nCity of Chicago, 863 F.3d 645, 648 (7th Cir. 2017); see also Foster v. BNSF Ry. Co., 866\n\nF.3d 962, 966 (8th Cir. 2017) (holding same); Freeman v. Oakland Unified Sch. Dist.,\n\n\n 21\n\f291 F.3d 632, 636 (9th Cir. 2002) (same). We join these circuits today in reiterating our\n\ndecision in Hill and Chacko that plaintiffs may bring Title VII claims for the first time\n\nbefore a district court, so long as they are like or reasonably related to charges in the\n\noriginal administrative complaint, and if they reasonably could have developed from the\n\nagency’s investigation of the original complaint. See Hill, 672 F.2d at 390 n.6; Chacko,\n\n429 F.3d at 506.\n\n Crucially, this “like or related” limitation also allays the PTO’s third argument\n\nregarding gamesmanship. The PTO argues that should we reverse the district court, a\n\nfederal employee could file a “perfunctory initial ‘charge,’ seek to add new claims\n\nimmediately before the 180-day ‘mark,’ and then file a civil action immediately\n\nfollowing that same ‘mark.’” Appellee’s Br. at 28. First, as discussed above, we already\n\npermit courts to adjudicate reasonably related claims not heard in the first instance by\n\nagencies. The “like or related” limitation limits the universe of charges that the litigant\n\nmay bring and guards against the gamesmanship concern that litigants will raise wholly\n\nunrelated claims for the first time before a district court.\n\n Second, as Stewart correctly points out, existing procedural guardrails further\n\nprotect against such gamesmanship. When amending a complaint before the agency, the\n\nemployee must file a letter with the agency’s Office of Equal Employment Director\n\n“describing the new incident(s) and stating that s/he wishes to amend his/her complaint to\n\ninclude the new incident(s).” EEOC Mgmt. Directive 110, Ch. 5.B. The Director must\n\nthen review this request to determine if the claims are like or related, and “whether a fair\n\nand impartial investigation of the new claims can be accomplished within 360 days of the\n\n\n 22\n\foriginal filed complaint.” Id. If not, then the individual must start a new administrative\n\nprocess with respect to the new claim. Accordingly, employees cannot game the\n\nadministrative process in the way suggested by the PTO. Indeed, if we were to accept the\n\ndistrict court’s holding, we may even risk disincentivizing plaintiffs from bringing a “like\n\nor related” claim before the agency, as each amendment would only further delay the\n\nplaintiff’s access to court. Under the district court’s reading of 42 U.S.C. § 2000e-16(c)\n\nand 29 C.F.R. § 1614.407(b), a plaintiff might be better served by holding onto their “like\n\nor related” claims until the filing of a civil action. But this outcome would undermine the\n\npolicy goals underlying Title VII’s administrative framework to encourage “quicker, less\n\nformal, and less expensive resolution of disputes.” Sydnor, 681 F.3d at 593 (quoting\n\nChris v. Tenet, 221 F.3d 648, 653 (4th Cir. 2000)).\n\n Our holding maintains the careful balance between the Title VII’s administrative\n\nframework and judicial remedies, between “providing notice to employers and the\n\n[agency] on the one hand and ensuring plaintiffs are not tripped up over technicalities on\n\nthe other.” Id. at 594. We recognize the “substantial role” played by the administrative\n\nprocess in narrowing “formal litigation.” Chacko, 429 F.3d at 509. But it is equally\n\nwell-established that if the claim raised for the first time before the district court contains\n\nfactual allegations that “are reasonably related to the factual allegations in the formal\n\nlitigation, the connection between the charge and the claim is sufficient.” Id. (citation\n\nomitted); see also Kersting v. Wal-Mart Stores, Inc., 250 F.3d 1109, 1118 (7th Cir. 2001)\n\n(noting that a plaintiff may pursue a claim not explicitly included in an administrative\n\ncomplaint if the allegations are “like or reasonably related to” those in the charge).\n\n\n 23\n\f *****\n\n The plain text of 42 U.S.C. § 2000e-16(c) and 29 C.F.R. 1614.407(b), as well as\n\nthe legislative context and purpose of Title VII, dictate the outcome of this case.\n\nContrary to the district court’s holding, Section 2000e-16(c)’s 180-day waiting period\n\noperates independently of the agency’s extended investigation window for amended\n\ncomplaints. Instead, the 180-day waiting period “gives great weight to the complainant’s\n\ninterest in obtaining speedy resolution of the complaint” and ensures ready access to the\n\ncourts. Wilson, 79 F.3d at 167. Accordingly, we hold that Section 2000e-16(c)’s 180-\n\nday waiting period for filing a civil action, absent agency final action, commences with\n\nthe filing of the initial administrative complaint, regardless of subsequent amendments to\n\nthat complaint.\n\n IV.\n\n For the foregoing reasons, we reverse the district court’s dismissal of Stewart’s\n\namended complaint and remand for further proceedings.\n\n REVERSED AND REMANDED\n\n\n\n\n 24\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Fenyang Ajamu STEWART, Plaintiff - Appellant, v. Andrei IANCU, Defendant - Appellee.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-08\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-1815\\n\\n\\nFENYANG AJAMU STEWART,\\n\\n Plaintiff - Appellant,\\n\\n v.\\n\\nANDREI IANCU,\\n\\n Defendant - Appellee.\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. Leonie M. Brinkema, District Judge. (1:16-cv-00213-LMB-JFA)\\n\\n\\nArgued: October 30, 2018 Decided: January 8, 2019\\n\\n\\nBefore GREGORY, Chief Judge, MOTZ and WYNN, Circuit Judges.\\n\\n\\nReversed and remanded by published opinion. Judge Wynn wrote the opinion, in which\\nChief Judge Gregory and Judge Motz joined.\\n\\n\\nARGUED: Kevin Spencer Elliker, HUNTON ANDREWS KURTH LLP, Richmond,\\nVirginia, for Appellant. Dennis Carl Barghaan, Jr., OFFICE OF THE UNITED STATES\\nATTORNEY, Alexandria, Virginia, for Appellee. ON BRIEF: G. Zachary Terwilliger,\\nUnited States Attorney, OFFICE OF THE UNITED STATES ATTORNEY, Alexandria,\\nVirginia, for Appellee.\\n\\fWYNN, Circuit Judge:\\n\\n This appeal arises from the district court’s determination that Fenyang Ajamu\\n\\nStewart (“Stewart”) is required to wait longer than 180 days to commence a civil action\\n\\nunder Title VII and the Rehabilitation Act after amending his initial administrative\\n\\ncomplaint before the relevant agency. But the text of Title VII, as well as the legislative\\n\\ncontext and purpose, plainly states that a claimant may commence a civil action 180 days\\n\\nfrom “the filing of the initial charge.” 42 U.S.C. § 2000e-16(c) (emphasis added). We,\\n\\ntherefore, reverse the district court and remand for further proceedings.\\n\\n I.\\n\\n Stewart worked as a patent examiner for the U.S. Patent and Trademark Office\\n\\n(“PTO”). He suffers from bulging discs in his lower back and radiculopathy, resulting\\n\\nfrom compression of his sciatic nerve, as well as post- and continuous-traumatic stress\\n\\ndisorder. Because of these medical conditions, Stewart filed a reasonable\\n\\naccommodation request with the PTO in April 2014. Specifically, he requested that he\\n\\nnot be required to (1) come into work at a specified, mandatory time; (2) report his work\\n\\nschedule to his supervisor; and (3) schedule his meetings before 12:00 p.m., as his pain\\n\\nmedications caused morning grogginess. In addition, Stewart requested an ergonomic\\n\\nchair and keyboard, a standing desk, and a foot stool.\\n\\n On September 19, 2014, the PTO granted Stewart’s requests for the keyboard,\\n\\nstanding desk, and foot stool. Stewart had already received an ergonomic chair by that\\n\\npoint. Regarding his work schedule, the PTO determined that Stewart was already on the\\n\\nIncreased Flexitime Program work schedule, which permitted him sufficient flexibility to\\n\\n\\n 2\\n\\f“work around any difficulties” and that Stewart’s supervisor, when possible, would\\n\\nschedule meetings specifically designed for Stewart after 12:00 pm. However, the PTO\\n\\ndenied Stewart’s request not to report his work schedule to his supervisor, as such a\\n\\nrequest would unduly burden his supervisor and the agency’s ability to oversee and\\n\\nadminister Stewart’s work.\\n\\n Stewart filed a formal complaint with the PTO’s Office of Equal Employment\\n\\nOpportunity and Diversity on July 14, 2015, challenging the PTO’s denial of his request\\n\\nfor accommodations, asserting a hostile work environment and discrimination, and\\n\\nalleging various claims of retaliation. Stewart amended this administrative complaint\\n\\neight times. After each of these amendments, the PTO’s Office of Equal Employment\\n\\nOpportunity and Diversity responded with a notice advising Stewart that (1) he may\\n\\namend his formal complaint at any time before the investigation is complete, and any\\n\\nnew claims “must be like or related to the claims raised” in the original complaint; and\\n\\n(2) he may “file a civil action in an appropriate United States District Court at any time\\n\\nafter 180 days have passed from the date [he] filed [his] original complaint. 29 C.F.R. §\\n\\n1614.407(b).” J.A. 114.\\n\\n On February 29, 2016—more than 180 days after the filing of his original\\n\\nadministrative complaint, but less than 180 days after the filing of several of the\\n\\namendments—Stewart filed pro se a civil action in the District Court for the Eastern\\n\\nDistrict of Virginia, alleging numerous violations of the Rehabilitation Act of 1973, 29\\n\\nU.S.C. § 701 et seq., and Title VII of the Civil Rights Act of 1964, 42 U.S.C. § 2000e et\\n\\nseq. Stewart’s claims rested on the PTO’s alleged failure to accommodate his\\n\\n\\n 3\\n\\fdisabilities; a hostile work environment; reprisal for participating in protected Equal\\n\\nEmployment Opportunity activity; disparate treatment discrimination on the basis of\\n\\ndisability and failure to accommodate; and retaliation for requesting reasonable\\n\\naccommodation. Stewart later amended the complaint in April 2016, adding two counts.\\n\\n The PTO filed a motion to dismiss, arguing that Stewart’s suit was premature\\n\\nunder both 42 U.S.C. § 2000e-16(c) and 29 C.F.R. § 1614.407(b) because he had not\\n\\nexhausted his administrative remedies. According to the PTO, Stewart was required to\\n\\nwait to file a civil action until the conclusion of the agency’s investigation period. That\\n\\ninvestigation period is extended when employees amend their administrative complaint to\\n\\nthe earlier of 180 days after the last amendment or 360 days after the filing of the initial\\n\\ncomplaint. 29 C.F.R. §§ 1614.106(e)(2); 1614.108(f).\\n\\n On March 17, 2017, the district court dismissed Stewart’s case without prejudice\\n\\nfor lack of subject matter jurisdiction. The district court held that Stewart had failed to\\n\\nexhaust his administrative remedies because under Section 1614.407(b), he was required\\n\\nto wait until July 8, 2016, the earlier of 180 days after Stewart’s last amendment or 360\\n\\ndays after the filing of his initial complaint, to file a civil action in federal court. Stewart\\n\\ntimely appealed the district court’s decision.\\n\\n II.\\n\\n A.\\n\\n Stewart alleges violations of both the Rehabilitation Act and Title VII.\\n\\nRehabilitation Act claims “must comply with the same administrative procedures that\\n\\ngovern federal employee Title VII claims.” Wilkinson v. Rumsfeld, 100 F. App’x 155,\\n\\n\\n 4\\n\\f157 (4th Cir. 2004). Section 717, codified at 42 U.S.C. § 2000e-16, amended Title VII to\\n\\npermit federal employees to file a civil action for employment discrimination under\\n\\ncertain circumstances. Federal employees may file a civil action based upon their\\n\\nadministrative complaint (1) within 90 days of receipt of notice of final agency action or\\n\\n(2) after 180 days from “the filing of the initial charge” with the agency, if there has been\\n\\nno final agency action on the complaint.\\n\\n In addition to 42 U.S.C. § 2000e-16, federal regulations govern the process for\\n\\nfiling a civil action based on employment discrimination. Congress has delegated to the\\n\\nEqual Employment Opportunity Commission (“EEOC”) the authority to promulgate\\n\\nregulations to implement Title VII. E.E.O.C. v. Randstad, 685 F.3d 433, 444 (4th Cir.\\n\\n2012). Accordingly, the EEOC has enacted regulations regarding individuals’ ability to\\n\\n(1) amend their administrative complaint and (2) file suit in federal court under Title VII.\\n\\nThese regulations reinforce Section 2000e-16. A federal employee may amend a\\n\\ncomplaint “at any time prior to the conclusion of the investigation to include issues or\\n\\nclaims like or related to those raised in the complaint.” 29 C.F.R. § 1614.106(d).\\n\\nEchoing the language of 42 U.S.C. § 2000e-16(c), the EEOC’s regulations also state that\\n\\nfederal employees seeking relief under Title VII and the Rehabilitation Act may file a\\n\\ncivil action in federal district court “[a]fter 180 days from the date of filing an individual\\n\\nor class complaint if an appeal has not been filed and final action has not been taken.” 29\\n\\nC.F.R. § 1614.407(b).\\n\\n\\n\\n\\n 5\\n\\f B.\\n\\n We begin with the threshold question of whether Title VII’s 180-day waiting\\n\\nperiod found in Section 2000e-16(c) is a jurisdictional bar, a question of first impression\\n\\nin this circuit. 1 Although the PTO filed its motion to dismiss under Fed. R. Civ. P.\\n\\n12(b)(6), the district court dismissed Stewart’s case under Fed. R. Civ. P. 12(b)(1) for\\n\\nlack of subject-matter jurisdiction, stating that the “administrative exhaustion\\n\\nrequirements for the Rehabilitation Act and Title VII claims are jurisdictional,” and\\n\\nStewart failed to exhaust his administrative remedies. J.A. 234 n.4. For the following\\n\\nreasons, we conclude that the district court incorrectly held that Section 2000e-16(c)’s\\n\\n180-day waiting period is jurisdictional.\\n\\n Title VII directs federal employees to exhaust administrative remedies before\\n\\nfiling suit. Pueschel v. United States, 369 F.3d 345, 353 (4th Cir. 2004). Requiring\\n\\nexhaustion of administrative remedies serves twin objectives: protecting agency authority\\n\\n\\n 1\\n We have previously treated certain Title VII exhaustion requirements as\\njurisdictional—for example, filing a charge of discrimination with the EEOC, see Jones\\nv. Calvert Grp., Ltd., 551 F.3d 297, 300 (4th Cir. 2009)—but have never considered\\nwhether the 180-day waiting period in Section 2000e-16(c) is a jurisdictional\\nprerequisite. We also recognize that circuits have split on whether the failure to exhaust\\nadministrative remedies under Title VII, broadly conceived, is a jurisdictional\\nrequirement. Again, however, none of these cases implicate the mandatory 180-day\\nwaiting period in Section 2000e-16(c) that is before us in this case. Compare Peppers v.\\nCobb Cty., 835 F.3d 1289, 1296–97 (11th Cir. 2016) (treating the administrative\\nexhaustion requirement as a jurisdictional prerequisite to filing a Title VII action), with\\nFowlkes v. Ironworkers Local 40, 790 F.3d 378, 385 (2d Cir. 2015) (holding that the\\nfailure to exhaust administrative remedies does not raise a jurisdictional bar); Artis v.\\nBernanke, 630 F.3d 1031, 1034 n.4 (D.C. Cir. 2011) (same); Frederique-Alexandre v.\\nDep’t of Nat. & Envtl. Res. of Puerto Rico, 478 F.3d 433, 440 (1st Cir. 2007) (same).\\n\\n\\n\\n 6\\n\\fin the administrative process and “promot[ing] efficiency” in the resolution of claims.\\n\\nWoodford v. Ngo, 548 U.S. 81, 89 (2006). By avoiding the “premature interruption of the\\n\\nadministrative process,” exhaustion requirements ensure that agencies are provided the\\n\\nfirst opportunity to “exercise [] discretion” or “apply [] expertise.” McKart v. United\\n\\nStates, 395 U.S. 185, 193–94 (1969). The 180-day waiting period serves these purposes:\\n\\nit ensures that the employer is “put on notice of the alleged violations” to facilitate out-\\n\\nof-court resolution and permits sufficient, but finite, time for the agency to address the\\n\\ndiscrimination charges in the first instance. Miles v. Dell, Inc., 429 F.3d 480, 491 (4th\\n\\nCir. 2005). Indeed, courts have regularly characterized Section 2000e-16(c)’s 180-day\\n\\nwaiting period as an exhaustion requirement. See Murthy v. Vilsack, 609 F.3d 460, 465\\n\\n(D.C. Cir. 2010); Brown v. Snow, 440 F.3d 1259, 1263 (11th Cir. 2006).\\n\\n However, it bears noting that the 180-day waiting period also is not a paradigmatic\\n\\nexhaustion requirement. Unlike most administrative exhaustion requirements premised\\n\\non agency action, after which injured parties may “seek review of an adverse decision\\n\\nand obtain a remedy” if warranted, the 180-day waiting period is satisfied by agency\\n\\ninaction. Darby v. Cisneros, 509 U.S. 137, 144 (1993) (citation omitted). Indeed,\\n\\nCongress passed Section 2000e-16(c) of Title VII in 1972 precisely because of its\\n\\nrecognition that federal employees frequently encountered an “administrative quagmire”\\n\\nin filing charges of discrimination. H.R. Rep. 92–238, at 12 (June 2, 1971). The 180-day\\n\\nwaiting period therefore “confines agencies and the EEOC to a tight schedule” and\\n\\nsignals congressional recognition that “the doctrine of exhaustion of remedies . . . had\\n\\nbecome [a] barrier to meaningful court review.” Wilson v. Pena, 79 F.3d 154, 167 (D.C.\\n\\n\\n 7\\n\\fCir. 1996) (quoting Grubbs v. Butz, 514 F.2d 1323, 1328 (D.C. Cir. 1975)). In light of\\n\\nthis legislative context, the 180-day waiting period functions more like a mandatory\\n\\nprocedural hurdle for litigants than an affirmative agency step potentially giving rise to a\\n\\nremedy on review.\\n\\n This distinction informs our consideration of whether Section 2000e-16(c)’s 180-\\n\\nday waiting period requirement is also a jurisdictional requirement. Not all exhaustion\\n\\nrequirements are jurisdictional. Rather, we have recognized that certain exhaustion\\n\\nrequirements may be jurisdictional while others are not. For example, in Davis v. North\\n\\nCarolina Department of Correction, we specifically distinguished one exhaustion\\n\\nrequirement as jurisdictional—the entitlement to a right-to-sue letter from the EEOC—\\n\\nfrom Title VII’s “timely filing requirements,” which the Supreme Court has held are not\\n\\njurisdictional. 48 F.3d 134, 140 (4th Cir. 1995) (citing Zipes v. Trans World Airlines,\\n\\nInc., 455 U.S. 385, 393 (1982)); see also Laber v. Harvey, 438 F.3d 404, 429 n.25 (4th\\n\\nCir. 2006) (concluding that the 90-day time limit set forth in 42 U.S.C. § 2000e–16(c) is\\n\\nnot a jurisdictional requirement).\\n\\n In recent years, the Supreme Court repeatedly has cautioned courts not to\\n\\n“confuse[] or conflate[]” subject-matter jurisdiction, on the one hand, with the “essential\\n\\ningredients of a federal claim for relief,” on the other. Arbaugh v. Y & H Corp., 546 U.S.\\n\\n500, 503 (2006). Applying this distinction, the Supreme Court has differentiated between\\n\\nnon-jurisdictional “claim-processing” rules and jurisdictional rules that govern a court’s\\n\\nadjudicatory authority. Kontrick v. Ryan, 540 U.S. 443, 456 (2004); see also Gonzalez v.\\n\\nThaler, 565 U.S. 134, 141 (2012) (pressing a “stricter distinction” between these two\\n\\n\\n 8\\n\\fcategories of rules). In particular, the Supreme Court has clarified that most time bars are\\n\\n“quintessential claim-processing rules,” which “promote the orderly progress of litigation\\n\\nby requiring that the parties take certain procedural steps at certain specified times.”\\n\\nHenderson v. Shinseki, 562 U.S. 428, 435 (2011) (holding that a statute requiring filing of\\n\\nnotice of appeal within 180 days of administrative decision constituted a “claim-\\n\\nprocessing rule” and therefore was not jurisdictional). Such rules do not strip a court of\\n\\njudicial authority to hear a case, even when the time limits are “framed in mandatory\\n\\nterms.” United States v. Kwai Fun Wong, 135 S. Ct. 1625, 1632 (2015) (holding that\\n\\ncertain timely filing provisions in the Federal Torts Claims Act were not jurisdictional).\\n\\n Instead, the Supreme Court has established a clear statement rule for\\n\\ndetermining whether procedural rules, including time bars, are jurisdictional. Only if the\\n\\nstatutory text “plainly show[s] that Congress imbued a procedural bar with jurisdictional\\n\\nconsequences” should a court treat a rule as jurisdictional. Id. Put otherwise, Congress\\n\\nmust explicitly “tag” a procedural bar “as jurisdictional.” Id. In conducting this clear\\n\\nstatement inquiry, the Supreme Court has looked to several factors, including the\\n\\nstatutory text (if it speaks in “jurisdictional terms”); the placement of the rule (if it is\\n\\nlocated in the jurisdiction-granting provision of the statute); and legislative context.\\n\\nHenderson, 562 U.S. at 438.\\n\\n Here, Congress has done nothing to “tag” as jurisdictional the 180-day waiting\\n\\nperiod. The text of Section 2000e-16(c) addresses only the timeliness of claims; it does\\n\\nnot refer to the district courts’ “authority to hear untimely suits.” Kwai Fun Wong, 135 S.\\n\\nCt. 1625, 1628 (2015). Much like the filing deadline at issue in Henderson, Section\\n\\n\\n 9\\n\\f2000e-16(c) does not contain “jurisdictional language”—language dictating that judicial\\n\\nreview be obtained within a prescribed time and manner before a particular court.\\n\\nHenderson, 562 U.S. at 438. Simply because the 180-day waiting period is “cast in\\n\\nmandatory language” does not render it jurisdictional. Id. at 439.\\n\\n In addition, Section 2000e-16(c)’s placement within Title VII is distinct from\\n\\nthose provisions pertaining to jurisdiction. Section 2000e-16(c), titled “Employment by\\n\\nFederal Government,” lays out the respective 90-day filing period and 180-day waiting\\n\\nperiods before stating that the federal employee “may file a civil action as provided in\\n\\nsection 2000e-5.” 42 U.S.C. § 2000e-16(c) (emphasis added). Section 2000e-5, titled\\n\\n“Enforcement provisions,” mandates that federal district courts “shall have jurisdiction of\\n\\nactions brought under this subchapter.” 42 U.S.C. § 2000e-5(f)(3). These statutory\\n\\nsections serve different functions: on the one hand, Section 2000e-16(c) extends Title VII\\n\\nprotections to federal employees, and on the other, Section 2000e-5, as the enforcement\\n\\nprovision, prescribes jurisdictional requirements. Nothing “conditions the jurisdictional\\n\\ngrant [in Section 2000e-5(f)(3)] on the limitations periods [in Section 2000e-16(c)], or\\n\\notherwise links those separate provisions.” Kwai Fun Wong, 135 S. Ct. at 1633; see also\\n\\nGad v. Kansas State Univ., 787 F.3d 1032, 1038 (10th Cir. 2015) (noting that “a Title VII\\n\\nstatutory requirement’s classification as jurisdictional or non-jurisdictional turns in large\\n\\npart on whether it is located in Title VII’s jurisdictional subsection—42 U.S.C. § 2000e-\\n\\n5(f)(3)). This division further supports a conclusion that the 180-day waiting period is\\n\\nnot a jurisdictional requirement but rather a “prudential prerequisite to suit,” Davis v.\\n\\n\\n\\n\\n 10\\n\\fFort Bend Cty., 893 F.3d 300, 305 (5th Cir. 2018), or “statutory precondition,” Vinieratos\\n\\nv. U.S. Dep’t of Air Force, 939 F.2d 762, 768 n.5 (9th Cir. 1991).\\n\\n In considering this issue, we emphasize the subtle, but important, distinction\\n\\nbetween those exhaustion requirements that operate as a jurisdictional bar and those that\\n\\nmerely function as a statutory prerequisite to filing suit under Title VII. See Vinieratos,\\n\\n939 F.2d at 768 n.5 (9th Cir. 1991). Because we conclude that Section 2000e-16(c)’s\\n\\n180-day waiting period is akin to a “claim-processing” rule that imposes procedural\\n\\nobligations on litigants, rather than implicates judicial authority to hear a class of cases,\\n\\nwe hold that the 180-day waiting period is not jurisdictional.\\n\\n Our holding also prevents the “drastic” consequences of treating a procedural rule\\n\\nas jurisdictional—consequences that “alter[] the normal operation of our adversarial\\n\\nsystem.” Henderson, 562 U.S. at 434. Jurisdictional defects can be raised at any time by\\n\\nthe parties or sua sponte by the courts, even post-judgment, which may result in the\\n\\n“waste of judicial resources and may unfairly prejudice litigants.” Id. Because of the\\n\\ngravity of a jurisdictional label, the Supreme Court has repeatedly and explicitly\\n\\ndemanded “discipline” in this inquiry. Id. at 435.\\n\\n To be clear, we do not hold that all exhaustion requirements set forth in Title VII\\n\\nare non-jurisdictional. Rather, whether a particular exhaustion requirement—in Title VII\\n\\nor any other statute—is jurisdictional turns on the statutory language and purpose of the\\n\\nexhaustion provision at issue. Here, Section 2000e-16(c) includes no language clearly\\n\\nindicating that Congress intended for the provision to serve as a jurisdictional bar.\\n\\nFurther, in practice, Section 2000e-16(c)’s 180-day waiting period functions more closely\\n\\n\\n 11\\n\\fas a “time prescription,” which imposes a mandatory obligation on litigants but does not\\n\\ngovern a court’s jurisdiction. Arbaugh, 546 U.S. at 510; see also Stroy v. Gibson, 896\\n\\nF.3d 693, 698 (5th Cir. 2018) (treating Section 2000e-16(c)’s 180-day waiting period as a\\n\\n“precondition to filing suit,” not a jurisdictional requirement).\\n\\n Accordingly, the district court erred in dismissing this case under Federal Rule of\\n\\nCivil Procedure 12(b)(1). Instead, it should have considered the 180-day waiting period\\n\\nas a non-jurisdictional rule and decided the case under Federal Rule of Civil Procedure\\n\\n12(b)(6).\\n\\n III.\\n\\n A.\\n\\n Having determined that Section 2000e-16(c)’s 180-day waiting period is not\\n\\njurisdictional, we now turn to whether the district court erred in dismissing Stewart’s\\n\\naction under that provision. “We review de novo the grant of a motion to dismiss for\\n\\nfailure to state a claim [under Rule 12(b)(6)]. In so doing, we must accept as true all of\\n\\nthe factual allegations contained in the complaint.” Gerner v. Cty. of Chesterfield, Va.,\\n\\n674 F.3d 264, 266 (4th Cir. 2012) (citation omitted).\\n\\n Stewart’s appeal requires us to construe the statutory language of Section 2000e-\\n\\n16(c), and that provision’s 180-day waiting period, in particular. When construing a\\n\\nstatute, we “first and foremost strive to implement congressional intent by examining the\\n\\nplain language.” Minor v. Bostwick Laboratories, Inc., 669 F.3d 428 (4th Cir. 2012)\\n\\n(citation omitted). “[U]nless otherwise defined, words will be interpreted as taking their\\n\\nordinary, contemporary, common meaning.” Kennedy v. St. Joseph’s Ministries, Inc.,\\n\\n\\n 12\\n\\f657 F.3d 189, 192 (4th Cir. 2011) (citation omitted). In interpreting the plain language of\\n\\nthe statute, we also look to “the specific context in which the language is used, and the\\n\\nbroader context of the statute as a whole,” Minor, 669 F.3d at 434–35 (citations omitted),\\n\\nas well as a statute’s legislative history as additional evidence of congressional intent,\\n\\nElm Grove Coal Co. v. Director, O.W.C.P., 480 F.3d 278, 293 (4th Cir. 2007). Here,\\n\\neach of these factors indicates that Stewart’s amendments of his complaint did not restart\\n\\nthe 180-day clock.\\n\\n We begin with the plain language of the statute. In relevant part, Section 2000e-\\n\\n16(c) permits aggrieved federal employees to file a civil action 180 days “from the filing\\n\\nof the initial charge with the department, agency, or unit” if the agency has “fail[ed] to\\n\\ntake final action on his complaint.” 42 U.S.C. § 2000e-16(c) (emphasis added). Given\\n\\nthe ordinary meaning of the word “initial,” Section 2000e-16(c) requires that the 180-day\\n\\nwaiting period begin upon the filing of the first, original charge. See Webster’s Third\\n\\nNew Int’l Dictionary 1163 (3d ed. 1976) (defining “initial” as “of or relating to the\\n\\nbeginning; marking the commencement”); American Heritage Dictionary of the English\\n\\nLanguage 902 (4th ed. 2009) (defining “initial” as “of, relating to, or occurring at the\\n\\nbeginning; first”). Therefore, in Stewart’s case, the 180-day waiting period began on July\\n\\n14, 2015, the date he filed his “initial,” formal administrative complaint of discrimination\\n\\nand retaliation before the PTO’s Office of Equal Employment and Diversity.\\n\\n The statute’s use of the modifier “initial” also implicitly allows for the possibility\\n\\nof subsequent amendments—that there may well be additional “charge[s]” that follow the\\n\\n“initial charge.” Accordingly, the 180-day waiting period does not reset upon subsequent\\n\\n\\n 13\\n\\famendments to the administrative complaint. Had Congress not contemplated the\\n\\npossibility of amendments to the complaint, there would have been no reason to use the\\n\\nword “initial.” See Alaska Dep’t of Envtl. Conservation v. E.P.A., 540 U.S. 461, 489 n.13\\n\\n(2004) (observing it is “a cardinal principle of statutory construction that a statute ought,\\n\\nupon the whole, to be so construed that, if it can be prevented, no clause, sentence, or\\n\\nword shall be superfluous, void, or insignificant”) (citations and alterations omitted).\\n\\nTherefore, we hold that upon the passage of 180 days from the filing of the original\\n\\ncomplaint, and absent agency final action on the complaint, federal employees may file a\\n\\ncivil action, regardless of subsequent amendments to that complaint. 2\\n\\n Turning to the legislative context, Congress passed Section 2000e-16(c) of Title\\n\\nVII in 1972 because of its recognition that aggrieved federal employees did not have\\n\\nsufficient access to the courts under Title VII. S. Rep. 92–415 at 16 (1971). Before the\\n\\n1972 Act, the “effective availability of either administrative or judicial relief” for federal\\n\\nemployees was uncertain. Brown v. General Servs. Admin., 425 U.S. 820, 825 (1976).\\n\\nFederal employees often faced an “administrative quagmire” in which parties had to wait\\n\\nseveral years in the overburdened administrative process. H.R. Rep. 92–238, at 12 (June\\n\\n\\n 2\\n In an unpublished per curiam opinion, we summarily affirmed a district court’s\\nholding that federal employees must wait beyond the 180-day period when they amend\\ntheir complaints. Laber v. Harvey, No. 1:05-cv-00803-CMH, 2005 WL 3008510, at *1\\n(E.D. Va. Nov. 7, 2005), aff’d, 204 F. App’x 332 (4th Cir. 2006). We are not bound by\\nthat opinion, which is devoid of reasoning. See Collins v. Pond Creek Mining Co., 468\\nF.3d 213, 219 (4th Cir. 2006) (noting that “we ordinarily do not accord precedential value\\nto our unpublished decisions” and they are “entitled only to the weight they generate by\\nthe persuasiveness of their reasoning”) (citation omitted).\\n\\n\\n\\n 14\\n\\f2, 1971). Ensuring that federal employees had “access to the courts” therefore drove the\\n\\npassage of Section 2000e-16(c). S. Rep. No. 92–415, at 16 (1971). The 180-day waiting\\n\\nperiod directly serves that end. In discussing Section 2000e-16(c)’s 180-day waiting\\n\\nprovision in the context of EEOC inaction, the D.C. Circuit observed that:\\n\\n The 180 day [waiting period] provision represents a Congressional\\n determination that providing prompt access to the courts in discrimination\\n disputes is so important that the administrative process will be given only a\\n finite time to deal alone with a given dispute. Indeed, the Act is in part a\\n response to Congressional realization that “the doctrine of exhaustion of\\n remedies . . . had become [a] barrier to meaningful court review.”\\n\\nWilson, 79 F.3d at 167 (quoting Grubbs, 514 F.2d at 1328). Allowing agencies to\\n\\nrepeatedly delay individuals’ ability to go to court, simply because they have amended\\n\\ntheir administrative complaints, would frustrate a “congressional policy to make the\\n\\ncourts the final tribunal for the resolution of controversies over charges of discrimination\\n\\nafter all administrative remedies have been exhausted.” Koger v. Ball, 497 F.2d 702, 706\\n\\n(4th Cir. 1974). Although Section 2000e-16(c) “provides for a careful blend of\\n\\nadministrative and judicial enforcement powers,” we cannot overlook that, in passing the\\n\\nprovision, Congress intended federal employees to have a robust judicial remedy, and\\n\\nready access to the courts, for employment discrimination claims. Brown, 425 U.S. at\\n\\n833\\n\\n Our conclusion also comports with the broader purpose of Title VII as a “remedial\\n\\nscheme in which laypersons, rather than lawyers, are expected to initiate the process.”\\n\\nSydnor, 681 F.3d at 594 (citation omitted); see also Alvarado v. Board of Trustees of\\n\\nMontgomery Community College, 848 F.2d 457, 460 (4th Cir. 1988) (“Title VII does not\\n\\n\\n\\n 15\\n\\frequire procedural exactness from lay complainants.”). We must be wary of “overly\\n\\ntechnical concerns” laying a “tripwire for hapless plaintiffs.” Syndor, 681 F.3d at 594.\\n\\nHere, for example, the PTO repeatedly informed Stewart, after each of his amendments—\\n\\nand in accordance with the statute’s plain language—that he could file a civil action “at\\n\\nany time after 180 days have passed from the date [he] filed [his] original complaint.”\\n\\nJ.A. 114. Permitting the agency to repeatedly confuse litigants in this manner would only\\n\\nfurther pervert Title VII’s remedial purpose.\\n\\n B.\\n\\n In support of its position that Stewart was required to wait beyond the initial 180-\\n\\nday waiting period, the PTO makes several arguments. First, the PTO argues that Section\\n\\n2000e-16(c)’s statutory text is “ambiguous” because it uses two different terms,\\n\\n“complaint” and “charge.” Second, the PTO argues that the EEOC’s regulations support\\n\\ntethering the 180-day waiting period to the agency’s extended investigation period for\\n\\namended complaints. Third, the PTO argues that should we reverse the district court’s\\n\\nholding, we would incentivize gamesmanship in Title VII claims. Each of these\\n\\narguments is unavailing.\\n\\n In support of its first argument—that Section 2000e-16(c)’s statutory text is\\n\\nambiguous 3—the PTO emphasizes Congress’s use of two terms within the statute:\\n\\n\\n 3\\n In repeatedly referring to Section 2000e-16(c)’s purported “ambiguity,” the PTO\\nappears to be implicitly invoking, or at least evoking, Chevron deference to its\\ninterpretation of the statute. However, the statute is not ambiguous. Further, we only\\ngrant Chevron deference to “an agency’s construction of the statute which it\\nadministers.” Chevron, U.S.A., Inc. v. Nat. Res. Def. Council, Inc., 467 U.S. 837, 842\\n(Continued)\\n\\n 16\\n\\f“complaint” and “charge.” The PTO argues that the term “complaint” in Section 2000e-\\n\\n16(c) references “an employee’s general use of the administrative process” to allege\\n\\nunlawful discrimination, while the phrase “initial charge” is “the first ‘statement’”\\n\\nthrough which an employee identifies this discrimination. Appellee’s Br. at 25–26. To\\n\\nthe PTO, it bears significance that Congress did not use the phrase “initial complaint” in\\n\\nSection 2000e-16(c) but rather “initial charge,” thus indicating that “Congress did not\\n\\nseek to trigger the 180-day period upon the commencement of the EEO process\\n\\ngenerally.” Appellee’s Br. at 26 (emphasis in original).\\n\\n Even if we were to accept the PTO’s proposed distinction between these two\\n\\nterms, such a distinction does not aid the PTO’s position. If we treat “initial charge” as\\n\\nthe first, informal “statement” through which an employee alleges unlawful\\n\\ndiscrimination, then the 180-day waiting period would be satisfied at the same time or\\n\\nearlier than under the reading we adopt because a “charge,” so conceived, never\\n\\ntemporally follows a “complaint.” Under the PTO’s construction, Stewart’s “initial\\n\\ncharge” occurred on April 30, 2015, when he submitted a document to the PTO’s Office\\n\\nof Equal Employment Opportunity and Diversity alleging harassment and discrimination\\n\\non the basis of disability. Accepting the PTO’s position, then, would only hasten the date\\n\\nupon which Stewart could file a civil action. More significantly, PTO’s position in no\\n\\n\\n\\n\\n(1984). The EEOC, not the PTO, administers Title VII, so even if Chevron deference\\nwere implicated here, the PTO is entitled to no such deference. The record includes no\\nindication that the EEOC concurs in the PTO’s construction of Section 2000e-16(c).\\n\\n\\n\\n 17\\n\\fway explains Congress’s express use of the word “initial,” which serves as the crux of\\n\\nour construction of Section 2000e-16(c)’s 180-day waiting period. The term “initial”\\n\\nmakes clear that Congress intended to begin the 180-day waiting period from the filing of\\n\\nthe original complaint, regardless of whether subsequent amendments to that complaint\\n\\nare filed. See United States v. Blannon, 836 F.2d 843, 854 (4th Cir. 1988) (“[A] court\\n\\nmay not manufacture an ambiguity in order to defeat Congress’ intent.”).\\n\\n Next, the PTO argues that the EEOC’s relevant regulations support its position\\n\\nthat Stewart was required to wait longer than 180 days before filing suit. However, we\\n\\nconclude that these regulations only reinforce our interpretation of Section 2000e-16(c).\\n\\n29 C.F.R. § 1614.407(b) mirrors the language found in Section 2000e-16(c), providing in\\n\\nrelevant part that a complainant is authorized under Title VII and the Rehabilitation Act\\n\\nto file a civil action in federal district court “[a]fter 180 days from the date of filing an\\n\\nindividual or class complaint if an appeal has not been filed and final action has not been\\n\\ntaken.” Given the regulation’s use of the term “individual . . . complaint,” the PTO\\n\\ncannot dispute that the 180-day waiting period begins upon filing of the individual\\n\\ncomplaint. Instead, the PTO attempts to wave away the regulation as a “generic rule,”\\n\\nbut this perfunctory argument is not persuasive. Appellee’s Br. at 29.\\n\\n The district court, and the PTO, wrongly tether Section 1614.407(b)’s 180-day\\n\\nwaiting period to other EEOC regulations extending the agency investigation period\\n\\nwhen a complaint has been amended to “within the earlier of 180 days after the last\\n\\namendment to the complaint or 360 days after the filing of the original complaint.” 29\\n\\nC.F.R. §§ 1614.106(e)(2), 1614.108(f). The district court reasoned that otherwise, the\\n\\n\\n 18\\n\\fcourt “would be adjudicating claims that the [PTO] has not yet had the opportunity to\\n\\ninvestigate, let alone adjudicate.” J.A. 236. We disagree for two reasons.\\n\\n First, as discussed above, the district court’s holding is contrary to the plain\\n\\nlanguage of both Section 2000e-16(c) of Title VII and 29 C.F.R. § 1614.407(b). Further,\\n\\nSection 1614.407(b) lacks any textual distinction between filing an initial complaint and\\n\\nfiling an amendment, which is particularly telling given that other regulations in the same\\n\\npart, such as those governing the agency investigation period, do make such a distinction.\\n\\nSee 29 C.F.R. §§ 1614.106(e)(2), 1614.108(f). Section 1614.407(b) does not hinge\\n\\nemployees’ ability to file a civil action on the conclusion of the agency investigation;\\n\\nrather, it establishes a bright-line 180-day waiting period after which the employee can be\\n\\n“assured of having reasonably prompt access to the courts.” Wilson, 79 F.3d at 167 (D.C.\\n\\nCir. 1996).\\n\\n Additionally, the district court neglected an important facet of Title VII claims: we\\n\\nhave long held that courts may in fact adjudicate claims not raised before the agency, if\\n\\ncertain requirements are met. In Hill v. Western Electric Company, Inc., we recognized\\n\\nthe “generally accepted principle” that the “scope of a Title VII lawsuit may extend to\\n\\n‘any kind of discrimination like or related to allegations contained in the charge and\\n\\ngrowing out of such allegations during the pendency of the case’” before the agency. 672\\n\\nF.2d 381, 390 n.6 (4th Cir. 1982). Put otherwise, an “administrative charge of\\n\\ndiscrimination does not strictly limit a Title VII suit which may follow,” and federal\\n\\ncourts may still hear claims that the employee did not raise before the agency, as long as\\n\\nthey are “like or related” and grow out of the allegations during the pendency of the case\\n\\n\\n 19\\n\\fbefore the agency. Sydnor, 681 F.3d at 594. Only “those discrimination claims stated in\\n\\nthe initial charge, those reasonably related to the original complaint, and those developed\\n\\nby reasonable investigation of the original complaint may be maintained in a subsequent\\n\\nTitle VII lawsuit.” Chacko v. Patuxent Institution, 429 F. 3d 505, 506 (4th Cir. 2005)\\n\\n(citation omitted); see also Smith v. First Union Nat. Bank, 202 F.3d 234, 247 (4th Cir.\\n\\n2000) (“If a plaintiff’s claims in her judicial complaint are reasonably related to her\\n\\nEEOC charge and can be expected to follow from a reasonable administrative\\n\\ninvestigation, the plaintiff may advance such claims in her subsequent civil suit.”). Our\\n\\nprecedent makes clear that plaintiffs, although circumscribed by their administrative\\n\\ncomplaints, are not wholly banned from raising claims for the first time before the district\\n\\ncourt, so long as they meet the requirements articulated in Hill and Chacko.\\n\\n Nor is a plaintiff’s ability to raise new claims before the district court cabined to\\n\\nthe context of retaliation claims, as the PTO appeared to briefly suggest at oral argument.\\n\\nOral Argument at 27:53–28:25 (“I don’t think he can amend his complaint, [] unless it\\n\\nwas for retaliation . . . because this Court’s jurisprudence provides that in cases of\\n\\nretaliation, the exhaustion procedures and principles are a little bit different.”). It is true\\n\\nthat we have often addressed a plaintiff’s ability to do so in the specific context of\\n\\nretaliation claims. See Nealon v. Stone, 958 F.2d 584, 590 (4th Cir. 1992). Importantly,\\n\\nhowever, we have never held that the rule applies exclusively in the context of retaliation\\n\\nclaims but rather that retaliation claims “receive extended flexibility” when being\\n\\nconsidered under the general rule referenced in Hill. Clarke v. Richmond Behavioral\\n\\nHealth Auth., No. 3:09CV743, 2011 WL 13274273, at *4 (E.D. Va. Aug. 10, 2011); see\\n\\n\\n 20\\n\\falso Brown v. Runyon, 139 F.3d 888 (4th Cir. 1988) (unpublished opinion) (noting that\\n\\nour precedent “presupposes both that a retaliation count in a Title VII lawsuit be ‘related\\n\\nto’ and have ‘grown out’ of the EEO charge while the administrative charge remained\\n\\npending”). We have reasoned that retaliation claims constitute a subset of the general\\n\\nrule noted in Hill, because “retaliation claims almost always relate back to previously\\n\\nfiled EEO charges, and, therefore, may be raised for the first time in district court without\\n\\nthe requirement that a plaintiff have exhausted his administrative remedies.” Brown, 139\\n\\nF.3d at 888. Accordingly, retaliation claims represent the “inevitable corollary,” but not\\n\\nthe exclusive application, of the “generally accepted principle” articulated in Hill. Id.\\n\\n(quoting Nealon, 958 F.2d at 590). We have therefore left open the possibility that\\n\\ndistrict courts may hear claims for the first time, beyond just retaliation claims, if they are\\n\\n“reasonably related to the original complaint” and “developed by reasonable investigation\\n\\nof the original complaint.” Chacko, 429 F.3d at 506.\\n\\n Indeed, other circuits have recognized the need to grant Title VII plaintiffs\\n\\n“significant leeway” in drafting administrative complaints, given their lack of technical\\n\\nexpertise. Cheek v. W. & S. Life Ins. Co., 31 F.3d 497, 500 (7th Cir. 1994) (citation\\n\\nomitted). Applying this principle of liberal construction, other circuits permit litigants to\\n\\nbring claims not specifically pressed before the agency if they are “like or reasonably\\n\\nrelated to those contained in the [agency] complaint” and if they “reasonably could have\\n\\ndeveloped from the [agency’s] investigation of the charges before it.” Sommerfield v.\\n\\nCity of Chicago, 863 F.3d 645, 648 (7th Cir. 2017); see also Foster v. BNSF Ry. Co., 866\\n\\nF.3d 962, 966 (8th Cir. 2017) (holding same); Freeman v. Oakland Unified Sch. Dist.,\\n\\n\\n 21\\n\\f291 F.3d 632, 636 (9th Cir. 2002) (same). We join these circuits today in reiterating our\\n\\ndecision in Hill and Chacko that plaintiffs may bring Title VII claims for the first time\\n\\nbefore a district court, so long as they are like or reasonably related to charges in the\\n\\noriginal administrative complaint, and if they reasonably could have developed from the\\n\\nagency’s investigation of the original complaint. See Hill, 672 F.2d at 390 n.6; Chacko,\\n\\n429 F.3d at 506.\\n\\n Crucially, this “like or related” limitation also allays the PTO’s third argument\\n\\nregarding gamesmanship. The PTO argues that should we reverse the district court, a\\n\\nfederal employee could file a “perfunctory initial ‘charge,’ seek to add new claims\\n\\nimmediately before the 180-day ‘mark,’ and then file a civil action immediately\\n\\nfollowing that same ‘mark.’” Appellee’s Br. at 28. First, as discussed above, we already\\n\\npermit courts to adjudicate reasonably related claims not heard in the first instance by\\n\\nagencies. The “like or related” limitation limits the universe of charges that the litigant\\n\\nmay bring and guards against the gamesmanship concern that litigants will raise wholly\\n\\nunrelated claims for the first time before a district court.\\n\\n Second, as Stewart correctly points out, existing procedural guardrails further\\n\\nprotect against such gamesmanship. When amending a complaint before the agency, the\\n\\nemployee must file a letter with the agency’s Office of Equal Employment Director\\n\\n“describing the new incident(s) and stating that s/he wishes to amend his/her complaint to\\n\\ninclude the new incident(s).” EEOC Mgmt. Directive 110, Ch. 5.B. The Director must\\n\\nthen review this request to determine if the claims are like or related, and “whether a fair\\n\\nand impartial investigation of the new claims can be accomplished within 360 days of the\\n\\n\\n 22\\n\\foriginal filed complaint.” Id. If not, then the individual must start a new administrative\\n\\nprocess with respect to the new claim. Accordingly, employees cannot game the\\n\\nadministrative process in the way suggested by the PTO. Indeed, if we were to accept the\\n\\ndistrict court’s holding, we may even risk disincentivizing plaintiffs from bringing a “like\\n\\nor related” claim before the agency, as each amendment would only further delay the\\n\\nplaintiff’s access to court. Under the district court’s reading of 42 U.S.C. § 2000e-16(c)\\n\\nand 29 C.F.R. § 1614.407(b), a plaintiff might be better served by holding onto their “like\\n\\nor related” claims until the filing of a civil action. But this outcome would undermine the\\n\\npolicy goals underlying Title VII’s administrative framework to encourage “quicker, less\\n\\nformal, and less expensive resolution of disputes.” Sydnor, 681 F.3d at 593 (quoting\\n\\nChris v. Tenet, 221 F.3d 648, 653 (4th Cir. 2000)).\\n\\n Our holding maintains the careful balance between the Title VII’s administrative\\n\\nframework and judicial remedies, between “providing notice to employers and the\\n\\n[agency] on the one hand and ensuring plaintiffs are not tripped up over technicalities on\\n\\nthe other.” Id. at 594. We recognize the “substantial role” played by the administrative\\n\\nprocess in narrowing “formal litigation.” Chacko, 429 F.3d at 509. But it is equally\\n\\nwell-established that if the claim raised for the first time before the district court contains\\n\\nfactual allegations that “are reasonably related to the factual allegations in the formal\\n\\nlitigation, the connection between the charge and the claim is sufficient.” Id. (citation\\n\\nomitted); see also Kersting v. Wal-Mart Stores, Inc., 250 F.3d 1109, 1118 (7th Cir. 2001)\\n\\n(noting that a plaintiff may pursue a claim not explicitly included in an administrative\\n\\ncomplaint if the allegations are “like or reasonably related to” those in the charge).\\n\\n\\n 23\\n\\f *****\\n\\n The plain text of 42 U.S.C. § 2000e-16(c) and 29 C.F.R. 1614.407(b), as well as\\n\\nthe legislative context and purpose of Title VII, dictate the outcome of this case.\\n\\nContrary to the district court’s holding, Section 2000e-16(c)’s 180-day waiting period\\n\\noperates independently of the agency’s extended investigation window for amended\\n\\ncomplaints. Instead, the 180-day waiting period “gives great weight to the complainant’s\\n\\ninterest in obtaining speedy resolution of the complaint” and ensures ready access to the\\n\\ncourts. Wilson, 79 F.3d at 167. Accordingly, we hold that Section 2000e-16(c)’s 180-\\n\\nday waiting period for filing a civil action, absent agency final action, commences with\\n\\nthe filing of the initial administrative complaint, regardless of subsequent amendments to\\n\\nthat complaint.\\n\\n IV.\\n\\n For the foregoing reasons, we reverse the district court’s dismissal of Stewart’s\\n\\namended complaint and remand for further proceedings.\\n\\n REVERSED AND REMANDED\\n\\n\\n\\n\\n 24\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":90,"cells":{"id":{"kind":"number","value":4580036,"string":"4,580,036"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Brian Davison v. Phyllis Randall"},"decision_date":{"kind":"string","value":"2019-01-09"},"docket_number":{"kind":"string","value":"17-2002"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before KEENAN, WYNN, and HARRIS, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"WYNN, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-2002\\n\\n\\nBRIAN DAVISON,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nPHYLLIS RANDALL, In her official and individual capacity,\\n\\n Defendant - Appellant,\\n\\n and\\n\\nLOUDOUN COUNTY BOARD OF SUPERVISORS, In their official and\\nindividual capacities; LEO ROGERS, In his official capacity; TONY\\nBUFFINGTON, In his official capacity; RON MEYER, In his official capacity;\\nGEARY HIGGINS, In his official capacity,\\n\\n Defendants.\\n\\n------------------------------\\n\\nLOCAL GOVERNMENT ATTORNEYS OF VIRGINIA, INC.;\\nINTERNATIONAL MUNICIPAL LAWYERS ASSOCIATION; VIRGINIA\\nASSOCIATION OF COUNTIES; VIRGINIA MUNICIPAL LEAGUE,\\n\\n Amici Supporting Appellant,\\n\\nAMERICAN CIVIL LIBERTIES UNION; ACLU OF VIRGINIA; ACLU OF\\nMARYLAND; ACLU OF NORTH CAROLINA; ACLU OF SOUTH\\nCAROLINA; ACLU OF WEST VIRGINIA,\\n\\n Amici Supporting Appellee.\\n\\n No. 17-2003\\n\\n\\nBRIAN C. DAVISON,\\n\\n Plaintiff - Appellant,\\n\\n v.\\n\\nPHYLLIS RANDALL, In her official and individual capacity; LOUDOUN\\nCOUNTY BOARD OF SUPERVISORS, In their official and individual\\ncapacities,\\n\\n Defendants - Appellees,\\n\\n and\\n\\nLEO ROGERS, In his official capacity; TONY BUFFINGTON, In his official\\ncapacity; RON MEYER, In his official capacity; GEARY HIGGINS, In his\\nofficial capacity,\\n\\n Defendants.\\n\\n\\nAppeals from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. James C. Cacheris, Senior District Judge. (1:16-cv-00932-JCC-IDD)\\n\\n\\nArgued: September 26, 2018 Decided: January 7, 2019\\n Amended: January 9, 2019\\n\\n\\nBefore KEENAN, WYNN, and HARRIS, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Wynn wrote the opinion, in which Judge Keenan\\nand Judge Harris concurred. Judge Keenan wrote a separate concurring opinion.\\n\\n\\nARGUED: Scott E. Gant, BOIES SCHILLER FLEXNER, LLP, Washington, D.C.; Leo\\nP. Rogers, LOUDON COUNTY ATTORNEY, Leesburg, Virginia, for Appellant/Cross-\\n\\n\\n 2\\n\\nAppellee. Katherine A. Fallow, KNIGHT FIRST AMENDMENT INSTITUTE AT\\nCOLUMBIA UNIVERSITY, New York, New York, for Appellee/Cross-Appellant. ON\\nBRIEF: Aaron E. Nathan, BOIES SCHILLER FLEXNER LLP, Washington, D.C., for\\nAppellant/Cross-Appellee. Jameel Jaffer, Carrie DeCell, KNIGHT FIRST\\nAMENDMENT INSTITUTE AT COLUMBIA UNIVERSITY, New York, New York,\\nfor Appellee/Cross-Appellant. Vishal Agraharkar, AMERICAN CIVIL LIBERTIES\\nUNION FOUNDATION OF VIRGINIA, Richmond, Virginia; Esha Bhandari, Vera\\nEidelman, AMERICAN CIVIL LIBERTIES UNION FOUNDATION, New York, New\\nYork; Susan K. Dunn, ACLU OF SC FOUNDATION, INC., Charleston, South Carolina;\\nChristopher Brook, AMERICAN CIVIL LIBERTIES UNION OF NORTH CAROLINA\\nLEGAL FOUNDATION, Raleigh, North Carolina; Deborah A. Jeon, ACLU\\nFOUNDATION OF MARYLAND, Baltimore, Maryland; Jennifer D. Oliva, ACLU OF\\nWEST VIRGINIA FOUNDATION, Charleston, West Virginia, for Amici American\\nCivil Liberties Union, ACLU of Virginia, ACLU of Maryland, ACLU of North Carolina,\\nACLU of South Carolina, and ACLU of West Virginia. Joshua A. Geltzer, Douglas\\nLetter, Amy L. Marshak, Mary B. McCord, INSTITUTE FOR CONSTITUTIONAL\\nADVOCACY AND PROTECTION GEORGETOWN UNIVERSITY LAW CENTER,\\nWashington, D.C.; Kwaku A. Akowuah, Christopher C. Fonzone, Kate Heinzelman,\\nSIDLEY AUSTIN LLP, Washington, D.C., for Amici Curiae First Amendment Legal\\nScholars.\\n\\n\\n\\n\\n 3\\n\\nWYNN, Circuit Judge:\\n\\n Phyllis Randall, Chair of the Loudoun County, Virginia, Board of Supervisors (the\\n\\n“Loudoun Board”), brings this appeal, arguing that the district court erred in concluding\\n\\nthat she violated the First Amendment rights of one of her constituents, Brian Davison,\\n\\nwhen she banned Davison from the “Chair Phyllis J. Randall” Facebook page she\\n\\nadministered. In a cross appeal, Davison principally argues that the district court erred\\n\\nin dismissing his procedural due process claim premised on the ban. For the reasons that\\n\\nfollow, we affirm.\\n\\n I.\\n\\n A.\\n\\n Randall has chaired the Loudoun County Board of Supervisors since January 1,\\n\\n2016. The day before she was sworn in as chair, Randall created the “Chair Phyllis J.\\n\\nRandall” Facebook Page (the “Chair’s Facebook Page”). According to Facebook, Inc.,\\n\\nunlike personal Facebook profiles, which are for non-commercial use and represent\\n\\nindividual people, Facebook “Pages”—like the Chair’s Facebook Page—“help\\n\\nbusinesses, organizations, and brands share their stories and connect with people.” J.A.\\n\\n403. “Pages are managed by people who have personal profiles,” the company explains.\\n\\nJ.A. 403. In addition to the Chair’s Facebook Page, Randall created and maintained two\\n\\nother Facebook profiles: a personal profile and a Page devoted to her campaign. Randall\\n\\nclassified her campaign page as belonging to a “politician” and used no designation for\\n\\nher personal profile, but she designated the Chair’s Facebook Page as a “governmental\\n\\nofficial” page. J.A. 209–10.\\n\\n\\n 4\\n\\n Randall and her Chief of Staff, Jeanine Arnett, share administrative control over\\n\\nthe Chair’s Facebook Page, although Randall almost exclusively controls the page’s\\n\\ncontent. On her campaign page, Randall characterized the Chair’s Facebook Page as her\\n\\n“county Facebook page” stating:\\n\\n I really want to hear from ANY Loudoun citizen on ANY issues, request,\\n criticism, complement or just your thoughts. However, I really try to keep\\n back and forth conversations (as opposed to one time information items\\n such as road closures) on my county Facebook page (Chair Phyllis J.\\n Randall) or County email (Phyllis.randall@loudoun.gov). Having back and\\n forth constituent conversations are Foiable ([Freedom of Information Act])\\n so if you could reach out to me on these mediums that would be\\n appreciated.\\n\\nJ.A. 455 (emphasis added).\\n\\n The Chair’s Facebook Page includes three columns. The left column, which is\\n\\ntopped by a picture of Randall, includes several links to allow visitors to quickly navigate\\n\\nthe contents of the Chair’s Facebook Page.\\n\\n The middle column, which is organized in reverse chronological order similar to a\\n\\npersonal profile’s News Feed, is composed of posts by Randall and comments by\\n\\nFacebook users on those posts. Randall’s posts are almost always directed to “Loudoun,”\\n\\nsee, e.g., J.A. 408–10, and deal with numerous aspects of Randall’s official\\n\\nresponsibilities. For example, Randall used the Chair’s Facebook Page to notify the\\n\\npublic about upcoming Loudoun Board meetings, and the subjects to be discussed during\\n\\nthose meetings. Randall also used the page to inform Loudoun County residents about\\n\\nsignificant public safety issues. See, e.g., J.A. 412 (stating that Loudoun Board had\\n\\n“been informed by the Sheriff’s Office about the non-legitimate threat made on social\\n\\n\\n\\n 5\\n\\nmedia toward Dominion High School in Sterling”); J.A. 418 (reporting that she “ha[d]\\n\\nbeen briefed regarding the student falling from the water tower this morning” and\\n\\nadvising the public to “not make any assumptions but wait for information”). And\\n\\nRandall used the Chair’s Facebook Page to coordinate Loudoun County’s response to a\\n\\nlarge snow storm, including to communicate with constituents regarding which municipal\\n\\nstreets required plowing.\\n\\n Other posts by Randall to the Chair’s Facebook Page invited members of the\\n\\npublic to apply to participate on a public commission and to participate in public\\n\\nmeetings regarding key issues facing Loudoun County residents, such as revised flood\\n\\nplain zones and the Zika virus. Randall also authored posts regarding a variety of trips\\n\\nand meetings she had taken in furtherance of Loudoun County business. E.g., J.A. 408\\n\\n(reporting that Randall “address[ed] the (county) role in Treatment” at a “regional\\n\\nconference on Opioid and Substance Abuse Addiction”); J.A. 410 (stating that Randall\\n\\nrepresented Loudoun County at its “annual credit rating presentation” in New York); J.A.\\n\\n415 (informing public of trip to Loudoun’s “Sister City” in Germany); J.A. 426\\n\\n(reporting that Randall was “in Richmond lobbying for [Loudoun County’s] legislative\\n\\nprogram”). Finally, Randall used the page to advise the public regarding official actions\\n\\ntaken by the Loudoun Board. E.g., J.A. 433 (reporting that Loudoun Board “approved\\n\\nfunding for new breathing apparatus for our Loudoun Firefighters”); J.A. 442 (listing\\n\\nseveral “proclamations of note” by the Loudoun Board); J.A. 443 (informing public that\\n\\nLoudoun Board “adopted a budget for Fiscal Year 2017 totaling $2.46 billion for the\\n\\ngeneral county government and schools”). Although Randall’s posts on the Chair’s\\n\\n\\n 6\\n\\nFacebook Page principally addressed her official responsibilities, a few posts addressed\\n\\ntopics less closely related to her official activities such as her affection for the German\\n\\nlanguage or pride in becoming an organ donor.\\n\\n Members of the public, including Davison, “liked” 1 or commented on several of\\n\\nRandall’s posts on the Chair’s Facebook Page. Each “like” or comment identified the\\n\\nname of the personal profile or Page of the authoring party. Many of the comments\\n\\nthanked Randall and the Loudoun Board for representing the public’s interests. Other\\n\\nposts by members of the public offered feedback on various issues faced by Randall and\\n\\nthe Loudoun Board. E.g., J.A. 427 (stating that “[p]utting recreation in a flood plain is\\n\\nnot a good idea”); J.A. 448 (stating that “more needs to be done with the explosion of\\n\\nLyme disease in Loudoun”). And other comments dealt with constituent-specific issues.\\n\\nE.g., J.A. 415 (constituent stating, in response to post by Randall regarding visit to\\n\\nLoudoun County’s “Sister City” in Germany, that constituent’s “daughter is interested in\\n\\nexchange programs”); J.A. 454 (stating that “there [we]re no [snow] plows to be seen” in\\n\\na particular neighborhood). Finally, several comments, including a number authored by\\n\\nDavison, criticized the Loudoun Board, generally, and Randall, in particular, for actions\\n\\ntaken in their official capacities. E.g., J.A. 429–30 (Davison criticizing public school\\n\\nsystem budget and expenditures); J.A. 438–39 (member of public criticizing\\n\\ngovernmental entity’s inspection of farm, claiming it failed to uncover animal abuse);\\n\\n\\n 1\\n “‘Liking’ on Facebook is a way for Facebook users to share information with\\neach other.” Bland v. Roberts, 730 F.3d 368, 385 (4th Cir. 2013).\\n\\n\\n\\n 7\\n\\nJ.A. 449 (Davison characterizing question he posed at Loudoun Board and Loudoun\\n\\nSchool Board joint town hall). On some occasions, Randall responded to these\\n\\ncomments or criticisms.\\n\\n In the right column of the Chair’s Facebook Page, the page is identified as a\\n\\n“government official” page. It provides contact information for Randall’s county office,\\n\\nincluding her office telephone number, Randall’s official county email address, and the\\n\\ninternet address for the official county website. The column also identifies how many\\n\\nand which Facebook personal profiles and Pages “like” and “follow” the Chair’s\\n\\nFacebook Page. 2 And the column includes a list of personal profiles and Pages “liked”\\n\\nby the Chair’s Facebook Page.\\n\\n Randall publicized the Chair’s Facebook Page in her official “Chair Phyllis J.\\n\\nRandall” newsletter, which is prepared by County employees, hosted on the County’s\\n\\nwebsite, and distributed to Loudoun citizens using Randall’s official county email\\n\\naccount. The newsletter ends with the words “STAY CONNECTED” and a Facebook\\n\\nicon that hyperlinks to the Chair’s Facebook Page. Randall also highlighted the Chair’s\\n\\nFacebook Page in “Winter Storm Information” notices emailed from her official county\\n\\naccount to Loudoun County residents, advising recipients to “Visit [the Chair’s Facebook\\n\\nPage] for Updates.” J.A. 341–42, 344.\\n\\n 2\\n According to Facebook, “[l]iking a Facebook Page means you are connecting to\\nthat Page. When you connect to a Page, it will appear in [a user’s] timeline and [the user]\\nwill appear on the page as a person who likes that Page. The Page will also be able to\\npost content into [the user’s] News Feed.” Bland, 730 F.3d at 385 (internal quotation\\nmarks omitted).\\n\\n\\n\\n 8\\n\\n Davison, an outspoken resident of Loudoun County, apparently largely focuses his\\n\\ncivic engagement and expression on “the funding and . . . management of public\\n\\nschools.” J.A. 95. To that end, he has repeatedly expressed concern about “School Board\\n\\nmembers failing to disclose personal conflicts as required by law before voting on\\n\\nfinancial transactions before the School Board.” J.A. 96.\\n\\n On February 3, 2016, Davison attended a Loudoun town hall meeting that\\n\\nincluded the Loudoun County School Board and Randall. At the meeting, Davison\\n\\nsubmitted a question implying that certain School Board members had acted unethically\\n\\nin approving financial transactions. Randall volunteered to answer the question but\\n\\ncharacterized it as a “set-up question” that she did not “appreciate.” J.A. 103. Shortly\\n\\nafter Randall answered the question—and while the town hall meeting was still\\n\\nongoing—Davison posted a message on Twitter in which he tagged Randall:\\n\\n“@ChairRandall ‘set up question’? You might want to strictly follow FOIA and the\\n\\nCOIA as well.” J.A. 470–71.\\n\\n Later that evening, Randall posted about the town hall meeting on the Chair’s\\n\\nFacebook Page, describing “what was generally discussed at the meeting.” J.A. 268. In\\n\\nresponse, Davison then used one of the Facebook Pages he manages through his personal\\n\\nFacebook profile—“Virginia SGP,” which Davison frequently uses to post political\\n\\ncommentary—to comment on Randall’s post about the town hall meeting. Although\\n\\nneither Davison nor Randall remember the precise content of Davison’s comment,\\n\\nRandall testified that it contained “accusations” regarding School Board members’ and\\n\\ntheir families’ putative conflicts of interest related to municipal financial transactions,\\n\\n\\n 9\\n\\nsuggesting, in Randall’s opinion, that School Board members had been “taking kickback\\n\\nmoney.” See J.A. 268–69, 289–90. Randall stated that she “had no idea if any of th[e]\\n\\n[accusations] w[ere] correct,” but she determined that the post was “probably not\\n\\nsomething [she] want[ed] to leave” on the Chair’s Facebook Page. J.A. 269. Randall\\n\\nthen “deleted the whole post,” including her original post regarding the town hall\\n\\nmeeting, Davison’s comment and replies thereto, and all other public comments. J.A.\\n\\n269. Randall also banned Davison’s Virginia SGP Page from the Chair’s Facebook Page,\\n\\nwhich precluded Davison from using his Virginia SGP Page from commenting on the\\n\\nChair’s Facebook Page. The next morning, about twelve hours later, Randall\\n\\nreconsidered her actions and unbanned Davison’s Virginia SGP Page.\\n\\n B.\\n\\n On November 3, 2016, Davison filed an amended complaint seeking declaratory\\n\\nand injunctive relief under 42 U.S.C. § 1983 against Randall, in both her official and\\n\\nindividual capacities, and the Loudoun Board alleging that the “banning of [Davison]\\n\\nfrom commenting on [the Chair’s Facebook Page] is viewpoint discrimination.” J.A. 31.\\n\\nDavison further alleged that the ban violated his procedural due process rights protected\\n\\nby the Fourteenth Amendment because “Randall blocked Davison’s constitutionally\\n\\nprotected speech on [the Chair’s Facebook Page], a limited public forum, without prior\\n\\nnotice and without providing an opportunity for appealing [her] decision.” J.A. 32.\\n\\nDavison did not challenge Randall’s deletion of his post.\\n\\n On March 6, 2017—four days before the close of discovery and approximately\\n\\ntwo months before trial—Davison moved for leave to amend his complaint a second time\\n\\n\\n 10\\n\\nto add claims under the Virginia Constitution that were materially indistinguishable from\\n\\nhis previously asserted First and Fourteenth Amendment claims premised on the ban, as\\n\\nwell as a separate First Amendment claim against the Loudoun Board. Davison’s\\n\\nproposed new First Amendment claim theorized that the County violated his free speech\\n\\nrights by choosing to use Facebook Pages as public forums, when Facebook allows\\n\\nprivate users to restrict access to their posts, including posts to any Page a municipality\\n\\ndesignates as a limited public forum. Pl.’s Mem. in Supp. of Mot. for Leave to File\\n\\nSecond Am. Compl. 3–9, Davison v. Loudoun County Bd. of Supervisors, 16-cv-932-\\n\\nJCC-IDD, ECF No. 68. The district court referred the motion to a magistrate judge, who\\n\\ngranted leave to amend regarding the claims under the Virginia Constitution but denied\\n\\nleave as to the new First Amendment claim against the Loudoun Board. Davison lodged\\n\\nobjections to the magistrate judge’s partial denial of leave to amend, which objections the\\n\\ndistrict court overruled.\\n\\n Around the same time, Randall and the Loudoun Board each moved for summary\\n\\njudgment. The Loudoun Board asserted that the municipality could not be held liable for\\n\\nRandall’s banning of Davison from the Chair’s Facebook Page because the Chair’s\\n\\nFacebook Page was not an official municipal page and because Randall, not the Loudoun\\n\\nBoard as a body, was solely responsible for creating and administering the Chair’s\\n\\nFacebook Page. The Loudoun Board and Randall further asserted that the Chair’s\\n\\nFacebook Page did not amount to a public forum, and therefore Randall’s ban of\\n\\nDavison’s Virginia SGP Page did not implicate his free speech or procedural due process\\n\\nrights. Finally, Randall asserted that she was entitled to qualified immunity.\\n\\n\\n 11\\n\\n On May 10, 2017, the district court granted summary judgment in favor of the\\n\\nLoudoun Board, dismissing it from the suit. But as to Randall, the district court\\n\\nconcluded that Davison’s evidence established a material dispute of fact as to whether the\\n\\nChair’s Facebook Page amounted to a limited public forum and whether Randall, in her\\n\\nindividual capacity, acted under color of state law in banning Davison from the Chair’s\\n\\nFacebook Page. Davison v. Loudoun Cty. Bd. of Supervisors, No. 1:16-cv-932, 2017 WL\\n\\n1929406, at *6–9 (E.D. Va. May 10, 2017). The district court also rejected Randall’s\\n\\nqualified immunity argument. Id. at *8.\\n\\n Following a one-day bench trial of Davison’s claims against Randall, the district\\n\\ncourt issued a memorandum opinion and order awarding judgment in Davison’s favor on\\n\\nhis claims under the First Amendment and the analogous free speech provision in the\\n\\nVirginia Constitution. See Davison v. Loudoun Cty. Bd. of Supervisors, 267 F. Supp. 3d\\n\\n702, 714–18 (E.D. Va. 2017). The district court further entered judgment in Randall’s\\n\\nfavor on Davison’s federal and state procedural due process claims. Id. at 719–22. As to\\n\\nremedy, the district court denied Davison’s request for injunctive relief but granted\\n\\nDavison’s request for a declaratory judgment to resolve the “uncertainty regarding the\\n\\nlegal status of [the Chair’s Facebook Page].” Id. at 723.\\n\\n Randall and Davison, respectively, filed this appeal and cross appeal.\\n\\n II.\\n\\n On appeal, Randall argues that (A) Davison failed to establish standing to obtain\\n\\nprospective declaratory relief based on Randall’s alleged First Amendment violation; (B)\\n\\nthe district court erred in concluding that Randall acted under “color of state law” when\\n\\n\\n 12\\n\\nshe banned Davison’s Virginia SGP Page from the Chair’s Facebook Page; and (C) the\\n\\ndistrict court erred in concluding that Randall’s banning of Davison’s Virginia SGP Page\\n\\nviolated the First Amendment.\\n\\n A.\\n\\n Notwithstanding that she did not challenge Davison’s standing below—and\\n\\ntherefore that the district court never squarely addressed his standing—Randall now\\n\\nargues that Davison failed to establish Article III standing to support the district court’s\\n\\naward of prospective declaratory relief. Even though Defendants did not challenge\\n\\nDavison’s standing below, “standing to sue is a jurisdictional issue of constitutional\\n\\ndimensions, and it may be raised and addressed for the first time on appeal.” Hodges v.\\n\\nAbraham, 300 F.3d 432, 443 (4th Cir. 2002). This Court reviews de novo “whether a\\n\\ndistrict court possessed jurisdiction in a declaratory judgment proceeding.” Volvo Const.\\n\\nEquip. N. Am., Inc. v. CLM Equip. Co., Inc., 386 F.3d 581, 591 (4th Cir. 2004).\\n\\n To establish Article III standing, a plaintiff must prove that: “1) he or she suffered\\n\\nan ‘injury in fact’ that is concrete and particularized, and is actual or imminent; 2) the\\n\\ninjury is fairly traceable to the challenged action of the defendant; and 3) the injury likely\\n\\nwill be redressed by a favorable decision.” Friends of the Earth, Inc. v. Gaston Copper\\n\\nRecycling Corp., 629 F.3d 387, 396 (4th Cir. 2011). Randall does not dispute that any\\n\\ninjury Davison suffered is fairly traceable to her decision to ban him from the Chair’s\\n\\nFacebook Page. Nor does Randall dispute that any such injury would be remedied by a\\n\\nfavorable decision. Rather, Randall claims that Davison failed to adduce evidence\\n\\n\\n\\n\\n 13\\n\\nestablishing that he suffered an “injury in fact” sufficient to support prospective\\n\\ndeclaratory relief.\\n\\n “Injury in fact is ‘an invasion of a legally protected interest’ that is ‘concrete and\\n\\nparticularized’ and ‘actual or imminent, not conjectural or hypothetical.’” Kenny v.\\n\\nWilson, 885 F.3d 280, 287 (4th Cir. 2018) (quoting Spokeo, Inc. v. Robins, 136 S. Ct.\\n\\n1540, 1548 (2016)). Because “‘[p]ast exposure to illegal conduct does not in itself show\\n\\na present case or controversy regarding injunctive relief . . . if unaccompanied by any\\n\\ncontinuing, present adverse effects,’” a plaintiff seeking “declaratory or injunctive relief .\\n\\n. . must establish an ongoing or future injury in fact.” Id. at 287–88 (quoting O’Shea v.\\n\\nLittleton, 414 U.S. 488, 495–96 (1974)). Significantly, this Court—along with several\\n\\nother circuits—has held that “standing requirements are somewhat relaxed in First\\n\\nAmendment cases,” particularly regarding the injury-in-fact requirement. Cooksey v.\\n\\nFutrell, 721 F.3d 226, 235 (4th Cir. 2013) (collecting cases).\\n\\n In Kenny v. Wilson, 885 F.3d 280 (4th Cir. 2018), this Court addressed what\\n\\nevidence a plaintiff seeking relief under the First Amendment, like Davison, must put\\n\\nforward to establish a future injury-in-fact adequate to confer Article III standing to\\n\\nobtain prospective declaratory relief. In Kenny, several high school students lodged First\\n\\nAmendment challenges to two South Carolina disorderly conduct statutes. Id. at 284.\\n\\nThis Court explained that “there is a sufficiently imminent injury in fact if plaintiffs\\n\\nallege [1] ‘an intention to engage in a course of conduct arguably affected with a\\n\\nconstitutional interest, but proscribed by a statute, and [2] there exists a credible threat of\\n\\nprosecution thereunder.’” Id. at 288 (quoting Babbitt v. Farm Workers Nat’l Union, 442\\n\\n\\n 14\\n\\nU.S. 289, 298 (1979)). The Kenny plaintiffs satisfied the first prong because they “attend\\n\\nschool” and “attending school inevitably involves expressive conduct” that implicates the\\n\\ndisorderly conduct statutes. Id. As to the second element—whether the students alleged\\n\\na “credible threat of future enforcement”—we held that such a threat exists so long as it\\n\\n“is not imaginary or wholly speculative, chimerical, or wholly conjectural.” Id. (internal\\n\\nquotation marks, citations, and alterations omitted). “[P]ast enforcement against the same\\n\\nconduct is good evidence that the threat of enforcement is not chimerical.” Id. (quoting\\n\\nSusan B. Anthony List v. Driehaus, 134 S. Ct. 2334, 2345 (2014)). “Threat of\\n\\nprosecution is especially credible when defendants have not ‘disavowed enforcement’ if\\n\\nplaintiffs engage in similar conduct in the future.” Id. (quoting Driehaus, 134 S. Ct. at\\n\\n2345). Applying this standard, we held that the plaintiffs alleged a credible threat of\\n\\nenforcement “because these three plaintiffs regularly attend schools where they allege\\n\\nthere may be future encounters with school resource officers or other law enforcement;\\n\\nthey have been prosecuted under the laws in the past; and the defendants have not\\n\\ndisavowed enforcement if plaintiffs engage in similar conduct in the future.” Id. at 289.\\n\\n Under Kenny, Davison’s evidence established his standing to obtain prospective\\n\\ndeclaratory relief. Relevant to the first prong—whether Davison intends to engage in a\\n\\ncourse of conduct “arguably” impacted by the challenged conduct, Babbitt, 442 U.S. at\\n\\n298—the district court found, in awarding Davison declaratory relief, that he “continues\\n\\nto avail himself” of the Chair’s Facebook Page and that Davison is “active in local\\n\\npolitics, and has a particular interest in what he believes to be corruption on the part of\\n\\nLoudoun County’s school board.” Davison, 267 F. Supp. 3d at 707, 723. Accordingly,\\n\\n\\n 15\\n\\nthe evidence establishes that Davison continues to engage in a course of conduct—\\n\\nnamely, posting about alleged municipal corruption on the Chair’s Facebook Page—\\n\\nlikely to be impacted by Randall’s allegedly unconstitutional approach to managing the\\n\\npage.\\n\\n Turning to the second prong—whether there is a credible threat of enforcement—\\n\\nRandall previously blocked Davison from the Chair’s Facebook Page based on the\\n\\ncontent of his posts, providing “good evidence that the threat of enforcement is not\\n\\nchimerical.” Driehaus, 134 S. Ct. at 2345 (internal quotation marks omitted).\\n\\nAdditionally, Randall testified that she continues to believe she can ban Davison and\\n\\nothers from the Chair’s Facebook Page based on their views without triggering the First\\n\\nAmendment at all. See J.A. 277 (Randall stating she would “be happy to” ban other\\n\\ncommenters on her “Chair’s Facebook” page); J.A. 250 (Randall testifying that\\n\\ncomments “attacking another person” would not be allowed on her “Chair’s Facebook”\\n\\npage). To that end, in awarding Davison declaratory relief, the district court found that\\n\\nRandall “maintains she is permitted to administer this Facebook page as a purely personal\\n\\npage.” Davison, 267 F. Supp. 3d at 723. Accordingly, Davison established that he has\\n\\nbeen subject to past enforcement and that Randall has not “disavowed” future\\n\\nenforcement, which, under Kenny, is sufficient to establish a credible threat of\\n\\nenforcement. Cf. City of Lakewood v. Plain Dealer Pub. Co., 486 U.S. 750, 757 (1988)\\n\\n(“[T]he mere existence of the licensor’s unfettered discretion, coupled with the power of\\n\\nprior restraint, intimidates parties into censoring their own speech, even if the discretion\\n\\nand power are never actually abused.”).\\n\\n\\n 16\\n\\n In sum, Davison’s evidence demonstrated—and the district court found—that\\n\\nDavison intends to continue to use the Chair’s Facebook Page and that Davison faces a\\n\\ncredible threat of future enforcement. See Davison, 267 F. Supp. 3d at 723.\\n\\nAccordingly, Davison adduced facts establishing an injury in fact sufficient to justify the\\n\\nprospective declaratory relief awarded by the district court.\\n\\n B.\\n\\n Next, Randall asserts that the district court erred in concluding, with regard to\\n\\nDavison’s individual capacity First Amendment claim, that Randall acted “under color of\\n\\nstate law,” as that phrase is used in Section 1983, in administering the Chair’s Facebook\\n\\nPage and banning Davison from that page. “This Court reviews judgments stemming\\n\\nfrom a bench trial under a mixed standard: factual findings are reviewed for clear error,\\n\\nwhereas conclusions of law are reviewed de novo.” Helton v. AT&T Inc., 709 F.3d 343,\\n\\n350 (4th Cir. 2013). Whether, under the undisputed facts, Randall acted under color of\\n\\nstate law is a legal question this Court reviews de novo. Rossignol v. Voorhaar, 316 F.3d\\n\\n516, 523 (4th Cir. 2003).\\n\\n To state a claim under Section 1983, a plaintiff must show that the alleged\\n\\nconstitutional deprivation at issue occurred because of action taken by the defendant\\n\\n“under color of . . . state law.” Philips v. Pitt Cty. Mem’l Hosp., 572 F.3d 176, 180 (4th\\n\\nCir. 2009). “The traditional definition of acting under color of state law requires that the\\n\\ndefendant in a § 1983 action have exercised power ‘possessed by virtue of state law and\\n\\nmade possible only because the wrongdoer is clothed with the authority of state law.’”\\n\\nWest v. Atkins, 487 U.S. 42, 49 (1988) (quoting United States v. Classic, 313 U.S. 299,\\n\\n\\n 17\\n\\n326 (1941)). Section 1983’s “color-of-law prerequisite is synonymous with the more\\n\\nfamiliar state-action requirement” applicable to Fourteenth Amendment claims, “and the\\n\\nanalysis for each is identical.” Pitt Cty. Mem’l Hosp., 572 F.3d at 180. Both inquiries\\n\\ndemand that “the conduct allegedly causing the deprivation of a federal right be fairly\\n\\nattributable to the State.” Holly v. Scott, 434 F.3d 287, 292 (4th Cir. 2006) (quoting\\n\\nLugar v. Edmondson Oil Co., Inc., 457 U.S. 922, 937 (1982)).\\n\\n “[T]here is no specific formula for determining whether state action is present.”\\n\\nId. at 292 (internal quotation marks omitted). Rather, “[w]hat is fairly attributable [to the\\n\\nstate]”—i.e., what constitutes action under color of state law—“is a matter of normative\\n\\njudgment, and the criteria lack rigid simplicity.” Id. (internal quotation marks omitted).\\n\\nCourts must examine the “totality of the circumstances,” id. (internal quotation marks\\n\\nomitted), to determine if the action at issue “bore a ‘sufficiently close nexus’ with the\\n\\nState to be ‘fairly treated as that of the State itself,’” Rossignol, 316 F.3d at 525 (quoting\\n\\nJackson v. Metro. Edison Co., 419 U.S. 345, 351 (1974)).\\n\\n Although no one factor is determinative, this Court has held that a defendant’s\\n\\npurportedly private actions bear a “sufficiently close nexus” with the State to satisfy\\n\\nSection 1983’s color-of-law requirement when the defendant’s challenged “actions are\\n\\nlinked to events which arose out of his official status.” Id. at 524. When a defendant’s\\n\\n“status” as a public official “enabled [her] to execute [a challenged action] in a manner\\n\\nthat private citizens never could have,” then the action also is more likely to be treated as\\n\\nattributable to the state. Id. at 526; see also Martinez v. Colon, 54 F.3d 980, 986 (1st Cir.\\n\\n1995) (“[S]ection 1983 is . . . implicated . . . [when] the conduct is such that the actor\\n\\n\\n 18\\n\\ncould not have behaved in that way but for the authority of his office.”); Goldstein v.\\n\\nChestnut Ridge Volunteer Fire Co., 218 F.3d 337, 343 (4th Cir. 2000) (holding that\\n\\nchallenged conduct is more likely to amount to state action when “the injury caused is\\n\\naggravated in a unique way by the incidents of governmental authority” (internal\\n\\nquotation marks omitted)). Likewise, an official’s conduct is more likely to amount to\\n\\nstate action when it “occurs in the course of performing an actual or apparent duty of his\\n\\noffice.” Martinez, 54 F.3d at 986. And the challenged action of a defendant\\n\\ngovernmental official is likely to be treated as taken under color of law when the official\\n\\n“use[d] the power and prestige of his state office to damage the plaintiff.” Harris v.\\n\\nHarvey, 605 F.2d 330, 337 (7th Cir. 1979). In the context of an alleged First Amendment\\n\\nviolation, in particular, this Court has found that a challenged action by a governmental\\n\\nofficial is fairly attributable to the state when “the sole intention” of the official in taking\\n\\nthe action was “to suppress speech critical of his conduct of official duties or fitness for\\n\\npublic office.” Rossignol, 316 F.3d at 524.\\n\\n Here, after thoroughly analyzing the totality of the circumstances surrounding\\n\\nRandall’s creation and administration of the Chair’s Facebook Page and banning of\\n\\nDavison from that page, the district court concluded that Randall acted under color of\\n\\nstate law. Davison, 267 F. Supp. 3d at 723. We agree.\\n\\n Randall created and administered the Chair’s Facebook Page to further her duties\\n\\nas a municipal official. She used the Chair’s Facebook Page “as a tool of governance,”\\n\\nid. at 713: through the Chair’s Facebook Page, Randall provides information to the public\\n\\n\\n\\n\\n 19\\n\\nabout her and the Loudoun Board’s official activities and solicits input from the public on\\n\\npolicy issues she and the Loudoun Board confront. See supra Part I.A.\\n\\n For instance, Randall used the Chair’s Facebook Page to inform the public about\\n\\nserious public safety events and to keep her constituents abreast of the County’s response\\n\\nto a snowstorm and to coordinate snow removal activities. And, as the district court\\n\\ncorrectly emphasized, Randall\\n\\n swathe[d] the [Chair’s Facebook Page] in the trappings of her office.\\n Among other things, (1) the title of the page includes [Randall]’s title; (2)\\n the page is categorized as that of a government official; (3) the page lists as\\n contact information [Randall]’s official County email address and the\\n telephone number of [Randall]’s County office; (4) the page includes the\\n web address of [Randall]’s official County website; (5) many—perhaps\\n most—of the posts are expressly addressed to “Loudoun,” [Randall]’s\\n constituents; (6) [Randall] has submitted posts on behalf of the [Loudoun\\n Board] as a whole; (7) [Randall] has asked her constituents to use the\\n [Chair‘s Facebook Page] as a channel for “back and forth constituent\\n conversations”; and (8) the content posted has a strong tendency toward\\n matters related to [Randall]’s office.\\n\\nDavison, 267 F. Supp. 3d at 714. A private citizen could not have created and used the\\n\\nChair’s Facebook Page in such a manner. Rossignol, 316 F.3d at 526. Put simply,\\n\\nRandall clothed the Chair’s Facebook Page in “the power and prestige of h[er] state\\n\\noffice,” Harris, 605 F.2d at 337, and created and administered the page to “perform[]\\n\\nactual or apparent dut[ies] of h[er] office,” Martinez, 54 F.3d at 986.\\n\\n Additionally, the specific actions giving rise to Davison’s claim—Randall’s\\n\\nbanning of Davison’s Virginia SGP Page—“are linked to events which arose out of h[er]\\n\\nofficial status.” Rossignol, 316 F.3d at 524. Randall’s post to the Chair’s Facebook Page\\n\\nthat prompted Davison’s comment informed the public about what happened at the\\n\\n\\n\\n 20\\n\\nLoudoun Board and Loudoun County School Board’s joint meeting. And Davison’s\\n\\ncomment also dealt with an issue related to that meeting and of significant public\\n\\ninterest—School Board members’ alleged conflicts of interest in approving financial\\n\\ntransactions. That Randall’s ban of Davison amounted to an effort “to suppress speech\\n\\ncritical of [such members’] conduct of [their] official duties or fitness for public office”\\n\\nfurther reinforces that the ban was taken under color of state law. Id. at 525. Considering\\n\\nthe totality of these circumstances, the district court correctly held that Randall acted\\n\\nunder color of state law in banning Davison from the Chair’s Facebook Page.\\n\\n C.\\n\\n Third, Randall argues that the district court erred in ruling in Davison’s favor on\\n\\nhis individual capacity First Amendment claim against Randall. Randall principally\\n\\nchallenges the district court’s conclusion that the Chair’s Facebook Page constitutes a\\n\\n“public forum” under traditional First Amendment law. We review this legal question de\\n\\nnovo. See Helton, 709 F.3d at 350.\\n\\n Under long-established First Amendment law, governmental entities are “strictly\\n\\nlimited” in their ability to regulate private speech in public fora. Pleasant Grove City,\\n\\nUtah v. Summum, 555 U.S. 460, 469 (2009). The Supreme Court has recognized two\\n\\ncategories of public fora: “traditional public forums” and “limited (or designated) public\\n\\nforums.” Am. Civil Liberties Union v. Mote, 423 F.3d 438, 443 (4th Cir. 2005).\\n\\n“Traditional” public forums—“such as streets, sidewalks, and parks”—“have the\\n\\ncharacteristics of a public thoroughfare, a purpose that is compatible with expressive\\n\\nconduct, as well as a tradition and history of being used for expressive public conduct.”\\n\\n\\n 21\\n\\nId. “Limited” or “designated” forums are forums that are “not traditionally public, but\\n\\n[that] the government has purposefully opened to the public, or some segment of the\\n\\npublic, for expressive activity.” Id. Accordingly, the hallmark of both types of public\\n\\nfora—what renders the fora “public”—is that the government has made the space\\n\\navailable—either by designation or long-standing custom—for “expressive public\\n\\nconduct” or “expressive activity,” and the space is compatible with such activity. Id.\\n\\n“Conversely, a non-public forum is one that has not traditionally been open to the public,\\n\\nwhere opening it to expressive conduct would ‘somehow interfere with the objective use\\n\\nand purpose to which the property has been dedicated.’” Id. (quoting Warren v. Fairfax\\n\\nCty., 196 F.3d 186, 190–91 (4th Cir. 1999)).\\n\\n Although neither the Supreme Court nor any Circuit has squarely addressed\\n\\nwhether, and in what circumstances, a governmental social media page—like the Chair’s\\n\\nFacebook Page—constitutes a public forum, 3 aspects of the Chair’s Facebook Page bear\\n\\nthe hallmarks of a public forum. Randall “intentionally open[ed the public comment\\n\\nsection of the Chair’s Facebook Page] for public discourse,” Cornelius v. NAACP Legal\\n\\nDefense & Educ. Fund, Inc., 473 U.S. 788, 802 (1985), inviting “ANY Loudoun citizen”\\n\\n 3\\n In addition to the court below, two other district courts have considered whether\\na government official’s social media page constituted a public forum. Those courts\\nreached conflicting results. Compare Morgan v. Bevin, 298 F. Supp. 3d 1003, 1010 (E.D.\\nKy. 2018) (holding that First Amendment forum analysis did not apply to restrictions on\\nspeech in the official Facebook and Twitter pages of the Governor of Kentucky), with\\nKnight First Amend. Inst. at Colum. Univ. v. Trump, 302 F. Supp. 3d 541, 573 (S.D.N.Y.\\n2018) (holding that the interactive component of the President’s Twitter account, as\\nopposed to the President’s tweets themselves, constituted a designated public forum),\\nappeal docketed, No. 18-1691 (2d Cir. Oct. 24, 2018).\\n\\n\\n\\n 22\\n\\nto make posts to the comments section of the Chair’s Facebook Page—the interactive\\n\\ncomponent of the page—“on ANY issues, request, criticism, complement or just your\\n\\nthoughts,” J.A. 455. Randall placed no restrictions on the public’s access to the page or\\n\\nuse of the interactive component of the Chair’s Facebook Page. And, in accordance with\\n\\nRandall’s invitation, the public made numerous posts on matters of public concern.\\n\\n The Chair’s Facebook Page also is “compatib[le] with expressive activity.”\\n\\nCornelius, 473 U.S. at 802. “Congress [has] recognized the internet and interactive\\n\\ncomputer services as offering ‘a forum for a true diversity of political discourse, unique\\n\\nopportunities for cultural development, and myriad avenues for intellectual activity.’”\\n\\nZeran v. Am. Online, Inc., 129 F.3d 327, 330 (4th Cir. 1997) (quoting 47 U.S.C. §\\n\\n230(a)(3)); cf. Bland, 730 F.3d at 386 (finding post to campaign Facebook page\\n\\n“constituted pure speech”). And the Supreme Court recently analogized social media\\n\\nsites, like the Chair’s Facebook Page, to “traditional” public forums, characterizing the\\n\\ninternet as “the most important place[] (in a spatial sense) for the exchange of views.”\\n\\nPackingham v. North Carolina, 137 S. Ct. 1730, 1735 (2017). An “exchange of views”\\n\\nis precisely what Randall sought—and what in fact transpired—when she expressly\\n\\ninvited “ANY Loudoun citizen” to visit the page and comment “on ANY issues,” and\\n\\nreceived numerous such posts and comments. J.A. 455.\\n\\n Randall nevertheless argues that traditional public forum analysis should not apply\\n\\nto the Chair’s Facebook Page for two reasons: (1) the Chair’s Facebook Page is “a private\\n\\nwebsite” and therefore does not constitute “public property” susceptible to forum\\n\\nanalysis, and (2) the Chair’s Facebook Page, in its entirety, constitutes “government\\n\\n\\n 23\\n\\nspeech” properly analyzed under the framework set forth in Pleasant Grove. Randall’s\\n\\nBr. at 19–21, 29–31. We disagree.\\n\\n Even assuming the intangible space at issue is “private property,” as Randall\\n\\nclaims—which is not at all clear from the record before us 4—the Supreme Court never\\n\\nhas circumscribed forum analysis solely to government-owned property. For example, in\\n\\nCornelius, the Court recognized that forum analysis applies “to private property\\n\\ndedicated to public use.” Cornelius, 473 U.S. at 801 (emphasis added); see also\\n\\nChristian Legal Soc’y Chapter of the Univ. of Cal. v. Martinez, 561 U.S. 661, 679 (2010)\\n\\n(“[T]his Court has employed forum analysis to determine when a governmental entity, in\\n\\nregulating property in its charge, may place limitations on speech.” (emphasis added)).\\n\\n 4\\n The Facebook “platform” and the “software” that underlies that platform is,\\naccording to Facebook’s Terms of Service, property of Facebook, Inc. Terms of Service,\\nFacebook, https://www.facebook.com/terms.php (last visited Jan. 4, 2019). Facebook’s\\nTerms of Service further provide that users “own the content [they] create and share on\\nFacebook and the other Facebook Products,” including Pages. Id. There would seem to\\nbe a good argument, therefore, that content created, and posted to Facebook, by\\ngovernment officials performing the functions and duties of their offices constitutes\\ngovernment property. Cf. Solomons v. United States, 137 U.S. 342, 346–48 (1890)\\n(holding that intellectual property created by government employee in the course of his\\nofficial duties constituted government property because “[i]f one is employed to devise or\\nperfect an instrument, or a means for accomplishing a prescribed result, he cannot, after\\nsuccessfully accomplishing the work for which he was employed, plead title thereto as\\nagainst his employer”). Likewise, under Facebook’s Terms of Service, the posts and\\ncomments by individual Facebook users—like Davison—to a Facebook Page—like the\\nChair’s Facebook Page—constitute property of those users. Accordingly, a single\\nFacebook Page—including the Chair’s Facebook Page—encompasses a web of property\\nrights, some of which may lie with the government. We need not—and thus do not—\\ndecide with whom these property rights lie in this particular case, however, because we\\nhold that even assuming the Chair’s Facebook Page constitutes private property, Randall,\\nacting under color of state law, exercised control over the aspects of that page giving rise\\nto Davison’s claim.\\n\\n\\n\\n 24\\n\\nAnd the Supreme Court and lower courts have held that private property, whether\\n\\ntangible or intangible, constituted a public forum when, for example, the government\\n\\nretained substantial control over the property under regulation or by contract. See, e.g.,\\n\\nSe. Promotions, Ltd. v. Conrad, 420 U.S. 546, 547, 555 (1975) (holding that “a privately\\n\\nowned Chattanooga theater under long-term lease to the city” was a “public forum[]\\n\\ndesigned for and dedicated to expressive activities”); Halleck v. Manhattan Community\\n\\nAccess Corp., 882 F.3d 300, 306–07 (2d Cir. 2018) (holding that public access television\\n\\nchannels operated by a private non-profit corporation constituted public forums), cert.\\n\\ngranted 139 S. Ct. 360 (2018) (mem.); First Unitarian Church of Salt Lake City v. Salt\\n\\nLake City Corp., 308 F.3d 1114, 1122 (10th Cir. 2002) (“[F]orum analysis does not\\n\\nrequire that the government have a possessory interest in or title to the underlying land.\\n\\nEither government ownership or regulation is sufficient for a First Amendment forum of\\n\\nsome kind to exist.”); Freedom from Religion Foundation, Inc. v. City of Marshfield,\\n\\nWis., 203 F.3d 487, 494 (7th Cir. 2000) (holding that private property abutted by public\\n\\npark constituted public forum).\\n\\n Significantly, even assuming the relevant aspects of the Chair’s Facebook Page\\n\\nconstitute private property—which, again, is not entirely clear from the record before\\n\\nus—Randall, acting under color of state law, retained and exercised significant control\\n\\nover the page. She created the Chair’s Facebook Page. She designated the page as\\n\\nbelonging to a “governmental official.” She clothed the page in the trappings of her\\n\\npublic office. She chose to list her official contact information on the page. And she\\n\\n\\n\\n\\n 25\\n\\ncurated the links in the left column of the page and the lists of Facebook Pages or profiles\\n\\n“liked” by the Chair’s Facebook Page in the right column.\\n\\n Of particular importance, Randall had complete control over the aspect of the\\n\\nChair’s Facebook Page giving rise to Davison’s challenge because, as administrator of\\n\\nthe page, Randall had authority to ban Facebook profiles or Pages from using the Chair’s\\n\\nFacebook Page—and, therefore, the interactive component of the page—authority she\\n\\nexercised in banning Davison’s Virginia SGP Page. Cf. Knight, 302 F. Supp. 3d at 566–\\n\\n67 (holding that the interactive component of the President’s Twitter account constituted\\n\\npublic forum because the President and his advisors “exercise control over various\\n\\naspects of the . . . account,” including the power to block other users from accessing the\\n\\naccount).\\n\\n The Second Circuit’s decision in Halleck dealing with privately operated public\\n\\naccess television channels is instructive. Federal law allows cable franchising authorities\\n\\nto require cable operators to designate channel capacity for public use. Halleck, 882 F.3d\\n\\nat 302. Likewise, New York regulations oblige cable operators to designate at least one\\n\\nchannel for full-time public use. Id. Pursuant to that authority, the City of New York\\n\\nentered into a cable franchise agreement with a cable company requiring the company to\\n\\nmake available four public access channels, which channels were operated by a private,\\n\\nnon-profit corporation, MNN. Id. Several producers of public access programming sued\\n\\nMNN, alleging that MNN violated the producers’ First Amendment rights by indefinitely\\n\\nsuspending them from using the public access channels “because of disapproval of the\\n\\ncontent of a TV program” they had submitted for airing. Id.\\n\\n\\n 26\\n\\n The Second Circuit concluded that the public access channels constituted a public\\n\\nforum, notwithstanding that they were operated by a private company. Id. at 306–08.\\n\\nThe court reached that conclusion for two reasons. First, it pointed to the similarities\\n\\nbetween public access channels and traditional public forums, like parks, describing “[a]\\n\\npublic access channel [a]s the electronic version of the public square.” Id. at 306.\\n\\nSecond, the court emphasized the extensive government involvement with, and control\\n\\nover, public access channels by virtue of the federal and state regulatory schemes. See id.\\n\\n(“[W]here, as here, federal law authorizes setting aside channels to be ‘the electronic\\n\\nmarketplace of ideas,’ state regulation requires cable operators to provide at least one\\n\\npublic access channel, a municipal contract requires a cable operator to provide four such\\n\\nchannels, and a municipal official has designated a private corporation to run those\\n\\nchannels, those channels are public forums.” (emphasis added)).\\n\\n Although not subject to the extensive federal and state regulatory regime\\n\\napplicable in Halleck, 5 the Chair’s Facebook Page is in many ways analogous to the\\n\\nprivately-operated public access channels considered by the Second Circuit. Just as the\\n\\nfederal government sought to establish an “electronic marketplace of ideas” by\\n\\nmandating provision of public access channels, Randall expressly sought to—and did, in\\n\\n\\n 5\\n The federal Communications Decency Act allows private online intermediaries,\\nlike Facebook, the ability to moderate content by providing such intermediaries with\\nbroad immunity from user-generated content posted on their sites. 47 U.S.C. § 230. This\\nCourt has recognized that an “important purpose of § 230 was to encourage service\\nproviders to self-regulate the dissemination of offensive material over their services.”\\nZeran, 129 F.3d at 331.\\n\\n\\n\\n 27\\n\\nfact—create an “electronic marketplace of ideas” by inviting “ANY” constituent to post\\n\\nto the Chair Page on “ANY issues.” J.A. 455. Likewise, just as the City of New York\\n\\nchose to have a private corporation operate the public access channels, Randall chose to\\n\\ncreate her electronic marketplace of ideas, the Chair’s Facebook Page, on a private\\n\\nplatform, Facebook. Indeed, the present case provides a stronger basis for treating the\\n\\ninteractive component of the Chair’s Facebook Page as a public forum because whereas\\n\\nthe private corporation in Halleck, MNN, exercised control over the aspect of the public\\n\\naccess channel giving rise to the First Amendment claim—banning the public access\\n\\nprogram producer—a public official, Randall exercised unconstrained control over the\\n\\naspect of the Chair’s Facebook Page giving rise to Davison’s claim—banning of other\\n\\nFacebook profiles and Pages. 6\\n\\n\\n 6\\n On October 12, 2018, the Supreme Court granted MNN’s petition for writ of\\ncertiorari in Halleck. 139 S. Ct. 360. MNN’s petition presented two questions: (1)\\n“[w]hether the Second Circuit erred in rejecting th[e Supreme] Court’s state actor tests\\nand instead creating a per se rule that private operators of public access channels are state\\nactors subject to constitutional liability” and (2) “[w]hether the Second Circuit erred in\\nholding—contrary to the Sixth and D.C. Circuits—that private entities operating public\\naccess televisions stations are state actors for constitutional purposes where the state has\\nno control over the private entity’s board or operations.” Petition for Writ of Certiorari i,\\nManhattan Community Access Corp. v. Halleck, --- S. Ct. --- (No. 17-1702). MNN’s\\nargument before the Supreme Court, therefore, focuses on the Second Circuit’s\\ndetermination that MNN constituted a state actor, not the court’s determination that the\\npublic access channels constituted a public forum.\\n\\n Although not identified as an issue on appeal, MNN’s petition also took issue with\\nthe Second Circuit’s determination that the public access channels operated by MNN\\nconstituted a public forum. But that contention was entirely derivative of its state action\\nargument. In particular, MNN objected to the Second Circuit’s public forum conclusion\\nonly because the public access channels were privately operated and because, in its\\nopinion, the Second Circuit’s purportedly “categorical” holding that public access\\n(Continued)\\n\\n 28\\n\\n Not only does case law contradict Randall’s argument that public forum analysis\\n\\nnever applies to private property, her argument also fails because it makes no legal sense\\n\\nto establish a bright-line rule that forum analysis applies only to government-owned\\n\\nproperty. Why, for example, should the First Amendment allow a municipality to engage\\n\\nin viewpoint discrimination in curating a public library branch in leased space but not\\n\\nallow the municipality to engage in such discrimination in a library branch on\\n\\nmunicipally owned property? Cf. Bd. of Educ., Island Trees Union Free Sch. Dist. No.\\n\\n26 v. Pico, 457 U.S. 853, 870–71 (1982) (plurality op.) (“If a Democratic school board,\\n\\nmotivated by partisan affiliation, ordered removal of all books written by or in favor of\\n\\nRepublicans, few would doubt that the order violated the constitutional rights of the\\n\\nstudents denied access to those books.”). Or why should a municipality be allowed to\\n\\nengage in viewpoint discrimination when holding a virtual public meeting hosted on a\\n\\nprivate website when such discrimination would be unconstitutional if the meeting was\\n\\nheld in a governmental building? Cf. Lyrissa Lidsky, Public Forum 2.0, 91 B.U. L. Rev.\\n\\n1975, 1996 (2011) (“Just as the government can rent a building to use as a forum for\\n\\npublic debate and discussion, so, too, can it ‘rent’ a social media page for the promotion\\n\\n\\n\\nchannels constitute public forums ignore[d] “the far more critical issue of whether (and to\\nwhat extent) there is government control over a public access channel.” Id. at 19–20.\\n\\n Here, a government official acting under color of state law, Randall, exercised\\nunconstrained control over the aspect of the Chair’s Facebook Page giving rise to\\nDavison’s claim.\\n\\n\\n\\n\\n 29\\n\\nof public discussion.”). We do not believe the First Amendment draws such arbitrary\\n\\nlines.\\n\\n Randall’s second argument—that the Chair’s Facebook Page amounts to\\n\\n“government speech”—fails to recognize the meaningful difference between Randall’s\\n\\nposts to the Chair’s Facebook Page and the public comments and posts she invited in the\\n\\npage’s interactive space. To be sure, Randall’s comments and curated references on the\\n\\nChair’s Facebook Page to other Pages, personal profiles, and websites amount to\\n\\ngovernmental speech. See Sutliffe v. Epping School Dist., 584 F.3d 314, 329–30 (1st Cir.\\n\\n2009) (holding that municipality’s refusal to place hyperlink on municipal website to\\n\\nwebsite of group opposed to municipal budget constituted government speech); Page v.\\n\\nLexington Cty. School Dist. One, 531 F.3d 275, 283–85 (4th Cir. 2008) (holding that\\n\\nSchool District’s refusal to place hyperlink on its website to website of group that\\n\\nopposed School District’s position on pending legislation constituted government speech\\n\\nbecause, in part, “the links to other websites were selected by the School District alone as\\n\\nones that supported its own message”); Knight, 302 F. Supp. 3d at 571 (“[T]he\\n\\nPresident’s tweets are [not] susceptible to forum analysis . . . because the content is\\n\\ngovernment speech.”).\\n\\n But the interactive component of the Chair’s Facebook Page—the portion of the\\n\\nmiddle column in which the public can post comments, reply to posts, and “like”\\n\\ncomments and posts—is materially different. See Knight, 302 F. Supp. 3d at 572\\n\\n(distinguishing a government official’s tweets and “the interactive space for replies and\\n\\nretweets”). Randall placed no formal limitations on the ability of Facebook personal\\n\\n\\n 30\\n\\nprofiles and Pages to access the Chair’s Facebook Page and make comments and posts to\\n\\nthe interactive component of the page. On the contrary, she expressly invited posts to the\\n\\npage “from ANY Loudon citizen on ANY issues, request, criticism, complement or just\\n\\nyour thoughts.” J.A. 455. And comments and posts by users cannot be mistaken for\\n\\nRandall’s own speech because they identify the posting or replying personal profile or\\n\\nPage, and thereby distinguish that user from Randall.\\n\\n Contrary to Randall’s argument that the Chair’s Facebook Page, in its entirety,\\n\\namounts to government speech, the present case also is meaningfully distinguishable\\n\\nfrom the government speech framework identified in Pleasant Grove. There, a\\n\\nmunicipality denied a private religious group’s request to allow it to erect a “monument\\n\\nin a city park in which other donated monuments were previously erected,” including a\\n\\nmonument depicting a prominent symbol of a different religion. 555 U.S. at 464. The\\n\\nplaintiff religious group sought relief under the First Amendment, arguing that the city\\n\\npark constituted a traditional public forum, and therefore that the city could not reject the\\n\\nreligious group’s proposed monument when it had previously allowed construction of a\\n\\nmonument associated with another religion. Id. at 466.\\n\\n The Supreme Court held that the city did not violate the First Amendment because\\n\\nthe government speech framework, rather than forum analysis, applied to the conduct at\\n\\nissue. In reaching that conclusion, the Court emphasized that the city never “opened up\\n\\nthe Park for the placement of whatever permanent monuments might be offered by\\n\\nprivate donors.” Id. at 472–73. “Rather, the City has ‘effectively controlled’ the\\n\\nmessages sent by the monuments in the Park by exercising ‘final approval authority’ over\\n\\n\\n 31\\n\\ntheir selection.” Id. at 473. The Court further emphasized that “[t]he forum doctrine has\\n\\nbeen applied in situations in which government-owned property or a government\\n\\nprogram was capable of accommodating a large number of public speakers without\\n\\ndefeating the essential function of the land or the program.” Id. at 478. A city park,\\n\\nhowever, “can accommodate only a limited number of permanent monuments,” and\\n\\ntherefore a municipality cannot—and need not—provide park space for all who wish to\\n\\nerect a monument. Id.\\n\\n Here, Randall “effectively controlled” certain aspects of the Chair’s Facebook\\n\\nPage: she curated the Chair’s Facebook Page’s left and right columns and made posts to\\n\\nthe middle column. Id. at 472. But Randall also expressly opened the Chair’s Facebook\\n\\nPage’s middle column—its interactive space—for “ANY” user to post on “ANY issues,”\\n\\nJ.A. 455, and therefore did not retain “final approval authority” over that aspect of the\\n\\nChair’s Facebook Page, Pleasant Grove, 555 U.S. at 473. Just as the parkland\\n\\nsurrounding monuments in Pleasant Grove continued to constitute a public forum, even\\n\\nthough the monuments themselves constituted government speech, so too the interactive\\n\\ncomponent of the Chair’s Facebook Page constitutes a public forum, even though\\n\\nRandall’s curation of and posts to the Chair’s Facebook Page amount to government\\n\\nspeech. Additionally, the interactive component of the Chair’s Facebook Page does not\\n\\nface the same spacial limitations as those of the park in Pleasant Grove, but instead is\\n\\n“capable of accommodating a large number of public speakers without defeating [its]\\n\\nessential function.” Id. at 578. Accordingly, Pleasant Grove supports, rather than\\n\\n\\n\\n\\n 32\\n\\nundermines, our conclusion that the interactive component of the Chair’s Facebook Page\\n\\nconstitutes a public forum.\\n\\n Upon concluding that interactive component of the Chair’s Facebook Page\\n\\namounts to a public forum, we would normally need to determine whether it constitutes a\\n\\ntraditional public forum or designated or limited public forum. In the present case,\\n\\nhowever, we need not decide that question because Randall’s ban of Davison amounted\\n\\nto “viewpoint discrimination,” which is “prohibited in all forums.” See Child Evangelism\\n\\nFellowship of S.C. v. Anderson Sch. Dist. Five, 470 F.3d 1062, 1067 n.2 (4th Cir. 2006).\\n\\n“Viewpoint discrimination . . . ‘targets not subject matter, but particular views taken by\\n\\nspeakers on a subject.’” Id. (quoting Rosenberger v. Rector & Visitors of Univ. of Va.,\\n\\n515 U.S. 819, 829 (1995)). Viewpoint discrimination is apparent, for example, if a\\n\\ngovernment official’s decision to take a challenged action was “impermissibly motivated\\n\\nby a desire to suppress a particular point of view.” Cornelius, 473 U.S. at 812–13.\\n\\n Here, the district court found—as the record amply supports—that Randall banned\\n\\nDavison’s Virginia SGP Page because Davison posted a comment using that page\\n\\nalleging “corruption on the part of Loudoun County’s School Board involving conflicts\\n\\nof interests among the School Board and their family members.” Davison, 267 F. Supp.\\n\\n3d at 711. Although Randall stated that she had “no idea” whether Davison’s allegations\\n\\nwere “correct,” she nonetheless banned him because she viewed the allegations as\\n\\n“slanderous” and she “didn’t want [the allegations] on the site.” Id. at 717. Randall’s\\n\\ndecision to ban Davison because of his allegation of governmental corruption constitutes\\n\\nblack-letter viewpoint discrimination.\\n\\n\\n 33\\n\\n Put simply, Randall unconstitutionally sought to “suppress” Davison’s opinion\\n\\nthat there was corruption on the School Board. Cornelius, 473 U.S. at 812–13; see also,\\n\\ne.g., Rossignol, 316 F.3d at 521 (holding that sheriff’s deputies engaged in viewpoint\\n\\ndiscrimination when they seized an issue of a newspaper that criticized the county\\n\\nsheriff’s and his deputies’ performance of their official duties); Putnam Pit, Inc. v. City of\\n\\nCookeville, Tenn., 221 F.3d 834, 846 (6th Cir. 2000) (holding that a municipality engages\\n\\nin viewpoint discrimination if it refuses to link newspaper webpage to the city’s website\\n\\nsolely because the newspaper sought to expose municipal corruption); Knight, 302 F.\\n\\nSupp. 3d at 575 (holding that the President engaged in viewpoint discrimination when he\\n\\nblocked individuals from his Twitter account because the individuals “posted tweets that\\n\\ncriticized the President or his policies”). 7 That Randall’s action targeted comments\\n\\ncritical of the School Board members’ official actions and fitness for office renders the\\n\\nbanning all the more problematic as such speech “occupies the core of the protection\\n\\nafforded by the First Amendment.” Rossignol, 316 F.3d at 521 (quoting McIntyre v.\\n\\nOhio Elections Comm’n, 514 U.S. 334, 346 (1995)).\\n\\n In sum, the interactive component of the Chair’s Facebook Page constituted a\\n\\npublic forum, and Randall engaged in unconstitutional viewpoint discrimination when\\n\\nshe banned Davison’s Virginia SGP Page from that forum.\\n\\n\\n 7\\n Randall also asserts that she did not violate Davison’s First Amendment rights\\nbecause she banned his “Virginia SGP” Page, not his “Brian Davison” profile. Davison\\nis the sole operator of the “Virginia SGP” Page, however, and therefore the ban\\nimplicated his First Amendment rights. Randall fails to identify any case supporting her\\nposition, nor have we found any. Accordingly, we reject this argument.\\n\\n\\n 34\\n\\n III.\\n\\n In his cross-appeal, Davison asserts that the district court reversibly erred in two\\n\\nways: (A) by dismissing his claim against Randall in her official capacity and (B) by\\n\\ndenying his motion to amend his complaint to add the new First Amendment claim\\n\\nagainst the Loudoun Board. 8 We disagree.\\n\\n A.\\n\\n Davison first argues that the district court erred in dismissing his claim against\\n\\nRandall in her official capacity. Whereas “[p]ersonal-capacity suits seek to impose\\n\\npersonal liability upon a government official for actions [she] takes under color of state\\n\\nlaw,” Kentucky v. Graham, 473 U.S. 159, 165 (1985), “official capacity suits are ‘treated\\n\\nas suits against the municipality,’” Santos v. Frederick Cty. Bd. of Comm’rs, 725 F.3d\\n\\n451, 469 (4th Cir. 2013) (quoting Hafer v. Melo, 502 U.S. 21, 25 (1991)). Because\\n\\n“municipal liability under Section 1983 does not amount to respondeat superior . . . a\\n\\n 8\\n Davison also argues that the district court erred in rejecting his procedural due\\nprocess claims under the Fourteenth Amendment and an analogous provision in the\\nVirginia Constitution. Before the district court, Davison “flatly asserted that due process\\nalways requires the government to provide a hearing before imposing a prior restraint on\\nspeech,” and therefore that Randall violated Davison’s First Amendment rights by failing\\nto conduct a pre-ban hearing. Davison, 267 F. Supp. 3d at 719. The district court\\ncorrectly rejected Davison’s proposed categorical rule. Id. (citing Cafeteria & Rest.\\nWorkers Union Local 473, AFL-CIO v. McElroy, 367 U.S. 886, 895 (1961). And\\nDavison has abandoned that asserted categorical rule on appeal, Davison’s Br. at 49–50\\nn.19 (“[I]t might be permissible in certain contexts to delete an individual comment\\nwithout providing full pre-deprivation process . . . .”), instead arguing he is entitled to\\nrelief under the balancing test set forth in Mathews v. Eldridge, 424 U.S. 319, 334–35\\n(1976). Because Davison did not make that argument before the district court, we decline\\nto consider it now. See CoreTel Va., LLC v. Verizon Va., LLC, 808 F.3d 978, 988 (4th\\nCir. 2015).\\n\\n\\n\\n 35\\n\\nmunicipality is subject to Section 1983 liability only when its ‘policy or custom, whether\\n\\nmade by its lawmakers or by those whose edicts or acts may fairly be said to represent\\n\\nofficial policy, inflicts the [plaintiff’s] injury.’” Id. at 469–70 (quoting Monell v. Dep’t of\\n\\nSoc. Servs. of the City of N.Y., 436 U.S. 658, 694 (1978)).\\n\\n Here, the district court dismissed Davison’s official capacity claim because it\\n\\nfound that “no policy—whether County-wide or specific to [Randall]’s office—played\\n\\nany role in [Randall]’s decision to ban [Davison] from her [Chair’s Facebook Page].”\\n\\nDavison, 267 F. Supp. 3d at 715. We review the district court’s factual findings bearing\\n\\non whether Randall acted pursuant to a municipal policy or custom for clear error and its\\n\\nlegal conclusions de novo. Helton, 709 F.3d at 350.\\n\\n On appeal, Davison does not dispute the district court’s finding—which the record\\n\\namply supports—that Loudoun County did not promulgate a policy governing individual\\n\\nLoudoun Board members’ Facebook pages. Rather, Davison principally 9 argues that “the\\n\\ncounty can be held liable for Randall’s actions because in banning Davison, Randall\\n\\nacted as a municipal policymaker.” Davison’s Br. at 47.\\n\\n\\n\\n\\n 9\\n Davison also argues the Loudoun Board’s failure to adopt a policy pertaining to\\nindividual board members’ Facebook pages gives rise to an official capacity claim\\nbecause it establishes that the Loudoun “Board was—and remains—deliberately\\nindifferent to the likelihood of unconstitutional censorship and viewpoint-based\\ndiscrimination on individual supervisors’ social media sites.” Davison’s Br. at 46. But\\nDavison never advanced a “deliberate indifference” theory of municipal liability before\\nthe district court. Again, we decline to consider an argument Davison raises for the first\\ntime on appeal. See CoreTel, LLC, 808 F.3d at 988.\\n\\n\\n\\n 36\\n\\n Davison is correct that “municipal liability may be imposed for a single decision\\n\\nby municipal policymakers under appropriate circumstances.” Hunter v. Town of\\n\\nMocksville, N.C., 897 F.3d 538, 554 (4th Cir. 2018) (quoting Pembaur v. City of\\n\\nCincinnati, 475 U.S. 469, 480 (1986)). “[I]n assessing whether a municipality may be\\n\\nheld liable for constitutional or statutory violations of their decisionmakers, the\\n\\ntouchstone inquiry is whether ‘the decisionmaker possesses final authority to establish\\n\\nmunicipal policy with respect to the action ordered.’” Id. at 554–55 (emphasis added)\\n\\n(quoting Liverman v. City of Petersburg, 844 F.3d 400, 413 (4th Cir. 2016)).\\n\\n Here, Davison failed to put forward evidence establishing that Randall was a final\\n\\nmunicipal policymaker with regard to her banning of Davison from the Chair’s Facebook\\n\\nPage. On the contrary, record evidence establishes that the Loudoun Board retained\\n\\nauthority to establish municipal policy with respect to social media pages, as it adopted a\\n\\nsocial media policy governing the County’s official social media pages. Davison\\n\\nconcedes as much, arguing that the Loudoun Board “neglected . . . to extend its written\\n\\nguidelines to Board members’ official pages.” Davison’s Br. at 46. But that argument\\n\\npresupposes that the Loudoun Board—not Randall—had authority to establish municipal\\n\\npolicy with respect “to Board members’ official pages.”\\n\\n Davison nevertheless argues that the Loudoun Board “implicitly” delegated its\\n\\nfinal policymaking authority to Randall by not addressing individual Loudoun Board\\n\\nmembers’ official pages in its social media policy. Davison is correct that delegation of\\n\\nfinal policy making authority may be “implied from a continued course of knowing\\n\\nacquiescence by the governing body in the exercise of policymaking authority by an\\n\\n\\n 37\\n\\nagency or official.” Id. at 48 (quoting Spell v. McDaniel, 824 F.2d 1380, 1387 (4th Cir.\\n\\n1987)). But Davison identifies no evidence that the Loudoun Board knew of the Chair’s\\n\\nFacebook Page, let alone that it “aquiesce[d]” in Randall’s administration of the page and\\n\\nbanning of Davison, in particular. On the contrary, the district court found that Randall\\n\\nmade a one-off, “unilateral decision to ban [Davison] in the heat of the moment, and\\n\\nreconsidered soon thereafter,” Davison, 267 F. Supp. 3d at 715—before the Loudoun\\n\\nBoard had a chance to learn of her action. In such circumstances, the district court did\\n\\nnot reversibly err in rejecting Davison’s official capacity claim.\\n\\n B.\\n\\n Next, Davison argues that the district court erred in denying him leave to amend\\n\\nhis complaint to add a claim that “the County violates the First Amendment by\\n\\nmaintaining a limited public forum on Facebook,” when policies imposed by Facebook,\\n\\nrather than the County, restrain, or have the potential to restrain, speech. J.A. 74. “A\\n\\ndistrict court may deny a motion to amend when the amendment would be prejudicial to\\n\\nthe opposing party, the moving party has acted in bad faith, or the amendment would be\\n\\nfutile.” Equal Rights Ctr. v. Niles Bolton Assocs., 602 F.3d 597, 603 (4th Cir. 2010).\\n\\nThe magistrate judge recommended—and the district court agreed—that Davison be\\n\\ndenied leave to amend on grounds of both futility and prejudice. We review for abuse of\\n\\ndiscretion a district court’s denial of leave to amend for prejudice, whereas we review de\\n\\nnovo a district court’s denial of leave to amend on the basis of futility. See U.S. ex rel.\\n\\nAhumada v. NISH, 756 F.3d 268, 274 (4th Cir. 2014).\\n\\n\\n\\n\\n 38\\n\\n Regarding prejudice, the district court determined that the amendment came “too\\n\\nlate in these proceedings” and would “add a new, novel legal theory to the case after the\\n\\nclose of discovery, after the existing claims against [the Loudoun Board] have been\\n\\nshown to be meritless, after the point at which Defendants could have addressed the\\n\\nclaim in briefing before trial, and on the eve of trial.” J.A. 74. The district court did not\\n\\nabuse its discretion in denying leave to amend in such circumstances. See, e.g., Equal\\n\\nRights Ctr., 602 F.3d at 603–04 (holding that district court did not abuse its discretion in\\n\\ndenying leave to amend on the basis of prejudice when amendment came after the close\\n\\nof discovery and “on the eve of the deadline for dispositive motions” and therefore\\n\\n“would [have] change[d] the nature of the litigation”); Deasy v. Hill, 833 F.2d 38, 41 (4th\\n\\nCir. 1987) (affirming denial of leave to amend on grounds of prejudice when “the motion\\n\\nto amend came right before trial and after discovery was complete”).\\n\\n Although we affirm the district court’s judgment on the basis of its finding of\\n\\nprejudice, we do not concur in its conclusion as to futility. “Futility is apparent if the\\n\\nproposed amended complaint fails to state a claim under the applicable rules and\\n\\naccompanying standards.” Katyle v. Penn Nat. Gaming, Inc., 637 F.3d 462, 471 (4th Cir.\\n\\n2011). Accordingly, Davison’s proposed amendment was futile if the new claim would\\n\\nnot have survived a motion to dismiss under Federal Rule of Civil Procedure 12(b)(6).\\n\\nSee Runnion ex rel. Runnion v. Girl Scouts of Greater Chicago & Nw. Ind., 786 F.3d 510,\\n\\n524 (7th Cir. 2015) (“[W]hen the basis for denial is futility, we apply the legal\\n\\nsufficiency standard of Rule 12(b)(6) to determine whether the proposed amended\\n\\ncomplaint fails to state a claim.”).\\n\\n\\n 39\\n\\n Davison’s proposed First Amendment claim deals not with the Chair’s Facebook\\n\\nPage—which the Loudoun Board did not authorize or attempt to regulate—but rather\\n\\nwith Loudoun County’s official Facebook Pages created and maintained pursuant to the\\n\\nLoudoun Board’s social media policy. As with his claims related to the Chair’s\\n\\nFacebook Page, Davison alleged that the Facebook Pages created and maintained by the\\n\\nLoudoun Board constituted public forums subject to the First Amendment. Davison\\n\\ntheorized that the Loudoun Board’s decision to use Facebook as its social media forum\\n\\nviolated his First Amendment rights because Facebook rules permit individual\\n\\n“requesting” users to ban other personal profiles and Pages such that the banned users can\\n\\nno longer see posts authored by the requesting users. In such circumstances, the banned\\n\\nusers “cannot see [the requesting user’s] comment[s] or participate in the discussion\\n\\nsurrounding the [requesting] party’s comment.” Davison’s Br. at 59. Davison’s\\n\\nproposed amended complaint asserted that “this scenario violates the First Amendment\\n\\nbecause Loudoun County has effectively enabled third parties to exclude discussion\\n\\nwithin a public forum—something a government body could not permissibly do in a\\n\\nphysical forum.” Id. at 59–60 (internal citation omitted). Put differently, Davison\\n\\ntheorized that Loudoun County violated the First Amendment by choosing to use\\n\\nFacebook as a public forum, when rules imposed by Facebook allow private users to\\n\\nrestrict access to their posts—and comments on and responses to those posts—including\\n\\nposts to any municipal Facebook Page.\\n\\n No court appears to have addressed that novel legal theory. And although the First\\n\\nAmendment constrains only government policies, not policies established by private\\n\\n\\n 40\\n\\nentities, one can conceive of a colorable legal argument that a governmental actor’s\\n\\ndecision to select a private social media website for use as a public forum—and therefore\\n\\nselect that website’s suite of rules and regulations—could violate the First Amendment, if\\n\\nthe private website included certain types of exclusionary rules. For example, if the\\n\\ngovernment chose as its electronic public forum a social media site that allowed only\\n\\nregistered members of one political party to post and comment, there would seem to be a\\n\\ncompelling argument that the government’s selection of that social media site violated the\\n\\nFirst Amendment rights of members of other political parties, even if the partisan\\n\\nrestriction was imposed by the private company, not the governmental body. Such a\\n\\nrestriction would be seem to be no different than a municipality choosing to hold a town\\n\\nhall meeting in a venue that refused admission to individuals associated with a disfavored\\n\\npolitical party or viewpoint. Cf. DeBoer v. Village of Oak Park, 267 F.3d 558, 571 (7th\\n\\nCir. 2001) (“[T]he government engages in viewpoint discrimination when it denies access\\n\\nto a speaker solely to suppress the point of view he espouses on an otherwise includible\\n\\nsubject.”).\\n\\n Given that Davison’s proposed claim asserted a novel and colorable legal theory\\n\\nand that “Rule 12(b)(6) dismissals are especially disfavored in cases where the complaint\\n\\nsets forth a novel legal theory that can best be assessed after factual development,”\\n\\nWright v. North Carolina, 787 F.3d 256, 263 (4th Cir. 2015) (internal quotation marks\\n\\nomitted), we affirm the district court’s denial of Davison’s motion for leave to amend his\\n\\ncomplaint on the basis of its finding of prejudice but not on the basis of futility.\\n\\n IV.\\n\\n\\n 41\\n\\nFor the foregoing reasons, we affirm the judgment of the district court.\\n\\n AFFIRMED\\n\\n\\n\\n\\n 42\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4357289/\", \"author_raw\": \"WYNN, Circuit Judge:\"}, {\"author\": \"BARBARA MILANO KEENAN, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"BARBARA MILANO KEENAN, Circuit Judge, concurring:\\n\\n I join the well-reasoned majority opinion in full. I agree that the central “aspects\\n\\nof the Chair’s Facebook Page bear the hallmarks of a public forum.” I am particularly\\n\\npersuaded by the facts concerning Randall’s conduct of impressing the Chair Facebook\\n\\nPage with the trappings of a “government official” Facebook Page and of inviting\\n\\ncitizens to comment, without restriction, on matters of public concern. Accordingly,\\n\\nunder our precedent, I agree that Randall’s conduct of banning Davison’s Virginia SGP\\n\\nPage based on the content of a comment is attributable to the government and violates the\\n\\nFirst Amendment. See Rossignol v. Voorhaar, 316 F.3d 516, 523-25 (4th Cir. 2003).\\n\\n I nonetheless write separately to call attention to two issues regarding\\n\\ngovernmental use of social media that do not fit neatly into our precedent. First, I\\n\\nquestion whether any and all public officials, regardless of their roles, should be treated\\n\\nequally in their ability to open a public forum on social media. The Supreme Court\\n\\nrecently cited a series of decisions in which “a unit of government” had created a public\\n\\nforum. Matal v. Tam, 137 S. Ct. 1744, 1763 (2017) (emphasis added) (citing cases); see\\n\\nalso Pleasant Grove City v. Summum, 555 U.S. 460, 470 (2009) (“a government entity\\n\\nmay create a forum” (emphasis added)). However, it appears to be an open question\\n\\nwhether an individual public official serving in a legislative capacity qualifies as a unit of\\n\\ngovernment or a government entity for purposes of her ability to open a public forum.\\n\\nInstead, our precedent merely directs us to consider whether the challenged action “bore a\\n\\nsufficiently close nexus” with the government to be “fairly treated” as that of the\\n\\n\\n\\n\\n 43\\n\\ngovernment itself. Rossignol, 316 F.3d at 525 (internal quotation marks and citation\\n\\nomitted).\\n\\n The nature and extent of a public official’s authority should have some bearing on\\n\\nthe official’s ability to open a public forum on social media. While the nine-member\\n\\nLoudoun County Board of Supervisors (the Board) serves to set policies, adopt\\n\\nordinances, and appropriate funds, the Chair simply is empowered individually to oversee\\n\\nmeetings and to set agendas. 1 The record before us is silent regarding the Chair’s\\n\\nauthority to take any official action on her own.\\n\\n In contrast, certain elected executive officials, under given circumstances, can\\n\\nconduct government business and set official policy unilaterally, including through the\\n\\nuse of social media. See, e.g., Knight First Amendment Inst. at Columbia Univ. v. Trump,\\n\\n302 F. Supp. 3d 541, 567 (S.D.N.Y. 2018) (discussing President Donald J. Trump’s use\\n\\nof his Twitter account to appoint and remove officers and conduct foreign policy), appeal\\n\\ndocketed, No. 18-1691 (2d Cir. Oct. 24, 2018); Schisler v. State, 907 A.2d 175, 218-20\\n\\n(Md. 2006) (describing the governor’s unilateral power to remove certain officers). The\\n\\nrelevance of such distinctions to a public official’s ability to create a public forum on\\n\\nsocial media is a matter that should be addressed by the Supreme Court. Because this is\\n\\nan open question, we are bound by current precedent and, for the reasons set forth in the\\n\\n\\n\\n 1\\n See Bd. of Supervisors Operations Manual, LOUDOUN CTY., VA chs. 2-3,\\nhttps://www.loudoun.gov/DocumentCenter/View/117084/Board-of-Supervisors-\\nOperations-Manual-2016-2020 (last visited Dec. 20, 2018) (saved as ECF opinion\\nattachment).\\n\\n\\n 44\\n\\nmajority opinion, Randall as a single board member acted under of color of law and\\n\\nopened a public forum on Facebook.\\n\\n Second, the Supreme Court should consider further the reach of the First\\n\\nAmendment in the context of social media. I acknowledge that the Supreme Court has\\n\\nreferred to social media as “the modern public square,” Packingham v. North Carolina,\\n\\n137 S. Ct. 1730, 1737 (2017), implying that First Amendment principles protecting\\n\\nspeech from government intrusion do extend to social media. However, the interplay\\n\\nbetween private companies hosting social media sites and government actors managing\\n\\nthose sites necessarily blurs the line regarding which party is responsible for burdens\\n\\nplaced on a participant’s speech.\\n\\n For example, hate speech is protected under the First Amendment. See Matal, 137\\n\\nS. Ct. at 1763-64 (holding that the disparagement clause of the Lanham Act violated the\\n\\nFirst Amendment free speech clause because it prohibited hate speech). But social media\\n\\ncompanies like Facebook and others have policies forbidding hate speech on their\\n\\nplatforms. 2 Thus, while a government official, who under color of law has opened a\\n\\npublic forum on a social media platform like Facebook, could not ban a user’s comment\\n\\ncontaining hate speech, that official could report the hate speech to Facebook. And\\n\\nFacebook personnel could ban the user’s comment, arguably circumventing First\\n\\nAmendment protections.\\n\\n\\n 2\\n See, e.g., Cmty. Standards, Hate Speech, FACEBOOK, https://www.facebook.com/\\ncommunitystandards/hate_speech (last visited Dec. 20, 2018) (saved as ECF opinion\\nattachment).\\n\\n\\n\\n 45\\n\\n Admittedly, this question is not directly presented in the present case, given that\\n\\nthe public official, not a Facebook employee, acted to restrict speech. Nonetheless, cases\\n\\nnecessarily will arise requiring courts to consider the nuances of social media and their\\n\\nvarious roles in hosting public forums established by government officials or entities.\\n\\nTherefore, in my view, courts must exercise great caution when examining these issues,\\n\\nas we await further guidance from the Supreme Court on the First Amendment’s reach\\n\\ninto social media.\\n\\n\\n\\n\\n 46\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4357289/\", \"author_raw\": \"BARBARA MILANO KEENAN, Circuit Judge, concurring\"}]}"},"judge1":{"kind":"string","value":"KEENAN"},"judge2":{"kind":"string","value":"WYNN"},"judge3":{"kind":"string","value":"HARRIS"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"KEENAN\": \", Circuit\", \"WYNN\": \", Circuit\", \"HARRIS\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":2,"string":"2"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":1,"string":"1"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4580036/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Brian Davison v. Phyllis Randall\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-09\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-2002\n\n\nBRIAN DAVISON,\n\n Plaintiff - Appellee,\n\n v.\n\nPHYLLIS RANDALL, In her official and individual capacity,\n\n Defendant - Appellant,\n\n and\n\nLOUDOUN COUNTY BOARD OF SUPERVISORS, In their official and\nindividual capacities; LEO ROGERS, In his official capacity; TONY\nBUFFINGTON, In his official capacity; RON MEYER, In his official capacity;\nGEARY HIGGINS, In his official capacity,\n\n Defendants.\n\n------------------------------\n\nLOCAL GOVERNMENT ATTORNEYS OF VIRGINIA, INC.;\nINTERNATIONAL MUNICIPAL LAWYERS ASSOCIATION; VIRGINIA\nASSOCIATION OF COUNTIES; VIRGINIA MUNICIPAL LEAGUE,\n\n Amici Supporting Appellant,\n\nAMERICAN CIVIL LIBERTIES UNION; ACLU OF VIRGINIA; ACLU OF\nMARYLAND; ACLU OF NORTH CAROLINA; ACLU OF SOUTH\nCAROLINA; ACLU OF WEST VIRGINIA,\n\n Amici Supporting Appellee.\n\n No. 17-2003\n\n\nBRIAN C. DAVISON,\n\n Plaintiff - Appellant,\n\n v.\n\nPHYLLIS RANDALL, In her official and individual capacity; LOUDOUN\nCOUNTY BOARD OF SUPERVISORS, In their official and individual\ncapacities,\n\n Defendants - Appellees,\n\n and\n\nLEO ROGERS, In his official capacity; TONY BUFFINGTON, In his official\ncapacity; RON MEYER, In his official capacity; GEARY HIGGINS, In his\nofficial capacity,\n\n Defendants.\n\n\nAppeals from the United States District Court for the Eastern District of Virginia, at\nAlexandria. James C. Cacheris, Senior District Judge. (1:16-cv-00932-JCC-IDD)\n\n\nArgued: September 26, 2018 Decided: January 7, 2019\n Amended: January 9, 2019\n\n\nBefore KEENAN, WYNN, and HARRIS, Circuit Judges.\n\n\nAffirmed by published opinion. Judge Wynn wrote the opinion, in which Judge Keenan\nand Judge Harris concurred. Judge Keenan wrote a separate concurring opinion.\n\n\nARGUED: Scott E. Gant, BOIES SCHILLER FLEXNER, LLP, Washington, D.C.; Leo\nP. Rogers, LOUDON COUNTY ATTORNEY, Leesburg, Virginia, for Appellant/Cross-\n\n\n 2\n\nAppellee. Katherine A. Fallow, KNIGHT FIRST AMENDMENT INSTITUTE AT\nCOLUMBIA UNIVERSITY, New York, New York, for Appellee/Cross-Appellant. ON\nBRIEF: Aaron E. Nathan, BOIES SCHILLER FLEXNER LLP, Washington, D.C., for\nAppellant/Cross-Appellee. Jameel Jaffer, Carrie DeCell, KNIGHT FIRST\nAMENDMENT INSTITUTE AT COLUMBIA UNIVERSITY, New York, New York,\nfor Appellee/Cross-Appellant. Vishal Agraharkar, AMERICAN CIVIL LIBERTIES\nUNION FOUNDATION OF VIRGINIA, Richmond, Virginia; Esha Bhandari, Vera\nEidelman, AMERICAN CIVIL LIBERTIES UNION FOUNDATION, New York, New\nYork; Susan K. Dunn, ACLU OF SC FOUNDATION, INC., Charleston, South Carolina;\nChristopher Brook, AMERICAN CIVIL LIBERTIES UNION OF NORTH CAROLINA\nLEGAL FOUNDATION, Raleigh, North Carolina; Deborah A. Jeon, ACLU\nFOUNDATION OF MARYLAND, Baltimore, Maryland; Jennifer D. Oliva, ACLU OF\nWEST VIRGINIA FOUNDATION, Charleston, West Virginia, for Amici American\nCivil Liberties Union, ACLU of Virginia, ACLU of Maryland, ACLU of North Carolina,\nACLU of South Carolina, and ACLU of West Virginia. Joshua A. Geltzer, Douglas\nLetter, Amy L. Marshak, Mary B. McCord, INSTITUTE FOR CONSTITUTIONAL\nADVOCACY AND PROTECTION GEORGETOWN UNIVERSITY LAW CENTER,\nWashington, D.C.; Kwaku A. Akowuah, Christopher C. Fonzone, Kate Heinzelman,\nSIDLEY AUSTIN LLP, Washington, D.C., for Amici Curiae First Amendment Legal\nScholars.\n\n\n\n\n 3\n\nWYNN, Circuit Judge:\n\n Phyllis Randall, Chair of the Loudoun County, Virginia, Board of Supervisors (the\n\n“Loudoun Board”), brings this appeal, arguing that the district court erred in concluding\n\nthat she violated the First Amendment rights of one of her constituents, Brian Davison,\n\nwhen she banned Davison from the “Chair Phyllis J. Randall” Facebook page she\n\nadministered. In a cross appeal, Davison principally argues that the district court erred\n\nin dismissing his procedural due process claim premised on the ban. For the reasons that\n\nfollow, we affirm.\n\n I.\n\n A.\n\n Randall has chaired the Loudoun County Board of Supervisors since January 1,\n\n2016. The day before she was sworn in as chair, Randall created the “Chair Phyllis J.\n\nRandall” Facebook Page (the “Chair’s Facebook Page”). According to Facebook, Inc.,\n\nunlike personal Facebook profiles, which are for non-commercial use and represent\n\nindividual people, Facebook “Pages”—like the Chair’s Facebook Page—“help\n\nbusinesses, organizations, and brands share their stories and connect with people.” J.A.\n\n403. “Pages are managed by people who have personal profiles,” the company explains.\n\nJ.A. 403. In addition to the Chair’s Facebook Page, Randall created and maintained two\n\nother Facebook profiles: a personal profile and a Page devoted to her campaign. Randall\n\nclassified her campaign page as belonging to a “politician” and used no designation for\n\nher personal profile, but she designated the Chair’s Facebook Page as a “governmental\n\nofficial” page. J.A. 209–10.\n\n\n 4\n\n Randall and her Chief of Staff, Jeanine Arnett, share administrative control over\n\nthe Chair’s Facebook Page, although Randall almost exclusively controls the page’s\n\ncontent. On her campaign page, Randall characterized the Chair’s Facebook Page as her\n\n“county Facebook page” stating:\n\n I really want to hear from ANY Loudoun citizen on ANY issues, request,\n criticism, complement or just your thoughts. However, I really try to keep\n back and forth conversations (as opposed to one time information items\n such as road closures) on my county Facebook page (Chair Phyllis J.\n Randall) or County email (Phyllis.randall@loudoun.gov). Having back and\n forth constituent conversations are Foiable ([Freedom of Information Act])\n so if you could reach out to me on these mediums that would be\n appreciated.\n\nJ.A. 455 (emphasis added).\n\n The Chair’s Facebook Page includes three columns. The left column, which is\n\ntopped by a picture of Randall, includes several links to allow visitors to quickly navigate\n\nthe contents of the Chair’s Facebook Page.\n\n The middle column, which is organized in reverse chronological order similar to a\n\npersonal profile’s News Feed, is composed of posts by Randall and comments by\n\nFacebook users on those posts. Randall’s posts are almost always directed to “Loudoun,”\n\nsee, e.g., J.A. 408–10, and deal with numerous aspects of Randall’s official\n\nresponsibilities. For example, Randall used the Chair’s Facebook Page to notify the\n\npublic about upcoming Loudoun Board meetings, and the subjects to be discussed during\n\nthose meetings. Randall also used the page to inform Loudoun County residents about\n\nsignificant public safety issues. See, e.g., J.A. 412 (stating that Loudoun Board had\n\n“been informed by the Sheriff’s Office about the non-legitimate threat made on social\n\n\n\n 5\n\nmedia toward Dominion High School in Sterling”); J.A. 418 (reporting that she “ha[d]\n\nbeen briefed regarding the student falling from the water tower this morning” and\n\nadvising the public to “not make any assumptions but wait for information”). And\n\nRandall used the Chair’s Facebook Page to coordinate Loudoun County’s response to a\n\nlarge snow storm, including to communicate with constituents regarding which municipal\n\nstreets required plowing.\n\n Other posts by Randall to the Chair’s Facebook Page invited members of the\n\npublic to apply to participate on a public commission and to participate in public\n\nmeetings regarding key issues facing Loudoun County residents, such as revised flood\n\nplain zones and the Zika virus. Randall also authored posts regarding a variety of trips\n\nand meetings she had taken in furtherance of Loudoun County business. E.g., J.A. 408\n\n(reporting that Randall “address[ed] the (county) role in Treatment” at a “regional\n\nconference on Opioid and Substance Abuse Addiction”); J.A. 410 (stating that Randall\n\nrepresented Loudoun County at its “annual credit rating presentation” in New York); J.A.\n\n415 (informing public of trip to Loudoun’s “Sister City” in Germany); J.A. 426\n\n(reporting that Randall was “in Richmond lobbying for [Loudoun County’s] legislative\n\nprogram”). Finally, Randall used the page to advise the public regarding official actions\n\ntaken by the Loudoun Board. E.g., J.A. 433 (reporting that Loudoun Board “approved\n\nfunding for new breathing apparatus for our Loudoun Firefighters”); J.A. 442 (listing\n\nseveral “proclamations of note” by the Loudoun Board); J.A. 443 (informing public that\n\nLoudoun Board “adopted a budget for Fiscal Year 2017 totaling $2.46 billion for the\n\ngeneral county government and schools”). Although Randall’s posts on the Chair’s\n\n\n 6\n\nFacebook Page principally addressed her official responsibilities, a few posts addressed\n\ntopics less closely related to her official activities such as her affection for the German\n\nlanguage or pride in becoming an organ donor.\n\n Members of the public, including Davison, “liked” 1 or commented on several of\n\nRandall’s posts on the Chair’s Facebook Page. Each “like” or comment identified the\n\nname of the personal profile or Page of the authoring party. Many of the comments\n\nthanked Randall and the Loudoun Board for representing the public’s interests. Other\n\nposts by members of the public offered feedback on various issues faced by Randall and\n\nthe Loudoun Board. E.g., J.A. 427 (stating that “[p]utting recreation in a flood plain is\n\nnot a good idea”); J.A. 448 (stating that “more needs to be done with the explosion of\n\nLyme disease in Loudoun”). And other comments dealt with constituent-specific issues.\n\nE.g., J.A. 415 (constituent stating, in response to post by Randall regarding visit to\n\nLoudoun County’s “Sister City” in Germany, that constituent’s “daughter is interested in\n\nexchange programs”); J.A. 454 (stating that “there [we]re no [snow] plows to be seen” in\n\na particular neighborhood). Finally, several comments, including a number authored by\n\nDavison, criticized the Loudoun Board, generally, and Randall, in particular, for actions\n\ntaken in their official capacities. E.g., J.A. 429–30 (Davison criticizing public school\n\nsystem budget and expenditures); J.A. 438–39 (member of public criticizing\n\ngovernmental entity’s inspection of farm, claiming it failed to uncover animal abuse);\n\n\n 1\n “‘Liking’ on Facebook is a way for Facebook users to share information with\neach other.” Bland v. Roberts, 730 F.3d 368, 385 (4th Cir. 2013).\n\n\n\n 7\n\nJ.A. 449 (Davison characterizing question he posed at Loudoun Board and Loudoun\n\nSchool Board joint town hall). On some occasions, Randall responded to these\n\ncomments or criticisms.\n\n In the right column of the Chair’s Facebook Page, the page is identified as a\n\n“government official” page. It provides contact information for Randall’s county office,\n\nincluding her office telephone number, Randall’s official county email address, and the\n\ninternet address for the official county website. The column also identifies how many\n\nand which Facebook personal profiles and Pages “like” and “follow” the Chair’s\n\nFacebook Page. 2 And the column includes a list of personal profiles and Pages “liked”\n\nby the Chair’s Facebook Page.\n\n Randall publicized the Chair’s Facebook Page in her official “Chair Phyllis J.\n\nRandall” newsletter, which is prepared by County employees, hosted on the County’s\n\nwebsite, and distributed to Loudoun citizens using Randall’s official county email\n\naccount. The newsletter ends with the words “STAY CONNECTED” and a Facebook\n\nicon that hyperlinks to the Chair’s Facebook Page. Randall also highlighted the Chair’s\n\nFacebook Page in “Winter Storm Information” notices emailed from her official county\n\naccount to Loudoun County residents, advising recipients to “Visit [the Chair’s Facebook\n\nPage] for Updates.” J.A. 341–42, 344.\n\n 2\n According to Facebook, “[l]iking a Facebook Page means you are connecting to\nthat Page. When you connect to a Page, it will appear in [a user’s] timeline and [the user]\nwill appear on the page as a person who likes that Page. The Page will also be able to\npost content into [the user’s] News Feed.” Bland, 730 F.3d at 385 (internal quotation\nmarks omitted).\n\n\n\n 8\n\n Davison, an outspoken resident of Loudoun County, apparently largely focuses his\n\ncivic engagement and expression on “the funding and . . . management of public\n\nschools.” J.A. 95. To that end, he has repeatedly expressed concern about “School Board\n\nmembers failing to disclose personal conflicts as required by law before voting on\n\nfinancial transactions before the School Board.” J.A. 96.\n\n On February 3, 2016, Davison attended a Loudoun town hall meeting that\n\nincluded the Loudoun County School Board and Randall. At the meeting, Davison\n\nsubmitted a question implying that certain School Board members had acted unethically\n\nin approving financial transactions. Randall volunteered to answer the question but\n\ncharacterized it as a “set-up question” that she did not “appreciate.” J.A. 103. Shortly\n\nafter Randall answered the question—and while the town hall meeting was still\n\nongoing—Davison posted a message on Twitter in which he tagged Randall:\n\n“@ChairRandall ‘set up question’? You might want to strictly follow FOIA and the\n\nCOIA as well.” J.A. 470–71.\n\n Later that evening, Randall posted about the town hall meeting on the Chair’s\n\nFacebook Page, describing “what was generally discussed at the meeting.” J.A. 268. In\n\nresponse, Davison then used one of the Facebook Pages he manages through his personal\n\nFacebook profile—“Virginia SGP,” which Davison frequently uses to post political\n\ncommentary—to comment on Randall’s post about the town hall meeting. Although\n\nneither Davison nor Randall remember the precise content of Davison’s comment,\n\nRandall testified that it contained “accusations” regarding School Board members’ and\n\ntheir families’ putative conflicts of interest related to municipal financial transactions,\n\n\n 9\n\nsuggesting, in Randall’s opinion, that School Board members had been “taking kickback\n\nmoney.” See J.A. 268–69, 289–90. Randall stated that she “had no idea if any of th[e]\n\n[accusations] w[ere] correct,” but she determined that the post was “probably not\n\nsomething [she] want[ed] to leave” on the Chair’s Facebook Page. J.A. 269. Randall\n\nthen “deleted the whole post,” including her original post regarding the town hall\n\nmeeting, Davison’s comment and replies thereto, and all other public comments. J.A.\n\n269. Randall also banned Davison’s Virginia SGP Page from the Chair’s Facebook Page,\n\nwhich precluded Davison from using his Virginia SGP Page from commenting on the\n\nChair’s Facebook Page. The next morning, about twelve hours later, Randall\n\nreconsidered her actions and unbanned Davison’s Virginia SGP Page.\n\n B.\n\n On November 3, 2016, Davison filed an amended complaint seeking declaratory\n\nand injunctive relief under 42 U.S.C. § 1983 against Randall, in both her official and\n\nindividual capacities, and the Loudoun Board alleging that the “banning of [Davison]\n\nfrom commenting on [the Chair’s Facebook Page] is viewpoint discrimination.” J.A. 31.\n\nDavison further alleged that the ban violated his procedural due process rights protected\n\nby the Fourteenth Amendment because “Randall blocked Davison’s constitutionally\n\nprotected speech on [the Chair’s Facebook Page], a limited public forum, without prior\n\nnotice and without providing an opportunity for appealing [her] decision.” J.A. 32.\n\nDavison did not challenge Randall’s deletion of his post.\n\n On March 6, 2017—four days before the close of discovery and approximately\n\ntwo months before trial—Davison moved for leave to amend his complaint a second time\n\n\n 10\n\nto add claims under the Virginia Constitution that were materially indistinguishable from\n\nhis previously asserted First and Fourteenth Amendment claims premised on the ban, as\n\nwell as a separate First Amendment claim against the Loudoun Board. Davison’s\n\nproposed new First Amendment claim theorized that the County violated his free speech\n\nrights by choosing to use Facebook Pages as public forums, when Facebook allows\n\nprivate users to restrict access to their posts, including posts to any Page a municipality\n\ndesignates as a limited public forum. Pl.’s Mem. in Supp. of Mot. for Leave to File\n\nSecond Am. Compl. 3–9, Davison v. Loudoun County Bd. of Supervisors, 16-cv-932-\n\nJCC-IDD, ECF No. 68. The district court referred the motion to a magistrate judge, who\n\ngranted leave to amend regarding the claims under the Virginia Constitution but denied\n\nleave as to the new First Amendment claim against the Loudoun Board. Davison lodged\n\nobjections to the magistrate judge’s partial denial of leave to amend, which objections the\n\ndistrict court overruled.\n\n Around the same time, Randall and the Loudoun Board each moved for summary\n\njudgment. The Loudoun Board asserted that the municipality could not be held liable for\n\nRandall’s banning of Davison from the Chair’s Facebook Page because the Chair’s\n\nFacebook Page was not an official municipal page and because Randall, not the Loudoun\n\nBoard as a body, was solely responsible for creating and administering the Chair’s\n\nFacebook Page. The Loudoun Board and Randall further asserted that the Chair’s\n\nFacebook Page did not amount to a public forum, and therefore Randall’s ban of\n\nDavison’s Virginia SGP Page did not implicate his free speech or procedural due process\n\nrights. Finally, Randall asserted that she was entitled to qualified immunity.\n\n\n 11\n\n On May 10, 2017, the district court granted summary judgment in favor of the\n\nLoudoun Board, dismissing it from the suit. But as to Randall, the district court\n\nconcluded that Davison’s evidence established a material dispute of fact as to whether the\n\nChair’s Facebook Page amounted to a limited public forum and whether Randall, in her\n\nindividual capacity, acted under color of state law in banning Davison from the Chair’s\n\nFacebook Page. Davison v. Loudoun Cty. Bd. of Supervisors, No. 1:16-cv-932, 2017 WL\n\n1929406, at *6–9 (E.D. Va. May 10, 2017). The district court also rejected Randall’s\n\nqualified immunity argument. Id. at *8.\n\n Following a one-day bench trial of Davison’s claims against Randall, the district\n\ncourt issued a memorandum opinion and order awarding judgment in Davison’s favor on\n\nhis claims under the First Amendment and the analogous free speech provision in the\n\nVirginia Constitution. See Davison v. Loudoun Cty. Bd. of Supervisors, 267 F. Supp. 3d\n\n702, 714–18 (E.D. Va. 2017). The district court further entered judgment in Randall’s\n\nfavor on Davison’s federal and state procedural due process claims. Id. at 719–22. As to\n\nremedy, the district court denied Davison’s request for injunctive relief but granted\n\nDavison’s request for a declaratory judgment to resolve the “uncertainty regarding the\n\nlegal status of [the Chair’s Facebook Page].” Id. at 723.\n\n Randall and Davison, respectively, filed this appeal and cross appeal.\n\n II.\n\n On appeal, Randall argues that (A) Davison failed to establish standing to obtain\n\nprospective declaratory relief based on Randall’s alleged First Amendment violation; (B)\n\nthe district court erred in concluding that Randall acted under “color of state law” when\n\n\n 12\n\nshe banned Davison’s Virginia SGP Page from the Chair’s Facebook Page; and (C) the\n\ndistrict court erred in concluding that Randall’s banning of Davison’s Virginia SGP Page\n\nviolated the First Amendment.\n\n A.\n\n Notwithstanding that she did not challenge Davison’s standing below—and\n\ntherefore that the district court never squarely addressed his standing—Randall now\n\nargues that Davison failed to establish Article III standing to support the district court’s\n\naward of prospective declaratory relief. Even though Defendants did not challenge\n\nDavison’s standing below, “standing to sue is a jurisdictional issue of constitutional\n\ndimensions, and it may be raised and addressed for the first time on appeal.” Hodges v.\n\nAbraham, 300 F.3d 432, 443 (4th Cir. 2002). This Court reviews de novo “whether a\n\ndistrict court possessed jurisdiction in a declaratory judgment proceeding.” Volvo Const.\n\nEquip. N. Am., Inc. v. CLM Equip. Co., Inc., 386 F.3d 581, 591 (4th Cir. 2004).\n\n To establish Article III standing, a plaintiff must prove that: “1) he or she suffered\n\nan ‘injury in fact’ that is concrete and particularized, and is actual or imminent; 2) the\n\ninjury is fairly traceable to the challenged action of the defendant; and 3) the injury likely\n\nwill be redressed by a favorable decision.” Friends of the Earth, Inc. v. Gaston Copper\n\nRecycling Corp., 629 F.3d 387, 396 (4th Cir. 2011). Randall does not dispute that any\n\ninjury Davison suffered is fairly traceable to her decision to ban him from the Chair’s\n\nFacebook Page. Nor does Randall dispute that any such injury would be remedied by a\n\nfavorable decision. Rather, Randall claims that Davison failed to adduce evidence\n\n\n\n\n 13\n\nestablishing that he suffered an “injury in fact” sufficient to support prospective\n\ndeclaratory relief.\n\n “Injury in fact is ‘an invasion of a legally protected interest’ that is ‘concrete and\n\nparticularized’ and ‘actual or imminent, not conjectural or hypothetical.’” Kenny v.\n\nWilson, 885 F.3d 280, 287 (4th Cir. 2018) (quoting Spokeo, Inc. v. Robins, 136 S. Ct.\n\n1540, 1548 (2016)). Because “‘[p]ast exposure to illegal conduct does not in itself show\n\na present case or controversy regarding injunctive relief . . . if unaccompanied by any\n\ncontinuing, present adverse effects,’” a plaintiff seeking “declaratory or injunctive relief .\n\n. . must establish an ongoing or future injury in fact.” Id. at 287–88 (quoting O’Shea v.\n\nLittleton, 414 U.S. 488, 495–96 (1974)). Significantly, this Court—along with several\n\nother circuits—has held that “standing requirements are somewhat relaxed in First\n\nAmendment cases,” particularly regarding the injury-in-fact requirement. Cooksey v.\n\nFutrell, 721 F.3d 226, 235 (4th Cir. 2013) (collecting cases).\n\n In Kenny v. Wilson, 885 F.3d 280 (4th Cir. 2018), this Court addressed what\n\nevidence a plaintiff seeking relief under the First Amendment, like Davison, must put\n\nforward to establish a future injury-in-fact adequate to confer Article III standing to\n\nobtain prospective declaratory relief. In Kenny, several high school students lodged First\n\nAmendment challenges to two South Carolina disorderly conduct statutes. Id. at 284.\n\nThis Court explained that “there is a sufficiently imminent injury in fact if plaintiffs\n\nallege [1] ‘an intention to engage in a course of conduct arguably affected with a\n\nconstitutional interest, but proscribed by a statute, and [2] there exists a credible threat of\n\nprosecution thereunder.’” Id. at 288 (quoting Babbitt v. Farm Workers Nat’l Union, 442\n\n\n 14\n\nU.S. 289, 298 (1979)). The Kenny plaintiffs satisfied the first prong because they “attend\n\nschool” and “attending school inevitably involves expressive conduct” that implicates the\n\ndisorderly conduct statutes. Id. As to the second element—whether the students alleged\n\na “credible threat of future enforcement”—we held that such a threat exists so long as it\n\n“is not imaginary or wholly speculative, chimerical, or wholly conjectural.” Id. (internal\n\nquotation marks, citations, and alterations omitted). “[P]ast enforcement against the same\n\nconduct is good evidence that the threat of enforcement is not chimerical.” Id. (quoting\n\nSusan B. Anthony List v. Driehaus, 134 S. Ct. 2334, 2345 (2014)). “Threat of\n\nprosecution is especially credible when defendants have not ‘disavowed enforcement’ if\n\nplaintiffs engage in similar conduct in the future.” Id. (quoting Driehaus, 134 S. Ct. at\n\n2345). Applying this standard, we held that the plaintiffs alleged a credible threat of\n\nenforcement “because these three plaintiffs regularly attend schools where they allege\n\nthere may be future encounters with school resource officers or other law enforcement;\n\nthey have been prosecuted under the laws in the past; and the defendants have not\n\ndisavowed enforcement if plaintiffs engage in similar conduct in the future.” Id. at 289.\n\n Under Kenny, Davison’s evidence established his standing to obtain prospective\n\ndeclaratory relief. Relevant to the first prong—whether Davison intends to engage in a\n\ncourse of conduct “arguably” impacted by the challenged conduct, Babbitt, 442 U.S. at\n\n298—the district court found, in awarding Davison declaratory relief, that he “continues\n\nto avail himself” of the Chair’s Facebook Page and that Davison is “active in local\n\npolitics, and has a particular interest in what he believes to be corruption on the part of\n\nLoudoun County’s school board.” Davison, 267 F. Supp. 3d at 707, 723. Accordingly,\n\n\n 15\n\nthe evidence establishes that Davison continues to engage in a course of conduct—\n\nnamely, posting about alleged municipal corruption on the Chair’s Facebook Page—\n\nlikely to be impacted by Randall’s allegedly unconstitutional approach to managing the\n\npage.\n\n Turning to the second prong—whether there is a credible threat of enforcement—\n\nRandall previously blocked Davison from the Chair’s Facebook Page based on the\n\ncontent of his posts, providing “good evidence that the threat of enforcement is not\n\nchimerical.” Driehaus, 134 S. Ct. at 2345 (internal quotation marks omitted).\n\nAdditionally, Randall testified that she continues to believe she can ban Davison and\n\nothers from the Chair’s Facebook Page based on their views without triggering the First\n\nAmendment at all. See J.A. 277 (Randall stating she would “be happy to” ban other\n\ncommenters on her “Chair’s Facebook” page); J.A. 250 (Randall testifying that\n\ncomments “attacking another person” would not be allowed on her “Chair’s Facebook”\n\npage). To that end, in awarding Davison declaratory relief, the district court found that\n\nRandall “maintains she is permitted to administer this Facebook page as a purely personal\n\npage.” Davison, 267 F. Supp. 3d at 723. Accordingly, Davison established that he has\n\nbeen subject to past enforcement and that Randall has not “disavowed” future\n\nenforcement, which, under Kenny, is sufficient to establish a credible threat of\n\nenforcement. Cf. City of Lakewood v. Plain Dealer Pub. Co., 486 U.S. 750, 757 (1988)\n\n(“[T]he mere existence of the licensor’s unfettered discretion, coupled with the power of\n\nprior restraint, intimidates parties into censoring their own speech, even if the discretion\n\nand power are never actually abused.”).\n\n\n 16\n\n In sum, Davison’s evidence demonstrated—and the district court found—that\n\nDavison intends to continue to use the Chair’s Facebook Page and that Davison faces a\n\ncredible threat of future enforcement. See Davison, 267 F. Supp. 3d at 723.\n\nAccordingly, Davison adduced facts establishing an injury in fact sufficient to justify the\n\nprospective declaratory relief awarded by the district court.\n\n B.\n\n Next, Randall asserts that the district court erred in concluding, with regard to\n\nDavison’s individual capacity First Amendment claim, that Randall acted “under color of\n\nstate law,” as that phrase is used in Section 1983, in administering the Chair’s Facebook\n\nPage and banning Davison from that page. “This Court reviews judgments stemming\n\nfrom a bench trial under a mixed standard: factual findings are reviewed for clear error,\n\nwhereas conclusions of law are reviewed de novo.” Helton v. AT&T Inc., 709 F.3d 343,\n\n350 (4th Cir. 2013). Whether, under the undisputed facts, Randall acted under color of\n\nstate law is a legal question this Court reviews de novo. Rossignol v. Voorhaar, 316 F.3d\n\n516, 523 (4th Cir. 2003).\n\n To state a claim under Section 1983, a plaintiff must show that the alleged\n\nconstitutional deprivation at issue occurred because of action taken by the defendant\n\n“under color of . . . state law.” Philips v. Pitt Cty. Mem’l Hosp., 572 F.3d 176, 180 (4th\n\nCir. 2009). “The traditional definition of acting under color of state law requires that the\n\ndefendant in a § 1983 action have exercised power ‘possessed by virtue of state law and\n\nmade possible only because the wrongdoer is clothed with the authority of state law.’”\n\nWest v. Atkins, 487 U.S. 42, 49 (1988) (quoting United States v. Classic, 313 U.S. 299,\n\n\n 17\n\n326 (1941)). Section 1983’s “color-of-law prerequisite is synonymous with the more\n\nfamiliar state-action requirement” applicable to Fourteenth Amendment claims, “and the\n\nanalysis for each is identical.” Pitt Cty. Mem’l Hosp., 572 F.3d at 180. Both inquiries\n\ndemand that “the conduct allegedly causing the deprivation of a federal right be fairly\n\nattributable to the State.” Holly v. Scott, 434 F.3d 287, 292 (4th Cir. 2006) (quoting\n\nLugar v. Edmondson Oil Co., Inc., 457 U.S. 922, 937 (1982)).\n\n “[T]here is no specific formula for determining whether state action is present.”\n\nId. at 292 (internal quotation marks omitted). Rather, “[w]hat is fairly attributable [to the\n\nstate]”—i.e., what constitutes action under color of state law—“is a matter of normative\n\njudgment, and the criteria lack rigid simplicity.” Id. (internal quotation marks omitted).\n\nCourts must examine the “totality of the circumstances,” id. (internal quotation marks\n\nomitted), to determine if the action at issue “bore a ‘sufficiently close nexus’ with the\n\nState to be ‘fairly treated as that of the State itself,’” Rossignol, 316 F.3d at 525 (quoting\n\nJackson v. Metro. Edison Co., 419 U.S. 345, 351 (1974)).\n\n Although no one factor is determinative, this Court has held that a defendant’s\n\npurportedly private actions bear a “sufficiently close nexus” with the State to satisfy\n\nSection 1983’s color-of-law requirement when the defendant’s challenged “actions are\n\nlinked to events which arose out of his official status.” Id. at 524. When a defendant’s\n\n“status” as a public official “enabled [her] to execute [a challenged action] in a manner\n\nthat private citizens never could have,” then the action also is more likely to be treated as\n\nattributable to the state. Id. at 526; see also Martinez v. Colon, 54 F.3d 980, 986 (1st Cir.\n\n1995) (“[S]ection 1983 is . . . implicated . . . [when] the conduct is such that the actor\n\n\n 18\n\ncould not have behaved in that way but for the authority of his office.”); Goldstein v.\n\nChestnut Ridge Volunteer Fire Co., 218 F.3d 337, 343 (4th Cir. 2000) (holding that\n\nchallenged conduct is more likely to amount to state action when “the injury caused is\n\naggravated in a unique way by the incidents of governmental authority” (internal\n\nquotation marks omitted)). Likewise, an official’s conduct is more likely to amount to\n\nstate action when it “occurs in the course of performing an actual or apparent duty of his\n\noffice.” Martinez, 54 F.3d at 986. And the challenged action of a defendant\n\ngovernmental official is likely to be treated as taken under color of law when the official\n\n“use[d] the power and prestige of his state office to damage the plaintiff.” Harris v.\n\nHarvey, 605 F.2d 330, 337 (7th Cir. 1979). In the context of an alleged First Amendment\n\nviolation, in particular, this Court has found that a challenged action by a governmental\n\nofficial is fairly attributable to the state when “the sole intention” of the official in taking\n\nthe action was “to suppress speech critical of his conduct of official duties or fitness for\n\npublic office.” Rossignol, 316 F.3d at 524.\n\n Here, after thoroughly analyzing the totality of the circumstances surrounding\n\nRandall’s creation and administration of the Chair’s Facebook Page and banning of\n\nDavison from that page, the district court concluded that Randall acted under color of\n\nstate law. Davison, 267 F. Supp. 3d at 723. We agree.\n\n Randall created and administered the Chair’s Facebook Page to further her duties\n\nas a municipal official. She used the Chair’s Facebook Page “as a tool of governance,”\n\nid. at 713: through the Chair’s Facebook Page, Randall provides information to the public\n\n\n\n\n 19\n\nabout her and the Loudoun Board’s official activities and solicits input from the public on\n\npolicy issues she and the Loudoun Board confront. See supra Part I.A.\n\n For instance, Randall used the Chair’s Facebook Page to inform the public about\n\nserious public safety events and to keep her constituents abreast of the County’s response\n\nto a snowstorm and to coordinate snow removal activities. And, as the district court\n\ncorrectly emphasized, Randall\n\n swathe[d] the [Chair’s Facebook Page] in the trappings of her office.\n Among other things, (1) the title of the page includes [Randall]’s title; (2)\n the page is categorized as that of a government official; (3) the page lists as\n contact information [Randall]’s official County email address and the\n telephone number of [Randall]’s County office; (4) the page includes the\n web address of [Randall]’s official County website; (5) many—perhaps\n most—of the posts are expressly addressed to “Loudoun,” [Randall]’s\n constituents; (6) [Randall] has submitted posts on behalf of the [Loudoun\n Board] as a whole; (7) [Randall] has asked her constituents to use the\n [Chair‘s Facebook Page] as a channel for “back and forth constituent\n conversations”; and (8) the content posted has a strong tendency toward\n matters related to [Randall]’s office.\n\nDavison, 267 F. Supp. 3d at 714. A private citizen could not have created and used the\n\nChair’s Facebook Page in such a manner. Rossignol, 316 F.3d at 526. Put simply,\n\nRandall clothed the Chair’s Facebook Page in “the power and prestige of h[er] state\n\noffice,” Harris, 605 F.2d at 337, and created and administered the page to “perform[]\n\nactual or apparent dut[ies] of h[er] office,” Martinez, 54 F.3d at 986.\n\n Additionally, the specific actions giving rise to Davison’s claim—Randall’s\n\nbanning of Davison’s Virginia SGP Page—“are linked to events which arose out of h[er]\n\nofficial status.” Rossignol, 316 F.3d at 524. Randall’s post to the Chair’s Facebook Page\n\nthat prompted Davison’s comment informed the public about what happened at the\n\n\n\n 20\n\nLoudoun Board and Loudoun County School Board’s joint meeting. And Davison’s\n\ncomment also dealt with an issue related to that meeting and of significant public\n\ninterest—School Board members’ alleged conflicts of interest in approving financial\n\ntransactions. That Randall’s ban of Davison amounted to an effort “to suppress speech\n\ncritical of [such members’] conduct of [their] official duties or fitness for public office”\n\nfurther reinforces that the ban was taken under color of state law. Id. at 525. Considering\n\nthe totality of these circumstances, the district court correctly held that Randall acted\n\nunder color of state law in banning Davison from the Chair’s Facebook Page.\n\n C.\n\n Third, Randall argues that the district court erred in ruling in Davison’s favor on\n\nhis individual capacity First Amendment claim against Randall. Randall principally\n\nchallenges the district court’s conclusion that the Chair’s Facebook Page constitutes a\n\n“public forum” under traditional First Amendment law. We review this legal question de\n\nnovo. See Helton, 709 F.3d at 350.\n\n Under long-established First Amendment law, governmental entities are “strictly\n\nlimited” in their ability to regulate private speech in public fora. Pleasant Grove City,\n\nUtah v. Summum, 555 U.S. 460, 469 (2009). The Supreme Court has recognized two\n\ncategories of public fora: “traditional public forums” and “limited (or designated) public\n\nforums.” Am. Civil Liberties Union v. Mote, 423 F.3d 438, 443 (4th Cir. 2005).\n\n“Traditional” public forums—“such as streets, sidewalks, and parks”—“have the\n\ncharacteristics of a public thoroughfare, a purpose that is compatible with expressive\n\nconduct, as well as a tradition and history of being used for expressive public conduct.”\n\n\n 21\n\nId. “Limited” or “designated” forums are forums that are “not traditionally public, but\n\n[that] the government has purposefully opened to the public, or some segment of the\n\npublic, for expressive activity.” Id. Accordingly, the hallmark of both types of public\n\nfora—what renders the fora “public”—is that the government has made the space\n\navailable—either by designation or long-standing custom—for “expressive public\n\nconduct” or “expressive activity,” and the space is compatible with such activity. Id.\n\n“Conversely, a non-public forum is one that has not traditionally been open to the public,\n\nwhere opening it to expressive conduct would ‘somehow interfere with the objective use\n\nand purpose to which the property has been dedicated.’” Id. (quoting Warren v. Fairfax\n\nCty., 196 F.3d 186, 190–91 (4th Cir. 1999)).\n\n Although neither the Supreme Court nor any Circuit has squarely addressed\n\nwhether, and in what circumstances, a governmental social media page—like the Chair’s\n\nFacebook Page—constitutes a public forum, 3 aspects of the Chair’s Facebook Page bear\n\nthe hallmarks of a public forum. Randall “intentionally open[ed the public comment\n\nsection of the Chair’s Facebook Page] for public discourse,” Cornelius v. NAACP Legal\n\nDefense & Educ. Fund, Inc., 473 U.S. 788, 802 (1985), inviting “ANY Loudoun citizen”\n\n 3\n In addition to the court below, two other district courts have considered whether\na government official’s social media page constituted a public forum. Those courts\nreached conflicting results. Compare Morgan v. Bevin, 298 F. Supp. 3d 1003, 1010 (E.D.\nKy. 2018) (holding that First Amendment forum analysis did not apply to restrictions on\nspeech in the official Facebook and Twitter pages of the Governor of Kentucky), with\nKnight First Amend. Inst. at Colum. Univ. v. Trump, 302 F. Supp. 3d 541, 573 (S.D.N.Y.\n2018) (holding that the interactive component of the President’s Twitter account, as\nopposed to the President’s tweets themselves, constituted a designated public forum),\nappeal docketed, No. 18-1691 (2d Cir. Oct. 24, 2018).\n\n\n\n 22\n\nto make posts to the comments section of the Chair’s Facebook Page—the interactive\n\ncomponent of the page—“on ANY issues, request, criticism, complement or just your\n\nthoughts,” J.A. 455. Randall placed no restrictions on the public’s access to the page or\n\nuse of the interactive component of the Chair’s Facebook Page. And, in accordance with\n\nRandall’s invitation, the public made numerous posts on matters of public concern.\n\n The Chair’s Facebook Page also is “compatib[le] with expressive activity.”\n\nCornelius, 473 U.S. at 802. “Congress [has] recognized the internet and interactive\n\ncomputer services as offering ‘a forum for a true diversity of political discourse, unique\n\nopportunities for cultural development, and myriad avenues for intellectual activity.’”\n\nZeran v. Am. Online, Inc., 129 F.3d 327, 330 (4th Cir. 1997) (quoting 47 U.S.C. §\n\n230(a)(3)); cf. Bland, 730 F.3d at 386 (finding post to campaign Facebook page\n\n“constituted pure speech”). And the Supreme Court recently analogized social media\n\nsites, like the Chair’s Facebook Page, to “traditional” public forums, characterizing the\n\ninternet as “the most important place[] (in a spatial sense) for the exchange of views.”\n\nPackingham v. North Carolina, 137 S. Ct. 1730, 1735 (2017). An “exchange of views”\n\nis precisely what Randall sought—and what in fact transpired—when she expressly\n\ninvited “ANY Loudoun citizen” to visit the page and comment “on ANY issues,” and\n\nreceived numerous such posts and comments. J.A. 455.\n\n Randall nevertheless argues that traditional public forum analysis should not apply\n\nto the Chair’s Facebook Page for two reasons: (1) the Chair’s Facebook Page is “a private\n\nwebsite” and therefore does not constitute “public property” susceptible to forum\n\nanalysis, and (2) the Chair’s Facebook Page, in its entirety, constitutes “government\n\n\n 23\n\nspeech” properly analyzed under the framework set forth in Pleasant Grove. Randall’s\n\nBr. at 19–21, 29–31. We disagree.\n\n Even assuming the intangible space at issue is “private property,” as Randall\n\nclaims—which is not at all clear from the record before us 4—the Supreme Court never\n\nhas circumscribed forum analysis solely to government-owned property. For example, in\n\nCornelius, the Court recognized that forum analysis applies “to private property\n\ndedicated to public use.” Cornelius, 473 U.S. at 801 (emphasis added); see also\n\nChristian Legal Soc’y Chapter of the Univ. of Cal. v. Martinez, 561 U.S. 661, 679 (2010)\n\n(“[T]his Court has employed forum analysis to determine when a governmental entity, in\n\nregulating property in its charge, may place limitations on speech.” (emphasis added)).\n\n 4\n The Facebook “platform” and the “software” that underlies that platform is,\naccording to Facebook’s Terms of Service, property of Facebook, Inc. Terms of Service,\nFacebook, https://www.facebook.com/terms.php (last visited Jan. 4, 2019). Facebook’s\nTerms of Service further provide that users “own the content [they] create and share on\nFacebook and the other Facebook Products,” including Pages. Id. There would seem to\nbe a good argument, therefore, that content created, and posted to Facebook, by\ngovernment officials performing the functions and duties of their offices constitutes\ngovernment property. Cf. Solomons v. United States, 137 U.S. 342, 346–48 (1890)\n(holding that intellectual property created by government employee in the course of his\nofficial duties constituted government property because “[i]f one is employed to devise or\nperfect an instrument, or a means for accomplishing a prescribed result, he cannot, after\nsuccessfully accomplishing the work for which he was employed, plead title thereto as\nagainst his employer”). Likewise, under Facebook’s Terms of Service, the posts and\ncomments by individual Facebook users—like Davison—to a Facebook Page—like the\nChair’s Facebook Page—constitute property of those users. Accordingly, a single\nFacebook Page—including the Chair’s Facebook Page—encompasses a web of property\nrights, some of which may lie with the government. We need not—and thus do not—\ndecide with whom these property rights lie in this particular case, however, because we\nhold that even assuming the Chair’s Facebook Page constitutes private property, Randall,\nacting under color of state law, exercised control over the aspects of that page giving rise\nto Davison’s claim.\n\n\n\n 24\n\nAnd the Supreme Court and lower courts have held that private property, whether\n\ntangible or intangible, constituted a public forum when, for example, the government\n\nretained substantial control over the property under regulation or by contract. See, e.g.,\n\nSe. Promotions, Ltd. v. Conrad, 420 U.S. 546, 547, 555 (1975) (holding that “a privately\n\nowned Chattanooga theater under long-term lease to the city” was a “public forum[]\n\ndesigned for and dedicated to expressive activities”); Halleck v. Manhattan Community\n\nAccess Corp., 882 F.3d 300, 306–07 (2d Cir. 2018) (holding that public access television\n\nchannels operated by a private non-profit corporation constituted public forums), cert.\n\ngranted 139 S. Ct. 360 (2018) (mem.); First Unitarian Church of Salt Lake City v. Salt\n\nLake City Corp., 308 F.3d 1114, 1122 (10th Cir. 2002) (“[F]orum analysis does not\n\nrequire that the government have a possessory interest in or title to the underlying land.\n\nEither government ownership or regulation is sufficient for a First Amendment forum of\n\nsome kind to exist.”); Freedom from Religion Foundation, Inc. v. City of Marshfield,\n\nWis., 203 F.3d 487, 494 (7th Cir. 2000) (holding that private property abutted by public\n\npark constituted public forum).\n\n Significantly, even assuming the relevant aspects of the Chair’s Facebook Page\n\nconstitute private property—which, again, is not entirely clear from the record before\n\nus—Randall, acting under color of state law, retained and exercised significant control\n\nover the page. She created the Chair’s Facebook Page. She designated the page as\n\nbelonging to a “governmental official.” She clothed the page in the trappings of her\n\npublic office. She chose to list her official contact information on the page. And she\n\n\n\n\n 25\n\ncurated the links in the left column of the page and the lists of Facebook Pages or profiles\n\n“liked” by the Chair’s Facebook Page in the right column.\n\n Of particular importance, Randall had complete control over the aspect of the\n\nChair’s Facebook Page giving rise to Davison’s challenge because, as administrator of\n\nthe page, Randall had authority to ban Facebook profiles or Pages from using the Chair’s\n\nFacebook Page—and, therefore, the interactive component of the page—authority she\n\nexercised in banning Davison’s Virginia SGP Page. Cf. Knight, 302 F. Supp. 3d at 566–\n\n67 (holding that the interactive component of the President’s Twitter account constituted\n\npublic forum because the President and his advisors “exercise control over various\n\naspects of the . . . account,” including the power to block other users from accessing the\n\naccount).\n\n The Second Circuit’s decision in Halleck dealing with privately operated public\n\naccess television channels is instructive. Federal law allows cable franchising authorities\n\nto require cable operators to designate channel capacity for public use. Halleck, 882 F.3d\n\nat 302. Likewise, New York regulations oblige cable operators to designate at least one\n\nchannel for full-time public use. Id. Pursuant to that authority, the City of New York\n\nentered into a cable franchise agreement with a cable company requiring the company to\n\nmake available four public access channels, which channels were operated by a private,\n\nnon-profit corporation, MNN. Id. Several producers of public access programming sued\n\nMNN, alleging that MNN violated the producers’ First Amendment rights by indefinitely\n\nsuspending them from using the public access channels “because of disapproval of the\n\ncontent of a TV program” they had submitted for airing. Id.\n\n\n 26\n\n The Second Circuit concluded that the public access channels constituted a public\n\nforum, notwithstanding that they were operated by a private company. Id. at 306–08.\n\nThe court reached that conclusion for two reasons. First, it pointed to the similarities\n\nbetween public access channels and traditional public forums, like parks, describing “[a]\n\npublic access channel [a]s the electronic version of the public square.” Id. at 306.\n\nSecond, the court emphasized the extensive government involvement with, and control\n\nover, public access channels by virtue of the federal and state regulatory schemes. See id.\n\n(“[W]here, as here, federal law authorizes setting aside channels to be ‘the electronic\n\nmarketplace of ideas,’ state regulation requires cable operators to provide at least one\n\npublic access channel, a municipal contract requires a cable operator to provide four such\n\nchannels, and a municipal official has designated a private corporation to run those\n\nchannels, those channels are public forums.” (emphasis added)).\n\n Although not subject to the extensive federal and state regulatory regime\n\napplicable in Halleck, 5 the Chair’s Facebook Page is in many ways analogous to the\n\nprivately-operated public access channels considered by the Second Circuit. Just as the\n\nfederal government sought to establish an “electronic marketplace of ideas” by\n\nmandating provision of public access channels, Randall expressly sought to—and did, in\n\n\n 5\n The federal Communications Decency Act allows private online intermediaries,\nlike Facebook, the ability to moderate content by providing such intermediaries with\nbroad immunity from user-generated content posted on their sites. 47 U.S.C. § 230. This\nCourt has recognized that an “important purpose of § 230 was to encourage service\nproviders to self-regulate the dissemination of offensive material over their services.”\nZeran, 129 F.3d at 331.\n\n\n\n 27\n\nfact—create an “electronic marketplace of ideas” by inviting “ANY” constituent to post\n\nto the Chair Page on “ANY issues.” J.A. 455. Likewise, just as the City of New York\n\nchose to have a private corporation operate the public access channels, Randall chose to\n\ncreate her electronic marketplace of ideas, the Chair’s Facebook Page, on a private\n\nplatform, Facebook. Indeed, the present case provides a stronger basis for treating the\n\ninteractive component of the Chair’s Facebook Page as a public forum because whereas\n\nthe private corporation in Halleck, MNN, exercised control over the aspect of the public\n\naccess channel giving rise to the First Amendment claim—banning the public access\n\nprogram producer—a public official, Randall exercised unconstrained control over the\n\naspect of the Chair’s Facebook Page giving rise to Davison’s claim—banning of other\n\nFacebook profiles and Pages. 6\n\n\n 6\n On October 12, 2018, the Supreme Court granted MNN’s petition for writ of\ncertiorari in Halleck. 139 S. Ct. 360. MNN’s petition presented two questions: (1)\n“[w]hether the Second Circuit erred in rejecting th[e Supreme] Court’s state actor tests\nand instead creating a per se rule that private operators of public access channels are state\nactors subject to constitutional liability” and (2) “[w]hether the Second Circuit erred in\nholding—contrary to the Sixth and D.C. Circuits—that private entities operating public\naccess televisions stations are state actors for constitutional purposes where the state has\nno control over the private entity’s board or operations.” Petition for Writ of Certiorari i,\nManhattan Community Access Corp. v. Halleck, --- S. Ct. --- (No. 17-1702). MNN’s\nargument before the Supreme Court, therefore, focuses on the Second Circuit’s\ndetermination that MNN constituted a state actor, not the court’s determination that the\npublic access channels constituted a public forum.\n\n Although not identified as an issue on appeal, MNN’s petition also took issue with\nthe Second Circuit’s determination that the public access channels operated by MNN\nconstituted a public forum. But that contention was entirely derivative of its state action\nargument. In particular, MNN objected to the Second Circuit’s public forum conclusion\nonly because the public access channels were privately operated and because, in its\nopinion, the Second Circuit’s purportedly “categorical” holding that public access\n(Continued)\n\n 28\n\n Not only does case law contradict Randall’s argument that public forum analysis\n\nnever applies to private property, her argument also fails because it makes no legal sense\n\nto establish a bright-line rule that forum analysis applies only to government-owned\n\nproperty. Why, for example, should the First Amendment allow a municipality to engage\n\nin viewpoint discrimination in curating a public library branch in leased space but not\n\nallow the municipality to engage in such discrimination in a library branch on\n\nmunicipally owned property? Cf. Bd. of Educ., Island Trees Union Free Sch. Dist. No.\n\n26 v. Pico, 457 U.S. 853, 870–71 (1982) (plurality op.) (“If a Democratic school board,\n\nmotivated by partisan affiliation, ordered removal of all books written by or in favor of\n\nRepublicans, few would doubt that the order violated the constitutional rights of the\n\nstudents denied access to those books.”). Or why should a municipality be allowed to\n\nengage in viewpoint discrimination when holding a virtual public meeting hosted on a\n\nprivate website when such discrimination would be unconstitutional if the meeting was\n\nheld in a governmental building? Cf. Lyrissa Lidsky, Public Forum 2.0, 91 B.U. L. Rev.\n\n1975, 1996 (2011) (“Just as the government can rent a building to use as a forum for\n\npublic debate and discussion, so, too, can it ‘rent’ a social media page for the promotion\n\n\n\nchannels constitute public forums ignore[d] “the far more critical issue of whether (and to\nwhat extent) there is government control over a public access channel.” Id. at 19–20.\n\n Here, a government official acting under color of state law, Randall, exercised\nunconstrained control over the aspect of the Chair’s Facebook Page giving rise to\nDavison’s claim.\n\n\n\n\n 29\n\nof public discussion.”). We do not believe the First Amendment draws such arbitrary\n\nlines.\n\n Randall’s second argument—that the Chair’s Facebook Page amounts to\n\n“government speech”—fails to recognize the meaningful difference between Randall’s\n\nposts to the Chair’s Facebook Page and the public comments and posts she invited in the\n\npage’s interactive space. To be sure, Randall’s comments and curated references on the\n\nChair’s Facebook Page to other Pages, personal profiles, and websites amount to\n\ngovernmental speech. See Sutliffe v. Epping School Dist., 584 F.3d 314, 329–30 (1st Cir.\n\n2009) (holding that municipality’s refusal to place hyperlink on municipal website to\n\nwebsite of group opposed to municipal budget constituted government speech); Page v.\n\nLexington Cty. School Dist. One, 531 F.3d 275, 283–85 (4th Cir. 2008) (holding that\n\nSchool District’s refusal to place hyperlink on its website to website of group that\n\nopposed School District’s position on pending legislation constituted government speech\n\nbecause, in part, “the links to other websites were selected by the School District alone as\n\nones that supported its own message”); Knight, 302 F. Supp. 3d at 571 (“[T]he\n\nPresident’s tweets are [not] susceptible to forum analysis . . . because the content is\n\ngovernment speech.”).\n\n But the interactive component of the Chair’s Facebook Page—the portion of the\n\nmiddle column in which the public can post comments, reply to posts, and “like”\n\ncomments and posts—is materially different. See Knight, 302 F. Supp. 3d at 572\n\n(distinguishing a government official’s tweets and “the interactive space for replies and\n\nretweets”). Randall placed no formal limitations on the ability of Facebook personal\n\n\n 30\n\nprofiles and Pages to access the Chair’s Facebook Page and make comments and posts to\n\nthe interactive component of the page. On the contrary, she expressly invited posts to the\n\npage “from ANY Loudon citizen on ANY issues, request, criticism, complement or just\n\nyour thoughts.” J.A. 455. And comments and posts by users cannot be mistaken for\n\nRandall’s own speech because they identify the posting or replying personal profile or\n\nPage, and thereby distinguish that user from Randall.\n\n Contrary to Randall’s argument that the Chair’s Facebook Page, in its entirety,\n\namounts to government speech, the present case also is meaningfully distinguishable\n\nfrom the government speech framework identified in Pleasant Grove. There, a\n\nmunicipality denied a private religious group’s request to allow it to erect a “monument\n\nin a city park in which other donated monuments were previously erected,” including a\n\nmonument depicting a prominent symbol of a different religion. 555 U.S. at 464. The\n\nplaintiff religious group sought relief under the First Amendment, arguing that the city\n\npark constituted a traditional public forum, and therefore that the city could not reject the\n\nreligious group’s proposed monument when it had previously allowed construction of a\n\nmonument associated with another religion. Id. at 466.\n\n The Supreme Court held that the city did not violate the First Amendment because\n\nthe government speech framework, rather than forum analysis, applied to the conduct at\n\nissue. In reaching that conclusion, the Court emphasized that the city never “opened up\n\nthe Park for the placement of whatever permanent monuments might be offered by\n\nprivate donors.” Id. at 472–73. “Rather, the City has ‘effectively controlled’ the\n\nmessages sent by the monuments in the Park by exercising ‘final approval authority’ over\n\n\n 31\n\ntheir selection.” Id. at 473. The Court further emphasized that “[t]he forum doctrine has\n\nbeen applied in situations in which government-owned property or a government\n\nprogram was capable of accommodating a large number of public speakers without\n\ndefeating the essential function of the land or the program.” Id. at 478. A city park,\n\nhowever, “can accommodate only a limited number of permanent monuments,” and\n\ntherefore a municipality cannot—and need not—provide park space for all who wish to\n\nerect a monument. Id.\n\n Here, Randall “effectively controlled” certain aspects of the Chair’s Facebook\n\nPage: she curated the Chair’s Facebook Page’s left and right columns and made posts to\n\nthe middle column. Id. at 472. But Randall also expressly opened the Chair’s Facebook\n\nPage’s middle column—its interactive space—for “ANY” user to post on “ANY issues,”\n\nJ.A. 455, and therefore did not retain “final approval authority” over that aspect of the\n\nChair’s Facebook Page, Pleasant Grove, 555 U.S. at 473. Just as the parkland\n\nsurrounding monuments in Pleasant Grove continued to constitute a public forum, even\n\nthough the monuments themselves constituted government speech, so too the interactive\n\ncomponent of the Chair’s Facebook Page constitutes a public forum, even though\n\nRandall’s curation of and posts to the Chair’s Facebook Page amount to government\n\nspeech. Additionally, the interactive component of the Chair’s Facebook Page does not\n\nface the same spacial limitations as those of the park in Pleasant Grove, but instead is\n\n“capable of accommodating a large number of public speakers without defeating [its]\n\nessential function.” Id. at 578. Accordingly, Pleasant Grove supports, rather than\n\n\n\n\n 32\n\nundermines, our conclusion that the interactive component of the Chair’s Facebook Page\n\nconstitutes a public forum.\n\n Upon concluding that interactive component of the Chair’s Facebook Page\n\namounts to a public forum, we would normally need to determine whether it constitutes a\n\ntraditional public forum or designated or limited public forum. In the present case,\n\nhowever, we need not decide that question because Randall’s ban of Davison amounted\n\nto “viewpoint discrimination,” which is “prohibited in all forums.” See Child Evangelism\n\nFellowship of S.C. v. Anderson Sch. Dist. Five, 470 F.3d 1062, 1067 n.2 (4th Cir. 2006).\n\n“Viewpoint discrimination . . . ‘targets not subject matter, but particular views taken by\n\nspeakers on a subject.’” Id. (quoting Rosenberger v. Rector & Visitors of Univ. of Va.,\n\n515 U.S. 819, 829 (1995)). Viewpoint discrimination is apparent, for example, if a\n\ngovernment official’s decision to take a challenged action was “impermissibly motivated\n\nby a desire to suppress a particular point of view.” Cornelius, 473 U.S. at 812–13.\n\n Here, the district court found—as the record amply supports—that Randall banned\n\nDavison’s Virginia SGP Page because Davison posted a comment using that page\n\nalleging “corruption on the part of Loudoun County’s School Board involving conflicts\n\nof interests among the School Board and their family members.” Davison, 267 F. Supp.\n\n3d at 711. Although Randall stated that she had “no idea” whether Davison’s allegations\n\nwere “correct,” she nonetheless banned him because she viewed the allegations as\n\n“slanderous” and she “didn’t want [the allegations] on the site.” Id. at 717. Randall’s\n\ndecision to ban Davison because of his allegation of governmental corruption constitutes\n\nblack-letter viewpoint discrimination.\n\n\n 33\n\n Put simply, Randall unconstitutionally sought to “suppress” Davison’s opinion\n\nthat there was corruption on the School Board. Cornelius, 473 U.S. at 812–13; see also,\n\ne.g., Rossignol, 316 F.3d at 521 (holding that sheriff’s deputies engaged in viewpoint\n\ndiscrimination when they seized an issue of a newspaper that criticized the county\n\nsheriff’s and his deputies’ performance of their official duties); Putnam Pit, Inc. v. City of\n\nCookeville, Tenn., 221 F.3d 834, 846 (6th Cir. 2000) (holding that a municipality engages\n\nin viewpoint discrimination if it refuses to link newspaper webpage to the city’s website\n\nsolely because the newspaper sought to expose municipal corruption); Knight, 302 F.\n\nSupp. 3d at 575 (holding that the President engaged in viewpoint discrimination when he\n\nblocked individuals from his Twitter account because the individuals “posted tweets that\n\ncriticized the President or his policies”). 7 That Randall’s action targeted comments\n\ncritical of the School Board members’ official actions and fitness for office renders the\n\nbanning all the more problematic as such speech “occupies the core of the protection\n\nafforded by the First Amendment.” Rossignol, 316 F.3d at 521 (quoting McIntyre v.\n\nOhio Elections Comm’n, 514 U.S. 334, 346 (1995)).\n\n In sum, the interactive component of the Chair’s Facebook Page constituted a\n\npublic forum, and Randall engaged in unconstitutional viewpoint discrimination when\n\nshe banned Davison’s Virginia SGP Page from that forum.\n\n\n 7\n Randall also asserts that she did not violate Davison’s First Amendment rights\nbecause she banned his “Virginia SGP” Page, not his “Brian Davison” profile. Davison\nis the sole operator of the “Virginia SGP” Page, however, and therefore the ban\nimplicated his First Amendment rights. Randall fails to identify any case supporting her\nposition, nor have we found any. Accordingly, we reject this argument.\n\n\n 34\n\n III.\n\n In his cross-appeal, Davison asserts that the district court reversibly erred in two\n\nways: (A) by dismissing his claim against Randall in her official capacity and (B) by\n\ndenying his motion to amend his complaint to add the new First Amendment claim\n\nagainst the Loudoun Board. 8 We disagree.\n\n A.\n\n Davison first argues that the district court erred in dismissing his claim against\n\nRandall in her official capacity. Whereas “[p]ersonal-capacity suits seek to impose\n\npersonal liability upon a government official for actions [she] takes under color of state\n\nlaw,” Kentucky v. Graham, 473 U.S. 159, 165 (1985), “official capacity suits are ‘treated\n\nas suits against the municipality,’” Santos v. Frederick Cty. Bd. of Comm’rs, 725 F.3d\n\n451, 469 (4th Cir. 2013) (quoting Hafer v. Melo, 502 U.S. 21, 25 (1991)). Because\n\n“municipal liability under Section 1983 does not amount to respondeat superior . . . a\n\n 8\n Davison also argues that the district court erred in rejecting his procedural due\nprocess claims under the Fourteenth Amendment and an analogous provision in the\nVirginia Constitution. Before the district court, Davison “flatly asserted that due process\nalways requires the government to provide a hearing before imposing a prior restraint on\nspeech,” and therefore that Randall violated Davison’s First Amendment rights by failing\nto conduct a pre-ban hearing. Davison, 267 F. Supp. 3d at 719. The district court\ncorrectly rejected Davison’s proposed categorical rule. Id. (citing Cafeteria & Rest.\nWorkers Union Local 473, AFL-CIO v. McElroy, 367 U.S. 886, 895 (1961). And\nDavison has abandoned that asserted categorical rule on appeal, Davison’s Br. at 49–50\nn.19 (“[I]t might be permissible in certain contexts to delete an individual comment\nwithout providing full pre-deprivation process . . . .”), instead arguing he is entitled to\nrelief under the balancing test set forth in Mathews v. Eldridge, 424 U.S. 319, 334–35\n(1976). Because Davison did not make that argument before the district court, we decline\nto consider it now. See CoreTel Va., LLC v. Verizon Va., LLC, 808 F.3d 978, 988 (4th\nCir. 2015).\n\n\n\n 35\n\nmunicipality is subject to Section 1983 liability only when its ‘policy or custom, whether\n\nmade by its lawmakers or by those whose edicts or acts may fairly be said to represent\n\nofficial policy, inflicts the [plaintiff’s] injury.’” Id. at 469–70 (quoting Monell v. Dep’t of\n\nSoc. Servs. of the City of N.Y., 436 U.S. 658, 694 (1978)).\n\n Here, the district court dismissed Davison’s official capacity claim because it\n\nfound that “no policy—whether County-wide or specific to [Randall]’s office—played\n\nany role in [Randall]’s decision to ban [Davison] from her [Chair’s Facebook Page].”\n\nDavison, 267 F. Supp. 3d at 715. We review the district court’s factual findings bearing\n\non whether Randall acted pursuant to a municipal policy or custom for clear error and its\n\nlegal conclusions de novo. Helton, 709 F.3d at 350.\n\n On appeal, Davison does not dispute the district court’s finding—which the record\n\namply supports—that Loudoun County did not promulgate a policy governing individual\n\nLoudoun Board members’ Facebook pages. Rather, Davison principally 9 argues that “the\n\ncounty can be held liable for Randall’s actions because in banning Davison, Randall\n\nacted as a municipal policymaker.” Davison’s Br. at 47.\n\n\n\n\n 9\n Davison also argues the Loudoun Board’s failure to adopt a policy pertaining to\nindividual board members’ Facebook pages gives rise to an official capacity claim\nbecause it establishes that the Loudoun “Board was—and remains—deliberately\nindifferent to the likelihood of unconstitutional censorship and viewpoint-based\ndiscrimination on individual supervisors’ social media sites.” Davison’s Br. at 46. But\nDavison never advanced a “deliberate indifference” theory of municipal liability before\nthe district court. Again, we decline to consider an argument Davison raises for the first\ntime on appeal. See CoreTel, LLC, 808 F.3d at 988.\n\n\n\n 36\n\n Davison is correct that “municipal liability may be imposed for a single decision\n\nby municipal policymakers under appropriate circumstances.” Hunter v. Town of\n\nMocksville, N.C., 897 F.3d 538, 554 (4th Cir. 2018) (quoting Pembaur v. City of\n\nCincinnati, 475 U.S. 469, 480 (1986)). “[I]n assessing whether a municipality may be\n\nheld liable for constitutional or statutory violations of their decisionmakers, the\n\ntouchstone inquiry is whether ‘the decisionmaker possesses final authority to establish\n\nmunicipal policy with respect to the action ordered.’” Id. at 554–55 (emphasis added)\n\n(quoting Liverman v. City of Petersburg, 844 F.3d 400, 413 (4th Cir. 2016)).\n\n Here, Davison failed to put forward evidence establishing that Randall was a final\n\nmunicipal policymaker with regard to her banning of Davison from the Chair’s Facebook\n\nPage. On the contrary, record evidence establishes that the Loudoun Board retained\n\nauthority to establish municipal policy with respect to social media pages, as it adopted a\n\nsocial media policy governing the County’s official social media pages. Davison\n\nconcedes as much, arguing that the Loudoun Board “neglected . . . to extend its written\n\nguidelines to Board members’ official pages.” Davison’s Br. at 46. But that argument\n\npresupposes that the Loudoun Board—not Randall—had authority to establish municipal\n\npolicy with respect “to Board members’ official pages.”\n\n Davison nevertheless argues that the Loudoun Board “implicitly” delegated its\n\nfinal policymaking authority to Randall by not addressing individual Loudoun Board\n\nmembers’ official pages in its social media policy. Davison is correct that delegation of\n\nfinal policy making authority may be “implied from a continued course of knowing\n\nacquiescence by the governing body in the exercise of policymaking authority by an\n\n\n 37\n\nagency or official.” Id. at 48 (quoting Spell v. McDaniel, 824 F.2d 1380, 1387 (4th Cir.\n\n1987)). But Davison identifies no evidence that the Loudoun Board knew of the Chair’s\n\nFacebook Page, let alone that it “aquiesce[d]” in Randall’s administration of the page and\n\nbanning of Davison, in particular. On the contrary, the district court found that Randall\n\nmade a one-off, “unilateral decision to ban [Davison] in the heat of the moment, and\n\nreconsidered soon thereafter,” Davison, 267 F. Supp. 3d at 715—before the Loudoun\n\nBoard had a chance to learn of her action. In such circumstances, the district court did\n\nnot reversibly err in rejecting Davison’s official capacity claim.\n\n B.\n\n Next, Davison argues that the district court erred in denying him leave to amend\n\nhis complaint to add a claim that “the County violates the First Amendment by\n\nmaintaining a limited public forum on Facebook,” when policies imposed by Facebook,\n\nrather than the County, restrain, or have the potential to restrain, speech. J.A. 74. “A\n\ndistrict court may deny a motion to amend when the amendment would be prejudicial to\n\nthe opposing party, the moving party has acted in bad faith, or the amendment would be\n\nfutile.” Equal Rights Ctr. v. Niles Bolton Assocs., 602 F.3d 597, 603 (4th Cir. 2010).\n\nThe magistrate judge recommended—and the district court agreed—that Davison be\n\ndenied leave to amend on grounds of both futility and prejudice. We review for abuse of\n\ndiscretion a district court’s denial of leave to amend for prejudice, whereas we review de\n\nnovo a district court’s denial of leave to amend on the basis of futility. See U.S. ex rel.\n\nAhumada v. NISH, 756 F.3d 268, 274 (4th Cir. 2014).\n\n\n\n\n 38\n\n Regarding prejudice, the district court determined that the amendment came “too\n\nlate in these proceedings” and would “add a new, novel legal theory to the case after the\n\nclose of discovery, after the existing claims against [the Loudoun Board] have been\n\nshown to be meritless, after the point at which Defendants could have addressed the\n\nclaim in briefing before trial, and on the eve of trial.” J.A. 74. The district court did not\n\nabuse its discretion in denying leave to amend in such circumstances. See, e.g., Equal\n\nRights Ctr., 602 F.3d at 603–04 (holding that district court did not abuse its discretion in\n\ndenying leave to amend on the basis of prejudice when amendment came after the close\n\nof discovery and “on the eve of the deadline for dispositive motions” and therefore\n\n“would [have] change[d] the nature of the litigation”); Deasy v. Hill, 833 F.2d 38, 41 (4th\n\nCir. 1987) (affirming denial of leave to amend on grounds of prejudice when “the motion\n\nto amend came right before trial and after discovery was complete”).\n\n Although we affirm the district court’s judgment on the basis of its finding of\n\nprejudice, we do not concur in its conclusion as to futility. “Futility is apparent if the\n\nproposed amended complaint fails to state a claim under the applicable rules and\n\naccompanying standards.” Katyle v. Penn Nat. Gaming, Inc., 637 F.3d 462, 471 (4th Cir.\n\n2011). Accordingly, Davison’s proposed amendment was futile if the new claim would\n\nnot have survived a motion to dismiss under Federal Rule of Civil Procedure 12(b)(6).\n\nSee Runnion ex rel. Runnion v. Girl Scouts of Greater Chicago & Nw. Ind., 786 F.3d 510,\n\n524 (7th Cir. 2015) (“[W]hen the basis for denial is futility, we apply the legal\n\nsufficiency standard of Rule 12(b)(6) to determine whether the proposed amended\n\ncomplaint fails to state a claim.”).\n\n\n 39\n\n Davison’s proposed First Amendment claim deals not with the Chair’s Facebook\n\nPage—which the Loudoun Board did not authorize or attempt to regulate—but rather\n\nwith Loudoun County’s official Facebook Pages created and maintained pursuant to the\n\nLoudoun Board’s social media policy. As with his claims related to the Chair’s\n\nFacebook Page, Davison alleged that the Facebook Pages created and maintained by the\n\nLoudoun Board constituted public forums subject to the First Amendment. Davison\n\ntheorized that the Loudoun Board’s decision to use Facebook as its social media forum\n\nviolated his First Amendment rights because Facebook rules permit individual\n\n“requesting” users to ban other personal profiles and Pages such that the banned users can\n\nno longer see posts authored by the requesting users. In such circumstances, the banned\n\nusers “cannot see [the requesting user’s] comment[s] or participate in the discussion\n\nsurrounding the [requesting] party’s comment.” Davison’s Br. at 59. Davison’s\n\nproposed amended complaint asserted that “this scenario violates the First Amendment\n\nbecause Loudoun County has effectively enabled third parties to exclude discussion\n\nwithin a public forum—something a government body could not permissibly do in a\n\nphysical forum.” Id. at 59–60 (internal citation omitted). Put differently, Davison\n\ntheorized that Loudoun County violated the First Amendment by choosing to use\n\nFacebook as a public forum, when rules imposed by Facebook allow private users to\n\nrestrict access to their posts—and comments on and responses to those posts—including\n\nposts to any municipal Facebook Page.\n\n No court appears to have addressed that novel legal theory. And although the First\n\nAmendment constrains only government policies, not policies established by private\n\n\n 40\n\nentities, one can conceive of a colorable legal argument that a governmental actor’s\n\ndecision to select a private social media website for use as a public forum—and therefore\n\nselect that website’s suite of rules and regulations—could violate the First Amendment, if\n\nthe private website included certain types of exclusionary rules. For example, if the\n\ngovernment chose as its electronic public forum a social media site that allowed only\n\nregistered members of one political party to post and comment, there would seem to be a\n\ncompelling argument that the government’s selection of that social media site violated the\n\nFirst Amendment rights of members of other political parties, even if the partisan\n\nrestriction was imposed by the private company, not the governmental body. Such a\n\nrestriction would be seem to be no different than a municipality choosing to hold a town\n\nhall meeting in a venue that refused admission to individuals associated with a disfavored\n\npolitical party or viewpoint. Cf. DeBoer v. Village of Oak Park, 267 F.3d 558, 571 (7th\n\nCir. 2001) (“[T]he government engages in viewpoint discrimination when it denies access\n\nto a speaker solely to suppress the point of view he espouses on an otherwise includible\n\nsubject.”).\n\n Given that Davison’s proposed claim asserted a novel and colorable legal theory\n\nand that “Rule 12(b)(6) dismissals are especially disfavored in cases where the complaint\n\nsets forth a novel legal theory that can best be assessed after factual development,”\n\nWright v. North Carolina, 787 F.3d 256, 263 (4th Cir. 2015) (internal quotation marks\n\nomitted), we affirm the district court’s denial of Davison’s motion for leave to amend his\n\ncomplaint on the basis of its finding of prejudice but not on the basis of futility.\n\n IV.\n\n\n 41\n\nFor the foregoing reasons, we affirm the judgment of the district court.\n\n AFFIRMED\n\n\n\n\n 42\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Brian Davison v. Phyllis Randall\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-09\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-2002\\n\\n\\nBRIAN DAVISON,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nPHYLLIS RANDALL, In her official and individual capacity,\\n\\n Defendant - Appellant,\\n\\n and\\n\\nLOUDOUN COUNTY BOARD OF SUPERVISORS, In their official and\\nindividual capacities; LEO ROGERS, In his official capacity; TONY\\nBUFFINGTON, In his official capacity; RON MEYER, In his official capacity;\\nGEARY HIGGINS, In his official capacity,\\n\\n Defendants.\\n\\n------------------------------\\n\\nLOCAL GOVERNMENT ATTORNEYS OF VIRGINIA, INC.;\\nINTERNATIONAL MUNICIPAL LAWYERS ASSOCIATION; VIRGINIA\\nASSOCIATION OF COUNTIES; VIRGINIA MUNICIPAL LEAGUE,\\n\\n Amici Supporting Appellant,\\n\\nAMERICAN CIVIL LIBERTIES UNION; ACLU OF VIRGINIA; ACLU OF\\nMARYLAND; ACLU OF NORTH CAROLINA; ACLU OF SOUTH\\nCAROLINA; ACLU OF WEST VIRGINIA,\\n\\n Amici Supporting Appellee.\\n\\n No. 17-2003\\n\\n\\nBRIAN C. DAVISON,\\n\\n Plaintiff - Appellant,\\n\\n v.\\n\\nPHYLLIS RANDALL, In her official and individual capacity; LOUDOUN\\nCOUNTY BOARD OF SUPERVISORS, In their official and individual\\ncapacities,\\n\\n Defendants - Appellees,\\n\\n and\\n\\nLEO ROGERS, In his official capacity; TONY BUFFINGTON, In his official\\ncapacity; RON MEYER, In his official capacity; GEARY HIGGINS, In his\\nofficial capacity,\\n\\n Defendants.\\n\\n\\nAppeals from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. James C. Cacheris, Senior District Judge. (1:16-cv-00932-JCC-IDD)\\n\\n\\nArgued: September 26, 2018 Decided: January 7, 2019\\n Amended: January 9, 2019\\n\\n\\nBefore KEENAN, WYNN, and HARRIS, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Wynn wrote the opinion, in which Judge Keenan\\nand Judge Harris concurred. Judge Keenan wrote a separate concurring opinion.\\n\\n\\nARGUED: Scott E. Gant, BOIES SCHILLER FLEXNER, LLP, Washington, D.C.; Leo\\nP. Rogers, LOUDON COUNTY ATTORNEY, Leesburg, Virginia, for Appellant/Cross-\\n\\n\\n 2\\n\\nAppellee. Katherine A. Fallow, KNIGHT FIRST AMENDMENT INSTITUTE AT\\nCOLUMBIA UNIVERSITY, New York, New York, for Appellee/Cross-Appellant. ON\\nBRIEF: Aaron E. Nathan, BOIES SCHILLER FLEXNER LLP, Washington, D.C., for\\nAppellant/Cross-Appellee. Jameel Jaffer, Carrie DeCell, KNIGHT FIRST\\nAMENDMENT INSTITUTE AT COLUMBIA UNIVERSITY, New York, New York,\\nfor Appellee/Cross-Appellant. Vishal Agraharkar, AMERICAN CIVIL LIBERTIES\\nUNION FOUNDATION OF VIRGINIA, Richmond, Virginia; Esha Bhandari, Vera\\nEidelman, AMERICAN CIVIL LIBERTIES UNION FOUNDATION, New York, New\\nYork; Susan K. Dunn, ACLU OF SC FOUNDATION, INC., Charleston, South Carolina;\\nChristopher Brook, AMERICAN CIVIL LIBERTIES UNION OF NORTH CAROLINA\\nLEGAL FOUNDATION, Raleigh, North Carolina; Deborah A. Jeon, ACLU\\nFOUNDATION OF MARYLAND, Baltimore, Maryland; Jennifer D. Oliva, ACLU OF\\nWEST VIRGINIA FOUNDATION, Charleston, West Virginia, for Amici American\\nCivil Liberties Union, ACLU of Virginia, ACLU of Maryland, ACLU of North Carolina,\\nACLU of South Carolina, and ACLU of West Virginia. Joshua A. Geltzer, Douglas\\nLetter, Amy L. Marshak, Mary B. McCord, INSTITUTE FOR CONSTITUTIONAL\\nADVOCACY AND PROTECTION GEORGETOWN UNIVERSITY LAW CENTER,\\nWashington, D.C.; Kwaku A. Akowuah, Christopher C. Fonzone, Kate Heinzelman,\\nSIDLEY AUSTIN LLP, Washington, D.C., for Amici Curiae First Amendment Legal\\nScholars.\\n\\n\\n\\n\\n 3\\n\\nWYNN, Circuit Judge:\\n\\n Phyllis Randall, Chair of the Loudoun County, Virginia, Board of Supervisors (the\\n\\n“Loudoun Board”), brings this appeal, arguing that the district court erred in concluding\\n\\nthat she violated the First Amendment rights of one of her constituents, Brian Davison,\\n\\nwhen she banned Davison from the “Chair Phyllis J. Randall” Facebook page she\\n\\nadministered. In a cross appeal, Davison principally argues that the district court erred\\n\\nin dismissing his procedural due process claim premised on the ban. For the reasons that\\n\\nfollow, we affirm.\\n\\n I.\\n\\n A.\\n\\n Randall has chaired the Loudoun County Board of Supervisors since January 1,\\n\\n2016. The day before she was sworn in as chair, Randall created the “Chair Phyllis J.\\n\\nRandall” Facebook Page (the “Chair’s Facebook Page”). According to Facebook, Inc.,\\n\\nunlike personal Facebook profiles, which are for non-commercial use and represent\\n\\nindividual people, Facebook “Pages”—like the Chair’s Facebook Page—“help\\n\\nbusinesses, organizations, and brands share their stories and connect with people.” J.A.\\n\\n403. “Pages are managed by people who have personal profiles,” the company explains.\\n\\nJ.A. 403. In addition to the Chair’s Facebook Page, Randall created and maintained two\\n\\nother Facebook profiles: a personal profile and a Page devoted to her campaign. Randall\\n\\nclassified her campaign page as belonging to a “politician” and used no designation for\\n\\nher personal profile, but she designated the Chair’s Facebook Page as a “governmental\\n\\nofficial” page. J.A. 209–10.\\n\\n\\n 4\\n\\n Randall and her Chief of Staff, Jeanine Arnett, share administrative control over\\n\\nthe Chair’s Facebook Page, although Randall almost exclusively controls the page’s\\n\\ncontent. On her campaign page, Randall characterized the Chair’s Facebook Page as her\\n\\n“county Facebook page” stating:\\n\\n I really want to hear from ANY Loudoun citizen on ANY issues, request,\\n criticism, complement or just your thoughts. However, I really try to keep\\n back and forth conversations (as opposed to one time information items\\n such as road closures) on my county Facebook page (Chair Phyllis J.\\n Randall) or County email (Phyllis.randall@loudoun.gov). Having back and\\n forth constituent conversations are Foiable ([Freedom of Information Act])\\n so if you could reach out to me on these mediums that would be\\n appreciated.\\n\\nJ.A. 455 (emphasis added).\\n\\n The Chair’s Facebook Page includes three columns. The left column, which is\\n\\ntopped by a picture of Randall, includes several links to allow visitors to quickly navigate\\n\\nthe contents of the Chair’s Facebook Page.\\n\\n The middle column, which is organized in reverse chronological order similar to a\\n\\npersonal profile’s News Feed, is composed of posts by Randall and comments by\\n\\nFacebook users on those posts. Randall’s posts are almost always directed to “Loudoun,”\\n\\nsee, e.g., J.A. 408–10, and deal with numerous aspects of Randall’s official\\n\\nresponsibilities. For example, Randall used the Chair’s Facebook Page to notify the\\n\\npublic about upcoming Loudoun Board meetings, and the subjects to be discussed during\\n\\nthose meetings. Randall also used the page to inform Loudoun County residents about\\n\\nsignificant public safety issues. See, e.g., J.A. 412 (stating that Loudoun Board had\\n\\n“been informed by the Sheriff’s Office about the non-legitimate threat made on social\\n\\n\\n\\n 5\\n\\nmedia toward Dominion High School in Sterling”); J.A. 418 (reporting that she “ha[d]\\n\\nbeen briefed regarding the student falling from the water tower this morning” and\\n\\nadvising the public to “not make any assumptions but wait for information”). And\\n\\nRandall used the Chair’s Facebook Page to coordinate Loudoun County’s response to a\\n\\nlarge snow storm, including to communicate with constituents regarding which municipal\\n\\nstreets required plowing.\\n\\n Other posts by Randall to the Chair’s Facebook Page invited members of the\\n\\npublic to apply to participate on a public commission and to participate in public\\n\\nmeetings regarding key issues facing Loudoun County residents, such as revised flood\\n\\nplain zones and the Zika virus. Randall also authored posts regarding a variety of trips\\n\\nand meetings she had taken in furtherance of Loudoun County business. E.g., J.A. 408\\n\\n(reporting that Randall “address[ed] the (county) role in Treatment” at a “regional\\n\\nconference on Opioid and Substance Abuse Addiction”); J.A. 410 (stating that Randall\\n\\nrepresented Loudoun County at its “annual credit rating presentation” in New York); J.A.\\n\\n415 (informing public of trip to Loudoun’s “Sister City” in Germany); J.A. 426\\n\\n(reporting that Randall was “in Richmond lobbying for [Loudoun County’s] legislative\\n\\nprogram”). Finally, Randall used the page to advise the public regarding official actions\\n\\ntaken by the Loudoun Board. E.g., J.A. 433 (reporting that Loudoun Board “approved\\n\\nfunding for new breathing apparatus for our Loudoun Firefighters”); J.A. 442 (listing\\n\\nseveral “proclamations of note” by the Loudoun Board); J.A. 443 (informing public that\\n\\nLoudoun Board “adopted a budget for Fiscal Year 2017 totaling $2.46 billion for the\\n\\ngeneral county government and schools”). Although Randall’s posts on the Chair’s\\n\\n\\n 6\\n\\nFacebook Page principally addressed her official responsibilities, a few posts addressed\\n\\ntopics less closely related to her official activities such as her affection for the German\\n\\nlanguage or pride in becoming an organ donor.\\n\\n Members of the public, including Davison, “liked” 1 or commented on several of\\n\\nRandall’s posts on the Chair’s Facebook Page. Each “like” or comment identified the\\n\\nname of the personal profile or Page of the authoring party. Many of the comments\\n\\nthanked Randall and the Loudoun Board for representing the public’s interests. Other\\n\\nposts by members of the public offered feedback on various issues faced by Randall and\\n\\nthe Loudoun Board. E.g., J.A. 427 (stating that “[p]utting recreation in a flood plain is\\n\\nnot a good idea”); J.A. 448 (stating that “more needs to be done with the explosion of\\n\\nLyme disease in Loudoun”). And other comments dealt with constituent-specific issues.\\n\\nE.g., J.A. 415 (constituent stating, in response to post by Randall regarding visit to\\n\\nLoudoun County’s “Sister City” in Germany, that constituent’s “daughter is interested in\\n\\nexchange programs”); J.A. 454 (stating that “there [we]re no [snow] plows to be seen” in\\n\\na particular neighborhood). Finally, several comments, including a number authored by\\n\\nDavison, criticized the Loudoun Board, generally, and Randall, in particular, for actions\\n\\ntaken in their official capacities. E.g., J.A. 429–30 (Davison criticizing public school\\n\\nsystem budget and expenditures); J.A. 438–39 (member of public criticizing\\n\\ngovernmental entity’s inspection of farm, claiming it failed to uncover animal abuse);\\n\\n\\n 1\\n “‘Liking’ on Facebook is a way for Facebook users to share information with\\neach other.” Bland v. Roberts, 730 F.3d 368, 385 (4th Cir. 2013).\\n\\n\\n\\n 7\\n\\nJ.A. 449 (Davison characterizing question he posed at Loudoun Board and Loudoun\\n\\nSchool Board joint town hall). On some occasions, Randall responded to these\\n\\ncomments or criticisms.\\n\\n In the right column of the Chair’s Facebook Page, the page is identified as a\\n\\n“government official” page. It provides contact information for Randall’s county office,\\n\\nincluding her office telephone number, Randall’s official county email address, and the\\n\\ninternet address for the official county website. The column also identifies how many\\n\\nand which Facebook personal profiles and Pages “like” and “follow” the Chair’s\\n\\nFacebook Page. 2 And the column includes a list of personal profiles and Pages “liked”\\n\\nby the Chair’s Facebook Page.\\n\\n Randall publicized the Chair’s Facebook Page in her official “Chair Phyllis J.\\n\\nRandall” newsletter, which is prepared by County employees, hosted on the County’s\\n\\nwebsite, and distributed to Loudoun citizens using Randall’s official county email\\n\\naccount. The newsletter ends with the words “STAY CONNECTED” and a Facebook\\n\\nicon that hyperlinks to the Chair’s Facebook Page. Randall also highlighted the Chair’s\\n\\nFacebook Page in “Winter Storm Information” notices emailed from her official county\\n\\naccount to Loudoun County residents, advising recipients to “Visit [the Chair’s Facebook\\n\\nPage] for Updates.” J.A. 341–42, 344.\\n\\n 2\\n According to Facebook, “[l]iking a Facebook Page means you are connecting to\\nthat Page. When you connect to a Page, it will appear in [a user’s] timeline and [the user]\\nwill appear on the page as a person who likes that Page. The Page will also be able to\\npost content into [the user’s] News Feed.” Bland, 730 F.3d at 385 (internal quotation\\nmarks omitted).\\n\\n\\n\\n 8\\n\\n Davison, an outspoken resident of Loudoun County, apparently largely focuses his\\n\\ncivic engagement and expression on “the funding and . . . management of public\\n\\nschools.” J.A. 95. To that end, he has repeatedly expressed concern about “School Board\\n\\nmembers failing to disclose personal conflicts as required by law before voting on\\n\\nfinancial transactions before the School Board.” J.A. 96.\\n\\n On February 3, 2016, Davison attended a Loudoun town hall meeting that\\n\\nincluded the Loudoun County School Board and Randall. At the meeting, Davison\\n\\nsubmitted a question implying that certain School Board members had acted unethically\\n\\nin approving financial transactions. Randall volunteered to answer the question but\\n\\ncharacterized it as a “set-up question” that she did not “appreciate.” J.A. 103. Shortly\\n\\nafter Randall answered the question—and while the town hall meeting was still\\n\\nongoing—Davison posted a message on Twitter in which he tagged Randall:\\n\\n“@ChairRandall ‘set up question’? You might want to strictly follow FOIA and the\\n\\nCOIA as well.” J.A. 470–71.\\n\\n Later that evening, Randall posted about the town hall meeting on the Chair’s\\n\\nFacebook Page, describing “what was generally discussed at the meeting.” J.A. 268. In\\n\\nresponse, Davison then used one of the Facebook Pages he manages through his personal\\n\\nFacebook profile—“Virginia SGP,” which Davison frequently uses to post political\\n\\ncommentary—to comment on Randall’s post about the town hall meeting. Although\\n\\nneither Davison nor Randall remember the precise content of Davison’s comment,\\n\\nRandall testified that it contained “accusations” regarding School Board members’ and\\n\\ntheir families’ putative conflicts of interest related to municipal financial transactions,\\n\\n\\n 9\\n\\nsuggesting, in Randall’s opinion, that School Board members had been “taking kickback\\n\\nmoney.” See J.A. 268–69, 289–90. Randall stated that she “had no idea if any of th[e]\\n\\n[accusations] w[ere] correct,” but she determined that the post was “probably not\\n\\nsomething [she] want[ed] to leave” on the Chair’s Facebook Page. J.A. 269. Randall\\n\\nthen “deleted the whole post,” including her original post regarding the town hall\\n\\nmeeting, Davison’s comment and replies thereto, and all other public comments. J.A.\\n\\n269. Randall also banned Davison’s Virginia SGP Page from the Chair’s Facebook Page,\\n\\nwhich precluded Davison from using his Virginia SGP Page from commenting on the\\n\\nChair’s Facebook Page. The next morning, about twelve hours later, Randall\\n\\nreconsidered her actions and unbanned Davison’s Virginia SGP Page.\\n\\n B.\\n\\n On November 3, 2016, Davison filed an amended complaint seeking declaratory\\n\\nand injunctive relief under 42 U.S.C. § 1983 against Randall, in both her official and\\n\\nindividual capacities, and the Loudoun Board alleging that the “banning of [Davison]\\n\\nfrom commenting on [the Chair’s Facebook Page] is viewpoint discrimination.” J.A. 31.\\n\\nDavison further alleged that the ban violated his procedural due process rights protected\\n\\nby the Fourteenth Amendment because “Randall blocked Davison’s constitutionally\\n\\nprotected speech on [the Chair’s Facebook Page], a limited public forum, without prior\\n\\nnotice and without providing an opportunity for appealing [her] decision.” J.A. 32.\\n\\nDavison did not challenge Randall’s deletion of his post.\\n\\n On March 6, 2017—four days before the close of discovery and approximately\\n\\ntwo months before trial—Davison moved for leave to amend his complaint a second time\\n\\n\\n 10\\n\\nto add claims under the Virginia Constitution that were materially indistinguishable from\\n\\nhis previously asserted First and Fourteenth Amendment claims premised on the ban, as\\n\\nwell as a separate First Amendment claim against the Loudoun Board. Davison’s\\n\\nproposed new First Amendment claim theorized that the County violated his free speech\\n\\nrights by choosing to use Facebook Pages as public forums, when Facebook allows\\n\\nprivate users to restrict access to their posts, including posts to any Page a municipality\\n\\ndesignates as a limited public forum. Pl.’s Mem. in Supp. of Mot. for Leave to File\\n\\nSecond Am. Compl. 3–9, Davison v. Loudoun County Bd. of Supervisors, 16-cv-932-\\n\\nJCC-IDD, ECF No. 68. The district court referred the motion to a magistrate judge, who\\n\\ngranted leave to amend regarding the claims under the Virginia Constitution but denied\\n\\nleave as to the new First Amendment claim against the Loudoun Board. Davison lodged\\n\\nobjections to the magistrate judge’s partial denial of leave to amend, which objections the\\n\\ndistrict court overruled.\\n\\n Around the same time, Randall and the Loudoun Board each moved for summary\\n\\njudgment. The Loudoun Board asserted that the municipality could not be held liable for\\n\\nRandall’s banning of Davison from the Chair’s Facebook Page because the Chair’s\\n\\nFacebook Page was not an official municipal page and because Randall, not the Loudoun\\n\\nBoard as a body, was solely responsible for creating and administering the Chair’s\\n\\nFacebook Page. The Loudoun Board and Randall further asserted that the Chair’s\\n\\nFacebook Page did not amount to a public forum, and therefore Randall’s ban of\\n\\nDavison’s Virginia SGP Page did not implicate his free speech or procedural due process\\n\\nrights. Finally, Randall asserted that she was entitled to qualified immunity.\\n\\n\\n 11\\n\\n On May 10, 2017, the district court granted summary judgment in favor of the\\n\\nLoudoun Board, dismissing it from the suit. But as to Randall, the district court\\n\\nconcluded that Davison’s evidence established a material dispute of fact as to whether the\\n\\nChair’s Facebook Page amounted to a limited public forum and whether Randall, in her\\n\\nindividual capacity, acted under color of state law in banning Davison from the Chair’s\\n\\nFacebook Page. Davison v. Loudoun Cty. Bd. of Supervisors, No. 1:16-cv-932, 2017 WL\\n\\n1929406, at *6–9 (E.D. Va. May 10, 2017). The district court also rejected Randall’s\\n\\nqualified immunity argument. Id. at *8.\\n\\n Following a one-day bench trial of Davison’s claims against Randall, the district\\n\\ncourt issued a memorandum opinion and order awarding judgment in Davison’s favor on\\n\\nhis claims under the First Amendment and the analogous free speech provision in the\\n\\nVirginia Constitution. See Davison v. Loudoun Cty. Bd. of Supervisors, 267 F. Supp. 3d\\n\\n702, 714–18 (E.D. Va. 2017). The district court further entered judgment in Randall’s\\n\\nfavor on Davison’s federal and state procedural due process claims. Id. at 719–22. As to\\n\\nremedy, the district court denied Davison’s request for injunctive relief but granted\\n\\nDavison’s request for a declaratory judgment to resolve the “uncertainty regarding the\\n\\nlegal status of [the Chair’s Facebook Page].” Id. at 723.\\n\\n Randall and Davison, respectively, filed this appeal and cross appeal.\\n\\n II.\\n\\n On appeal, Randall argues that (A) Davison failed to establish standing to obtain\\n\\nprospective declaratory relief based on Randall’s alleged First Amendment violation; (B)\\n\\nthe district court erred in concluding that Randall acted under “color of state law” when\\n\\n\\n 12\\n\\nshe banned Davison’s Virginia SGP Page from the Chair’s Facebook Page; and (C) the\\n\\ndistrict court erred in concluding that Randall’s banning of Davison’s Virginia SGP Page\\n\\nviolated the First Amendment.\\n\\n A.\\n\\n Notwithstanding that she did not challenge Davison’s standing below—and\\n\\ntherefore that the district court never squarely addressed his standing—Randall now\\n\\nargues that Davison failed to establish Article III standing to support the district court’s\\n\\naward of prospective declaratory relief. Even though Defendants did not challenge\\n\\nDavison’s standing below, “standing to sue is a jurisdictional issue of constitutional\\n\\ndimensions, and it may be raised and addressed for the first time on appeal.” Hodges v.\\n\\nAbraham, 300 F.3d 432, 443 (4th Cir. 2002). This Court reviews de novo “whether a\\n\\ndistrict court possessed jurisdiction in a declaratory judgment proceeding.” Volvo Const.\\n\\nEquip. N. Am., Inc. v. CLM Equip. Co., Inc., 386 F.3d 581, 591 (4th Cir. 2004).\\n\\n To establish Article III standing, a plaintiff must prove that: “1) he or she suffered\\n\\nan ‘injury in fact’ that is concrete and particularized, and is actual or imminent; 2) the\\n\\ninjury is fairly traceable to the challenged action of the defendant; and 3) the injury likely\\n\\nwill be redressed by a favorable decision.” Friends of the Earth, Inc. v. Gaston Copper\\n\\nRecycling Corp., 629 F.3d 387, 396 (4th Cir. 2011). Randall does not dispute that any\\n\\ninjury Davison suffered is fairly traceable to her decision to ban him from the Chair’s\\n\\nFacebook Page. Nor does Randall dispute that any such injury would be remedied by a\\n\\nfavorable decision. Rather, Randall claims that Davison failed to adduce evidence\\n\\n\\n\\n\\n 13\\n\\nestablishing that he suffered an “injury in fact” sufficient to support prospective\\n\\ndeclaratory relief.\\n\\n “Injury in fact is ‘an invasion of a legally protected interest’ that is ‘concrete and\\n\\nparticularized’ and ‘actual or imminent, not conjectural or hypothetical.’” Kenny v.\\n\\nWilson, 885 F.3d 280, 287 (4th Cir. 2018) (quoting Spokeo, Inc. v. Robins, 136 S. Ct.\\n\\n1540, 1548 (2016)). Because “‘[p]ast exposure to illegal conduct does not in itself show\\n\\na present case or controversy regarding injunctive relief . . . if unaccompanied by any\\n\\ncontinuing, present adverse effects,’” a plaintiff seeking “declaratory or injunctive relief .\\n\\n. . must establish an ongoing or future injury in fact.” Id. at 287–88 (quoting O’Shea v.\\n\\nLittleton, 414 U.S. 488, 495–96 (1974)). Significantly, this Court—along with several\\n\\nother circuits—has held that “standing requirements are somewhat relaxed in First\\n\\nAmendment cases,” particularly regarding the injury-in-fact requirement. Cooksey v.\\n\\nFutrell, 721 F.3d 226, 235 (4th Cir. 2013) (collecting cases).\\n\\n In Kenny v. Wilson, 885 F.3d 280 (4th Cir. 2018), this Court addressed what\\n\\nevidence a plaintiff seeking relief under the First Amendment, like Davison, must put\\n\\nforward to establish a future injury-in-fact adequate to confer Article III standing to\\n\\nobtain prospective declaratory relief. In Kenny, several high school students lodged First\\n\\nAmendment challenges to two South Carolina disorderly conduct statutes. Id. at 284.\\n\\nThis Court explained that “there is a sufficiently imminent injury in fact if plaintiffs\\n\\nallege [1] ‘an intention to engage in a course of conduct arguably affected with a\\n\\nconstitutional interest, but proscribed by a statute, and [2] there exists a credible threat of\\n\\nprosecution thereunder.’” Id. at 288 (quoting Babbitt v. Farm Workers Nat’l Union, 442\\n\\n\\n 14\\n\\nU.S. 289, 298 (1979)). The Kenny plaintiffs satisfied the first prong because they “attend\\n\\nschool” and “attending school inevitably involves expressive conduct” that implicates the\\n\\ndisorderly conduct statutes. Id. As to the second element—whether the students alleged\\n\\na “credible threat of future enforcement”—we held that such a threat exists so long as it\\n\\n“is not imaginary or wholly speculative, chimerical, or wholly conjectural.” Id. (internal\\n\\nquotation marks, citations, and alterations omitted). “[P]ast enforcement against the same\\n\\nconduct is good evidence that the threat of enforcement is not chimerical.” Id. (quoting\\n\\nSusan B. Anthony List v. Driehaus, 134 S. Ct. 2334, 2345 (2014)). “Threat of\\n\\nprosecution is especially credible when defendants have not ‘disavowed enforcement’ if\\n\\nplaintiffs engage in similar conduct in the future.” Id. (quoting Driehaus, 134 S. Ct. at\\n\\n2345). Applying this standard, we held that the plaintiffs alleged a credible threat of\\n\\nenforcement “because these three plaintiffs regularly attend schools where they allege\\n\\nthere may be future encounters with school resource officers or other law enforcement;\\n\\nthey have been prosecuted under the laws in the past; and the defendants have not\\n\\ndisavowed enforcement if plaintiffs engage in similar conduct in the future.” Id. at 289.\\n\\n Under Kenny, Davison’s evidence established his standing to obtain prospective\\n\\ndeclaratory relief. Relevant to the first prong—whether Davison intends to engage in a\\n\\ncourse of conduct “arguably” impacted by the challenged conduct, Babbitt, 442 U.S. at\\n\\n298—the district court found, in awarding Davison declaratory relief, that he “continues\\n\\nto avail himself” of the Chair’s Facebook Page and that Davison is “active in local\\n\\npolitics, and has a particular interest in what he believes to be corruption on the part of\\n\\nLoudoun County’s school board.” Davison, 267 F. Supp. 3d at 707, 723. Accordingly,\\n\\n\\n 15\\n\\nthe evidence establishes that Davison continues to engage in a course of conduct—\\n\\nnamely, posting about alleged municipal corruption on the Chair’s Facebook Page—\\n\\nlikely to be impacted by Randall’s allegedly unconstitutional approach to managing the\\n\\npage.\\n\\n Turning to the second prong—whether there is a credible threat of enforcement—\\n\\nRandall previously blocked Davison from the Chair’s Facebook Page based on the\\n\\ncontent of his posts, providing “good evidence that the threat of enforcement is not\\n\\nchimerical.” Driehaus, 134 S. Ct. at 2345 (internal quotation marks omitted).\\n\\nAdditionally, Randall testified that she continues to believe she can ban Davison and\\n\\nothers from the Chair’s Facebook Page based on their views without triggering the First\\n\\nAmendment at all. See J.A. 277 (Randall stating she would “be happy to” ban other\\n\\ncommenters on her “Chair’s Facebook” page); J.A. 250 (Randall testifying that\\n\\ncomments “attacking another person” would not be allowed on her “Chair’s Facebook”\\n\\npage). To that end, in awarding Davison declaratory relief, the district court found that\\n\\nRandall “maintains she is permitted to administer this Facebook page as a purely personal\\n\\npage.” Davison, 267 F. Supp. 3d at 723. Accordingly, Davison established that he has\\n\\nbeen subject to past enforcement and that Randall has not “disavowed” future\\n\\nenforcement, which, under Kenny, is sufficient to establish a credible threat of\\n\\nenforcement. Cf. City of Lakewood v. Plain Dealer Pub. Co., 486 U.S. 750, 757 (1988)\\n\\n(“[T]he mere existence of the licensor’s unfettered discretion, coupled with the power of\\n\\nprior restraint, intimidates parties into censoring their own speech, even if the discretion\\n\\nand power are never actually abused.”).\\n\\n\\n 16\\n\\n In sum, Davison’s evidence demonstrated—and the district court found—that\\n\\nDavison intends to continue to use the Chair’s Facebook Page and that Davison faces a\\n\\ncredible threat of future enforcement. See Davison, 267 F. Supp. 3d at 723.\\n\\nAccordingly, Davison adduced facts establishing an injury in fact sufficient to justify the\\n\\nprospective declaratory relief awarded by the district court.\\n\\n B.\\n\\n Next, Randall asserts that the district court erred in concluding, with regard to\\n\\nDavison’s individual capacity First Amendment claim, that Randall acted “under color of\\n\\nstate law,” as that phrase is used in Section 1983, in administering the Chair’s Facebook\\n\\nPage and banning Davison from that page. “This Court reviews judgments stemming\\n\\nfrom a bench trial under a mixed standard: factual findings are reviewed for clear error,\\n\\nwhereas conclusions of law are reviewed de novo.” Helton v. AT&T Inc., 709 F.3d 343,\\n\\n350 (4th Cir. 2013). Whether, under the undisputed facts, Randall acted under color of\\n\\nstate law is a legal question this Court reviews de novo. Rossignol v. Voorhaar, 316 F.3d\\n\\n516, 523 (4th Cir. 2003).\\n\\n To state a claim under Section 1983, a plaintiff must show that the alleged\\n\\nconstitutional deprivation at issue occurred because of action taken by the defendant\\n\\n“under color of . . . state law.” Philips v. Pitt Cty. Mem’l Hosp., 572 F.3d 176, 180 (4th\\n\\nCir. 2009). “The traditional definition of acting under color of state law requires that the\\n\\ndefendant in a § 1983 action have exercised power ‘possessed by virtue of state law and\\n\\nmade possible only because the wrongdoer is clothed with the authority of state law.’”\\n\\nWest v. Atkins, 487 U.S. 42, 49 (1988) (quoting United States v. Classic, 313 U.S. 299,\\n\\n\\n 17\\n\\n326 (1941)). Section 1983’s “color-of-law prerequisite is synonymous with the more\\n\\nfamiliar state-action requirement” applicable to Fourteenth Amendment claims, “and the\\n\\nanalysis for each is identical.” Pitt Cty. Mem’l Hosp., 572 F.3d at 180. Both inquiries\\n\\ndemand that “the conduct allegedly causing the deprivation of a federal right be fairly\\n\\nattributable to the State.” Holly v. Scott, 434 F.3d 287, 292 (4th Cir. 2006) (quoting\\n\\nLugar v. Edmondson Oil Co., Inc., 457 U.S. 922, 937 (1982)).\\n\\n “[T]here is no specific formula for determining whether state action is present.”\\n\\nId. at 292 (internal quotation marks omitted). Rather, “[w]hat is fairly attributable [to the\\n\\nstate]”—i.e., what constitutes action under color of state law—“is a matter of normative\\n\\njudgment, and the criteria lack rigid simplicity.” Id. (internal quotation marks omitted).\\n\\nCourts must examine the “totality of the circumstances,” id. (internal quotation marks\\n\\nomitted), to determine if the action at issue “bore a ‘sufficiently close nexus’ with the\\n\\nState to be ‘fairly treated as that of the State itself,’” Rossignol, 316 F.3d at 525 (quoting\\n\\nJackson v. Metro. Edison Co., 419 U.S. 345, 351 (1974)).\\n\\n Although no one factor is determinative, this Court has held that a defendant’s\\n\\npurportedly private actions bear a “sufficiently close nexus” with the State to satisfy\\n\\nSection 1983’s color-of-law requirement when the defendant’s challenged “actions are\\n\\nlinked to events which arose out of his official status.” Id. at 524. When a defendant’s\\n\\n“status” as a public official “enabled [her] to execute [a challenged action] in a manner\\n\\nthat private citizens never could have,” then the action also is more likely to be treated as\\n\\nattributable to the state. Id. at 526; see also Martinez v. Colon, 54 F.3d 980, 986 (1st Cir.\\n\\n1995) (“[S]ection 1983 is . . . implicated . . . [when] the conduct is such that the actor\\n\\n\\n 18\\n\\ncould not have behaved in that way but for the authority of his office.”); Goldstein v.\\n\\nChestnut Ridge Volunteer Fire Co., 218 F.3d 337, 343 (4th Cir. 2000) (holding that\\n\\nchallenged conduct is more likely to amount to state action when “the injury caused is\\n\\naggravated in a unique way by the incidents of governmental authority” (internal\\n\\nquotation marks omitted)). Likewise, an official’s conduct is more likely to amount to\\n\\nstate action when it “occurs in the course of performing an actual or apparent duty of his\\n\\noffice.” Martinez, 54 F.3d at 986. And the challenged action of a defendant\\n\\ngovernmental official is likely to be treated as taken under color of law when the official\\n\\n“use[d] the power and prestige of his state office to damage the plaintiff.” Harris v.\\n\\nHarvey, 605 F.2d 330, 337 (7th Cir. 1979). In the context of an alleged First Amendment\\n\\nviolation, in particular, this Court has found that a challenged action by a governmental\\n\\nofficial is fairly attributable to the state when “the sole intention” of the official in taking\\n\\nthe action was “to suppress speech critical of his conduct of official duties or fitness for\\n\\npublic office.” Rossignol, 316 F.3d at 524.\\n\\n Here, after thoroughly analyzing the totality of the circumstances surrounding\\n\\nRandall’s creation and administration of the Chair’s Facebook Page and banning of\\n\\nDavison from that page, the district court concluded that Randall acted under color of\\n\\nstate law. Davison, 267 F. Supp. 3d at 723. We agree.\\n\\n Randall created and administered the Chair’s Facebook Page to further her duties\\n\\nas a municipal official. She used the Chair’s Facebook Page “as a tool of governance,”\\n\\nid. at 713: through the Chair’s Facebook Page, Randall provides information to the public\\n\\n\\n\\n\\n 19\\n\\nabout her and the Loudoun Board’s official activities and solicits input from the public on\\n\\npolicy issues she and the Loudoun Board confront. See supra Part I.A.\\n\\n For instance, Randall used the Chair’s Facebook Page to inform the public about\\n\\nserious public safety events and to keep her constituents abreast of the County’s response\\n\\nto a snowstorm and to coordinate snow removal activities. And, as the district court\\n\\ncorrectly emphasized, Randall\\n\\n swathe[d] the [Chair’s Facebook Page] in the trappings of her office.\\n Among other things, (1) the title of the page includes [Randall]’s title; (2)\\n the page is categorized as that of a government official; (3) the page lists as\\n contact information [Randall]’s official County email address and the\\n telephone number of [Randall]’s County office; (4) the page includes the\\n web address of [Randall]’s official County website; (5) many—perhaps\\n most—of the posts are expressly addressed to “Loudoun,” [Randall]’s\\n constituents; (6) [Randall] has submitted posts on behalf of the [Loudoun\\n Board] as a whole; (7) [Randall] has asked her constituents to use the\\n [Chair‘s Facebook Page] as a channel for “back and forth constituent\\n conversations”; and (8) the content posted has a strong tendency toward\\n matters related to [Randall]’s office.\\n\\nDavison, 267 F. Supp. 3d at 714. A private citizen could not have created and used the\\n\\nChair’s Facebook Page in such a manner. Rossignol, 316 F.3d at 526. Put simply,\\n\\nRandall clothed the Chair’s Facebook Page in “the power and prestige of h[er] state\\n\\noffice,” Harris, 605 F.2d at 337, and created and administered the page to “perform[]\\n\\nactual or apparent dut[ies] of h[er] office,” Martinez, 54 F.3d at 986.\\n\\n Additionally, the specific actions giving rise to Davison’s claim—Randall’s\\n\\nbanning of Davison’s Virginia SGP Page—“are linked to events which arose out of h[er]\\n\\nofficial status.” Rossignol, 316 F.3d at 524. Randall’s post to the Chair’s Facebook Page\\n\\nthat prompted Davison’s comment informed the public about what happened at the\\n\\n\\n\\n 20\\n\\nLoudoun Board and Loudoun County School Board’s joint meeting. And Davison’s\\n\\ncomment also dealt with an issue related to that meeting and of significant public\\n\\ninterest—School Board members’ alleged conflicts of interest in approving financial\\n\\ntransactions. That Randall’s ban of Davison amounted to an effort “to suppress speech\\n\\ncritical of [such members’] conduct of [their] official duties or fitness for public office”\\n\\nfurther reinforces that the ban was taken under color of state law. Id. at 525. Considering\\n\\nthe totality of these circumstances, the district court correctly held that Randall acted\\n\\nunder color of state law in banning Davison from the Chair’s Facebook Page.\\n\\n C.\\n\\n Third, Randall argues that the district court erred in ruling in Davison’s favor on\\n\\nhis individual capacity First Amendment claim against Randall. Randall principally\\n\\nchallenges the district court’s conclusion that the Chair’s Facebook Page constitutes a\\n\\n“public forum” under traditional First Amendment law. We review this legal question de\\n\\nnovo. See Helton, 709 F.3d at 350.\\n\\n Under long-established First Amendment law, governmental entities are “strictly\\n\\nlimited” in their ability to regulate private speech in public fora. Pleasant Grove City,\\n\\nUtah v. Summum, 555 U.S. 460, 469 (2009). The Supreme Court has recognized two\\n\\ncategories of public fora: “traditional public forums” and “limited (or designated) public\\n\\nforums.” Am. Civil Liberties Union v. Mote, 423 F.3d 438, 443 (4th Cir. 2005).\\n\\n“Traditional” public forums—“such as streets, sidewalks, and parks”—“have the\\n\\ncharacteristics of a public thoroughfare, a purpose that is compatible with expressive\\n\\nconduct, as well as a tradition and history of being used for expressive public conduct.”\\n\\n\\n 21\\n\\nId. “Limited” or “designated” forums are forums that are “not traditionally public, but\\n\\n[that] the government has purposefully opened to the public, or some segment of the\\n\\npublic, for expressive activity.” Id. Accordingly, the hallmark of both types of public\\n\\nfora—what renders the fora “public”—is that the government has made the space\\n\\navailable—either by designation or long-standing custom—for “expressive public\\n\\nconduct” or “expressive activity,” and the space is compatible with such activity. Id.\\n\\n“Conversely, a non-public forum is one that has not traditionally been open to the public,\\n\\nwhere opening it to expressive conduct would ‘somehow interfere with the objective use\\n\\nand purpose to which the property has been dedicated.’” Id. (quoting Warren v. Fairfax\\n\\nCty., 196 F.3d 186, 190–91 (4th Cir. 1999)).\\n\\n Although neither the Supreme Court nor any Circuit has squarely addressed\\n\\nwhether, and in what circumstances, a governmental social media page—like the Chair’s\\n\\nFacebook Page—constitutes a public forum, 3 aspects of the Chair’s Facebook Page bear\\n\\nthe hallmarks of a public forum. Randall “intentionally open[ed the public comment\\n\\nsection of the Chair’s Facebook Page] for public discourse,” Cornelius v. NAACP Legal\\n\\nDefense & Educ. Fund, Inc., 473 U.S. 788, 802 (1985), inviting “ANY Loudoun citizen”\\n\\n 3\\n In addition to the court below, two other district courts have considered whether\\na government official’s social media page constituted a public forum. Those courts\\nreached conflicting results. Compare Morgan v. Bevin, 298 F. Supp. 3d 1003, 1010 (E.D.\\nKy. 2018) (holding that First Amendment forum analysis did not apply to restrictions on\\nspeech in the official Facebook and Twitter pages of the Governor of Kentucky), with\\nKnight First Amend. Inst. at Colum. Univ. v. Trump, 302 F. Supp. 3d 541, 573 (S.D.N.Y.\\n2018) (holding that the interactive component of the President’s Twitter account, as\\nopposed to the President’s tweets themselves, constituted a designated public forum),\\nappeal docketed, No. 18-1691 (2d Cir. Oct. 24, 2018).\\n\\n\\n\\n 22\\n\\nto make posts to the comments section of the Chair’s Facebook Page—the interactive\\n\\ncomponent of the page—“on ANY issues, request, criticism, complement or just your\\n\\nthoughts,” J.A. 455. Randall placed no restrictions on the public’s access to the page or\\n\\nuse of the interactive component of the Chair’s Facebook Page. And, in accordance with\\n\\nRandall’s invitation, the public made numerous posts on matters of public concern.\\n\\n The Chair’s Facebook Page also is “compatib[le] with expressive activity.”\\n\\nCornelius, 473 U.S. at 802. “Congress [has] recognized the internet and interactive\\n\\ncomputer services as offering ‘a forum for a true diversity of political discourse, unique\\n\\nopportunities for cultural development, and myriad avenues for intellectual activity.’”\\n\\nZeran v. Am. Online, Inc., 129 F.3d 327, 330 (4th Cir. 1997) (quoting 47 U.S.C. §\\n\\n230(a)(3)); cf. Bland, 730 F.3d at 386 (finding post to campaign Facebook page\\n\\n“constituted pure speech”). And the Supreme Court recently analogized social media\\n\\nsites, like the Chair’s Facebook Page, to “traditional” public forums, characterizing the\\n\\ninternet as “the most important place[] (in a spatial sense) for the exchange of views.”\\n\\nPackingham v. North Carolina, 137 S. Ct. 1730, 1735 (2017). An “exchange of views”\\n\\nis precisely what Randall sought—and what in fact transpired—when she expressly\\n\\ninvited “ANY Loudoun citizen” to visit the page and comment “on ANY issues,” and\\n\\nreceived numerous such posts and comments. J.A. 455.\\n\\n Randall nevertheless argues that traditional public forum analysis should not apply\\n\\nto the Chair’s Facebook Page for two reasons: (1) the Chair’s Facebook Page is “a private\\n\\nwebsite” and therefore does not constitute “public property” susceptible to forum\\n\\nanalysis, and (2) the Chair’s Facebook Page, in its entirety, constitutes “government\\n\\n\\n 23\\n\\nspeech” properly analyzed under the framework set forth in Pleasant Grove. Randall’s\\n\\nBr. at 19–21, 29–31. We disagree.\\n\\n Even assuming the intangible space at issue is “private property,” as Randall\\n\\nclaims—which is not at all clear from the record before us 4—the Supreme Court never\\n\\nhas circumscribed forum analysis solely to government-owned property. For example, in\\n\\nCornelius, the Court recognized that forum analysis applies “to private property\\n\\ndedicated to public use.” Cornelius, 473 U.S. at 801 (emphasis added); see also\\n\\nChristian Legal Soc’y Chapter of the Univ. of Cal. v. Martinez, 561 U.S. 661, 679 (2010)\\n\\n(“[T]his Court has employed forum analysis to determine when a governmental entity, in\\n\\nregulating property in its charge, may place limitations on speech.” (emphasis added)).\\n\\n 4\\n The Facebook “platform” and the “software” that underlies that platform is,\\naccording to Facebook’s Terms of Service, property of Facebook, Inc. Terms of Service,\\nFacebook, https://www.facebook.com/terms.php (last visited Jan. 4, 2019). Facebook’s\\nTerms of Service further provide that users “own the content [they] create and share on\\nFacebook and the other Facebook Products,” including Pages. Id. There would seem to\\nbe a good argument, therefore, that content created, and posted to Facebook, by\\ngovernment officials performing the functions and duties of their offices constitutes\\ngovernment property. Cf. Solomons v. United States, 137 U.S. 342, 346–48 (1890)\\n(holding that intellectual property created by government employee in the course of his\\nofficial duties constituted government property because “[i]f one is employed to devise or\\nperfect an instrument, or a means for accomplishing a prescribed result, he cannot, after\\nsuccessfully accomplishing the work for which he was employed, plead title thereto as\\nagainst his employer”). Likewise, under Facebook’s Terms of Service, the posts and\\ncomments by individual Facebook users—like Davison—to a Facebook Page—like the\\nChair’s Facebook Page—constitute property of those users. Accordingly, a single\\nFacebook Page—including the Chair’s Facebook Page—encompasses a web of property\\nrights, some of which may lie with the government. We need not—and thus do not—\\ndecide with whom these property rights lie in this particular case, however, because we\\nhold that even assuming the Chair’s Facebook Page constitutes private property, Randall,\\nacting under color of state law, exercised control over the aspects of that page giving rise\\nto Davison’s claim.\\n\\n\\n\\n 24\\n\\nAnd the Supreme Court and lower courts have held that private property, whether\\n\\ntangible or intangible, constituted a public forum when, for example, the government\\n\\nretained substantial control over the property under regulation or by contract. See, e.g.,\\n\\nSe. Promotions, Ltd. v. Conrad, 420 U.S. 546, 547, 555 (1975) (holding that “a privately\\n\\nowned Chattanooga theater under long-term lease to the city” was a “public forum[]\\n\\ndesigned for and dedicated to expressive activities”); Halleck v. Manhattan Community\\n\\nAccess Corp., 882 F.3d 300, 306–07 (2d Cir. 2018) (holding that public access television\\n\\nchannels operated by a private non-profit corporation constituted public forums), cert.\\n\\ngranted 139 S. Ct. 360 (2018) (mem.); First Unitarian Church of Salt Lake City v. Salt\\n\\nLake City Corp., 308 F.3d 1114, 1122 (10th Cir. 2002) (“[F]orum analysis does not\\n\\nrequire that the government have a possessory interest in or title to the underlying land.\\n\\nEither government ownership or regulation is sufficient for a First Amendment forum of\\n\\nsome kind to exist.”); Freedom from Religion Foundation, Inc. v. City of Marshfield,\\n\\nWis., 203 F.3d 487, 494 (7th Cir. 2000) (holding that private property abutted by public\\n\\npark constituted public forum).\\n\\n Significantly, even assuming the relevant aspects of the Chair’s Facebook Page\\n\\nconstitute private property—which, again, is not entirely clear from the record before\\n\\nus—Randall, acting under color of state law, retained and exercised significant control\\n\\nover the page. She created the Chair’s Facebook Page. She designated the page as\\n\\nbelonging to a “governmental official.” She clothed the page in the trappings of her\\n\\npublic office. She chose to list her official contact information on the page. And she\\n\\n\\n\\n\\n 25\\n\\ncurated the links in the left column of the page and the lists of Facebook Pages or profiles\\n\\n“liked” by the Chair’s Facebook Page in the right column.\\n\\n Of particular importance, Randall had complete control over the aspect of the\\n\\nChair’s Facebook Page giving rise to Davison’s challenge because, as administrator of\\n\\nthe page, Randall had authority to ban Facebook profiles or Pages from using the Chair’s\\n\\nFacebook Page—and, therefore, the interactive component of the page—authority she\\n\\nexercised in banning Davison’s Virginia SGP Page. Cf. Knight, 302 F. Supp. 3d at 566–\\n\\n67 (holding that the interactive component of the President’s Twitter account constituted\\n\\npublic forum because the President and his advisors “exercise control over various\\n\\naspects of the . . . account,” including the power to block other users from accessing the\\n\\naccount).\\n\\n The Second Circuit’s decision in Halleck dealing with privately operated public\\n\\naccess television channels is instructive. Federal law allows cable franchising authorities\\n\\nto require cable operators to designate channel capacity for public use. Halleck, 882 F.3d\\n\\nat 302. Likewise, New York regulations oblige cable operators to designate at least one\\n\\nchannel for full-time public use. Id. Pursuant to that authority, the City of New York\\n\\nentered into a cable franchise agreement with a cable company requiring the company to\\n\\nmake available four public access channels, which channels were operated by a private,\\n\\nnon-profit corporation, MNN. Id. Several producers of public access programming sued\\n\\nMNN, alleging that MNN violated the producers’ First Amendment rights by indefinitely\\n\\nsuspending them from using the public access channels “because of disapproval of the\\n\\ncontent of a TV program” they had submitted for airing. Id.\\n\\n\\n 26\\n\\n The Second Circuit concluded that the public access channels constituted a public\\n\\nforum, notwithstanding that they were operated by a private company. Id. at 306–08.\\n\\nThe court reached that conclusion for two reasons. First, it pointed to the similarities\\n\\nbetween public access channels and traditional public forums, like parks, describing “[a]\\n\\npublic access channel [a]s the electronic version of the public square.” Id. at 306.\\n\\nSecond, the court emphasized the extensive government involvement with, and control\\n\\nover, public access channels by virtue of the federal and state regulatory schemes. See id.\\n\\n(“[W]here, as here, federal law authorizes setting aside channels to be ‘the electronic\\n\\nmarketplace of ideas,’ state regulation requires cable operators to provide at least one\\n\\npublic access channel, a municipal contract requires a cable operator to provide four such\\n\\nchannels, and a municipal official has designated a private corporation to run those\\n\\nchannels, those channels are public forums.” (emphasis added)).\\n\\n Although not subject to the extensive federal and state regulatory regime\\n\\napplicable in Halleck, 5 the Chair’s Facebook Page is in many ways analogous to the\\n\\nprivately-operated public access channels considered by the Second Circuit. Just as the\\n\\nfederal government sought to establish an “electronic marketplace of ideas” by\\n\\nmandating provision of public access channels, Randall expressly sought to—and did, in\\n\\n\\n 5\\n The federal Communications Decency Act allows private online intermediaries,\\nlike Facebook, the ability to moderate content by providing such intermediaries with\\nbroad immunity from user-generated content posted on their sites. 47 U.S.C. § 230. This\\nCourt has recognized that an “important purpose of § 230 was to encourage service\\nproviders to self-regulate the dissemination of offensive material over their services.”\\nZeran, 129 F.3d at 331.\\n\\n\\n\\n 27\\n\\nfact—create an “electronic marketplace of ideas” by inviting “ANY” constituent to post\\n\\nto the Chair Page on “ANY issues.” J.A. 455. Likewise, just as the City of New York\\n\\nchose to have a private corporation operate the public access channels, Randall chose to\\n\\ncreate her electronic marketplace of ideas, the Chair’s Facebook Page, on a private\\n\\nplatform, Facebook. Indeed, the present case provides a stronger basis for treating the\\n\\ninteractive component of the Chair’s Facebook Page as a public forum because whereas\\n\\nthe private corporation in Halleck, MNN, exercised control over the aspect of the public\\n\\naccess channel giving rise to the First Amendment claim—banning the public access\\n\\nprogram producer—a public official, Randall exercised unconstrained control over the\\n\\naspect of the Chair’s Facebook Page giving rise to Davison’s claim—banning of other\\n\\nFacebook profiles and Pages. 6\\n\\n\\n 6\\n On October 12, 2018, the Supreme Court granted MNN’s petition for writ of\\ncertiorari in Halleck. 139 S. Ct. 360. MNN’s petition presented two questions: (1)\\n“[w]hether the Second Circuit erred in rejecting th[e Supreme] Court’s state actor tests\\nand instead creating a per se rule that private operators of public access channels are state\\nactors subject to constitutional liability” and (2) “[w]hether the Second Circuit erred in\\nholding—contrary to the Sixth and D.C. Circuits—that private entities operating public\\naccess televisions stations are state actors for constitutional purposes where the state has\\nno control over the private entity’s board or operations.” Petition for Writ of Certiorari i,\\nManhattan Community Access Corp. v. Halleck, --- S. Ct. --- (No. 17-1702). MNN’s\\nargument before the Supreme Court, therefore, focuses on the Second Circuit’s\\ndetermination that MNN constituted a state actor, not the court’s determination that the\\npublic access channels constituted a public forum.\\n\\n Although not identified as an issue on appeal, MNN’s petition also took issue with\\nthe Second Circuit’s determination that the public access channels operated by MNN\\nconstituted a public forum. But that contention was entirely derivative of its state action\\nargument. In particular, MNN objected to the Second Circuit’s public forum conclusion\\nonly because the public access channels were privately operated and because, in its\\nopinion, the Second Circuit’s purportedly “categorical” holding that public access\\n(Continued)\\n\\n 28\\n\\n Not only does case law contradict Randall’s argument that public forum analysis\\n\\nnever applies to private property, her argument also fails because it makes no legal sense\\n\\nto establish a bright-line rule that forum analysis applies only to government-owned\\n\\nproperty. Why, for example, should the First Amendment allow a municipality to engage\\n\\nin viewpoint discrimination in curating a public library branch in leased space but not\\n\\nallow the municipality to engage in such discrimination in a library branch on\\n\\nmunicipally owned property? Cf. Bd. of Educ., Island Trees Union Free Sch. Dist. No.\\n\\n26 v. Pico, 457 U.S. 853, 870–71 (1982) (plurality op.) (“If a Democratic school board,\\n\\nmotivated by partisan affiliation, ordered removal of all books written by or in favor of\\n\\nRepublicans, few would doubt that the order violated the constitutional rights of the\\n\\nstudents denied access to those books.”). Or why should a municipality be allowed to\\n\\nengage in viewpoint discrimination when holding a virtual public meeting hosted on a\\n\\nprivate website when such discrimination would be unconstitutional if the meeting was\\n\\nheld in a governmental building? Cf. Lyrissa Lidsky, Public Forum 2.0, 91 B.U. L. Rev.\\n\\n1975, 1996 (2011) (“Just as the government can rent a building to use as a forum for\\n\\npublic debate and discussion, so, too, can it ‘rent’ a social media page for the promotion\\n\\n\\n\\nchannels constitute public forums ignore[d] “the far more critical issue of whether (and to\\nwhat extent) there is government control over a public access channel.” Id. at 19–20.\\n\\n Here, a government official acting under color of state law, Randall, exercised\\nunconstrained control over the aspect of the Chair’s Facebook Page giving rise to\\nDavison’s claim.\\n\\n\\n\\n\\n 29\\n\\nof public discussion.”). We do not believe the First Amendment draws such arbitrary\\n\\nlines.\\n\\n Randall’s second argument—that the Chair’s Facebook Page amounts to\\n\\n“government speech”—fails to recognize the meaningful difference between Randall’s\\n\\nposts to the Chair’s Facebook Page and the public comments and posts she invited in the\\n\\npage’s interactive space. To be sure, Randall’s comments and curated references on the\\n\\nChair’s Facebook Page to other Pages, personal profiles, and websites amount to\\n\\ngovernmental speech. See Sutliffe v. Epping School Dist., 584 F.3d 314, 329–30 (1st Cir.\\n\\n2009) (holding that municipality’s refusal to place hyperlink on municipal website to\\n\\nwebsite of group opposed to municipal budget constituted government speech); Page v.\\n\\nLexington Cty. School Dist. One, 531 F.3d 275, 283–85 (4th Cir. 2008) (holding that\\n\\nSchool District’s refusal to place hyperlink on its website to website of group that\\n\\nopposed School District’s position on pending legislation constituted government speech\\n\\nbecause, in part, “the links to other websites were selected by the School District alone as\\n\\nones that supported its own message”); Knight, 302 F. Supp. 3d at 571 (“[T]he\\n\\nPresident’s tweets are [not] susceptible to forum analysis . . . because the content is\\n\\ngovernment speech.”).\\n\\n But the interactive component of the Chair’s Facebook Page—the portion of the\\n\\nmiddle column in which the public can post comments, reply to posts, and “like”\\n\\ncomments and posts—is materially different. See Knight, 302 F. Supp. 3d at 572\\n\\n(distinguishing a government official’s tweets and “the interactive space for replies and\\n\\nretweets”). Randall placed no formal limitations on the ability of Facebook personal\\n\\n\\n 30\\n\\nprofiles and Pages to access the Chair’s Facebook Page and make comments and posts to\\n\\nthe interactive component of the page. On the contrary, she expressly invited posts to the\\n\\npage “from ANY Loudon citizen on ANY issues, request, criticism, complement or just\\n\\nyour thoughts.” J.A. 455. And comments and posts by users cannot be mistaken for\\n\\nRandall’s own speech because they identify the posting or replying personal profile or\\n\\nPage, and thereby distinguish that user from Randall.\\n\\n Contrary to Randall’s argument that the Chair’s Facebook Page, in its entirety,\\n\\namounts to government speech, the present case also is meaningfully distinguishable\\n\\nfrom the government speech framework identified in Pleasant Grove. There, a\\n\\nmunicipality denied a private religious group’s request to allow it to erect a “monument\\n\\nin a city park in which other donated monuments were previously erected,” including a\\n\\nmonument depicting a prominent symbol of a different religion. 555 U.S. at 464. The\\n\\nplaintiff religious group sought relief under the First Amendment, arguing that the city\\n\\npark constituted a traditional public forum, and therefore that the city could not reject the\\n\\nreligious group’s proposed monument when it had previously allowed construction of a\\n\\nmonument associated with another religion. Id. at 466.\\n\\n The Supreme Court held that the city did not violate the First Amendment because\\n\\nthe government speech framework, rather than forum analysis, applied to the conduct at\\n\\nissue. In reaching that conclusion, the Court emphasized that the city never “opened up\\n\\nthe Park for the placement of whatever permanent monuments might be offered by\\n\\nprivate donors.” Id. at 472–73. “Rather, the City has ‘effectively controlled’ the\\n\\nmessages sent by the monuments in the Park by exercising ‘final approval authority’ over\\n\\n\\n 31\\n\\ntheir selection.” Id. at 473. The Court further emphasized that “[t]he forum doctrine has\\n\\nbeen applied in situations in which government-owned property or a government\\n\\nprogram was capable of accommodating a large number of public speakers without\\n\\ndefeating the essential function of the land or the program.” Id. at 478. A city park,\\n\\nhowever, “can accommodate only a limited number of permanent monuments,” and\\n\\ntherefore a municipality cannot—and need not—provide park space for all who wish to\\n\\nerect a monument. Id.\\n\\n Here, Randall “effectively controlled” certain aspects of the Chair’s Facebook\\n\\nPage: she curated the Chair’s Facebook Page’s left and right columns and made posts to\\n\\nthe middle column. Id. at 472. But Randall also expressly opened the Chair’s Facebook\\n\\nPage’s middle column—its interactive space—for “ANY” user to post on “ANY issues,”\\n\\nJ.A. 455, and therefore did not retain “final approval authority” over that aspect of the\\n\\nChair’s Facebook Page, Pleasant Grove, 555 U.S. at 473. Just as the parkland\\n\\nsurrounding monuments in Pleasant Grove continued to constitute a public forum, even\\n\\nthough the monuments themselves constituted government speech, so too the interactive\\n\\ncomponent of the Chair’s Facebook Page constitutes a public forum, even though\\n\\nRandall’s curation of and posts to the Chair’s Facebook Page amount to government\\n\\nspeech. Additionally, the interactive component of the Chair’s Facebook Page does not\\n\\nface the same spacial limitations as those of the park in Pleasant Grove, but instead is\\n\\n“capable of accommodating a large number of public speakers without defeating [its]\\n\\nessential function.” Id. at 578. Accordingly, Pleasant Grove supports, rather than\\n\\n\\n\\n\\n 32\\n\\nundermines, our conclusion that the interactive component of the Chair’s Facebook Page\\n\\nconstitutes a public forum.\\n\\n Upon concluding that interactive component of the Chair’s Facebook Page\\n\\namounts to a public forum, we would normally need to determine whether it constitutes a\\n\\ntraditional public forum or designated or limited public forum. In the present case,\\n\\nhowever, we need not decide that question because Randall’s ban of Davison amounted\\n\\nto “viewpoint discrimination,” which is “prohibited in all forums.” See Child Evangelism\\n\\nFellowship of S.C. v. Anderson Sch. Dist. Five, 470 F.3d 1062, 1067 n.2 (4th Cir. 2006).\\n\\n“Viewpoint discrimination . . . ‘targets not subject matter, but particular views taken by\\n\\nspeakers on a subject.’” Id. (quoting Rosenberger v. Rector & Visitors of Univ. of Va.,\\n\\n515 U.S. 819, 829 (1995)). Viewpoint discrimination is apparent, for example, if a\\n\\ngovernment official’s decision to take a challenged action was “impermissibly motivated\\n\\nby a desire to suppress a particular point of view.” Cornelius, 473 U.S. at 812–13.\\n\\n Here, the district court found—as the record amply supports—that Randall banned\\n\\nDavison’s Virginia SGP Page because Davison posted a comment using that page\\n\\nalleging “corruption on the part of Loudoun County’s School Board involving conflicts\\n\\nof interests among the School Board and their family members.” Davison, 267 F. Supp.\\n\\n3d at 711. Although Randall stated that she had “no idea” whether Davison’s allegations\\n\\nwere “correct,” she nonetheless banned him because she viewed the allegations as\\n\\n“slanderous” and she “didn’t want [the allegations] on the site.” Id. at 717. Randall’s\\n\\ndecision to ban Davison because of his allegation of governmental corruption constitutes\\n\\nblack-letter viewpoint discrimination.\\n\\n\\n 33\\n\\n Put simply, Randall unconstitutionally sought to “suppress” Davison’s opinion\\n\\nthat there was corruption on the School Board. Cornelius, 473 U.S. at 812–13; see also,\\n\\ne.g., Rossignol, 316 F.3d at 521 (holding that sheriff’s deputies engaged in viewpoint\\n\\ndiscrimination when they seized an issue of a newspaper that criticized the county\\n\\nsheriff’s and his deputies’ performance of their official duties); Putnam Pit, Inc. v. City of\\n\\nCookeville, Tenn., 221 F.3d 834, 846 (6th Cir. 2000) (holding that a municipality engages\\n\\nin viewpoint discrimination if it refuses to link newspaper webpage to the city’s website\\n\\nsolely because the newspaper sought to expose municipal corruption); Knight, 302 F.\\n\\nSupp. 3d at 575 (holding that the President engaged in viewpoint discrimination when he\\n\\nblocked individuals from his Twitter account because the individuals “posted tweets that\\n\\ncriticized the President or his policies”). 7 That Randall’s action targeted comments\\n\\ncritical of the School Board members’ official actions and fitness for office renders the\\n\\nbanning all the more problematic as such speech “occupies the core of the protection\\n\\nafforded by the First Amendment.” Rossignol, 316 F.3d at 521 (quoting McIntyre v.\\n\\nOhio Elections Comm’n, 514 U.S. 334, 346 (1995)).\\n\\n In sum, the interactive component of the Chair’s Facebook Page constituted a\\n\\npublic forum, and Randall engaged in unconstitutional viewpoint discrimination when\\n\\nshe banned Davison’s Virginia SGP Page from that forum.\\n\\n\\n 7\\n Randall also asserts that she did not violate Davison’s First Amendment rights\\nbecause she banned his “Virginia SGP” Page, not his “Brian Davison” profile. Davison\\nis the sole operator of the “Virginia SGP” Page, however, and therefore the ban\\nimplicated his First Amendment rights. Randall fails to identify any case supporting her\\nposition, nor have we found any. Accordingly, we reject this argument.\\n\\n\\n 34\\n\\n III.\\n\\n In his cross-appeal, Davison asserts that the district court reversibly erred in two\\n\\nways: (A) by dismissing his claim against Randall in her official capacity and (B) by\\n\\ndenying his motion to amend his complaint to add the new First Amendment claim\\n\\nagainst the Loudoun Board. 8 We disagree.\\n\\n A.\\n\\n Davison first argues that the district court erred in dismissing his claim against\\n\\nRandall in her official capacity. Whereas “[p]ersonal-capacity suits seek to impose\\n\\npersonal liability upon a government official for actions [she] takes under color of state\\n\\nlaw,” Kentucky v. Graham, 473 U.S. 159, 165 (1985), “official capacity suits are ‘treated\\n\\nas suits against the municipality,’” Santos v. Frederick Cty. Bd. of Comm’rs, 725 F.3d\\n\\n451, 469 (4th Cir. 2013) (quoting Hafer v. Melo, 502 U.S. 21, 25 (1991)). Because\\n\\n“municipal liability under Section 1983 does not amount to respondeat superior . . . a\\n\\n 8\\n Davison also argues that the district court erred in rejecting his procedural due\\nprocess claims under the Fourteenth Amendment and an analogous provision in the\\nVirginia Constitution. Before the district court, Davison “flatly asserted that due process\\nalways requires the government to provide a hearing before imposing a prior restraint on\\nspeech,” and therefore that Randall violated Davison’s First Amendment rights by failing\\nto conduct a pre-ban hearing. Davison, 267 F. Supp. 3d at 719. The district court\\ncorrectly rejected Davison’s proposed categorical rule. Id. (citing Cafeteria & Rest.\\nWorkers Union Local 473, AFL-CIO v. McElroy, 367 U.S. 886, 895 (1961). And\\nDavison has abandoned that asserted categorical rule on appeal, Davison’s Br. at 49–50\\nn.19 (“[I]t might be permissible in certain contexts to delete an individual comment\\nwithout providing full pre-deprivation process . . . .”), instead arguing he is entitled to\\nrelief under the balancing test set forth in Mathews v. Eldridge, 424 U.S. 319, 334–35\\n(1976). Because Davison did not make that argument before the district court, we decline\\nto consider it now. See CoreTel Va., LLC v. Verizon Va., LLC, 808 F.3d 978, 988 (4th\\nCir. 2015).\\n\\n\\n\\n 35\\n\\nmunicipality is subject to Section 1983 liability only when its ‘policy or custom, whether\\n\\nmade by its lawmakers or by those whose edicts or acts may fairly be said to represent\\n\\nofficial policy, inflicts the [plaintiff’s] injury.’” Id. at 469–70 (quoting Monell v. Dep’t of\\n\\nSoc. Servs. of the City of N.Y., 436 U.S. 658, 694 (1978)).\\n\\n Here, the district court dismissed Davison’s official capacity claim because it\\n\\nfound that “no policy—whether County-wide or specific to [Randall]’s office—played\\n\\nany role in [Randall]’s decision to ban [Davison] from her [Chair’s Facebook Page].”\\n\\nDavison, 267 F. Supp. 3d at 715. We review the district court’s factual findings bearing\\n\\non whether Randall acted pursuant to a municipal policy or custom for clear error and its\\n\\nlegal conclusions de novo. Helton, 709 F.3d at 350.\\n\\n On appeal, Davison does not dispute the district court’s finding—which the record\\n\\namply supports—that Loudoun County did not promulgate a policy governing individual\\n\\nLoudoun Board members’ Facebook pages. Rather, Davison principally 9 argues that “the\\n\\ncounty can be held liable for Randall’s actions because in banning Davison, Randall\\n\\nacted as a municipal policymaker.” Davison’s Br. at 47.\\n\\n\\n\\n\\n 9\\n Davison also argues the Loudoun Board’s failure to adopt a policy pertaining to\\nindividual board members’ Facebook pages gives rise to an official capacity claim\\nbecause it establishes that the Loudoun “Board was—and remains—deliberately\\nindifferent to the likelihood of unconstitutional censorship and viewpoint-based\\ndiscrimination on individual supervisors’ social media sites.” Davison’s Br. at 46. But\\nDavison never advanced a “deliberate indifference” theory of municipal liability before\\nthe district court. Again, we decline to consider an argument Davison raises for the first\\ntime on appeal. See CoreTel, LLC, 808 F.3d at 988.\\n\\n\\n\\n 36\\n\\n Davison is correct that “municipal liability may be imposed for a single decision\\n\\nby municipal policymakers under appropriate circumstances.” Hunter v. Town of\\n\\nMocksville, N.C., 897 F.3d 538, 554 (4th Cir. 2018) (quoting Pembaur v. City of\\n\\nCincinnati, 475 U.S. 469, 480 (1986)). “[I]n assessing whether a municipality may be\\n\\nheld liable for constitutional or statutory violations of their decisionmakers, the\\n\\ntouchstone inquiry is whether ‘the decisionmaker possesses final authority to establish\\n\\nmunicipal policy with respect to the action ordered.’” Id. at 554–55 (emphasis added)\\n\\n(quoting Liverman v. City of Petersburg, 844 F.3d 400, 413 (4th Cir. 2016)).\\n\\n Here, Davison failed to put forward evidence establishing that Randall was a final\\n\\nmunicipal policymaker with regard to her banning of Davison from the Chair’s Facebook\\n\\nPage. On the contrary, record evidence establishes that the Loudoun Board retained\\n\\nauthority to establish municipal policy with respect to social media pages, as it adopted a\\n\\nsocial media policy governing the County’s official social media pages. Davison\\n\\nconcedes as much, arguing that the Loudoun Board “neglected . . . to extend its written\\n\\nguidelines to Board members’ official pages.” Davison’s Br. at 46. But that argument\\n\\npresupposes that the Loudoun Board—not Randall—had authority to establish municipal\\n\\npolicy with respect “to Board members’ official pages.”\\n\\n Davison nevertheless argues that the Loudoun Board “implicitly” delegated its\\n\\nfinal policymaking authority to Randall by not addressing individual Loudoun Board\\n\\nmembers’ official pages in its social media policy. Davison is correct that delegation of\\n\\nfinal policy making authority may be “implied from a continued course of knowing\\n\\nacquiescence by the governing body in the exercise of policymaking authority by an\\n\\n\\n 37\\n\\nagency or official.” Id. at 48 (quoting Spell v. McDaniel, 824 F.2d 1380, 1387 (4th Cir.\\n\\n1987)). But Davison identifies no evidence that the Loudoun Board knew of the Chair’s\\n\\nFacebook Page, let alone that it “aquiesce[d]” in Randall’s administration of the page and\\n\\nbanning of Davison, in particular. On the contrary, the district court found that Randall\\n\\nmade a one-off, “unilateral decision to ban [Davison] in the heat of the moment, and\\n\\nreconsidered soon thereafter,” Davison, 267 F. Supp. 3d at 715—before the Loudoun\\n\\nBoard had a chance to learn of her action. In such circumstances, the district court did\\n\\nnot reversibly err in rejecting Davison’s official capacity claim.\\n\\n B.\\n\\n Next, Davison argues that the district court erred in denying him leave to amend\\n\\nhis complaint to add a claim that “the County violates the First Amendment by\\n\\nmaintaining a limited public forum on Facebook,” when policies imposed by Facebook,\\n\\nrather than the County, restrain, or have the potential to restrain, speech. J.A. 74. “A\\n\\ndistrict court may deny a motion to amend when the amendment would be prejudicial to\\n\\nthe opposing party, the moving party has acted in bad faith, or the amendment would be\\n\\nfutile.” Equal Rights Ctr. v. Niles Bolton Assocs., 602 F.3d 597, 603 (4th Cir. 2010).\\n\\nThe magistrate judge recommended—and the district court agreed—that Davison be\\n\\ndenied leave to amend on grounds of both futility and prejudice. We review for abuse of\\n\\ndiscretion a district court’s denial of leave to amend for prejudice, whereas we review de\\n\\nnovo a district court’s denial of leave to amend on the basis of futility. See U.S. ex rel.\\n\\nAhumada v. NISH, 756 F.3d 268, 274 (4th Cir. 2014).\\n\\n\\n\\n\\n 38\\n\\n Regarding prejudice, the district court determined that the amendment came “too\\n\\nlate in these proceedings” and would “add a new, novel legal theory to the case after the\\n\\nclose of discovery, after the existing claims against [the Loudoun Board] have been\\n\\nshown to be meritless, after the point at which Defendants could have addressed the\\n\\nclaim in briefing before trial, and on the eve of trial.” J.A. 74. The district court did not\\n\\nabuse its discretion in denying leave to amend in such circumstances. See, e.g., Equal\\n\\nRights Ctr., 602 F.3d at 603–04 (holding that district court did not abuse its discretion in\\n\\ndenying leave to amend on the basis of prejudice when amendment came after the close\\n\\nof discovery and “on the eve of the deadline for dispositive motions” and therefore\\n\\n“would [have] change[d] the nature of the litigation”); Deasy v. Hill, 833 F.2d 38, 41 (4th\\n\\nCir. 1987) (affirming denial of leave to amend on grounds of prejudice when “the motion\\n\\nto amend came right before trial and after discovery was complete”).\\n\\n Although we affirm the district court’s judgment on the basis of its finding of\\n\\nprejudice, we do not concur in its conclusion as to futility. “Futility is apparent if the\\n\\nproposed amended complaint fails to state a claim under the applicable rules and\\n\\naccompanying standards.” Katyle v. Penn Nat. Gaming, Inc., 637 F.3d 462, 471 (4th Cir.\\n\\n2011). Accordingly, Davison’s proposed amendment was futile if the new claim would\\n\\nnot have survived a motion to dismiss under Federal Rule of Civil Procedure 12(b)(6).\\n\\nSee Runnion ex rel. Runnion v. Girl Scouts of Greater Chicago & Nw. Ind., 786 F.3d 510,\\n\\n524 (7th Cir. 2015) (“[W]hen the basis for denial is futility, we apply the legal\\n\\nsufficiency standard of Rule 12(b)(6) to determine whether the proposed amended\\n\\ncomplaint fails to state a claim.”).\\n\\n\\n 39\\n\\n Davison’s proposed First Amendment claim deals not with the Chair’s Facebook\\n\\nPage—which the Loudoun Board did not authorize or attempt to regulate—but rather\\n\\nwith Loudoun County’s official Facebook Pages created and maintained pursuant to the\\n\\nLoudoun Board’s social media policy. As with his claims related to the Chair’s\\n\\nFacebook Page, Davison alleged that the Facebook Pages created and maintained by the\\n\\nLoudoun Board constituted public forums subject to the First Amendment. Davison\\n\\ntheorized that the Loudoun Board’s decision to use Facebook as its social media forum\\n\\nviolated his First Amendment rights because Facebook rules permit individual\\n\\n“requesting” users to ban other personal profiles and Pages such that the banned users can\\n\\nno longer see posts authored by the requesting users. In such circumstances, the banned\\n\\nusers “cannot see [the requesting user’s] comment[s] or participate in the discussion\\n\\nsurrounding the [requesting] party’s comment.” Davison’s Br. at 59. Davison’s\\n\\nproposed amended complaint asserted that “this scenario violates the First Amendment\\n\\nbecause Loudoun County has effectively enabled third parties to exclude discussion\\n\\nwithin a public forum—something a government body could not permissibly do in a\\n\\nphysical forum.” Id. at 59–60 (internal citation omitted). Put differently, Davison\\n\\ntheorized that Loudoun County violated the First Amendment by choosing to use\\n\\nFacebook as a public forum, when rules imposed by Facebook allow private users to\\n\\nrestrict access to their posts—and comments on and responses to those posts—including\\n\\nposts to any municipal Facebook Page.\\n\\n No court appears to have addressed that novel legal theory. And although the First\\n\\nAmendment constrains only government policies, not policies established by private\\n\\n\\n 40\\n\\nentities, one can conceive of a colorable legal argument that a governmental actor’s\\n\\ndecision to select a private social media website for use as a public forum—and therefore\\n\\nselect that website’s suite of rules and regulations—could violate the First Amendment, if\\n\\nthe private website included certain types of exclusionary rules. For example, if the\\n\\ngovernment chose as its electronic public forum a social media site that allowed only\\n\\nregistered members of one political party to post and comment, there would seem to be a\\n\\ncompelling argument that the government’s selection of that social media site violated the\\n\\nFirst Amendment rights of members of other political parties, even if the partisan\\n\\nrestriction was imposed by the private company, not the governmental body. Such a\\n\\nrestriction would be seem to be no different than a municipality choosing to hold a town\\n\\nhall meeting in a venue that refused admission to individuals associated with a disfavored\\n\\npolitical party or viewpoint. Cf. DeBoer v. Village of Oak Park, 267 F.3d 558, 571 (7th\\n\\nCir. 2001) (“[T]he government engages in viewpoint discrimination when it denies access\\n\\nto a speaker solely to suppress the point of view he espouses on an otherwise includible\\n\\nsubject.”).\\n\\n Given that Davison’s proposed claim asserted a novel and colorable legal theory\\n\\nand that “Rule 12(b)(6) dismissals are especially disfavored in cases where the complaint\\n\\nsets forth a novel legal theory that can best be assessed after factual development,”\\n\\nWright v. North Carolina, 787 F.3d 256, 263 (4th Cir. 2015) (internal quotation marks\\n\\nomitted), we affirm the district court’s denial of Davison’s motion for leave to amend his\\n\\ncomplaint on the basis of its finding of prejudice but not on the basis of futility.\\n\\n IV.\\n\\n\\n 41\\n\\nFor the foregoing reasons, we affirm the judgment of the district court.\\n\\n AFFIRMED\\n\\n\\n\\n\\n 42\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":91,"cells":{"id":{"kind":"number","value":4580037,"string":"4,580,037"},"name":{"kind":"string","value":"6TH CONGRESSIONAL DISTRICT REPUBLICAN COMMITTEE, Plaintiff - Appellee, and Anne Taetzsch Fitzgerald, Individually and as Chairman of the 20th House of Delegates District Republican Committee; Karen U. Kwiatkowski, Individually; Edward A. Yensho, Individually and as Chairman of the Green County Republican Committee; 20th House of Delegates District Republican Committee, Plaintiffs, v. James B. ALCORN, in His Official Capacity as Chairman of the Virginia State Board of Elections ; Clara Belle Wheeler, in Her Official Capacity as Vice-Chairman of the Virginia State Board of Elections ; Singleton B. McAllister, in Her Official Capacity as Secretary of the Virginia State Board of Elections ; Virginia Department of Elections, Defendants - Appellants."},"name_abbreviation":{"kind":"string","value":"6th Congressional District v. James Alcorn"},"decision_date":{"kind":"string","value":"2019-01-09"},"docket_number":{"kind":"string","value":"18-1111"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Wilkinson, Motz, Duncan\", \"parties\": \"\", \"opinions\": [{\"author\": \"WILKINSON, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1111\\n\\n\\n6TH CONGRESSIONAL DISTRICT REPUBLICAN COMMITTEE,\\n\\n Plaintiff – Appellee,\\n\\n and\\n\\nANNE TAETZSCH FITZGERALD, individually and as Chairman of the 20th\\nHouse of Delegates District Republican Committee; KAREN U.\\nKWIATKOWSKI, individually; EDWARD A. YENSHO, individually and as\\nChairman of the Green County Republican Committee; 20TH HOUSE OF\\nDELEGATES DISTRICT REPUBLICAN COMMITTEE,\\n\\n Plaintiffs,\\n\\n v.\\n\\nJAMES B. ALCORN, in his official capacity as Chairman of the Virginia State\\nBoard of Elections; CLARA BELLE WHEELER, in her official capacity as Vice-\\nChairman of the Virginia State Board of Elections; SINGLETON B.\\nMCALLISTER, in her official capacity as Secretary of the Virginia State Board of\\nElections; VIRGINIA DEPARTMENT OF ELECTIONS,\\n\\n Defendants - Appellants.\\n\\n\\nAppeal from the United States District Court for the Western District of Virginia, at\\nHarrisonburg. Michael F. Urbanski, Chief District Judge. (5:17-cv-00016-MFU-JCH)\\n\\n\\nArgued: December 12, 2018 Decided: January 9, 2019\\n\\n\\nBefore WILKINSON, MOTZ, and DUNCAN, Circuit Judges.\\n\\fAffirmed by published opinion. Judge Wilkinson wrote the opinion, in which Judge Motz\\nand Judge Duncan joined.\\n\\n\\nARGUED: Toby Jay Heytens, OFFICE OF THE ATTORNEY GENERAL OF\\nVIRGINIA, Richmond, Virginia, for Appellants. Jeffrey R. Adams, WHARTON,\\nALDHIZER & WEAVER, PLC, Harrisonburg, Virginia, for Appellee. ON BRIEF:\\nMark R. Herring, Attorney General, Stephen A. Cobb, Deputy Attorney General,\\nMatthew R. McGuire, Principal Deputy Solicitor General, Michelle S. Kallen, Deputy\\nSolicitor General, OFFICE OF THE ATTORNEY GENERAL OF VIRGINIA,\\nRichmond, Virginia, for Appellants. Charles F. Hilton, Thomas E. Ullrich, Lucas I.\\nPangle, WHARTON ALDHIZER & WEAVER, PLC, Harrisonburg, Virginia; John C.\\nWirth, NELSON MCPHERSON SUMMERS & SANTOS, Staunton, Virginia, for\\nAppellee.\\n\\n\\n\\n\\n 2\\n\\fWILKINSON, Circuit Judge:\\n\\n The 6th Congressional District Republican Committee argues that Virginia’s\\n\\nIncumbent Protection Act, Va. Code Ann. § 24.2-509(B), violates the First Amendment\\n\\nof the Constitution. The district court agreed and enjoined § 24.2-509(B) in its entirety.\\n\\nFor the reasons that follow, we now affirm.\\n\\n I.\\n\\n A.\\n\\n Virginia law generally allows the Commonwealth’s political parties considerable\\n\\ndiscretion in deciding how to nominate their candidates for office. Section 24.2-509(A)\\n\\nempowers the “duly constituted authorities” of the state and local parties “to determine\\n\\nthe method by which a party nomination . . . shall be made.” The parties make use of this\\n\\nlatitude. For example, the Republican Party of Virginia, with whom the appellee here is\\n\\naffiliated, allows for four different methods of nomination: a primary, a party canvass, a\\n\\nconvention, and a mass meeting. Fitzgerald v. Alcorn, 285 F. Supp. 3d 922, 927 (W.D.\\n\\nVa. 2018). Under the Party’s Plan of Organization, committees established in every\\n\\nlocality, state legislative district, and congressional district are empowered to choose\\n\\namong these methods to nominate candidates for their political subdivision. J.A. 37, 38,\\n\\n40.\\n\\n The differences between these methods are substantial. Each one “‘create[s] a\\n\\ndifferent distribution of potential voters (or decision makers) in the nomination process.’\\n\\nFor example, primaries involve the largest pool of potential voters, whereas conventions\\n\\nand mass meetings ‘lend themselves more toward committed partisans.’” Alcorn, 285 F.\\n\\n 3\\n\\fSupp. 3d at 935 (quoting J.A. 884-85, 885-86). The choice of method, therefore, could\\n\\nhave a significant influence on the choice of nominee.\\n\\n Subsection 24.2-509(B), often called the Incumbent Protection Act, however,\\n\\nlimits the broad authority recognized by subsection A. 1 The second and third sentences\\n\\napply to those subdivisions of the state party that select nominees for candidates to the\\n\\n\\n1\\n The full text of Virginia Code § 24.2-509 is reprinted below, with the sentences in\\nsubsection B numbered for ease of reference:\\n\\nA. The duly constituted authorities of the state political party shall have the right to\\n determine the method by which a party nomination for a member of the United States\\n Senate or for any statewide office shall be made. The duly constituted authorities of\\n the political party for the district, county, city, or town in which any other office is to\\n be filled shall have the right to determine the method by which a party nomination for\\n that office shall be made.\\n\\nB. [1] Notwithstanding subsection A, the following provisions shall apply to the\\n determination of the method of making party nominations. [2] A party shall nominate\\n its candidate for election for a General Assembly district where there is only one\\n incumbent of that party for the district by the method designated by that incumbent, or\\n absent any designation by him by the method of nomination determined by the party.\\n [3] A party shall nominate its candidates for election for a General Assembly district\\n where there is more than one incumbent of that party for the district by a primary\\n unless all the incumbents consent to a different method of nomination. [4] A party,\\n whose candidate at the immediately preceding election for a particular office other\\n than the General Assembly (i) was nominated by a primary or filed for a primary but\\n was not opposed and (ii) was elected at the general election, shall nominate a\\n candidate for the next election for that office by a primary unless all incumbents of\\n that party for that office consent to a different method.\\n\\n [5] When, under any of the foregoing provisions, no incumbents offer as candidates\\n for reelection to the same office, the method of nomination shall be determined by the\\n political party.\\n\\n [6] For the purposes of this subsection, any officeholder who offers for reelection to\\n the same office shall be deemed an incumbent notwithstanding that the district which\\n he represents differs in part from that for which he offers for election.\\n\\n\\n 4\\n\\fGeneral Assembly. Those sentences allow incumbent members of the General Assembly\\n\\nwho are running for reelection, where there is only one incumbent, to “designate[]” the\\n\\nmethod of nomination they prefer. Under this statute, the wishes of the party are\\n\\nimmaterial; no matter where the party’s plan of organization may vest the power to\\n\\nchoose nomination methods, the law trumps, granting the power to the incumbent.\\n\\n The fourth sentence of the Act applies to those components of political parties that\\n\\nmake the nominations for “particular office[s]” other than for the General Assembly,\\n\\nincluding nominations for the U.S. House of Representatives. In these races, the\\n\\nincumbent officeholder may insist that his or her party use a primary as its nomination\\n\\nmethod as long as (1) the incumbent was selected by primary in the previous election\\n\\ncycle and (2) the incumbent is running for reelection. Again, the statute trumps the\\n\\nparty’s plan of organization, which, in this case allows the committees responsible for\\n\\ncongressional nominations to choose between the approved methods (excluding mass\\n\\nmeetings) without interference by the incumbent, J.A. 37.\\n\\n The Virginia Department of Elections, however, has not always respected the\\n\\ndistinction made between the second and third sentences on the one hand, and the fourth\\n\\nsentence on the other. In the 2016 and 2017 election cycles, for example, the Department\\n\\npromulgated forms that allowed non-General Assembly incumbents to “designate” their\\n\\npreferred method of nomination as if their elections were governed by the second and\\n\\nthird sentences. After the commencement of this litigation, and only after the appellees\\n\\npointed out the mistake, the Department issued new forms that applied the fourth\\n\\nsentences to these races.\\n\\n 5\\n\\f Virginia has not identified a single other state that has a statute like the Incumbent\\n\\nProtection Act, and this is not the first case to consider a constitutional challenge to it. In\\n\\n2007, for example, this court considered a challenge to the Act. Miller v. Brown, 503\\n\\nF.3d 360 (4th Cir. 2007) (“Miller II”). There, we held that an incumbent cannot\\n\\nconstitutionally force his or her party to use an open primary, as this would be an\\n\\nimpermissible burden on the party’s associational rights. Id. at 368-71. We did not,\\n\\nhowever, reach the different question of the constitutionality of incumbents’ statutory\\n\\npower to dictate any nomination method.\\n\\n B.\\n\\n This appeal stems from the 6th Congressional District Republican Committee’s\\n\\nchallenge to the Incumbent Protection Act under 42 U.S.C. § 1983. See Alcorn, 285 F.\\n\\nSupp. 3d at 922. The Committee is responsible for nominating candidates for the U.S.\\n\\nHouse of Representatives for the 6th Congressional District, which “covers much of the\\n\\nwest-central portion of Virginia, from Roanoke to Front Royal.” Id. at 927. Under the\\n\\nParty’s Plan of Organization, it is composed of the “District Chairman,” the “Unit\\n\\nChairman” (the chair of each relevant locality’s committee), the “District Representative\\n\\nof the Virginia Federation of Republican Women,” the “Young Republican Federation\\n\\nDistrict Committeeman,” the “College Republican Federation District Committeeman,”\\n\\nand the “District members of the State Central Committee.” J.A. 36-37. The Committee,\\n\\nalong with other plaintiffs who were dismissed from the suit and do not appeal, raised\\n\\nfacial and as applied challenges to the Incumbent Protection Act, claiming that it\\n\\nabridged their rights under the First and Fourteenth Amendments of the U.S.\\n\\n 6\\n\\fConstitution. The named defendants include the Virginia Department of Elections and the\\n\\nthree members of the Virginia State Board of Elections at the time the suit was filed.\\n\\nAlcorn, 285 F. Supp. 3d at 928.\\n\\n The district court, relying on Miller v. Brown, 462 F.3d 312 (4th Cir. 2006)\\n\\n(“Miller I”), found that the Committee had standing to challenge the Act. Alcorn, 285 F.\\n\\nSupp. 3d at 937. It then proceeded to evaluate the burden posed by § 24.2-509(B) on the\\n\\nCommittee’s associational rights, concluding that it was “severe” because it provided\\n\\n“incumbents with a statutory right to dictate political parties’ internal affairs . . . .” Id. at\\n\\n952. The burden was “especially” onerous because it trespassed on the “realm of\\n\\nselecting candidates.” Id. Given the magnitude of the burden, the district court found that\\n\\n“the Act can survive constitutional scrutiny only if it is ‘narrowly tailored to advance a\\n\\ncompelling state interest.’” Id. (quoting Burdick v. Takushi, 504 U.S. 428, 433 (1992)).\\n\\nThe district court ultimately concluded that the Act did not survive such scrutiny. Id. at\\n\\n953.\\n\\n The district court thus permanently enjoined enforcement of the entire Incumbent\\n\\nProtection Act on January 19, 2018. J.A. 1473. The court enjoined all six sentences of\\n\\n§ 24.2-509(B) because, according to the court, the second and third sentences—which\\n\\nprotect the nomination prerogatives of incumbent General Assembly members—could\\n\\nnot be severed from the fourth—which protects the nomination prerogatives of, inter alia,\\n\\nmembers of Congress. The court additionally found that the Committee had standing to\\n\\nchallenge the second and third sentences under the overbreadth doctrine. Alcorn, 285 F.\\n\\nSupp. 3d at 955. Finally, the district court concluded that the Act had “no legitimate\\n\\n 7\\n\\fsweep” and so a facial challenge to all its provisions was appropriate. Id. at 955-56. After\\n\\nthe notice of appeal had been filed, the district court stayed its permanent injunction order\\n\\non February 5, 2018, to avoid interfering with the ongoing nomination cycle. J.A. 1481.\\n\\nAfter that cycle concluded, however, the district court vacated its stay on September 24,\\n\\n2018. J.A. 1680. During the course of this appeal, the Department filed a motion to\\n\\nvacate the injunction on the basis of mootness. We held that motion in abeyance pending\\n\\noral argument, and both parties expanded on their arguments in their briefing on the\\n\\nmerits.\\n\\n II.\\n\\n The district court found that the fourth sentence of the Incumbent Protection Act,\\n\\nwhich protects the nomination prerogatives of incumbent members of Congress among\\n\\nothers, violated the First Amendment. Because this provision imposes a severe burden on\\n\\nthe associational rights of Virginia’s political parties, and because the Commonwealth\\n\\nhas been unable to show that it is narrowly tailored to serve a compelling state interest,\\n\\nwe agree.\\n\\n A.\\n\\n Freedom of association has, for centuries, been at the heart of the American\\n\\nsystem of government and individual rights. In 1831, when Alexis de Tocqueville arrived\\n\\nin the United States, he was shocked to discover that our nation was the only “country on\\n\\nthe face of the earth where the citizens enjoy unlimited freedom of association for\\n\\npolitical purposes.” Alexis de Tocqueville, 2 Democracy in America 123 (Henry Reeves\\n\\ntrans., 1863). In America, “the most democratic country on the face of the earth,” the\\n\\n 8\\n\\f“art” of forming political associations had been “carried to the highest perfection.” Id. at\\n\\n115. Because of this, “Americans of all ages, all conditions, and all dispositions,\\n\\nconstantly form associations.” Id. at 114.\\n\\n De Tocqueville identified this propensity to associate as one of the sources of the\\n\\nastonishing political dynamism of the young Republic, writing that American political\\n\\nassociations are “the mother of action,” id. at 125, and that they “stimulate competition,\\n\\nand . . . discover those arguments which are most fitted to act upon the majority.” Id. at\\n\\n210. The right to associate for political purposes, de Tocqueville proclaimed, is “[t]he\\n\\nmost natural privilege of man, next to the right of acting for himself.” Id. at 209.\\n\\nAccordingly, “the right of association is almost as inalienable as the right of personal\\n\\nliberty. No legislator can attack it without impairing the very foundations of society.” Id.\\n\\n The multiplicity of political associations lauded by de Tocqueville was the result\\n\\nof the Founders’ decision to enshrine the “freedom to join together in furtherance of\\n\\ncommon political beliefs” in the First Amendment of the Constitution. Tashjian v.\\n\\nRepublican Party of Conn., 479 U.S. 208, 214-15 (1986). That Amendment promises\\n\\nAmericans the right not just to proclaim a political vision but to join with their\\n\\ncompatriots and actually advance that vision. Because, while an individual may be, in de\\n\\nTocqueville’s words, “feeble and consequently more incapable of preserving his\\n\\nfreedom,” de Tocqueville, supra, at 123, when individuals combine in association they\\n\\n“acquire facility in prosecuting great undertakings in common,” id. at 114. Some of the\\n\\n“great undertakings” accomplished by political associations protected by the First\\n\\nAmendment include the Abolitionist Movement, the Women’s Suffrage Movement, the\\n\\n 9\\n\\fLabor Movement, and the Civil Rights Movement—the fruits of which continue to shape\\n\\nour politics and society for the better to this day.\\n\\n Of all political associations protected by the First Amendment, political parties\\n\\nthemselves merit special attention. Like other political participants, parties advance a\\n\\nparticular vision. Unlike others, however, political parties must also nominate candidates\\n\\nfor office, compete in elections, and, if successful, help to translate campaign appeals into\\n\\nprogrammatic action. In so doing, political parties provide a vehicle for voters to advance\\n\\ntheir own political views. Without groups like modern political parties, “[r]epresentative\\n\\ndemocracy in any populous unit of governance” would be “unimaginable.” Cal.\\n\\nDemocratic Party v. Jones, 530 U.S. 567, 574 (2000).\\n\\n Perhaps no function of a party is more central to its purpose than the selection of\\n\\ncandidates for office, which “often determines the party’s positions on the most\\n\\nsignificant public policy issues of the day.” Id. at 575. It is no surprise, therefore, that the\\n\\nSupreme Court is “vigorous[]” in affirming the “special protection” owed to the\\n\\nassociational rights of political parties as they pertain to the parties’ choice of nominees.\\n\\nId. at 576. Statutes that severely burden a party’s associational rights must be narrowly\\n\\ntailored to advance a compelling government interest. Id. at 581-82. In Democratic Party\\n\\nof the United States v. Wisconsin ex rel. La Follette, the Court invalidated a Wisconsin\\n\\nlaw that required the national Democratic Party to seat certain delegates chosen in an\\n\\nopen primary. 450 U.S. 107 (1981). In Tashjian v. Republican Party of Connecticut, the\\n\\nCourt struck down a Connecticut law that forbade state parties from conducting open\\n\\nprimaries because the law burdened “associational opportunities at the crucial juncture at\\n\\n 10\\n\\fwhich the appeal to common principles may be translated into concerted action . . . .” 479\\n\\nU.S. at 216. In Eu v. San Francisco County Democratic Central Committee, the Court\\n\\ninvalidated laws dictating political parties’ internal affairs and prohibiting them from\\n\\nendorsing candidates for office. 489 U.S. 214 (1989). And in California Democratic\\n\\nParty v. Jones, the Court struck down a mandatory open primary law as it burdened the\\n\\n“political association’s right to exclude” in the “candidate-selection process.” 530 U.S. at\\n\\n575.\\n\\n Not every burden on associational rights is unconstitutional. “States have a major\\n\\nrole to play in structuring and monitoring the election process, including” nominee\\n\\nselection. Cal. Democratic Party, 530 U.S. at 572. Where the burden imposed by the\\n\\nstate is not “severe”—where it is “lesser”—courts engage in “less exacting review.”\\n\\nTimmons v. Twin Cities Area New Party, 520 U.S. 351, 358 (1997). In Timmons, the\\n\\nCourt upheld a Minnesota law that prohibited a candidate from appearing on the ballot as\\n\\nthe nominee of more than one party after finding that the law did “not severely burden\\n\\nthat party’s associational rights.” Id. at 359. Nothing prevented the party from endorsing\\n\\nthe candidate of another party; nothing prevented the party for campaigning for the\\n\\ncandidate of another party. The law’s only effect was to “reduce the universe of potential\\n\\ncandidates who may appear on the ballot as the party’s nominee . . . by ruling out those\\n\\nfew individuals who . . . have already agreed to be another party’s candidate.” Id. at 363.\\n\\nThis slight a reduction could not be a severe burden. Id.; see also Clingman v. Beaver,\\n\\n544 U.S. 581 (2005) (upholding law mandating a “semiclosed” primary, in which\\n\\nregistered members of opposing parties and unaffiliated voters could not participate).\\n\\n 11\\n\\f Political parties have, of course, come in for their fair share of criticism\\n\\nthroughout our history. Chancellor James Kent, in an 1830 letter to Daniel Webster,\\n\\nwrote that “Hamilton said in the Federalist, in his speeches, and a hundred times to me,\\n\\nthat factions would ruin us, and our government had not sufficient energy and balance to\\n\\nresist the propensity to them, and to control their tyranny and their profligacy.” John B.\\n\\nCassoday, James Kent & Joseph Story, 12 Yale L.J. 146, 151 (1903) (quoting letter). But\\n\\nwhether the divisiveness in public discourse traces to the presence of political parties or\\n\\nto the divisions inherent in the issues themselves elides the fact that parties have long\\n\\nsince become a fact of constitutional life. And what emerges from the above Supreme\\n\\nCourt cases is no all-or-nothing proposition but instead that law is not insensitive to\\n\\nmatters of degree: Those laws that impose a “heav[y]” or “severe” burden on a political\\n\\nparty’s right to choose its nominee are unconstitutional unless they serve a “compelling\\n\\nstate interest” and are “narrowly tailored” to do so. Cal. Democratic Party, 530 U.S. at\\n\\n583. It is to that inquiry that we now turn.\\n\\n B.\\n\\n The fourth sentence of Virginia Code § 24.2-509(B), the provision of the\\n\\nIncumbent Protection Act that applies to congressional incumbents among others,\\n\\nunquestionably poses a severe burden on the associational rights of the Commonwealth’s\\n\\npolitical parties. In evaluating the law’s imposition on associational rights, we must\\n\\n“weigh the ‘character and magnitude’ of the burden” it occasions. Timmons, 520 U.S. at\\n\\n358 (quoting Burdick, 504 U.S. at 434). We keep in mind also that “[a]ny interference\\n\\n\\n\\n 12\\n\\fwith the freedom of a party is simultaneously an interference with the freedom of its\\n\\nadherents.” Tashjian, 479 U.S. at 215 (quoting Democratic Party, 450 U.S. at 122).\\n\\n Subsection 24.2-509(A) grants the “duly constituted authorities” of the\\n\\nCommonwealth’s political parties considerable discretion in selecting the method of\\n\\nchoosing their nominees. The Incumbent Protection Act, subsection 24.1-509(B), carves\\n\\nexceptions to this rule in favor of incumbents. To recapitulate, the second and third\\n\\nsentences allow incumbent members of the General Assembly to dictate the method their\\n\\nparty shall use in selecting the nominee for the office that incumbent holds. The fourth\\n\\nsentence allows incumbent members of the U.S. House of Representatives, who were\\n\\nthemselves nominated by primary in the last election cycle, to require their party to use a\\n\\nprimary in the current election cycle to nominate a candidate for the office they hold if\\n\\nthey themselves are seeking reelection. In short, the associational rights of Virginia’s\\n\\npolitical parties that are recognized and protected by § 24.2-509(A) are taken away by §\\n\\n24.1-509(B) and given instead to a single individual—the incumbent.\\n\\n The weight of this burden could not be more obvious. The members of the 6th\\n\\nCongressional District Committee have, as generations of Americans did before them,\\n\\nbanded together to advance their political views. The selection of a nominee “often\\n\\ndetermines” the contours of the party platform. Cal. Democratic Party, 530 U.S. at 575.\\n\\nAnd “even when those positions are predetermined it is the nominee who becomes the\\n\\nparty’s ambassador to the general electorate in winning it over to the party’s views.” Id.\\n\\nYet, at the “crucial juncture” at which the members of this political association decide\\n\\nhow to select their nominee, id., the Commonwealth has taken the decision out of their\\n\\n 13\\n\\fhands: No matter what method of nomination the members of this party may prefer,\\n\\nVirginia law decrees that they must give way to the desire of the incumbent to hold a\\n\\nprimary if that incumbent was himself selected by primary previously and is seeking\\n\\nreelection.\\n\\n The burden is manifestly severe. This is not a case like Timmons, in which a\\n\\nparty’s ability to choose a nominee was reduced by only the small number of individuals\\n\\nthat already appeared elsewhere on the ballot. 520 U.S. at 351. Nor is this a case like\\n\\nClingman, in which the state’s Libertarian Party was required by state law to allow only\\n\\nits registered members and registered independent voters to participate in its primary. 544\\n\\nU.S. at 592. The burden there was not severe given the ease with which registered\\n\\nmembers of other parties who wanted to participate in the Libertarian primary could\\n\\nchange their registration. Id. Rather, this is a case in which the state has decided that the\\n\\nwishes of a party’s adherents must, in certain circumstances, be subordinated wholesale\\n\\nto the wishes of a single individual whose self-interest is self-evident; in these\\n\\ncircumstances, the party’s adherents are entirely shut out of the choice of nomination\\n\\nmethod—severely burdening their associational rights.\\n\\n C.\\n\\n Because the provision of the Incumbent Protection Act which protects\\n\\ncongressional incumbents—the fourth sentence—imposes a “severe” burden on the\\n\\nassociational rights of Virginia’s political parties, the Commonwealth must show that it is\\n\\n“narrowly tailored to serve a compelling state interest.” Cal. Democratic Party, 530 U.S.\\n\\nat 583. It cannot make this showing.\\n\\n 14\\n\\f Primaries add a crucial participatory dimension to democratic politics. Appellants\\n\\nassert that § 24.2-509(B) is akin to a mandatory primary statute, and therefore it serves\\n\\nthe interest of “assur[ing] that intraparty competition is resolved in a democratic fashion.”\\n\\nId. at 572. If § 24.2-509(B) truly were a mandatory primary statute its constitutionality\\n\\nwould be “too plain for argument.” Id. (quoting Am. Party of Tex. v. White, 415 U.S. 767,\\n\\n781 (1974)). But it is not: The statute does not by itself require any organ of a Virginia\\n\\npolitical party to use a primary as a method of nomination. Instead, the statute delegates\\n\\nthe power to force the party to use a primary to the incumbent office holder. Therein lies\\n\\nthe constitutional flaw.\\n\\n This delegation of power over the party to the incumbent office holder is not\\n\\nnarrowly tailored to meet the Commonwealth’s asserted interest. Under the terms of the\\n\\nstatute, the interest in democratic resolution of intraparty disputes will only be vindicated\\n\\nwhen and where an incumbent office holder decides that it is in his interest to do so. It is\\n\\nimplausible that the General Assembly would seek to vindicate this interest in such an\\n\\nodd, uneven, and underinclusive fashion. Instead, the text and structure of the law gives\\n\\nrise to the strong suggestion that the Incumbent Protection Act serves a different interest:\\n\\nthe interest, unsurprisingly, in incumbent protection.\\n\\n To be sure, incumbent protection is not per se an unconstitutional interest. In the\\n\\ncontext of redistricting, the Supreme Court has historically allowed maps to stand that\\n\\nwere drawn with the electoral interest of incumbents in mind. See, e.g., Karcher v.\\n\\nDaggett, 462 U.S. 725, 740 (1983). But the Court has not held that the interest in\\n\\nincumbent protection is a compelling one that can justify such direct intrusions on the\\n\\n 15\\n\\fFirst Amendment. See Gill v. Whitford, 138 S. Ct. 1916, 1934 (2018) (Kagan, J.,\\n\\nconcurring) (explaining that the Court did not address the First Amendment challenge to\\n\\nthe redistricting). Incumbent protection is simply not a strong enough interest here to\\n\\njustify the severe burden on the appellee’s associational rights.\\n\\n Incumbents, after all, are already blessed with myriad de facto advantages in the\\n\\nelectoral arena. Appellee’s expert, Professor Jeffrey A. Jenkins, testified that incumbents\\n\\ngenerally have better name recognition than challengers because of their time in the\\n\\npublic eye. J.A. 884. Incumbents also have the opportunity to win votes by enacting\\n\\npopular laws and servicing their constituents, and they have easier access to donors, as\\n\\nthey are proven winners. Id. All this contributes to the “scare-off” effect: potential\\n\\nchallengers, faced with the seemingly insurmountable hurdles, will decide not to run. Id.\\n\\n The other reason for incumbency advantage is more salutary. Voters may\\n\\nrecognize that incumbents provide our government with institutional memory and the\\n\\nwisdom that can only be won through experience. In the legislative branch, which could\\n\\nfind itself at a disadvantage when dealing with career officials and agency specialists of\\n\\nthe executive, the cumulative knowledge and experience brought by incumbents to the\\n\\nnegotiating table is particularly valuable. In this sense, incumbency evens the interbranch\\n\\nplaying field. Without it, novice legislators would find it more difficult to fulfill their\\n\\nconstitutional responsibilities.\\n\\n Thus, domination of the political parties by their incumbent office holders is,\\n\\nperhaps, a natural consequence of political reality. But to the already winning de facto\\n\\nhand dealt incumbents, § 24.2-509(B) adds a de jure ace: In the circumstances governed\\n\\n 16\\n\\fby the fourth sentence, challengers would have to compete with already advantaged\\n\\nincumbents in a selection process chosen by the incumbent himself. This goes too far. It\\n\\nnarrows the possibility of legislative renewal and refreshment through the infusion of\\n\\nnew blood. It risks making the electoral process sclerotic.\\n\\n Nothing in the foregoing analysis compromises the “major role” played by states\\n\\nin structuring their elections. Cal. Democratic Party, 530 U.S. at 572. Election\\n\\nadministration is necessarily an amalgam of state law and party procedures, and the\\n\\nCommonwealth is surely correct that the rights of political parties in this amalgam are not\\n\\nabsolute in character. We reiterate that “it is beyond question ‘that States may, and\\n\\ninevitably must, enact reasonable regulations of parties, elections, and ballots to reduce\\n\\nelection- and campaign-related disorder.’” Clingman, 544 U.S. at 593 (quoting Timmons,\\n\\n520 U.S. at 358). Rather, we simply hold that a state may not force a political party to\\n\\nhand control over its nomination method to a single, self-interested individual; the private\\n\\ninterest of an incumbent in winning reelection cannot, and certainly not in the manner\\n\\nchosen here, predominate over the associational rights of political parties.\\n\\n III.\\n\\n The district court also enjoined enforcement of the Act’s second and third\\n\\nsentences, which protect the nomination prerogatives of incumbent members of the\\n\\nGeneral Assembly. The Commonwealth argues that this was improper, as the Committee\\n\\nlacked standing to challenge those provisions. We disagree. The Committee suffered\\n\\ncognizable, traceable, and redressable injury from the Commonwealth’s application of\\n\\nthose sentences to its activities. And the second and third sentences are, if anything, even\\n\\n 17\\n\\fmore offensive to the First Amendment than the fourth. Accordingly, we affirm the\\n\\ndistrict court’s decision to enjoin the second and third sentences on § 24.2-509(B) as\\n\\nwell.\\n\\n Standing requires an injury in fact that is caused by the challenged conduct and is\\n\\nlikely to be redressed by a favorable decision. See Ohio Valley Envtl. Coal., Inc. v. Pruitt,\\n\\n893 F.3d 225, 229 (4th Cir. 2018). “To establish injury in fact, a plaintiff must show that\\n\\nhe or she suffered an invasion of a legally protected interest that is concrete and\\n\\nparticularized and actual or imminent, not conjectural or hypothetical.” Spokeo, Inc. v.\\n\\nRobins, 136 S. Ct. 1540, 1548 (2016) (internal quotation marks omitted). Throughout a\\n\\nlawsuit “the standing inquiry remains focused on whether the party invoking jurisdiction\\n\\nhad the requisite stake in the outcome when the suit was filed.” Davis v. Fed. Election\\n\\nComm’n, 554 U.S. 724, 734 (2008).\\n\\n The Committee suffered an injury in fact at the time the lawsuit was filed as a\\n\\nresult of the Commonwealth’s application of the second and third sentences, as\\n\\ndemonstrated by the “specific facts” adduced in its submissions to this court. Lujan v.\\n\\nDefenders of Wildlife, 504 U.S. 555, 561 (1992). These facts are as follows: The\\n\\nDepartment issues a series of forms for incumbents and party committees to notify the\\n\\nCommonwealth which nomination method they plan to use, as they are required to do by\\n\\nlaw. See Va. Code Ann. § 24.2-516. These forms reflect the Department’s understanding\\n\\nof how to apply the Incumbent Protection Act. And yet, throughout the 2016 election\\n\\ncycle and through the filing of this lawsuit, these forms applied the Act’s second and\\n\\nthird sentences, which should only apply to incumbent members of the General\\n\\n 18\\n\\fAssembly, to the 6th Congressional Committee as well. Incumbent members of Congress\\n\\nwere given the same plenary power to designate any method of nomination no matter the\\n\\ncircumstance, as if they were incumbent members of the General Assembly.\\n\\n The forms themselves best tell the story:\\n\\n DESIGNATION OF METHOD OF NOMINATION\\n for\\n SENATE OF VIRGINIA\\n 2015\\n ***\\n I, the undersigned incumbent of the Senate of Virginia district indicated\\n above, am seeking re-election and designate the following method of\\n nomination to be used in determining the party’s candidate for this office\\n subject to the forthcoming November general election.\\n\\nJ.A. 892.\\n\\n 2016 DESIGNATION OF METHOD OF NOMINATION\\n ***\\n I, the undersigned incumbent of the district indicated above, am seeking\\n re-election and designate the following method of nomination to be used in\\n determining the party’s candidate for this office subject to the coming\\n November general election.\\n\\nJ.A. 873. The form used by incumbent General Assembly members in the 2015 election\\n\\ncycle and by incumbent Members of Congress in the 2016 election cycle are in all\\n\\nmaterial respects the same. As the Committee noted, “[n]ot only did Appellants\\n\\npromulgate these forms, they directed non-General Assembly incumbents and party\\n\\nchairmen to use them.” Resp. Br. of Appellee at 13.\\n\\n It is plain therefore that, on those facts, the Committee suffered a sufficiently\\n\\n“concrete” injury in fact to sustain its challenge to the second and third sentences of the\\n\\nAct. Because of the forms, any candidate that the 6th Congressional Committee wished to\\n\\n\\n 19\\n\\frecruit, or anyone contemplating an electoral challenge to the incumbent, faced the\\n\\nprospect of having to compete in a nomination process selected by that incumbent.\\n\\nPlainly, this prospect would “dramatically change[] the plaintiffs’ decisions about\\n\\ncampaign financing, messages to stress, and candidates to recruit.” Miller I, 462 F.3d at\\n\\n317. This distortion of political decisionmaking constitutes an ongoing and concrete\\n\\ninjury sufficient to meet the injury-in-fact prong of constitutional standing analysis. Id. at\\n\\n317-18.\\n\\n That injury, of course, is particularized because the 6th Congressional Committee\\n\\nserves a unique function in selecting the Republican nominee for Virginia’s 6th\\n\\nCongressional District. See Lujan, 504 U.S. at 560. The remaining standing analysis is\\n\\nstraightforward: The injury was caused by promulgation of the forms based on the Act’s\\n\\nsecond and third sentences, and therefore will be redressed if we find those sentences to\\n\\nbe inconsistent with the First Amendment. For these reasons, the Committee has standing\\n\\nto challenge the portions of § 24.2-509(B) that protect the nomination prerogatives of\\n\\nGeneral Assembly members.\\n\\n In response, the Department argues that the challenge to the second and third\\n\\nsentences became moot when the Department updated the offending election forms. 2 But\\n\\n\\n2\\n The Department also argues that plaintiff’s challenge to the Act’s fourth sentence is\\nmoot. It notes that because the current 6th District incumbent was selected by convention,\\nthe plaintiff will not be forced to accede to a primary until 2022 at the earliest. But that\\nargument relies on the same cramped interpretation of standing that we rejected in Miller\\nI, 462 F.3d at 316-18. The injuries inflicted by laws that distort the primary process, like\\nthe Incumbent Protection Act, are not confined to the short duration of any particular\\nprimary, but instead reflect the reality that “campaign planning decisions have to be made\\n(Continued)\\n 20\\n\\fthe update occurred after the lawsuit had been filed. Promulgating new forms may well\\n\\nhave been the right thing to do in accordance with state law. But as a litigation tactic,\\n\\nsuch backpedaling will rarely serve to moot a case in federal court. Friends of the Earth,\\n\\nInc. v. Laidlaw Environmental Services (TOC), Inc., 528 U.S. 167, 189-94 (2000). The\\n\\nmootness doctrine ordinarily does not extend to situations where a party quits its\\n\\noffending conduct partway through litigation. Id. After all, “a party should not be able to\\n\\nevade judicial review, or to defeat a judgment, by temporarily altering questionable\\n\\nbehavior.” Porter v. Clarke, 852 F.3d 358, 364 (4th Cir. 2017) (internal quotation marks\\n\\nomitted). To overcome that general rule, the Department bears “[t]he heavy burden of\\n\\npersuading the court,” Laidlaw, 528 U.S. 167, 189 (2000) (internal quotation marks and\\n\\nalterations omitted), that it is “absolutely clear that the allegedly wrongful behavior could\\n\\nnot reasonably be expected to recur.” Wall v. Wade, 741 F.3d 492, 497 (2014) (quoting\\n\\nLaidlaw, 528 U.S. at 189).\\n\\n The Department cannot carry this burden. It has a history of frequently revising\\n\\nthe relevant election forms. The forms used for congressional nominations in 2014, for\\n\\nexample, reflected the fourth sentence of the Incumbent Protection Act and not the\\n\\nsecond and third. Yet the congressional nomination forms were inexplicably changed for\\n\\n\\nmonths, or even years, in advance of the election to be effective.” Id. at 317-18. The 6th\\nCongressional Committee’s claims thus did not become moot with the passing of the\\n2018 election season. The dispute over the Act’s fourth sentence, rather, is alive and well.\\nEven so, if the Department were correct that electoral disputes became moot with each\\npassing election cycle, this challenge, like many electoral challenges, would plainly be\\ncapable of repetition yet evading review. See, e.g., Davis v. Fed. Election Comm’n, 554\\nU.S. 724, 735-36 (2008).\\n\\n 21\\n\\fthe 2016 congressional elections to reflect the Act’s more fulsome General Assembly\\n\\nprotections instead. The Department has offered no explanation for why the forms were\\n\\nchanged to the benefit of incumbents between the 2014 and 2016 congressional elections.\\n\\nEven though the forms apparently have been edited once again, we have little confidence\\n\\nthat the forms will not revert back if we hold that this lawsuit is moot. Indeed, that danger\\n\\nis particularly acute when, as here, a change in the forms would confer benefits upon\\n\\npolitical incumbents. The Incumbent Protection Act transparently advances the interests\\n\\nof those who control the apparatus of government; it is hardly beyond the realm of\\n\\nplausibility that it would be administered with that same purpose in mind. The\\n\\nDepartment’s May 23, 2018 Suggestion of Mootness is accordingly denied.\\n\\n We may thus properly consider the 6th Congressional Committee’s facial and as\\n\\napplied First Amendment challenges to the Incumbent Protection Act’s protection of\\n\\nincumbent members of the General Assembly. A facial challenge to a law will succeed\\n\\nafter a showing “that no set of circumstances exist under which the law would be valid,\\n\\nor that the law lacks any plainly legitimate sweep.” Greater Balt. Center for Pregnancy\\n\\nConcerns, Inc. v. Mayor & City Council of Balt., 721 F.3d 264, 282 (4th Cir. 2013) (en\\n\\nbanc) (internal quotation marks and alterations omitted). In the First Amendment context,\\n\\na facial challenge may also succeed under overbreadth doctrine. Id. But there is no need\\n\\nto employ overbreadth doctrine in this case, for the Act’s second and third sentences\\n\\ncannot be applied in a manner consistent with the First Amendment.\\n\\n The Department fails to identify a single circumstance where the Act’s second and\\n\\nthird sentences could be lawfully applied. And we find none. The second and third\\n\\n 22\\n\\fsentences not only share the constitutional infirmities of the fourth sentence but exhibit\\n\\nthose infirmities to an even greater degree. The fourth sentence allows some incumbents\\n\\nto force a primary under certain designated circumstances. The second sentence goes\\n\\nfurther by empowering incumbents to impose their choice of any method of nomination\\n\\nno matter what the party prefers under almost any circumstances. 3 These advantages,\\n\\nwhen given to state or federal incumbents, run afoul of the First Amendment for all the\\n\\nreasons discussed in detail in Part II, supra.\\n\\n The Department raises yet one more challenge, arguing that the district court was\\n\\nwrong to enjoin the Incumbent Protection Act in its entirety. See Va. Code Ann. § 24.2-\\n\\n509(B). We review the district court’s decision to enjoin the statute for abuse of\\n\\ndiscretion. U.S. Airline Pilots Ass’n v. Awappa, LLC, 615 F.3d 312, 320 (4th Cir. 2010).\\n\\nThe Act comprises six sentences. We have now found that each of its operative\\n\\nprovisions—namely the second, third, and fourth sentences—is unconstitutional. The\\n\\nremaining sentences merely explain how to apply them. The district court did not abuse\\n\\nits discretion in enjoining the Incumbent Protection Act in toto.\\n\\n IV.\\n\\n Our decision is a narrow one. It is directed at a discrete constitutional imbalance\\n\\ncreated by permitting single office holders to negate the associational rights of political\\n\\nparties in an area central to the party’s very reason for being. Our ruling in no way limits\\n\\n 3\\n The third sentence applies in the relatively rare situation where there is more than\\none incumbent for the same office. In that situation, the statute requires incumbents’\\nconsent for any method of nomination other than a primary. § 24.2-509(B).\\n\\n\\n 23\\n\\fthe ability of states to enact “reasonable regulations of parties, elections, and ballots.”\\n\\nTimmons, 520 U.S. at 358. The associational rights of political parties are, after all, not\\n\\nabsolute. Laws that impose a slight or lesser burden on associational rights are owed\\n\\ndeference, especially when justified by the need “to reduce election- and campaign-\\n\\nrelated disorder.” Id. But our constitutional responsibility, set forth so plainly by the\\n\\nSupreme Court, requires us to ensure that this “deference does not risk such constitutional\\n\\nevils as, say, permitting incumbents to insulate themselves from effective electoral\\n\\nchallenge.” Nixon v. Shrink Mo. Gov’t PAC, 528 U.S. 377, 402 (2000) (Breyer, J.,\\n\\nconcurring). The Incumbent Protection Act reflects precisely that infirmity, and it is\\n\\nprecisely why we cannot allow the Act to stand.\\n\\n For the foregoing reasons, the judgment of the district court is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 24\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4357290/\", \"author_raw\": \"WILKINSON, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"WILKINSON"},"judge2":{"kind":"string","value":"MOTZ"},"judge3":{"kind":"string","value":"DUNCAN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4580037/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: 6TH CONGRESSIONAL DISTRICT REPUBLICAN COMMITTEE, Plaintiff - Appellee, and Anne Taetzsch Fitzgerald, Individually and as Chairman of the 20th House of Delegates District Republican Committee; Karen U. Kwiatkowski, Individually; Edward A. Yensho, Individually and as Chairman of the Green County Republican Committee; 20th House of Delegates District Republican Committee, Plaintiffs, v. James B. ALCORN, in His Official Capacity as Chairman of the Virginia State Board of Elections ; Clara Belle Wheeler, in Her Official Capacity as Vice-Chairman of the Virginia State Board of Elections ; Singleton B. McAllister, in Her Official Capacity as Secretary of the Virginia State Board of Elections ; Virginia Department of Elections, Defendants - Appellants.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-09\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1111\n\n\n6TH CONGRESSIONAL DISTRICT REPUBLICAN COMMITTEE,\n\n Plaintiff – Appellee,\n\n and\n\nANNE TAETZSCH FITZGERALD, individually and as Chairman of the 20th\nHouse of Delegates District Republican Committee; KAREN U.\nKWIATKOWSKI, individually; EDWARD A. YENSHO, individually and as\nChairman of the Green County Republican Committee; 20TH HOUSE OF\nDELEGATES DISTRICT REPUBLICAN COMMITTEE,\n\n Plaintiffs,\n\n v.\n\nJAMES B. ALCORN, in his official capacity as Chairman of the Virginia State\nBoard of Elections; CLARA BELLE WHEELER, in her official capacity as Vice-\nChairman of the Virginia State Board of Elections; SINGLETON B.\nMCALLISTER, in her official capacity as Secretary of the Virginia State Board of\nElections; VIRGINIA DEPARTMENT OF ELECTIONS,\n\n Defendants - Appellants.\n\n\nAppeal from the United States District Court for the Western District of Virginia, at\nHarrisonburg. Michael F. Urbanski, Chief District Judge. (5:17-cv-00016-MFU-JCH)\n\n\nArgued: December 12, 2018 Decided: January 9, 2019\n\n\nBefore WILKINSON, MOTZ, and DUNCAN, Circuit Judges.\n\fAffirmed by published opinion. Judge Wilkinson wrote the opinion, in which Judge Motz\nand Judge Duncan joined.\n\n\nARGUED: Toby Jay Heytens, OFFICE OF THE ATTORNEY GENERAL OF\nVIRGINIA, Richmond, Virginia, for Appellants. Jeffrey R. Adams, WHARTON,\nALDHIZER & WEAVER, PLC, Harrisonburg, Virginia, for Appellee. ON BRIEF:\nMark R. Herring, Attorney General, Stephen A. Cobb, Deputy Attorney General,\nMatthew R. McGuire, Principal Deputy Solicitor General, Michelle S. Kallen, Deputy\nSolicitor General, OFFICE OF THE ATTORNEY GENERAL OF VIRGINIA,\nRichmond, Virginia, for Appellants. Charles F. Hilton, Thomas E. Ullrich, Lucas I.\nPangle, WHARTON ALDHIZER & WEAVER, PLC, Harrisonburg, Virginia; John C.\nWirth, NELSON MCPHERSON SUMMERS & SANTOS, Staunton, Virginia, for\nAppellee.\n\n\n\n\n 2\n\fWILKINSON, Circuit Judge:\n\n The 6th Congressional District Republican Committee argues that Virginia’s\n\nIncumbent Protection Act, Va. Code Ann. § 24.2-509(B), violates the First Amendment\n\nof the Constitution. The district court agreed and enjoined § 24.2-509(B) in its entirety.\n\nFor the reasons that follow, we now affirm.\n\n I.\n\n A.\n\n Virginia law generally allows the Commonwealth’s political parties considerable\n\ndiscretion in deciding how to nominate their candidates for office. Section 24.2-509(A)\n\nempowers the “duly constituted authorities” of the state and local parties “to determine\n\nthe method by which a party nomination . . . shall be made.” The parties make use of this\n\nlatitude. For example, the Republican Party of Virginia, with whom the appellee here is\n\naffiliated, allows for four different methods of nomination: a primary, a party canvass, a\n\nconvention, and a mass meeting. Fitzgerald v. Alcorn, 285 F. Supp. 3d 922, 927 (W.D.\n\nVa. 2018). Under the Party’s Plan of Organization, committees established in every\n\nlocality, state legislative district, and congressional district are empowered to choose\n\namong these methods to nominate candidates for their political subdivision. J.A. 37, 38,\n\n40.\n\n The differences between these methods are substantial. Each one “‘create[s] a\n\ndifferent distribution of potential voters (or decision makers) in the nomination process.’\n\nFor example, primaries involve the largest pool of potential voters, whereas conventions\n\nand mass meetings ‘lend themselves more toward committed partisans.’” Alcorn, 285 F.\n\n 3\n\fSupp. 3d at 935 (quoting J.A. 884-85, 885-86). The choice of method, therefore, could\n\nhave a significant influence on the choice of nominee.\n\n Subsection 24.2-509(B), often called the Incumbent Protection Act, however,\n\nlimits the broad authority recognized by subsection A. 1 The second and third sentences\n\napply to those subdivisions of the state party that select nominees for candidates to the\n\n\n1\n The full text of Virginia Code § 24.2-509 is reprinted below, with the sentences in\nsubsection B numbered for ease of reference:\n\nA. The duly constituted authorities of the state political party shall have the right to\n determine the method by which a party nomination for a member of the United States\n Senate or for any statewide office shall be made. The duly constituted authorities of\n the political party for the district, county, city, or town in which any other office is to\n be filled shall have the right to determine the method by which a party nomination for\n that office shall be made.\n\nB. [1] Notwithstanding subsection A, the following provisions shall apply to the\n determination of the method of making party nominations. [2] A party shall nominate\n its candidate for election for a General Assembly district where there is only one\n incumbent of that party for the district by the method designated by that incumbent, or\n absent any designation by him by the method of nomination determined by the party.\n [3] A party shall nominate its candidates for election for a General Assembly district\n where there is more than one incumbent of that party for the district by a primary\n unless all the incumbents consent to a different method of nomination. [4] A party,\n whose candidate at the immediately preceding election for a particular office other\n than the General Assembly (i) was nominated by a primary or filed for a primary but\n was not opposed and (ii) was elected at the general election, shall nominate a\n candidate for the next election for that office by a primary unless all incumbents of\n that party for that office consent to a different method.\n\n [5] When, under any of the foregoing provisions, no incumbents offer as candidates\n for reelection to the same office, the method of nomination shall be determined by the\n political party.\n\n [6] For the purposes of this subsection, any officeholder who offers for reelection to\n the same office shall be deemed an incumbent notwithstanding that the district which\n he represents differs in part from that for which he offers for election.\n\n\n 4\n\fGeneral Assembly. Those sentences allow incumbent members of the General Assembly\n\nwho are running for reelection, where there is only one incumbent, to “designate[]” the\n\nmethod of nomination they prefer. Under this statute, the wishes of the party are\n\nimmaterial; no matter where the party’s plan of organization may vest the power to\n\nchoose nomination methods, the law trumps, granting the power to the incumbent.\n\n The fourth sentence of the Act applies to those components of political parties that\n\nmake the nominations for “particular office[s]” other than for the General Assembly,\n\nincluding nominations for the U.S. House of Representatives. In these races, the\n\nincumbent officeholder may insist that his or her party use a primary as its nomination\n\nmethod as long as (1) the incumbent was selected by primary in the previous election\n\ncycle and (2) the incumbent is running for reelection. Again, the statute trumps the\n\nparty’s plan of organization, which, in this case allows the committees responsible for\n\ncongressional nominations to choose between the approved methods (excluding mass\n\nmeetings) without interference by the incumbent, J.A. 37.\n\n The Virginia Department of Elections, however, has not always respected the\n\ndistinction made between the second and third sentences on the one hand, and the fourth\n\nsentence on the other. In the 2016 and 2017 election cycles, for example, the Department\n\npromulgated forms that allowed non-General Assembly incumbents to “designate” their\n\npreferred method of nomination as if their elections were governed by the second and\n\nthird sentences. After the commencement of this litigation, and only after the appellees\n\npointed out the mistake, the Department issued new forms that applied the fourth\n\nsentences to these races.\n\n 5\n\f Virginia has not identified a single other state that has a statute like the Incumbent\n\nProtection Act, and this is not the first case to consider a constitutional challenge to it. In\n\n2007, for example, this court considered a challenge to the Act. Miller v. Brown, 503\n\nF.3d 360 (4th Cir. 2007) (“Miller II”). There, we held that an incumbent cannot\n\nconstitutionally force his or her party to use an open primary, as this would be an\n\nimpermissible burden on the party’s associational rights. Id. at 368-71. We did not,\n\nhowever, reach the different question of the constitutionality of incumbents’ statutory\n\npower to dictate any nomination method.\n\n B.\n\n This appeal stems from the 6th Congressional District Republican Committee’s\n\nchallenge to the Incumbent Protection Act under 42 U.S.C. § 1983. See Alcorn, 285 F.\n\nSupp. 3d at 922. The Committee is responsible for nominating candidates for the U.S.\n\nHouse of Representatives for the 6th Congressional District, which “covers much of the\n\nwest-central portion of Virginia, from Roanoke to Front Royal.” Id. at 927. Under the\n\nParty’s Plan of Organization, it is composed of the “District Chairman,” the “Unit\n\nChairman” (the chair of each relevant locality’s committee), the “District Representative\n\nof the Virginia Federation of Republican Women,” the “Young Republican Federation\n\nDistrict Committeeman,” the “College Republican Federation District Committeeman,”\n\nand the “District members of the State Central Committee.” J.A. 36-37. The Committee,\n\nalong with other plaintiffs who were dismissed from the suit and do not appeal, raised\n\nfacial and as applied challenges to the Incumbent Protection Act, claiming that it\n\nabridged their rights under the First and Fourteenth Amendments of the U.S.\n\n 6\n\fConstitution. The named defendants include the Virginia Department of Elections and the\n\nthree members of the Virginia State Board of Elections at the time the suit was filed.\n\nAlcorn, 285 F. Supp. 3d at 928.\n\n The district court, relying on Miller v. Brown, 462 F.3d 312 (4th Cir. 2006)\n\n(“Miller I”), found that the Committee had standing to challenge the Act. Alcorn, 285 F.\n\nSupp. 3d at 937. It then proceeded to evaluate the burden posed by § 24.2-509(B) on the\n\nCommittee’s associational rights, concluding that it was “severe” because it provided\n\n“incumbents with a statutory right to dictate political parties’ internal affairs . . . .” Id. at\n\n952. The burden was “especially” onerous because it trespassed on the “realm of\n\nselecting candidates.” Id. Given the magnitude of the burden, the district court found that\n\n“the Act can survive constitutional scrutiny only if it is ‘narrowly tailored to advance a\n\ncompelling state interest.’” Id. (quoting Burdick v. Takushi, 504 U.S. 428, 433 (1992)).\n\nThe district court ultimately concluded that the Act did not survive such scrutiny. Id. at\n\n953.\n\n The district court thus permanently enjoined enforcement of the entire Incumbent\n\nProtection Act on January 19, 2018. J.A. 1473. The court enjoined all six sentences of\n\n§ 24.2-509(B) because, according to the court, the second and third sentences—which\n\nprotect the nomination prerogatives of incumbent General Assembly members—could\n\nnot be severed from the fourth—which protects the nomination prerogatives of, inter alia,\n\nmembers of Congress. The court additionally found that the Committee had standing to\n\nchallenge the second and third sentences under the overbreadth doctrine. Alcorn, 285 F.\n\nSupp. 3d at 955. Finally, the district court concluded that the Act had “no legitimate\n\n 7\n\fsweep” and so a facial challenge to all its provisions was appropriate. Id. at 955-56. After\n\nthe notice of appeal had been filed, the district court stayed its permanent injunction order\n\non February 5, 2018, to avoid interfering with the ongoing nomination cycle. J.A. 1481.\n\nAfter that cycle concluded, however, the district court vacated its stay on September 24,\n\n2018. J.A. 1680. During the course of this appeal, the Department filed a motion to\n\nvacate the injunction on the basis of mootness. We held that motion in abeyance pending\n\noral argument, and both parties expanded on their arguments in their briefing on the\n\nmerits.\n\n II.\n\n The district court found that the fourth sentence of the Incumbent Protection Act,\n\nwhich protects the nomination prerogatives of incumbent members of Congress among\n\nothers, violated the First Amendment. Because this provision imposes a severe burden on\n\nthe associational rights of Virginia’s political parties, and because the Commonwealth\n\nhas been unable to show that it is narrowly tailored to serve a compelling state interest,\n\nwe agree.\n\n A.\n\n Freedom of association has, for centuries, been at the heart of the American\n\nsystem of government and individual rights. In 1831, when Alexis de Tocqueville arrived\n\nin the United States, he was shocked to discover that our nation was the only “country on\n\nthe face of the earth where the citizens enjoy unlimited freedom of association for\n\npolitical purposes.” Alexis de Tocqueville, 2 Democracy in America 123 (Henry Reeves\n\ntrans., 1863). In America, “the most democratic country on the face of the earth,” the\n\n 8\n\f“art” of forming political associations had been “carried to the highest perfection.” Id. at\n\n115. Because of this, “Americans of all ages, all conditions, and all dispositions,\n\nconstantly form associations.” Id. at 114.\n\n De Tocqueville identified this propensity to associate as one of the sources of the\n\nastonishing political dynamism of the young Republic, writing that American political\n\nassociations are “the mother of action,” id. at 125, and that they “stimulate competition,\n\nand . . . discover those arguments which are most fitted to act upon the majority.” Id. at\n\n210. The right to associate for political purposes, de Tocqueville proclaimed, is “[t]he\n\nmost natural privilege of man, next to the right of acting for himself.” Id. at 209.\n\nAccordingly, “the right of association is almost as inalienable as the right of personal\n\nliberty. No legislator can attack it without impairing the very foundations of society.” Id.\n\n The multiplicity of political associations lauded by de Tocqueville was the result\n\nof the Founders’ decision to enshrine the “freedom to join together in furtherance of\n\ncommon political beliefs” in the First Amendment of the Constitution. Tashjian v.\n\nRepublican Party of Conn., 479 U.S. 208, 214-15 (1986). That Amendment promises\n\nAmericans the right not just to proclaim a political vision but to join with their\n\ncompatriots and actually advance that vision. Because, while an individual may be, in de\n\nTocqueville’s words, “feeble and consequently more incapable of preserving his\n\nfreedom,” de Tocqueville, supra, at 123, when individuals combine in association they\n\n“acquire facility in prosecuting great undertakings in common,” id. at 114. Some of the\n\n“great undertakings” accomplished by political associations protected by the First\n\nAmendment include the Abolitionist Movement, the Women’s Suffrage Movement, the\n\n 9\n\fLabor Movement, and the Civil Rights Movement—the fruits of which continue to shape\n\nour politics and society for the better to this day.\n\n Of all political associations protected by the First Amendment, political parties\n\nthemselves merit special attention. Like other political participants, parties advance a\n\nparticular vision. Unlike others, however, political parties must also nominate candidates\n\nfor office, compete in elections, and, if successful, help to translate campaign appeals into\n\nprogrammatic action. In so doing, political parties provide a vehicle for voters to advance\n\ntheir own political views. Without groups like modern political parties, “[r]epresentative\n\ndemocracy in any populous unit of governance” would be “unimaginable.” Cal.\n\nDemocratic Party v. Jones, 530 U.S. 567, 574 (2000).\n\n Perhaps no function of a party is more central to its purpose than the selection of\n\ncandidates for office, which “often determines the party’s positions on the most\n\nsignificant public policy issues of the day.” Id. at 575. It is no surprise, therefore, that the\n\nSupreme Court is “vigorous[]” in affirming the “special protection” owed to the\n\nassociational rights of political parties as they pertain to the parties’ choice of nominees.\n\nId. at 576. Statutes that severely burden a party’s associational rights must be narrowly\n\ntailored to advance a compelling government interest. Id. at 581-82. In Democratic Party\n\nof the United States v. Wisconsin ex rel. La Follette, the Court invalidated a Wisconsin\n\nlaw that required the national Democratic Party to seat certain delegates chosen in an\n\nopen primary. 450 U.S. 107 (1981). In Tashjian v. Republican Party of Connecticut, the\n\nCourt struck down a Connecticut law that forbade state parties from conducting open\n\nprimaries because the law burdened “associational opportunities at the crucial juncture at\n\n 10\n\fwhich the appeal to common principles may be translated into concerted action . . . .” 479\n\nU.S. at 216. In Eu v. San Francisco County Democratic Central Committee, the Court\n\ninvalidated laws dictating political parties’ internal affairs and prohibiting them from\n\nendorsing candidates for office. 489 U.S. 214 (1989). And in California Democratic\n\nParty v. Jones, the Court struck down a mandatory open primary law as it burdened the\n\n“political association’s right to exclude” in the “candidate-selection process.” 530 U.S. at\n\n575.\n\n Not every burden on associational rights is unconstitutional. “States have a major\n\nrole to play in structuring and monitoring the election process, including” nominee\n\nselection. Cal. Democratic Party, 530 U.S. at 572. Where the burden imposed by the\n\nstate is not “severe”—where it is “lesser”—courts engage in “less exacting review.”\n\nTimmons v. Twin Cities Area New Party, 520 U.S. 351, 358 (1997). In Timmons, the\n\nCourt upheld a Minnesota law that prohibited a candidate from appearing on the ballot as\n\nthe nominee of more than one party after finding that the law did “not severely burden\n\nthat party’s associational rights.” Id. at 359. Nothing prevented the party from endorsing\n\nthe candidate of another party; nothing prevented the party for campaigning for the\n\ncandidate of another party. The law’s only effect was to “reduce the universe of potential\n\ncandidates who may appear on the ballot as the party’s nominee . . . by ruling out those\n\nfew individuals who . . . have already agreed to be another party’s candidate.” Id. at 363.\n\nThis slight a reduction could not be a severe burden. Id.; see also Clingman v. Beaver,\n\n544 U.S. 581 (2005) (upholding law mandating a “semiclosed” primary, in which\n\nregistered members of opposing parties and unaffiliated voters could not participate).\n\n 11\n\f Political parties have, of course, come in for their fair share of criticism\n\nthroughout our history. Chancellor James Kent, in an 1830 letter to Daniel Webster,\n\nwrote that “Hamilton said in the Federalist, in his speeches, and a hundred times to me,\n\nthat factions would ruin us, and our government had not sufficient energy and balance to\n\nresist the propensity to them, and to control their tyranny and their profligacy.” John B.\n\nCassoday, James Kent & Joseph Story, 12 Yale L.J. 146, 151 (1903) (quoting letter). But\n\nwhether the divisiveness in public discourse traces to the presence of political parties or\n\nto the divisions inherent in the issues themselves elides the fact that parties have long\n\nsince become a fact of constitutional life. And what emerges from the above Supreme\n\nCourt cases is no all-or-nothing proposition but instead that law is not insensitive to\n\nmatters of degree: Those laws that impose a “heav[y]” or “severe” burden on a political\n\nparty’s right to choose its nominee are unconstitutional unless they serve a “compelling\n\nstate interest” and are “narrowly tailored” to do so. Cal. Democratic Party, 530 U.S. at\n\n583. It is to that inquiry that we now turn.\n\n B.\n\n The fourth sentence of Virginia Code § 24.2-509(B), the provision of the\n\nIncumbent Protection Act that applies to congressional incumbents among others,\n\nunquestionably poses a severe burden on the associational rights of the Commonwealth’s\n\npolitical parties. In evaluating the law’s imposition on associational rights, we must\n\n“weigh the ‘character and magnitude’ of the burden” it occasions. Timmons, 520 U.S. at\n\n358 (quoting Burdick, 504 U.S. at 434). We keep in mind also that “[a]ny interference\n\n\n\n 12\n\fwith the freedom of a party is simultaneously an interference with the freedom of its\n\nadherents.” Tashjian, 479 U.S. at 215 (quoting Democratic Party, 450 U.S. at 122).\n\n Subsection 24.2-509(A) grants the “duly constituted authorities” of the\n\nCommonwealth’s political parties considerable discretion in selecting the method of\n\nchoosing their nominees. The Incumbent Protection Act, subsection 24.1-509(B), carves\n\nexceptions to this rule in favor of incumbents. To recapitulate, the second and third\n\nsentences allow incumbent members of the General Assembly to dictate the method their\n\nparty shall use in selecting the nominee for the office that incumbent holds. The fourth\n\nsentence allows incumbent members of the U.S. House of Representatives, who were\n\nthemselves nominated by primary in the last election cycle, to require their party to use a\n\nprimary in the current election cycle to nominate a candidate for the office they hold if\n\nthey themselves are seeking reelection. In short, the associational rights of Virginia’s\n\npolitical parties that are recognized and protected by § 24.2-509(A) are taken away by §\n\n24.1-509(B) and given instead to a single individual—the incumbent.\n\n The weight of this burden could not be more obvious. The members of the 6th\n\nCongressional District Committee have, as generations of Americans did before them,\n\nbanded together to advance their political views. The selection of a nominee “often\n\ndetermines” the contours of the party platform. Cal. Democratic Party, 530 U.S. at 575.\n\nAnd “even when those positions are predetermined it is the nominee who becomes the\n\nparty’s ambassador to the general electorate in winning it over to the party’s views.” Id.\n\nYet, at the “crucial juncture” at which the members of this political association decide\n\nhow to select their nominee, id., the Commonwealth has taken the decision out of their\n\n 13\n\fhands: No matter what method of nomination the members of this party may prefer,\n\nVirginia law decrees that they must give way to the desire of the incumbent to hold a\n\nprimary if that incumbent was himself selected by primary previously and is seeking\n\nreelection.\n\n The burden is manifestly severe. This is not a case like Timmons, in which a\n\nparty’s ability to choose a nominee was reduced by only the small number of individuals\n\nthat already appeared elsewhere on the ballot. 520 U.S. at 351. Nor is this a case like\n\nClingman, in which the state’s Libertarian Party was required by state law to allow only\n\nits registered members and registered independent voters to participate in its primary. 544\n\nU.S. at 592. The burden there was not severe given the ease with which registered\n\nmembers of other parties who wanted to participate in the Libertarian primary could\n\nchange their registration. Id. Rather, this is a case in which the state has decided that the\n\nwishes of a party’s adherents must, in certain circumstances, be subordinated wholesale\n\nto the wishes of a single individual whose self-interest is self-evident; in these\n\ncircumstances, the party’s adherents are entirely shut out of the choice of nomination\n\nmethod—severely burdening their associational rights.\n\n C.\n\n Because the provision of the Incumbent Protection Act which protects\n\ncongressional incumbents—the fourth sentence—imposes a “severe” burden on the\n\nassociational rights of Virginia’s political parties, the Commonwealth must show that it is\n\n“narrowly tailored to serve a compelling state interest.” Cal. Democratic Party, 530 U.S.\n\nat 583. It cannot make this showing.\n\n 14\n\f Primaries add a crucial participatory dimension to democratic politics. Appellants\n\nassert that § 24.2-509(B) is akin to a mandatory primary statute, and therefore it serves\n\nthe interest of “assur[ing] that intraparty competition is resolved in a democratic fashion.”\n\nId. at 572. If § 24.2-509(B) truly were a mandatory primary statute its constitutionality\n\nwould be “too plain for argument.” Id. (quoting Am. Party of Tex. v. White, 415 U.S. 767,\n\n781 (1974)). But it is not: The statute does not by itself require any organ of a Virginia\n\npolitical party to use a primary as a method of nomination. Instead, the statute delegates\n\nthe power to force the party to use a primary to the incumbent office holder. Therein lies\n\nthe constitutional flaw.\n\n This delegation of power over the party to the incumbent office holder is not\n\nnarrowly tailored to meet the Commonwealth’s asserted interest. Under the terms of the\n\nstatute, the interest in democratic resolution of intraparty disputes will only be vindicated\n\nwhen and where an incumbent office holder decides that it is in his interest to do so. It is\n\nimplausible that the General Assembly would seek to vindicate this interest in such an\n\nodd, uneven, and underinclusive fashion. Instead, the text and structure of the law gives\n\nrise to the strong suggestion that the Incumbent Protection Act serves a different interest:\n\nthe interest, unsurprisingly, in incumbent protection.\n\n To be sure, incumbent protection is not per se an unconstitutional interest. In the\n\ncontext of redistricting, the Supreme Court has historically allowed maps to stand that\n\nwere drawn with the electoral interest of incumbents in mind. See, e.g., Karcher v.\n\nDaggett, 462 U.S. 725, 740 (1983). But the Court has not held that the interest in\n\nincumbent protection is a compelling one that can justify such direct intrusions on the\n\n 15\n\fFirst Amendment. See Gill v. Whitford, 138 S. Ct. 1916, 1934 (2018) (Kagan, J.,\n\nconcurring) (explaining that the Court did not address the First Amendment challenge to\n\nthe redistricting). Incumbent protection is simply not a strong enough interest here to\n\njustify the severe burden on the appellee’s associational rights.\n\n Incumbents, after all, are already blessed with myriad de facto advantages in the\n\nelectoral arena. Appellee’s expert, Professor Jeffrey A. Jenkins, testified that incumbents\n\ngenerally have better name recognition than challengers because of their time in the\n\npublic eye. J.A. 884. Incumbents also have the opportunity to win votes by enacting\n\npopular laws and servicing their constituents, and they have easier access to donors, as\n\nthey are proven winners. Id. All this contributes to the “scare-off” effect: potential\n\nchallengers, faced with the seemingly insurmountable hurdles, will decide not to run. Id.\n\n The other reason for incumbency advantage is more salutary. Voters may\n\nrecognize that incumbents provide our government with institutional memory and the\n\nwisdom that can only be won through experience. In the legislative branch, which could\n\nfind itself at a disadvantage when dealing with career officials and agency specialists of\n\nthe executive, the cumulative knowledge and experience brought by incumbents to the\n\nnegotiating table is particularly valuable. In this sense, incumbency evens the interbranch\n\nplaying field. Without it, novice legislators would find it more difficult to fulfill their\n\nconstitutional responsibilities.\n\n Thus, domination of the political parties by their incumbent office holders is,\n\nperhaps, a natural consequence of political reality. But to the already winning de facto\n\nhand dealt incumbents, § 24.2-509(B) adds a de jure ace: In the circumstances governed\n\n 16\n\fby the fourth sentence, challengers would have to compete with already advantaged\n\nincumbents in a selection process chosen by the incumbent himself. This goes too far. It\n\nnarrows the possibility of legislative renewal and refreshment through the infusion of\n\nnew blood. It risks making the electoral process sclerotic.\n\n Nothing in the foregoing analysis compromises the “major role” played by states\n\nin structuring their elections. Cal. Democratic Party, 530 U.S. at 572. Election\n\nadministration is necessarily an amalgam of state law and party procedures, and the\n\nCommonwealth is surely correct that the rights of political parties in this amalgam are not\n\nabsolute in character. We reiterate that “it is beyond question ‘that States may, and\n\ninevitably must, enact reasonable regulations of parties, elections, and ballots to reduce\n\nelection- and campaign-related disorder.’” Clingman, 544 U.S. at 593 (quoting Timmons,\n\n520 U.S. at 358). Rather, we simply hold that a state may not force a political party to\n\nhand control over its nomination method to a single, self-interested individual; the private\n\ninterest of an incumbent in winning reelection cannot, and certainly not in the manner\n\nchosen here, predominate over the associational rights of political parties.\n\n III.\n\n The district court also enjoined enforcement of the Act’s second and third\n\nsentences, which protect the nomination prerogatives of incumbent members of the\n\nGeneral Assembly. The Commonwealth argues that this was improper, as the Committee\n\nlacked standing to challenge those provisions. We disagree. The Committee suffered\n\ncognizable, traceable, and redressable injury from the Commonwealth’s application of\n\nthose sentences to its activities. And the second and third sentences are, if anything, even\n\n 17\n\fmore offensive to the First Amendment than the fourth. Accordingly, we affirm the\n\ndistrict court’s decision to enjoin the second and third sentences on § 24.2-509(B) as\n\nwell.\n\n Standing requires an injury in fact that is caused by the challenged conduct and is\n\nlikely to be redressed by a favorable decision. See Ohio Valley Envtl. Coal., Inc. v. Pruitt,\n\n893 F.3d 225, 229 (4th Cir. 2018). “To establish injury in fact, a plaintiff must show that\n\nhe or she suffered an invasion of a legally protected interest that is concrete and\n\nparticularized and actual or imminent, not conjectural or hypothetical.” Spokeo, Inc. v.\n\nRobins, 136 S. Ct. 1540, 1548 (2016) (internal quotation marks omitted). Throughout a\n\nlawsuit “the standing inquiry remains focused on whether the party invoking jurisdiction\n\nhad the requisite stake in the outcome when the suit was filed.” Davis v. Fed. Election\n\nComm’n, 554 U.S. 724, 734 (2008).\n\n The Committee suffered an injury in fact at the time the lawsuit was filed as a\n\nresult of the Commonwealth’s application of the second and third sentences, as\n\ndemonstrated by the “specific facts” adduced in its submissions to this court. Lujan v.\n\nDefenders of Wildlife, 504 U.S. 555, 561 (1992). These facts are as follows: The\n\nDepartment issues a series of forms for incumbents and party committees to notify the\n\nCommonwealth which nomination method they plan to use, as they are required to do by\n\nlaw. See Va. Code Ann. § 24.2-516. These forms reflect the Department’s understanding\n\nof how to apply the Incumbent Protection Act. And yet, throughout the 2016 election\n\ncycle and through the filing of this lawsuit, these forms applied the Act’s second and\n\nthird sentences, which should only apply to incumbent members of the General\n\n 18\n\fAssembly, to the 6th Congressional Committee as well. Incumbent members of Congress\n\nwere given the same plenary power to designate any method of nomination no matter the\n\ncircumstance, as if they were incumbent members of the General Assembly.\n\n The forms themselves best tell the story:\n\n DESIGNATION OF METHOD OF NOMINATION\n for\n SENATE OF VIRGINIA\n 2015\n ***\n I, the undersigned incumbent of the Senate of Virginia district indicated\n above, am seeking re-election and designate the following method of\n nomination to be used in determining the party’s candidate for this office\n subject to the forthcoming November general election.\n\nJ.A. 892.\n\n 2016 DESIGNATION OF METHOD OF NOMINATION\n ***\n I, the undersigned incumbent of the district indicated above, am seeking\n re-election and designate the following method of nomination to be used in\n determining the party’s candidate for this office subject to the coming\n November general election.\n\nJ.A. 873. The form used by incumbent General Assembly members in the 2015 election\n\ncycle and by incumbent Members of Congress in the 2016 election cycle are in all\n\nmaterial respects the same. As the Committee noted, “[n]ot only did Appellants\n\npromulgate these forms, they directed non-General Assembly incumbents and party\n\nchairmen to use them.” Resp. Br. of Appellee at 13.\n\n It is plain therefore that, on those facts, the Committee suffered a sufficiently\n\n“concrete” injury in fact to sustain its challenge to the second and third sentences of the\n\nAct. Because of the forms, any candidate that the 6th Congressional Committee wished to\n\n\n 19\n\frecruit, or anyone contemplating an electoral challenge to the incumbent, faced the\n\nprospect of having to compete in a nomination process selected by that incumbent.\n\nPlainly, this prospect would “dramatically change[] the plaintiffs’ decisions about\n\ncampaign financing, messages to stress, and candidates to recruit.” Miller I, 462 F.3d at\n\n317. This distortion of political decisionmaking constitutes an ongoing and concrete\n\ninjury sufficient to meet the injury-in-fact prong of constitutional standing analysis. Id. at\n\n317-18.\n\n That injury, of course, is particularized because the 6th Congressional Committee\n\nserves a unique function in selecting the Republican nominee for Virginia’s 6th\n\nCongressional District. See Lujan, 504 U.S. at 560. The remaining standing analysis is\n\nstraightforward: The injury was caused by promulgation of the forms based on the Act’s\n\nsecond and third sentences, and therefore will be redressed if we find those sentences to\n\nbe inconsistent with the First Amendment. For these reasons, the Committee has standing\n\nto challenge the portions of § 24.2-509(B) that protect the nomination prerogatives of\n\nGeneral Assembly members.\n\n In response, the Department argues that the challenge to the second and third\n\nsentences became moot when the Department updated the offending election forms. 2 But\n\n\n2\n The Department also argues that plaintiff’s challenge to the Act’s fourth sentence is\nmoot. It notes that because the current 6th District incumbent was selected by convention,\nthe plaintiff will not be forced to accede to a primary until 2022 at the earliest. But that\nargument relies on the same cramped interpretation of standing that we rejected in Miller\nI, 462 F.3d at 316-18. The injuries inflicted by laws that distort the primary process, like\nthe Incumbent Protection Act, are not confined to the short duration of any particular\nprimary, but instead reflect the reality that “campaign planning decisions have to be made\n(Continued)\n 20\n\fthe update occurred after the lawsuit had been filed. Promulgating new forms may well\n\nhave been the right thing to do in accordance with state law. But as a litigation tactic,\n\nsuch backpedaling will rarely serve to moot a case in federal court. Friends of the Earth,\n\nInc. v. Laidlaw Environmental Services (TOC), Inc., 528 U.S. 167, 189-94 (2000). The\n\nmootness doctrine ordinarily does not extend to situations where a party quits its\n\noffending conduct partway through litigation. Id. After all, “a party should not be able to\n\nevade judicial review, or to defeat a judgment, by temporarily altering questionable\n\nbehavior.” Porter v. Clarke, 852 F.3d 358, 364 (4th Cir. 2017) (internal quotation marks\n\nomitted). To overcome that general rule, the Department bears “[t]he heavy burden of\n\npersuading the court,” Laidlaw, 528 U.S. 167, 189 (2000) (internal quotation marks and\n\nalterations omitted), that it is “absolutely clear that the allegedly wrongful behavior could\n\nnot reasonably be expected to recur.” Wall v. Wade, 741 F.3d 492, 497 (2014) (quoting\n\nLaidlaw, 528 U.S. at 189).\n\n The Department cannot carry this burden. It has a history of frequently revising\n\nthe relevant election forms. The forms used for congressional nominations in 2014, for\n\nexample, reflected the fourth sentence of the Incumbent Protection Act and not the\n\nsecond and third. Yet the congressional nomination forms were inexplicably changed for\n\n\nmonths, or even years, in advance of the election to be effective.” Id. at 317-18. The 6th\nCongressional Committee’s claims thus did not become moot with the passing of the\n2018 election season. The dispute over the Act’s fourth sentence, rather, is alive and well.\nEven so, if the Department were correct that electoral disputes became moot with each\npassing election cycle, this challenge, like many electoral challenges, would plainly be\ncapable of repetition yet evading review. See, e.g., Davis v. Fed. Election Comm’n, 554\nU.S. 724, 735-36 (2008).\n\n 21\n\fthe 2016 congressional elections to reflect the Act’s more fulsome General Assembly\n\nprotections instead. The Department has offered no explanation for why the forms were\n\nchanged to the benefit of incumbents between the 2014 and 2016 congressional elections.\n\nEven though the forms apparently have been edited once again, we have little confidence\n\nthat the forms will not revert back if we hold that this lawsuit is moot. Indeed, that danger\n\nis particularly acute when, as here, a change in the forms would confer benefits upon\n\npolitical incumbents. The Incumbent Protection Act transparently advances the interests\n\nof those who control the apparatus of government; it is hardly beyond the realm of\n\nplausibility that it would be administered with that same purpose in mind. The\n\nDepartment’s May 23, 2018 Suggestion of Mootness is accordingly denied.\n\n We may thus properly consider the 6th Congressional Committee’s facial and as\n\napplied First Amendment challenges to the Incumbent Protection Act’s protection of\n\nincumbent members of the General Assembly. A facial challenge to a law will succeed\n\nafter a showing “that no set of circumstances exist under which the law would be valid,\n\nor that the law lacks any plainly legitimate sweep.” Greater Balt. Center for Pregnancy\n\nConcerns, Inc. v. Mayor & City Council of Balt., 721 F.3d 264, 282 (4th Cir. 2013) (en\n\nbanc) (internal quotation marks and alterations omitted). In the First Amendment context,\n\na facial challenge may also succeed under overbreadth doctrine. Id. But there is no need\n\nto employ overbreadth doctrine in this case, for the Act’s second and third sentences\n\ncannot be applied in a manner consistent with the First Amendment.\n\n The Department fails to identify a single circumstance where the Act’s second and\n\nthird sentences could be lawfully applied. And we find none. The second and third\n\n 22\n\fsentences not only share the constitutional infirmities of the fourth sentence but exhibit\n\nthose infirmities to an even greater degree. The fourth sentence allows some incumbents\n\nto force a primary under certain designated circumstances. The second sentence goes\n\nfurther by empowering incumbents to impose their choice of any method of nomination\n\nno matter what the party prefers under almost any circumstances. 3 These advantages,\n\nwhen given to state or federal incumbents, run afoul of the First Amendment for all the\n\nreasons discussed in detail in Part II, supra.\n\n The Department raises yet one more challenge, arguing that the district court was\n\nwrong to enjoin the Incumbent Protection Act in its entirety. See Va. Code Ann. § 24.2-\n\n509(B). We review the district court’s decision to enjoin the statute for abuse of\n\ndiscretion. U.S. Airline Pilots Ass’n v. Awappa, LLC, 615 F.3d 312, 320 (4th Cir. 2010).\n\nThe Act comprises six sentences. We have now found that each of its operative\n\nprovisions—namely the second, third, and fourth sentences—is unconstitutional. The\n\nremaining sentences merely explain how to apply them. The district court did not abuse\n\nits discretion in enjoining the Incumbent Protection Act in toto.\n\n IV.\n\n Our decision is a narrow one. It is directed at a discrete constitutional imbalance\n\ncreated by permitting single office holders to negate the associational rights of political\n\nparties in an area central to the party’s very reason for being. Our ruling in no way limits\n\n 3\n The third sentence applies in the relatively rare situation where there is more than\none incumbent for the same office. In that situation, the statute requires incumbents’\nconsent for any method of nomination other than a primary. § 24.2-509(B).\n\n\n 23\n\fthe ability of states to enact “reasonable regulations of parties, elections, and ballots.”\n\nTimmons, 520 U.S. at 358. The associational rights of political parties are, after all, not\n\nabsolute. Laws that impose a slight or lesser burden on associational rights are owed\n\ndeference, especially when justified by the need “to reduce election- and campaign-\n\nrelated disorder.” Id. But our constitutional responsibility, set forth so plainly by the\n\nSupreme Court, requires us to ensure that this “deference does not risk such constitutional\n\nevils as, say, permitting incumbents to insulate themselves from effective electoral\n\nchallenge.” Nixon v. Shrink Mo. Gov’t PAC, 528 U.S. 377, 402 (2000) (Breyer, J.,\n\nconcurring). The Incumbent Protection Act reflects precisely that infirmity, and it is\n\nprecisely why we cannot allow the Act to stand.\n\n For the foregoing reasons, the judgment of the district court is\n\n AFFIRMED.\n\n\n\n\n 24\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: 6TH CONGRESSIONAL DISTRICT REPUBLICAN COMMITTEE, Plaintiff - Appellee, and Anne Taetzsch Fitzgerald, Individually and as Chairman of the 20th House of Delegates District Republican Committee; Karen U. Kwiatkowski, Individually; Edward A. Yensho, Individually and as Chairman of the Green County Republican Committee; 20th House of Delegates District Republican Committee, Plaintiffs, v. James B. ALCORN, in His Official Capacity as Chairman of the Virginia State Board of Elections ; Clara Belle Wheeler, in Her Official Capacity as Vice-Chairman of the Virginia State Board of Elections ; Singleton B. McAllister, in Her Official Capacity as Secretary of the Virginia State Board of Elections ; Virginia Department of Elections, Defendants - Appellants.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-09\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1111\\n\\n\\n6TH CONGRESSIONAL DISTRICT REPUBLICAN COMMITTEE,\\n\\n Plaintiff – Appellee,\\n\\n and\\n\\nANNE TAETZSCH FITZGERALD, individually and as Chairman of the 20th\\nHouse of Delegates District Republican Committee; KAREN U.\\nKWIATKOWSKI, individually; EDWARD A. YENSHO, individually and as\\nChairman of the Green County Republican Committee; 20TH HOUSE OF\\nDELEGATES DISTRICT REPUBLICAN COMMITTEE,\\n\\n Plaintiffs,\\n\\n v.\\n\\nJAMES B. ALCORN, in his official capacity as Chairman of the Virginia State\\nBoard of Elections; CLARA BELLE WHEELER, in her official capacity as Vice-\\nChairman of the Virginia State Board of Elections; SINGLETON B.\\nMCALLISTER, in her official capacity as Secretary of the Virginia State Board of\\nElections; VIRGINIA DEPARTMENT OF ELECTIONS,\\n\\n Defendants - Appellants.\\n\\n\\nAppeal from the United States District Court for the Western District of Virginia, at\\nHarrisonburg. Michael F. Urbanski, Chief District Judge. (5:17-cv-00016-MFU-JCH)\\n\\n\\nArgued: December 12, 2018 Decided: January 9, 2019\\n\\n\\nBefore WILKINSON, MOTZ, and DUNCAN, Circuit Judges.\\n\\fAffirmed by published opinion. Judge Wilkinson wrote the opinion, in which Judge Motz\\nand Judge Duncan joined.\\n\\n\\nARGUED: Toby Jay Heytens, OFFICE OF THE ATTORNEY GENERAL OF\\nVIRGINIA, Richmond, Virginia, for Appellants. Jeffrey R. Adams, WHARTON,\\nALDHIZER & WEAVER, PLC, Harrisonburg, Virginia, for Appellee. ON BRIEF:\\nMark R. Herring, Attorney General, Stephen A. Cobb, Deputy Attorney General,\\nMatthew R. McGuire, Principal Deputy Solicitor General, Michelle S. Kallen, Deputy\\nSolicitor General, OFFICE OF THE ATTORNEY GENERAL OF VIRGINIA,\\nRichmond, Virginia, for Appellants. Charles F. Hilton, Thomas E. Ullrich, Lucas I.\\nPangle, WHARTON ALDHIZER & WEAVER, PLC, Harrisonburg, Virginia; John C.\\nWirth, NELSON MCPHERSON SUMMERS & SANTOS, Staunton, Virginia, for\\nAppellee.\\n\\n\\n\\n\\n 2\\n\\fWILKINSON, Circuit Judge:\\n\\n The 6th Congressional District Republican Committee argues that Virginia’s\\n\\nIncumbent Protection Act, Va. Code Ann. § 24.2-509(B), violates the First Amendment\\n\\nof the Constitution. The district court agreed and enjoined § 24.2-509(B) in its entirety.\\n\\nFor the reasons that follow, we now affirm.\\n\\n I.\\n\\n A.\\n\\n Virginia law generally allows the Commonwealth’s political parties considerable\\n\\ndiscretion in deciding how to nominate their candidates for office. Section 24.2-509(A)\\n\\nempowers the “duly constituted authorities” of the state and local parties “to determine\\n\\nthe method by which a party nomination . . . shall be made.” The parties make use of this\\n\\nlatitude. For example, the Republican Party of Virginia, with whom the appellee here is\\n\\naffiliated, allows for four different methods of nomination: a primary, a party canvass, a\\n\\nconvention, and a mass meeting. Fitzgerald v. Alcorn, 285 F. Supp. 3d 922, 927 (W.D.\\n\\nVa. 2018). Under the Party’s Plan of Organization, committees established in every\\n\\nlocality, state legislative district, and congressional district are empowered to choose\\n\\namong these methods to nominate candidates for their political subdivision. J.A. 37, 38,\\n\\n40.\\n\\n The differences between these methods are substantial. Each one “‘create[s] a\\n\\ndifferent distribution of potential voters (or decision makers) in the nomination process.’\\n\\nFor example, primaries involve the largest pool of potential voters, whereas conventions\\n\\nand mass meetings ‘lend themselves more toward committed partisans.’” Alcorn, 285 F.\\n\\n 3\\n\\fSupp. 3d at 935 (quoting J.A. 884-85, 885-86). The choice of method, therefore, could\\n\\nhave a significant influence on the choice of nominee.\\n\\n Subsection 24.2-509(B), often called the Incumbent Protection Act, however,\\n\\nlimits the broad authority recognized by subsection A. 1 The second and third sentences\\n\\napply to those subdivisions of the state party that select nominees for candidates to the\\n\\n\\n1\\n The full text of Virginia Code § 24.2-509 is reprinted below, with the sentences in\\nsubsection B numbered for ease of reference:\\n\\nA. The duly constituted authorities of the state political party shall have the right to\\n determine the method by which a party nomination for a member of the United States\\n Senate or for any statewide office shall be made. The duly constituted authorities of\\n the political party for the district, county, city, or town in which any other office is to\\n be filled shall have the right to determine the method by which a party nomination for\\n that office shall be made.\\n\\nB. [1] Notwithstanding subsection A, the following provisions shall apply to the\\n determination of the method of making party nominations. [2] A party shall nominate\\n its candidate for election for a General Assembly district where there is only one\\n incumbent of that party for the district by the method designated by that incumbent, or\\n absent any designation by him by the method of nomination determined by the party.\\n [3] A party shall nominate its candidates for election for a General Assembly district\\n where there is more than one incumbent of that party for the district by a primary\\n unless all the incumbents consent to a different method of nomination. [4] A party,\\n whose candidate at the immediately preceding election for a particular office other\\n than the General Assembly (i) was nominated by a primary or filed for a primary but\\n was not opposed and (ii) was elected at the general election, shall nominate a\\n candidate for the next election for that office by a primary unless all incumbents of\\n that party for that office consent to a different method.\\n\\n [5] When, under any of the foregoing provisions, no incumbents offer as candidates\\n for reelection to the same office, the method of nomination shall be determined by the\\n political party.\\n\\n [6] For the purposes of this subsection, any officeholder who offers for reelection to\\n the same office shall be deemed an incumbent notwithstanding that the district which\\n he represents differs in part from that for which he offers for election.\\n\\n\\n 4\\n\\fGeneral Assembly. Those sentences allow incumbent members of the General Assembly\\n\\nwho are running for reelection, where there is only one incumbent, to “designate[]” the\\n\\nmethod of nomination they prefer. Under this statute, the wishes of the party are\\n\\nimmaterial; no matter where the party’s plan of organization may vest the power to\\n\\nchoose nomination methods, the law trumps, granting the power to the incumbent.\\n\\n The fourth sentence of the Act applies to those components of political parties that\\n\\nmake the nominations for “particular office[s]” other than for the General Assembly,\\n\\nincluding nominations for the U.S. House of Representatives. In these races, the\\n\\nincumbent officeholder may insist that his or her party use a primary as its nomination\\n\\nmethod as long as (1) the incumbent was selected by primary in the previous election\\n\\ncycle and (2) the incumbent is running for reelection. Again, the statute trumps the\\n\\nparty’s plan of organization, which, in this case allows the committees responsible for\\n\\ncongressional nominations to choose between the approved methods (excluding mass\\n\\nmeetings) without interference by the incumbent, J.A. 37.\\n\\n The Virginia Department of Elections, however, has not always respected the\\n\\ndistinction made between the second and third sentences on the one hand, and the fourth\\n\\nsentence on the other. In the 2016 and 2017 election cycles, for example, the Department\\n\\npromulgated forms that allowed non-General Assembly incumbents to “designate” their\\n\\npreferred method of nomination as if their elections were governed by the second and\\n\\nthird sentences. After the commencement of this litigation, and only after the appellees\\n\\npointed out the mistake, the Department issued new forms that applied the fourth\\n\\nsentences to these races.\\n\\n 5\\n\\f Virginia has not identified a single other state that has a statute like the Incumbent\\n\\nProtection Act, and this is not the first case to consider a constitutional challenge to it. In\\n\\n2007, for example, this court considered a challenge to the Act. Miller v. Brown, 503\\n\\nF.3d 360 (4th Cir. 2007) (“Miller II”). There, we held that an incumbent cannot\\n\\nconstitutionally force his or her party to use an open primary, as this would be an\\n\\nimpermissible burden on the party’s associational rights. Id. at 368-71. We did not,\\n\\nhowever, reach the different question of the constitutionality of incumbents’ statutory\\n\\npower to dictate any nomination method.\\n\\n B.\\n\\n This appeal stems from the 6th Congressional District Republican Committee’s\\n\\nchallenge to the Incumbent Protection Act under 42 U.S.C. § 1983. See Alcorn, 285 F.\\n\\nSupp. 3d at 922. The Committee is responsible for nominating candidates for the U.S.\\n\\nHouse of Representatives for the 6th Congressional District, which “covers much of the\\n\\nwest-central portion of Virginia, from Roanoke to Front Royal.” Id. at 927. Under the\\n\\nParty’s Plan of Organization, it is composed of the “District Chairman,” the “Unit\\n\\nChairman” (the chair of each relevant locality’s committee), the “District Representative\\n\\nof the Virginia Federation of Republican Women,” the “Young Republican Federation\\n\\nDistrict Committeeman,” the “College Republican Federation District Committeeman,”\\n\\nand the “District members of the State Central Committee.” J.A. 36-37. The Committee,\\n\\nalong with other plaintiffs who were dismissed from the suit and do not appeal, raised\\n\\nfacial and as applied challenges to the Incumbent Protection Act, claiming that it\\n\\nabridged their rights under the First and Fourteenth Amendments of the U.S.\\n\\n 6\\n\\fConstitution. The named defendants include the Virginia Department of Elections and the\\n\\nthree members of the Virginia State Board of Elections at the time the suit was filed.\\n\\nAlcorn, 285 F. Supp. 3d at 928.\\n\\n The district court, relying on Miller v. Brown, 462 F.3d 312 (4th Cir. 2006)\\n\\n(“Miller I”), found that the Committee had standing to challenge the Act. Alcorn, 285 F.\\n\\nSupp. 3d at 937. It then proceeded to evaluate the burden posed by § 24.2-509(B) on the\\n\\nCommittee’s associational rights, concluding that it was “severe” because it provided\\n\\n“incumbents with a statutory right to dictate political parties’ internal affairs . . . .” Id. at\\n\\n952. The burden was “especially” onerous because it trespassed on the “realm of\\n\\nselecting candidates.” Id. Given the magnitude of the burden, the district court found that\\n\\n“the Act can survive constitutional scrutiny only if it is ‘narrowly tailored to advance a\\n\\ncompelling state interest.’” Id. (quoting Burdick v. Takushi, 504 U.S. 428, 433 (1992)).\\n\\nThe district court ultimately concluded that the Act did not survive such scrutiny. Id. at\\n\\n953.\\n\\n The district court thus permanently enjoined enforcement of the entire Incumbent\\n\\nProtection Act on January 19, 2018. J.A. 1473. The court enjoined all six sentences of\\n\\n§ 24.2-509(B) because, according to the court, the second and third sentences—which\\n\\nprotect the nomination prerogatives of incumbent General Assembly members—could\\n\\nnot be severed from the fourth—which protects the nomination prerogatives of, inter alia,\\n\\nmembers of Congress. The court additionally found that the Committee had standing to\\n\\nchallenge the second and third sentences under the overbreadth doctrine. Alcorn, 285 F.\\n\\nSupp. 3d at 955. Finally, the district court concluded that the Act had “no legitimate\\n\\n 7\\n\\fsweep” and so a facial challenge to all its provisions was appropriate. Id. at 955-56. After\\n\\nthe notice of appeal had been filed, the district court stayed its permanent injunction order\\n\\non February 5, 2018, to avoid interfering with the ongoing nomination cycle. J.A. 1481.\\n\\nAfter that cycle concluded, however, the district court vacated its stay on September 24,\\n\\n2018. J.A. 1680. During the course of this appeal, the Department filed a motion to\\n\\nvacate the injunction on the basis of mootness. We held that motion in abeyance pending\\n\\noral argument, and both parties expanded on their arguments in their briefing on the\\n\\nmerits.\\n\\n II.\\n\\n The district court found that the fourth sentence of the Incumbent Protection Act,\\n\\nwhich protects the nomination prerogatives of incumbent members of Congress among\\n\\nothers, violated the First Amendment. Because this provision imposes a severe burden on\\n\\nthe associational rights of Virginia’s political parties, and because the Commonwealth\\n\\nhas been unable to show that it is narrowly tailored to serve a compelling state interest,\\n\\nwe agree.\\n\\n A.\\n\\n Freedom of association has, for centuries, been at the heart of the American\\n\\nsystem of government and individual rights. In 1831, when Alexis de Tocqueville arrived\\n\\nin the United States, he was shocked to discover that our nation was the only “country on\\n\\nthe face of the earth where the citizens enjoy unlimited freedom of association for\\n\\npolitical purposes.” Alexis de Tocqueville, 2 Democracy in America 123 (Henry Reeves\\n\\ntrans., 1863). In America, “the most democratic country on the face of the earth,” the\\n\\n 8\\n\\f“art” of forming political associations had been “carried to the highest perfection.” Id. at\\n\\n115. Because of this, “Americans of all ages, all conditions, and all dispositions,\\n\\nconstantly form associations.” Id. at 114.\\n\\n De Tocqueville identified this propensity to associate as one of the sources of the\\n\\nastonishing political dynamism of the young Republic, writing that American political\\n\\nassociations are “the mother of action,” id. at 125, and that they “stimulate competition,\\n\\nand . . . discover those arguments which are most fitted to act upon the majority.” Id. at\\n\\n210. The right to associate for political purposes, de Tocqueville proclaimed, is “[t]he\\n\\nmost natural privilege of man, next to the right of acting for himself.” Id. at 209.\\n\\nAccordingly, “the right of association is almost as inalienable as the right of personal\\n\\nliberty. No legislator can attack it without impairing the very foundations of society.” Id.\\n\\n The multiplicity of political associations lauded by de Tocqueville was the result\\n\\nof the Founders’ decision to enshrine the “freedom to join together in furtherance of\\n\\ncommon political beliefs” in the First Amendment of the Constitution. Tashjian v.\\n\\nRepublican Party of Conn., 479 U.S. 208, 214-15 (1986). That Amendment promises\\n\\nAmericans the right not just to proclaim a political vision but to join with their\\n\\ncompatriots and actually advance that vision. Because, while an individual may be, in de\\n\\nTocqueville’s words, “feeble and consequently more incapable of preserving his\\n\\nfreedom,” de Tocqueville, supra, at 123, when individuals combine in association they\\n\\n“acquire facility in prosecuting great undertakings in common,” id. at 114. Some of the\\n\\n“great undertakings” accomplished by political associations protected by the First\\n\\nAmendment include the Abolitionist Movement, the Women’s Suffrage Movement, the\\n\\n 9\\n\\fLabor Movement, and the Civil Rights Movement—the fruits of which continue to shape\\n\\nour politics and society for the better to this day.\\n\\n Of all political associations protected by the First Amendment, political parties\\n\\nthemselves merit special attention. Like other political participants, parties advance a\\n\\nparticular vision. Unlike others, however, political parties must also nominate candidates\\n\\nfor office, compete in elections, and, if successful, help to translate campaign appeals into\\n\\nprogrammatic action. In so doing, political parties provide a vehicle for voters to advance\\n\\ntheir own political views. Without groups like modern political parties, “[r]epresentative\\n\\ndemocracy in any populous unit of governance” would be “unimaginable.” Cal.\\n\\nDemocratic Party v. Jones, 530 U.S. 567, 574 (2000).\\n\\n Perhaps no function of a party is more central to its purpose than the selection of\\n\\ncandidates for office, which “often determines the party’s positions on the most\\n\\nsignificant public policy issues of the day.” Id. at 575. It is no surprise, therefore, that the\\n\\nSupreme Court is “vigorous[]” in affirming the “special protection” owed to the\\n\\nassociational rights of political parties as they pertain to the parties’ choice of nominees.\\n\\nId. at 576. Statutes that severely burden a party’s associational rights must be narrowly\\n\\ntailored to advance a compelling government interest. Id. at 581-82. In Democratic Party\\n\\nof the United States v. Wisconsin ex rel. La Follette, the Court invalidated a Wisconsin\\n\\nlaw that required the national Democratic Party to seat certain delegates chosen in an\\n\\nopen primary. 450 U.S. 107 (1981). In Tashjian v. Republican Party of Connecticut, the\\n\\nCourt struck down a Connecticut law that forbade state parties from conducting open\\n\\nprimaries because the law burdened “associational opportunities at the crucial juncture at\\n\\n 10\\n\\fwhich the appeal to common principles may be translated into concerted action . . . .” 479\\n\\nU.S. at 216. In Eu v. San Francisco County Democratic Central Committee, the Court\\n\\ninvalidated laws dictating political parties’ internal affairs and prohibiting them from\\n\\nendorsing candidates for office. 489 U.S. 214 (1989). And in California Democratic\\n\\nParty v. Jones, the Court struck down a mandatory open primary law as it burdened the\\n\\n“political association’s right to exclude” in the “candidate-selection process.” 530 U.S. at\\n\\n575.\\n\\n Not every burden on associational rights is unconstitutional. “States have a major\\n\\nrole to play in structuring and monitoring the election process, including” nominee\\n\\nselection. Cal. Democratic Party, 530 U.S. at 572. Where the burden imposed by the\\n\\nstate is not “severe”—where it is “lesser”—courts engage in “less exacting review.”\\n\\nTimmons v. Twin Cities Area New Party, 520 U.S. 351, 358 (1997). In Timmons, the\\n\\nCourt upheld a Minnesota law that prohibited a candidate from appearing on the ballot as\\n\\nthe nominee of more than one party after finding that the law did “not severely burden\\n\\nthat party’s associational rights.” Id. at 359. Nothing prevented the party from endorsing\\n\\nthe candidate of another party; nothing prevented the party for campaigning for the\\n\\ncandidate of another party. The law’s only effect was to “reduce the universe of potential\\n\\ncandidates who may appear on the ballot as the party’s nominee . . . by ruling out those\\n\\nfew individuals who . . . have already agreed to be another party’s candidate.” Id. at 363.\\n\\nThis slight a reduction could not be a severe burden. Id.; see also Clingman v. Beaver,\\n\\n544 U.S. 581 (2005) (upholding law mandating a “semiclosed” primary, in which\\n\\nregistered members of opposing parties and unaffiliated voters could not participate).\\n\\n 11\\n\\f Political parties have, of course, come in for their fair share of criticism\\n\\nthroughout our history. Chancellor James Kent, in an 1830 letter to Daniel Webster,\\n\\nwrote that “Hamilton said in the Federalist, in his speeches, and a hundred times to me,\\n\\nthat factions would ruin us, and our government had not sufficient energy and balance to\\n\\nresist the propensity to them, and to control their tyranny and their profligacy.” John B.\\n\\nCassoday, James Kent & Joseph Story, 12 Yale L.J. 146, 151 (1903) (quoting letter). But\\n\\nwhether the divisiveness in public discourse traces to the presence of political parties or\\n\\nto the divisions inherent in the issues themselves elides the fact that parties have long\\n\\nsince become a fact of constitutional life. And what emerges from the above Supreme\\n\\nCourt cases is no all-or-nothing proposition but instead that law is not insensitive to\\n\\nmatters of degree: Those laws that impose a “heav[y]” or “severe” burden on a political\\n\\nparty’s right to choose its nominee are unconstitutional unless they serve a “compelling\\n\\nstate interest” and are “narrowly tailored” to do so. Cal. Democratic Party, 530 U.S. at\\n\\n583. It is to that inquiry that we now turn.\\n\\n B.\\n\\n The fourth sentence of Virginia Code § 24.2-509(B), the provision of the\\n\\nIncumbent Protection Act that applies to congressional incumbents among others,\\n\\nunquestionably poses a severe burden on the associational rights of the Commonwealth’s\\n\\npolitical parties. In evaluating the law’s imposition on associational rights, we must\\n\\n“weigh the ‘character and magnitude’ of the burden” it occasions. Timmons, 520 U.S. at\\n\\n358 (quoting Burdick, 504 U.S. at 434). We keep in mind also that “[a]ny interference\\n\\n\\n\\n 12\\n\\fwith the freedom of a party is simultaneously an interference with the freedom of its\\n\\nadherents.” Tashjian, 479 U.S. at 215 (quoting Democratic Party, 450 U.S. at 122).\\n\\n Subsection 24.2-509(A) grants the “duly constituted authorities” of the\\n\\nCommonwealth’s political parties considerable discretion in selecting the method of\\n\\nchoosing their nominees. The Incumbent Protection Act, subsection 24.1-509(B), carves\\n\\nexceptions to this rule in favor of incumbents. To recapitulate, the second and third\\n\\nsentences allow incumbent members of the General Assembly to dictate the method their\\n\\nparty shall use in selecting the nominee for the office that incumbent holds. The fourth\\n\\nsentence allows incumbent members of the U.S. House of Representatives, who were\\n\\nthemselves nominated by primary in the last election cycle, to require their party to use a\\n\\nprimary in the current election cycle to nominate a candidate for the office they hold if\\n\\nthey themselves are seeking reelection. In short, the associational rights of Virginia’s\\n\\npolitical parties that are recognized and protected by § 24.2-509(A) are taken away by §\\n\\n24.1-509(B) and given instead to a single individual—the incumbent.\\n\\n The weight of this burden could not be more obvious. The members of the 6th\\n\\nCongressional District Committee have, as generations of Americans did before them,\\n\\nbanded together to advance their political views. The selection of a nominee “often\\n\\ndetermines” the contours of the party platform. Cal. Democratic Party, 530 U.S. at 575.\\n\\nAnd “even when those positions are predetermined it is the nominee who becomes the\\n\\nparty’s ambassador to the general electorate in winning it over to the party’s views.” Id.\\n\\nYet, at the “crucial juncture” at which the members of this political association decide\\n\\nhow to select their nominee, id., the Commonwealth has taken the decision out of their\\n\\n 13\\n\\fhands: No matter what method of nomination the members of this party may prefer,\\n\\nVirginia law decrees that they must give way to the desire of the incumbent to hold a\\n\\nprimary if that incumbent was himself selected by primary previously and is seeking\\n\\nreelection.\\n\\n The burden is manifestly severe. This is not a case like Timmons, in which a\\n\\nparty’s ability to choose a nominee was reduced by only the small number of individuals\\n\\nthat already appeared elsewhere on the ballot. 520 U.S. at 351. Nor is this a case like\\n\\nClingman, in which the state’s Libertarian Party was required by state law to allow only\\n\\nits registered members and registered independent voters to participate in its primary. 544\\n\\nU.S. at 592. The burden there was not severe given the ease with which registered\\n\\nmembers of other parties who wanted to participate in the Libertarian primary could\\n\\nchange their registration. Id. Rather, this is a case in which the state has decided that the\\n\\nwishes of a party’s adherents must, in certain circumstances, be subordinated wholesale\\n\\nto the wishes of a single individual whose self-interest is self-evident; in these\\n\\ncircumstances, the party’s adherents are entirely shut out of the choice of nomination\\n\\nmethod—severely burdening their associational rights.\\n\\n C.\\n\\n Because the provision of the Incumbent Protection Act which protects\\n\\ncongressional incumbents—the fourth sentence—imposes a “severe” burden on the\\n\\nassociational rights of Virginia’s political parties, the Commonwealth must show that it is\\n\\n“narrowly tailored to serve a compelling state interest.” Cal. Democratic Party, 530 U.S.\\n\\nat 583. It cannot make this showing.\\n\\n 14\\n\\f Primaries add a crucial participatory dimension to democratic politics. Appellants\\n\\nassert that § 24.2-509(B) is akin to a mandatory primary statute, and therefore it serves\\n\\nthe interest of “assur[ing] that intraparty competition is resolved in a democratic fashion.”\\n\\nId. at 572. If § 24.2-509(B) truly were a mandatory primary statute its constitutionality\\n\\nwould be “too plain for argument.” Id. (quoting Am. Party of Tex. v. White, 415 U.S. 767,\\n\\n781 (1974)). But it is not: The statute does not by itself require any organ of a Virginia\\n\\npolitical party to use a primary as a method of nomination. Instead, the statute delegates\\n\\nthe power to force the party to use a primary to the incumbent office holder. Therein lies\\n\\nthe constitutional flaw.\\n\\n This delegation of power over the party to the incumbent office holder is not\\n\\nnarrowly tailored to meet the Commonwealth’s asserted interest. Under the terms of the\\n\\nstatute, the interest in democratic resolution of intraparty disputes will only be vindicated\\n\\nwhen and where an incumbent office holder decides that it is in his interest to do so. It is\\n\\nimplausible that the General Assembly would seek to vindicate this interest in such an\\n\\nodd, uneven, and underinclusive fashion. Instead, the text and structure of the law gives\\n\\nrise to the strong suggestion that the Incumbent Protection Act serves a different interest:\\n\\nthe interest, unsurprisingly, in incumbent protection.\\n\\n To be sure, incumbent protection is not per se an unconstitutional interest. In the\\n\\ncontext of redistricting, the Supreme Court has historically allowed maps to stand that\\n\\nwere drawn with the electoral interest of incumbents in mind. See, e.g., Karcher v.\\n\\nDaggett, 462 U.S. 725, 740 (1983). But the Court has not held that the interest in\\n\\nincumbent protection is a compelling one that can justify such direct intrusions on the\\n\\n 15\\n\\fFirst Amendment. See Gill v. Whitford, 138 S. Ct. 1916, 1934 (2018) (Kagan, J.,\\n\\nconcurring) (explaining that the Court did not address the First Amendment challenge to\\n\\nthe redistricting). Incumbent protection is simply not a strong enough interest here to\\n\\njustify the severe burden on the appellee’s associational rights.\\n\\n Incumbents, after all, are already blessed with myriad de facto advantages in the\\n\\nelectoral arena. Appellee’s expert, Professor Jeffrey A. Jenkins, testified that incumbents\\n\\ngenerally have better name recognition than challengers because of their time in the\\n\\npublic eye. J.A. 884. Incumbents also have the opportunity to win votes by enacting\\n\\npopular laws and servicing their constituents, and they have easier access to donors, as\\n\\nthey are proven winners. Id. All this contributes to the “scare-off” effect: potential\\n\\nchallengers, faced with the seemingly insurmountable hurdles, will decide not to run. Id.\\n\\n The other reason for incumbency advantage is more salutary. Voters may\\n\\nrecognize that incumbents provide our government with institutional memory and the\\n\\nwisdom that can only be won through experience. In the legislative branch, which could\\n\\nfind itself at a disadvantage when dealing with career officials and agency specialists of\\n\\nthe executive, the cumulative knowledge and experience brought by incumbents to the\\n\\nnegotiating table is particularly valuable. In this sense, incumbency evens the interbranch\\n\\nplaying field. Without it, novice legislators would find it more difficult to fulfill their\\n\\nconstitutional responsibilities.\\n\\n Thus, domination of the political parties by their incumbent office holders is,\\n\\nperhaps, a natural consequence of political reality. But to the already winning de facto\\n\\nhand dealt incumbents, § 24.2-509(B) adds a de jure ace: In the circumstances governed\\n\\n 16\\n\\fby the fourth sentence, challengers would have to compete with already advantaged\\n\\nincumbents in a selection process chosen by the incumbent himself. This goes too far. It\\n\\nnarrows the possibility of legislative renewal and refreshment through the infusion of\\n\\nnew blood. It risks making the electoral process sclerotic.\\n\\n Nothing in the foregoing analysis compromises the “major role” played by states\\n\\nin structuring their elections. Cal. Democratic Party, 530 U.S. at 572. Election\\n\\nadministration is necessarily an amalgam of state law and party procedures, and the\\n\\nCommonwealth is surely correct that the rights of political parties in this amalgam are not\\n\\nabsolute in character. We reiterate that “it is beyond question ‘that States may, and\\n\\ninevitably must, enact reasonable regulations of parties, elections, and ballots to reduce\\n\\nelection- and campaign-related disorder.’” Clingman, 544 U.S. at 593 (quoting Timmons,\\n\\n520 U.S. at 358). Rather, we simply hold that a state may not force a political party to\\n\\nhand control over its nomination method to a single, self-interested individual; the private\\n\\ninterest of an incumbent in winning reelection cannot, and certainly not in the manner\\n\\nchosen here, predominate over the associational rights of political parties.\\n\\n III.\\n\\n The district court also enjoined enforcement of the Act’s second and third\\n\\nsentences, which protect the nomination prerogatives of incumbent members of the\\n\\nGeneral Assembly. The Commonwealth argues that this was improper, as the Committee\\n\\nlacked standing to challenge those provisions. We disagree. The Committee suffered\\n\\ncognizable, traceable, and redressable injury from the Commonwealth’s application of\\n\\nthose sentences to its activities. And the second and third sentences are, if anything, even\\n\\n 17\\n\\fmore offensive to the First Amendment than the fourth. Accordingly, we affirm the\\n\\ndistrict court’s decision to enjoin the second and third sentences on § 24.2-509(B) as\\n\\nwell.\\n\\n Standing requires an injury in fact that is caused by the challenged conduct and is\\n\\nlikely to be redressed by a favorable decision. See Ohio Valley Envtl. Coal., Inc. v. Pruitt,\\n\\n893 F.3d 225, 229 (4th Cir. 2018). “To establish injury in fact, a plaintiff must show that\\n\\nhe or she suffered an invasion of a legally protected interest that is concrete and\\n\\nparticularized and actual or imminent, not conjectural or hypothetical.” Spokeo, Inc. v.\\n\\nRobins, 136 S. Ct. 1540, 1548 (2016) (internal quotation marks omitted). Throughout a\\n\\nlawsuit “the standing inquiry remains focused on whether the party invoking jurisdiction\\n\\nhad the requisite stake in the outcome when the suit was filed.” Davis v. Fed. Election\\n\\nComm’n, 554 U.S. 724, 734 (2008).\\n\\n The Committee suffered an injury in fact at the time the lawsuit was filed as a\\n\\nresult of the Commonwealth’s application of the second and third sentences, as\\n\\ndemonstrated by the “specific facts” adduced in its submissions to this court. Lujan v.\\n\\nDefenders of Wildlife, 504 U.S. 555, 561 (1992). These facts are as follows: The\\n\\nDepartment issues a series of forms for incumbents and party committees to notify the\\n\\nCommonwealth which nomination method they plan to use, as they are required to do by\\n\\nlaw. See Va. Code Ann. § 24.2-516. These forms reflect the Department’s understanding\\n\\nof how to apply the Incumbent Protection Act. And yet, throughout the 2016 election\\n\\ncycle and through the filing of this lawsuit, these forms applied the Act’s second and\\n\\nthird sentences, which should only apply to incumbent members of the General\\n\\n 18\\n\\fAssembly, to the 6th Congressional Committee as well. Incumbent members of Congress\\n\\nwere given the same plenary power to designate any method of nomination no matter the\\n\\ncircumstance, as if they were incumbent members of the General Assembly.\\n\\n The forms themselves best tell the story:\\n\\n DESIGNATION OF METHOD OF NOMINATION\\n for\\n SENATE OF VIRGINIA\\n 2015\\n ***\\n I, the undersigned incumbent of the Senate of Virginia district indicated\\n above, am seeking re-election and designate the following method of\\n nomination to be used in determining the party’s candidate for this office\\n subject to the forthcoming November general election.\\n\\nJ.A. 892.\\n\\n 2016 DESIGNATION OF METHOD OF NOMINATION\\n ***\\n I, the undersigned incumbent of the district indicated above, am seeking\\n re-election and designate the following method of nomination to be used in\\n determining the party’s candidate for this office subject to the coming\\n November general election.\\n\\nJ.A. 873. The form used by incumbent General Assembly members in the 2015 election\\n\\ncycle and by incumbent Members of Congress in the 2016 election cycle are in all\\n\\nmaterial respects the same. As the Committee noted, “[n]ot only did Appellants\\n\\npromulgate these forms, they directed non-General Assembly incumbents and party\\n\\nchairmen to use them.” Resp. Br. of Appellee at 13.\\n\\n It is plain therefore that, on those facts, the Committee suffered a sufficiently\\n\\n“concrete” injury in fact to sustain its challenge to the second and third sentences of the\\n\\nAct. Because of the forms, any candidate that the 6th Congressional Committee wished to\\n\\n\\n 19\\n\\frecruit, or anyone contemplating an electoral challenge to the incumbent, faced the\\n\\nprospect of having to compete in a nomination process selected by that incumbent.\\n\\nPlainly, this prospect would “dramatically change[] the plaintiffs’ decisions about\\n\\ncampaign financing, messages to stress, and candidates to recruit.” Miller I, 462 F.3d at\\n\\n317. This distortion of political decisionmaking constitutes an ongoing and concrete\\n\\ninjury sufficient to meet the injury-in-fact prong of constitutional standing analysis. Id. at\\n\\n317-18.\\n\\n That injury, of course, is particularized because the 6th Congressional Committee\\n\\nserves a unique function in selecting the Republican nominee for Virginia’s 6th\\n\\nCongressional District. See Lujan, 504 U.S. at 560. The remaining standing analysis is\\n\\nstraightforward: The injury was caused by promulgation of the forms based on the Act’s\\n\\nsecond and third sentences, and therefore will be redressed if we find those sentences to\\n\\nbe inconsistent with the First Amendment. For these reasons, the Committee has standing\\n\\nto challenge the portions of § 24.2-509(B) that protect the nomination prerogatives of\\n\\nGeneral Assembly members.\\n\\n In response, the Department argues that the challenge to the second and third\\n\\nsentences became moot when the Department updated the offending election forms. 2 But\\n\\n\\n2\\n The Department also argues that plaintiff’s challenge to the Act’s fourth sentence is\\nmoot. It notes that because the current 6th District incumbent was selected by convention,\\nthe plaintiff will not be forced to accede to a primary until 2022 at the earliest. But that\\nargument relies on the same cramped interpretation of standing that we rejected in Miller\\nI, 462 F.3d at 316-18. The injuries inflicted by laws that distort the primary process, like\\nthe Incumbent Protection Act, are not confined to the short duration of any particular\\nprimary, but instead reflect the reality that “campaign planning decisions have to be made\\n(Continued)\\n 20\\n\\fthe update occurred after the lawsuit had been filed. Promulgating new forms may well\\n\\nhave been the right thing to do in accordance with state law. But as a litigation tactic,\\n\\nsuch backpedaling will rarely serve to moot a case in federal court. Friends of the Earth,\\n\\nInc. v. Laidlaw Environmental Services (TOC), Inc., 528 U.S. 167, 189-94 (2000). The\\n\\nmootness doctrine ordinarily does not extend to situations where a party quits its\\n\\noffending conduct partway through litigation. Id. After all, “a party should not be able to\\n\\nevade judicial review, or to defeat a judgment, by temporarily altering questionable\\n\\nbehavior.” Porter v. Clarke, 852 F.3d 358, 364 (4th Cir. 2017) (internal quotation marks\\n\\nomitted). To overcome that general rule, the Department bears “[t]he heavy burden of\\n\\npersuading the court,” Laidlaw, 528 U.S. 167, 189 (2000) (internal quotation marks and\\n\\nalterations omitted), that it is “absolutely clear that the allegedly wrongful behavior could\\n\\nnot reasonably be expected to recur.” Wall v. Wade, 741 F.3d 492, 497 (2014) (quoting\\n\\nLaidlaw, 528 U.S. at 189).\\n\\n The Department cannot carry this burden. It has a history of frequently revising\\n\\nthe relevant election forms. The forms used for congressional nominations in 2014, for\\n\\nexample, reflected the fourth sentence of the Incumbent Protection Act and not the\\n\\nsecond and third. Yet the congressional nomination forms were inexplicably changed for\\n\\n\\nmonths, or even years, in advance of the election to be effective.” Id. at 317-18. The 6th\\nCongressional Committee’s claims thus did not become moot with the passing of the\\n2018 election season. The dispute over the Act’s fourth sentence, rather, is alive and well.\\nEven so, if the Department were correct that electoral disputes became moot with each\\npassing election cycle, this challenge, like many electoral challenges, would plainly be\\ncapable of repetition yet evading review. See, e.g., Davis v. Fed. Election Comm’n, 554\\nU.S. 724, 735-36 (2008).\\n\\n 21\\n\\fthe 2016 congressional elections to reflect the Act’s more fulsome General Assembly\\n\\nprotections instead. The Department has offered no explanation for why the forms were\\n\\nchanged to the benefit of incumbents between the 2014 and 2016 congressional elections.\\n\\nEven though the forms apparently have been edited once again, we have little confidence\\n\\nthat the forms will not revert back if we hold that this lawsuit is moot. Indeed, that danger\\n\\nis particularly acute when, as here, a change in the forms would confer benefits upon\\n\\npolitical incumbents. The Incumbent Protection Act transparently advances the interests\\n\\nof those who control the apparatus of government; it is hardly beyond the realm of\\n\\nplausibility that it would be administered with that same purpose in mind. The\\n\\nDepartment’s May 23, 2018 Suggestion of Mootness is accordingly denied.\\n\\n We may thus properly consider the 6th Congressional Committee’s facial and as\\n\\napplied First Amendment challenges to the Incumbent Protection Act’s protection of\\n\\nincumbent members of the General Assembly. A facial challenge to a law will succeed\\n\\nafter a showing “that no set of circumstances exist under which the law would be valid,\\n\\nor that the law lacks any plainly legitimate sweep.” Greater Balt. Center for Pregnancy\\n\\nConcerns, Inc. v. Mayor & City Council of Balt., 721 F.3d 264, 282 (4th Cir. 2013) (en\\n\\nbanc) (internal quotation marks and alterations omitted). In the First Amendment context,\\n\\na facial challenge may also succeed under overbreadth doctrine. Id. But there is no need\\n\\nto employ overbreadth doctrine in this case, for the Act’s second and third sentences\\n\\ncannot be applied in a manner consistent with the First Amendment.\\n\\n The Department fails to identify a single circumstance where the Act’s second and\\n\\nthird sentences could be lawfully applied. And we find none. The second and third\\n\\n 22\\n\\fsentences not only share the constitutional infirmities of the fourth sentence but exhibit\\n\\nthose infirmities to an even greater degree. The fourth sentence allows some incumbents\\n\\nto force a primary under certain designated circumstances. The second sentence goes\\n\\nfurther by empowering incumbents to impose their choice of any method of nomination\\n\\nno matter what the party prefers under almost any circumstances. 3 These advantages,\\n\\nwhen given to state or federal incumbents, run afoul of the First Amendment for all the\\n\\nreasons discussed in detail in Part II, supra.\\n\\n The Department raises yet one more challenge, arguing that the district court was\\n\\nwrong to enjoin the Incumbent Protection Act in its entirety. See Va. Code Ann. § 24.2-\\n\\n509(B). We review the district court’s decision to enjoin the statute for abuse of\\n\\ndiscretion. U.S. Airline Pilots Ass’n v. Awappa, LLC, 615 F.3d 312, 320 (4th Cir. 2010).\\n\\nThe Act comprises six sentences. We have now found that each of its operative\\n\\nprovisions—namely the second, third, and fourth sentences—is unconstitutional. The\\n\\nremaining sentences merely explain how to apply them. The district court did not abuse\\n\\nits discretion in enjoining the Incumbent Protection Act in toto.\\n\\n IV.\\n\\n Our decision is a narrow one. It is directed at a discrete constitutional imbalance\\n\\ncreated by permitting single office holders to negate the associational rights of political\\n\\nparties in an area central to the party’s very reason for being. Our ruling in no way limits\\n\\n 3\\n The third sentence applies in the relatively rare situation where there is more than\\none incumbent for the same office. In that situation, the statute requires incumbents’\\nconsent for any method of nomination other than a primary. § 24.2-509(B).\\n\\n\\n 23\\n\\fthe ability of states to enact “reasonable regulations of parties, elections, and ballots.”\\n\\nTimmons, 520 U.S. at 358. The associational rights of political parties are, after all, not\\n\\nabsolute. Laws that impose a slight or lesser burden on associational rights are owed\\n\\ndeference, especially when justified by the need “to reduce election- and campaign-\\n\\nrelated disorder.” Id. But our constitutional responsibility, set forth so plainly by the\\n\\nSupreme Court, requires us to ensure that this “deference does not risk such constitutional\\n\\nevils as, say, permitting incumbents to insulate themselves from effective electoral\\n\\nchallenge.” Nixon v. Shrink Mo. Gov’t PAC, 528 U.S. 377, 402 (2000) (Breyer, J.,\\n\\nconcurring). The Incumbent Protection Act reflects precisely that infirmity, and it is\\n\\nprecisely why we cannot allow the Act to stand.\\n\\n For the foregoing reasons, the judgment of the district court is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 24\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":92,"cells":{"id":{"kind":"number","value":4581300,"string":"4,581,300"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff - Appellee, v. Carl Javan ROSS, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Carl Ross"},"decision_date":{"kind":"string","value":"2019-01-14"},"docket_number":{"kind":"string","value":"17-4242"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Gregory, Niemeyer, Harris\", \"parties\": \"\", \"opinions\": [{\"author\": \"Vacated and remanded by published opinion. Chief Judge Gregory wrote the opinion, in\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-4242\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nCARL JAVAN ROSS,\\n\\n Defendant - Appellant.\\n\\n\\nAppeal from the United States District Court for the District of Maryland, at Baltimore.\\nJ. Frederick Motz, Senior District Judge. (1:16-cr-00020-JFM)\\n\\n\\nArgued: November 1, 2018 Decided: January 14, 2019\\n\\n\\nBefore GREGORY, Chief Judge, NIEMEYER, and HARRIS, Circuit Judges.\\n\\n\\nVacated and remanded by published opinion. Chief Judge Gregory wrote the opinion, in\\nwhich Judge Niemeyer and Judge Harris joined.\\n\\n\\nARGUED: Paresh S. Patel, OFFICE OF THE FEDERAL PUBLIC DEFENDER,\\nGreenbelt, Maryland, for Appellant. Paul E. Budlow, OFFICE OF THE UNITED\\nSTATES ATTORNEY, Baltimore, Maryland, for Appellee. ON BRIEF: James Wyda,\\nFederal Public Defender, Baltimore, Maryland, Joanna Silver, Appellate Attorney,\\nOFFICE OF THE FEDERAL PUBLIC DEFENDER, Greenbelt, Maryland, for\\nAppellant. Stephen M. Schenning, Acting United States Attorney, Paul Riley, Assistant\\nUnited States Attorney, OFFICE OF THE UNITED STATES ATTORNEY, Baltimore,\\nMaryland, for Appellee.\\n\\fGREGORY, Chief Judge:\\n\\n Defendant-Appellant Carl Javan Ross appeals his sentence, which the district\\n\\ncourt imposed after Ross was convicted of two counts in violation of 18 U.S.C.\\n\\n§ 2252(a)(2), and one count in violation of 18 U.S.C. § 2252(a)(4)(b). Ross contends the\\n\\ndistrict court did not explain why it imposed his term of confinement and did not address\\n\\nhis non-frivolous arguments in favor of a lower sentence. These omissions render his\\n\\nsentence procedurally unreasonable, according to Ross. In addition, Ross argues the\\n\\ndistrict court committed procedural error with its imposition of special conditions of\\n\\nsupervised release. We agree, and for the reasons that follow, we vacate Ross’s sentence\\n\\nand remand for resentencing.\\n\\n\\n\\n I.\\n\\n On December 7, 2016, a jury convicted Ross of two counts of receipt of child\\n\\npornography, in violation of 18 U.S.C. § 2252(a)(2), and one count of possession of child\\n\\npornography in violation of 18 U.S.C. § 2252(a)(4)(b). The United States Probation\\n\\nOffice filed a Presentence Investigation Report (“PSR”) that included a recommended\\n\\nterm of confinement and recommended special conditions of supervised released. The\\n\\nPSR calculated Ross’s final offense level as 35 and included various enhancements\\n\\nreflecting the repugnant nature of the materials in his possession. J.A. 92-93. The PSR\\n\\ncalculated Ross’s Criminal History Category as II given that he had a prior state court\\n\\n\\n\\n\\n 2\\n\\fconviction for a sexual offense involving a minor. 1 J.A. 94. The Government and Ross\\n\\nboth submitted sentencing memoranda.\\n\\n The district court held a sentencing hearing and adopted the PSR’s advisory\\n\\nGuidelines range: 188 months to 235 months in prison. The district court ordered a term\\n\\nof confinement of 120 months as to each count, to run concurrently with each other but\\n\\nconsecutive to his state court sentence. J.A. 63. The district court placed Ross on\\n\\nsupervised release for the rest of his life “subject to the special conditions set forth in the\\n\\nrecommended conditions of supervision.” Id. Ross timely appealed. We have\\n\\njurisdiction under 28 U.S.C. § 1291.\\n\\n\\n\\n II.\\n\\n At the sentencing hearing, the Government asked the district court to impose a\\n\\nterm of confinement of 120 months to be served consecutive to his 120-months state\\n\\ncourt term of confinement instead of Ross’s requested 60-month mandatory minimum\\n\\nsentence which he wanted to run concurrently to his state court sentence. The\\n\\nGovernment argued Ross’s request resulted in “essentially no sentence” and “absolutely\\n\\nzero impact, zero additional punishment as a result of the conduct in this case.” J.A. 17.\\n\\nAccording to the Government, the gravity of Ross’s conduct justified a longer and non-\\n\\nconcurrent sentence and his state court conviction constituted evidence of Ross’s threat to\\n\\nthe public. The Government highlighted that Ross deleted much of the illegal material he\\n\\n 1\\n While awaiting trial in his federal case, Ross received a state court term of\\nconfinement of 240 months, with 120 months suspended. J.A. 93.\\n\\n 3\\n\\fpossessed in order to avoid detection, still denied participating in the conduct that gave\\n\\nrise to his state court conviction and generally lacked remorse for his actions.\\n\\n Counsel for Ross replied that the Government’s sentencing position essentially\\n\\namounted to an above-Guidelines sentence because it would result in two separate 120-\\n\\nmonth terms of confinement that run consecutively. Counsel argued the district court\\n\\nshould consider his state court term of confinement when calculating his sentence. In\\n\\naddition, Ross’s counsel argued that felony convictions relating to sexual offenses are\\n\\nalready very punitive and that the lifelong social stigma Ross faces justified his request\\n\\nfor a 60-month concurrent sentence. Ross’s counsel defended his requested sentence\\n\\ngiven the stringent demands of supervised release he will face and the likelihood of his\\n\\nrecidivism if he violates his terms.\\n\\n Additionally, Ross’s counsel further explained while Ross did not appear\\n\\nremorseful, his demeanor reflected his mental health challenges and not a lack of\\n\\nremorse. Counsel presented Ross’s psychological forensic report, which explained\\n\\nRoss’s diagnosis of schizoid personality disorder, adjustment disorder, and an unspecified\\n\\nneurodevelopmental disorder. These conditions should have been considered in\\n\\nmitigation, according to Ross’s counsel. For instance, counsel asserted Ross’s mental\\n\\ndisorder caused Ross to insist on going to trial in his state court case against the advice of\\n\\nhis lawyer. Ross’s counsel further indicated that Ross’s mental health issues similarly\\n\\ncaused him to elect to go to trial instead of pleading guilty in his federal case as well,\\n\\nleading to increased exposure to criminal penalties. Ross’s counsel argued that Ross\\n\\nmaintained gainful employment, cared for his aging mother and had only a relatively\\n\\n 4\\n\\fsmall amount of illicit material compared to the average child pornography offender.\\n\\nAccording to Ross’s counsel, the district court should have considered all of these factors\\n\\nwhen calculating Ross’s term of confinement.\\n\\n Upon hearing arguments from both the Government and Ross, the district court\\n\\nimposed a sentence of 120 months to be served consecutive to his state court term of\\n\\nconfinement. The district court explained that it found Ross’s arguments unpersuasive\\n\\nand stated that “the Government’s recommendation is appropriate and that’s my sentence\\n\\nand the reason for it.” J.A. 63. After the district court pronounced Ross’s sentence, the\\n\\nGovernment requested the court to explain its basis for the sentence under the 18 U.S.C.\\n\\n§ 3553(a) factors. J.A. 63-64. The district court provided the following explanation:\\n\\n Well, I mean, it’s obviously [sic] the offense is a serious one. In terms of\\n specific deterrence, I am concerned about the lack of remorse while even if\\n there was remorse, there is a body of statistical evidence that—well, I’m\\n not going to say that, but that I believe it’s a specific deterrence, requires\\n the sentence I’m imposing. I did not find that the guidelines are so flawed\\n as to essentially have no sentence at all. And in terms of general\\n deterrence, I think that the sentence I’m imposing is required.\\n\\nJ.A. 64. In addition, the district court imposed a lifetime of supervised release. The\\n\\nspecial conditions of his supervised release prohibit Ross from using “computer systems,\\n\\nInternet-capable devices and/or similar electronic devices at any location (including\\n\\nemployment or educational program) without the prior written approval” of the probation\\n\\nofficer, and from owning, using, possessing, viewing, or reading any pornographic\\n\\nmaterials, as defined in 18 U.S.C. § 2256(2). J.A. 79.\\n\\n\\n\\n\\n 5\\n\\f III.\\n\\n Under the standard set forth in Gall v. United States, a sentence is reviewed for\\n\\nboth procedural and substantive reasonableness. 552 U.S. 38, 51 (2007). In the instant\\n\\ncase, procedural reasonableness is at issue. In determining procedural reasonableness,\\n\\nthis Court considers whether the district court properly calculated the defendant’s\\n\\nadvisory guidelines range, gave the parties an opportunity to argue for an appropriate\\n\\nsentence, considered the 18 U.S.C. § 3553(a) factors, and sufficiently explained the\\n\\nselected sentence. Id. at 49-51. We do not require the district court to “robotically tick\\n\\nthrough § 3553(a)’s every subsection, particularly when imposing a within-Guidelines\\n\\nsentence.” United States v. Powell, 650 F.3d 388, 395 (4th Cir. 2011) (internal citation\\n\\nand quotation marks omitted). Nevertheless, the district court must provide some\\n\\nindividualized assessment “justifying the sentence imposed and rejection of arguments\\n\\nfor a higher or lower sentence based on § 3553.” United States v. Lynn, 592 F.3d 572,\\n\\n584 (4th Cir. 2010). We will first turn to the procedural unreasonableness of Ross’s term\\n\\nof confinement and then to similar deficiencies pertaining to Ross’s special conditions of\\n\\nsupervised release.\\n\\n\\n\\n IV.\\n\\n Ross challenged his term of confinement at his sentencing hearing and therefore\\n\\nthis Court reviews the reasonableness of the term under “a deferential abuse-of-discretion\\n\\nstandard.” United States v. Cox, 744 F.3d 305, 308 (4th Cir. 2014). Under the law of this\\n\\ncircuit a district court must address or consider all non-frivolous reasons presented for\\n\\n 6\\n\\fimposing a different sentence and explain why he has rejected those arguments. United\\n\\nStates v. Blue, 877 F.3d 513, 518 (4th Cir. 2017); Slappy, 872 F.3d 202, 207 (4th Cir.\\n\\n2017) (internal citation and quotation marks omitted). Here, the district court did not\\n\\nfollow circuit precedent during Ross’s sentencing proceedings when determining his term\\n\\nof confinement. Indeed, the district court did not address or consider any of the\\n\\nnumerous non-frivolous arguments advanced by Ross’s counsel requesting a lower and\\n\\nconcurrent sentence. This Court has previously held that “[t]he adequacy of the\\n\\nsentencing court’s explanation depends on the complexity of each case. There is no\\n\\nmechanical approach to our sentencing review. The appropriateness of brevity or length,\\n\\nconsciousness or detail, when to write, what to say, depends upon the circumstances.”\\n\\nBlue, 877 F.3d at 518 (internal quotation marks and citations omitted). Here, it is\\n\\nundisputable that the sentencing court provided an insufficient explanation of its sentence\\n\\nand did not provide an “individualized assessment” of important mitigation evidence. Id.\\n\\nAn individualized assessment requires “that district courts consider the defendant’s\\n\\nnonfrivolous arguments for a downward departure, impose an individualized sentence\\n\\nbased on the characteristics of the defendant and the facts of the case, and explain the\\n\\nsentence chosen.” Id.\\n\\n As an initial matter, the district court did not provide an individualized assessment\\n\\nregarding important mitigation evidence related to Ross’s mental health. The district\\n\\ncourt noted that Ross lacked remorse but did not address his counsel’s arguments that his\\n\\nmental health issues, such as schizoid personality disorder, adjustment disorder, and an\\n\\nunspecified neurodevelopmental disorder, caused him to appear to lack remorse.\\n\\n 7\\n\\fMoreover, the district court did not address counsel’s arguments about how Ross’s\\n\\nmental health issues caused him to pursue litigation strategies that were contrary to his\\n\\nown interest and consequently raised his sentencing exposure. Finally, the district court\\n\\ndid not address Ross’s history of gainful employment, his role as a caretaker for his aging\\n\\nmother, and the relatively small amount of illicit material found in his computer as\\n\\nmitigating factors when calculating his term of confinement.\\n\\n The district court’s post-sentencing commentary is non-responsive to Ross’s\\n\\narguments and violates the legal standards for procedural reasonableness. The Supreme\\n\\nCourt makes clear that the district court must sufficiently address the parties’ arguments\\n\\nand provide an explanation for its sentence for this Court to engage in “meaningful\\n\\nappellate review.” Gall, 552 U.S. at 50. Although we have held that it is sometimes\\n\\npossible to discern a sentencing court’s rationale from the context surrounding its\\n\\ndecision, United States v. Montes-Pineda, 445 F.3d 375, 381 (4th Cir. 2006), an appellate\\n\\ncourt nonetheless “may not guess at the district court’s rationale, searching the record for\\n\\nstatements by the Government or defense counsel or for any other clues that might\\n\\nexplain a sentence,” United States v. Carter, 564 F.3d 325, 329-30 (4th Cir. 2009). The\\n\\ncomments made by the district court require this Court to impermissibly speculate as to\\n\\nthe reason for the district court’s sentencing decision.\\n\\n Contrary to the Government’s position, it is not harmless error that the district\\n\\ncourt did not explain its justification for Ross’s term of confinement. “For a procedural\\n\\nsentencing error to be harmless, the government must prove that the error did not have a\\n\\nsubstantial and injurious effect or influence on the result.” Lynn, 592 F.3d at 585\\n\\n 8\\n\\f(internal citation and quotation marks omitted). This Court cannot look at the district\\n\\ncourt’s comments and determine that the explicit consideration of Ross’s various\\n\\nmitigating arguments would not have affected the ultimate term of confinement imposed.\\n\\nFor instance, the district court mentioned that Ross lacked remorse when discussing its\\n\\nrationale for Ross’s term of confinement. But the record contains significant evidence of\\n\\nRoss’s mental health challenges as they affect his ability to show remorse. Given this\\n\\nrecord evidence, Ross’s demeanor arguably reflects mental health disorders and not a\\n\\ncallousness or denial of responsibility. The district court could have conceivably given\\n\\nRoss a different sentence if it had considered his non-frivolous mitigation arguments.\\n\\nThe district court had an obligation to specifically address Ross’s non-frivolous\\n\\narguments. It did not do so here. As noted at oral argument, even the Government\\n\\nnoticed that the district court did not provide a sufficient explanation and asked for\\n\\nclarification. Nonetheless, the district court cannot meet its responsibility through\\n\\nbroadly referring to the § 3553(a) factors in lieu of addressing the parties’ non-frivolous\\n\\narguments.\\n\\n\\n\\n V.\\n\\n The requirement that the district court adequately explain Ross’s term of\\n\\nconfinement similarly applies to the special conditions of his supervised release. United\\n\\nStates v. Armel, 585 F.3d 182, 186 (4th Cir. 2009). Ross did not challenge the special\\n\\nconditions of supervised release before the district court and concedes that this Court\\n\\n\\n\\n 9\\n\\fshould apply a plain-error standard of review. 2 United States v. Wesley, 81 F.3d 482, 484\\n\\n(4th Cir. 1996) (explaining that we reverse on plain error if the district court erred, the\\n\\nerror was plain, and the error affected the defendant’s substantial rights). Plain errors\\n\\nexist “if the settled law of the Supreme Court or this circuit establishes that an error has\\n\\noccurred.” United States v. Ramirez-Castillo, 748 F.3d 205, 215 (4th Cir. 2014).\\n\\n In imposing the conditions of supervised release, the district court at the\\n\\nsentencing hearing said, “I will place you on supervised release for life subject to the\\n\\ngeneral conditions and special conditions set forth in the recommended conditions of\\n\\nsupervision.” J.A. 63. The district court did not explain why Ross was given any of the\\n\\nspecial conditions for life. This lack of explanation contravenes the law of this circuit\\n\\nand constitutes plain error. Armel, 585 F.3d at 186. This error is not harmless. It is the\\n\\nsettled law of this circuit that Ross has a right to know why he faces special conditions\\n\\nthat will forever modify the course of his life, and the district court’s silence violated his\\n\\nrights. Id. This Court cannot look at the district court’s comments and ascertain its\\n\\nrationale for imposing very restrictive special conditions for the duration of Ross’s life.\\n\\n\\n\\n\\n 2\\n The parties briefed the special conditions of supervised release argument only\\nunder the plain-error standard. Recent circuit precedent suggests, however, that the abuse\\nof discretion standard should now apply because Ross challenged the term of\\nconfinement and thus preserved his challenge to the special conditions imposed as part of\\nhis supervised release. United States v. Ketter, 908 F.3d 61, 66 (4th Cir. 2018) (adopting\\na unitary approach to sentencing under which the term of confinement and term of\\nsupervised release constitute the same sentence for purposes of appellate review). Ross is\\nentitled to relief under either standard.\\n\\n\\n 10\\n\\fIt is procedurally unreasonable to impose special conditions for the remainder of Ross’s\\n\\nlife without providing an explanation or rationale for their justification. 3\\n\\n\\n\\n\\n VI.\\n\\n In conclusion, given that the district court failed to address Ross’s non-frivolous\\n\\nmitigation arguments and to properly explain its rationale for his term of confinement and\\n\\nhis special conditions, we vacate his sentence and remand so that the district court may\\n\\nprovide a sufficient explanation for the significant deprivation of liberty Ross faces as a\\n\\nresult of his criminal conduct. This Court makes no assessment regarding the fairness or\\n\\npropriety of Ross’s term of confinement or special conditions of supervised release.\\n\\n\\n\\n VACATED AND REMANDED\\n\\n\\n\\n\\n 3\\n Given that this Court is vacating Ross’s sentence regarding both the term of\\nconfinement and special conditions of supervised release, this Court need not address\\nRoss’s remaining arguments regarding the propriety of his special conditions.\\n\\n 11\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4358553/\", \"author_raw\": \"Vacated and remanded by published opinion. Chief Judge Gregory wrote the opinion, in\"}]}"},"judge1":{"kind":"string","value":"GREGORY"},"judge2":{"kind":"string","value":"NIEMEYER"},"judge3":{"kind":"string","value":"HARRIS"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4581300/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Carl Javan ROSS, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-14\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-4242\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff - Appellee,\n\n v.\n\nCARL JAVAN ROSS,\n\n Defendant - Appellant.\n\n\nAppeal from the United States District Court for the District of Maryland, at Baltimore.\nJ. Frederick Motz, Senior District Judge. (1:16-cr-00020-JFM)\n\n\nArgued: November 1, 2018 Decided: January 14, 2019\n\n\nBefore GREGORY, Chief Judge, NIEMEYER, and HARRIS, Circuit Judges.\n\n\nVacated and remanded by published opinion. Chief Judge Gregory wrote the opinion, in\nwhich Judge Niemeyer and Judge Harris joined.\n\n\nARGUED: Paresh S. Patel, OFFICE OF THE FEDERAL PUBLIC DEFENDER,\nGreenbelt, Maryland, for Appellant. Paul E. Budlow, OFFICE OF THE UNITED\nSTATES ATTORNEY, Baltimore, Maryland, for Appellee. ON BRIEF: James Wyda,\nFederal Public Defender, Baltimore, Maryland, Joanna Silver, Appellate Attorney,\nOFFICE OF THE FEDERAL PUBLIC DEFENDER, Greenbelt, Maryland, for\nAppellant. Stephen M. Schenning, Acting United States Attorney, Paul Riley, Assistant\nUnited States Attorney, OFFICE OF THE UNITED STATES ATTORNEY, Baltimore,\nMaryland, for Appellee.\n\fGREGORY, Chief Judge:\n\n Defendant-Appellant Carl Javan Ross appeals his sentence, which the district\n\ncourt imposed after Ross was convicted of two counts in violation of 18 U.S.C.\n\n§ 2252(a)(2), and one count in violation of 18 U.S.C. § 2252(a)(4)(b). Ross contends the\n\ndistrict court did not explain why it imposed his term of confinement and did not address\n\nhis non-frivolous arguments in favor of a lower sentence. These omissions render his\n\nsentence procedurally unreasonable, according to Ross. In addition, Ross argues the\n\ndistrict court committed procedural error with its imposition of special conditions of\n\nsupervised release. We agree, and for the reasons that follow, we vacate Ross’s sentence\n\nand remand for resentencing.\n\n\n\n I.\n\n On December 7, 2016, a jury convicted Ross of two counts of receipt of child\n\npornography, in violation of 18 U.S.C. § 2252(a)(2), and one count of possession of child\n\npornography in violation of 18 U.S.C. § 2252(a)(4)(b). The United States Probation\n\nOffice filed a Presentence Investigation Report (“PSR”) that included a recommended\n\nterm of confinement and recommended special conditions of supervised released. The\n\nPSR calculated Ross’s final offense level as 35 and included various enhancements\n\nreflecting the repugnant nature of the materials in his possession. J.A. 92-93. The PSR\n\ncalculated Ross’s Criminal History Category as II given that he had a prior state court\n\n\n\n\n 2\n\fconviction for a sexual offense involving a minor. 1 J.A. 94. The Government and Ross\n\nboth submitted sentencing memoranda.\n\n The district court held a sentencing hearing and adopted the PSR’s advisory\n\nGuidelines range: 188 months to 235 months in prison. The district court ordered a term\n\nof confinement of 120 months as to each count, to run concurrently with each other but\n\nconsecutive to his state court sentence. J.A. 63. The district court placed Ross on\n\nsupervised release for the rest of his life “subject to the special conditions set forth in the\n\nrecommended conditions of supervision.” Id. Ross timely appealed. We have\n\njurisdiction under 28 U.S.C. § 1291.\n\n\n\n II.\n\n At the sentencing hearing, the Government asked the district court to impose a\n\nterm of confinement of 120 months to be served consecutive to his 120-months state\n\ncourt term of confinement instead of Ross’s requested 60-month mandatory minimum\n\nsentence which he wanted to run concurrently to his state court sentence. The\n\nGovernment argued Ross’s request resulted in “essentially no sentence” and “absolutely\n\nzero impact, zero additional punishment as a result of the conduct in this case.” J.A. 17.\n\nAccording to the Government, the gravity of Ross’s conduct justified a longer and non-\n\nconcurrent sentence and his state court conviction constituted evidence of Ross’s threat to\n\nthe public. The Government highlighted that Ross deleted much of the illegal material he\n\n 1\n While awaiting trial in his federal case, Ross received a state court term of\nconfinement of 240 months, with 120 months suspended. J.A. 93.\n\n 3\n\fpossessed in order to avoid detection, still denied participating in the conduct that gave\n\nrise to his state court conviction and generally lacked remorse for his actions.\n\n Counsel for Ross replied that the Government’s sentencing position essentially\n\namounted to an above-Guidelines sentence because it would result in two separate 120-\n\nmonth terms of confinement that run consecutively. Counsel argued the district court\n\nshould consider his state court term of confinement when calculating his sentence. In\n\naddition, Ross’s counsel argued that felony convictions relating to sexual offenses are\n\nalready very punitive and that the lifelong social stigma Ross faces justified his request\n\nfor a 60-month concurrent sentence. Ross’s counsel defended his requested sentence\n\ngiven the stringent demands of supervised release he will face and the likelihood of his\n\nrecidivism if he violates his terms.\n\n Additionally, Ross’s counsel further explained while Ross did not appear\n\nremorseful, his demeanor reflected his mental health challenges and not a lack of\n\nremorse. Counsel presented Ross’s psychological forensic report, which explained\n\nRoss’s diagnosis of schizoid personality disorder, adjustment disorder, and an unspecified\n\nneurodevelopmental disorder. These conditions should have been considered in\n\nmitigation, according to Ross’s counsel. For instance, counsel asserted Ross’s mental\n\ndisorder caused Ross to insist on going to trial in his state court case against the advice of\n\nhis lawyer. Ross’s counsel further indicated that Ross’s mental health issues similarly\n\ncaused him to elect to go to trial instead of pleading guilty in his federal case as well,\n\nleading to increased exposure to criminal penalties. Ross’s counsel argued that Ross\n\nmaintained gainful employment, cared for his aging mother and had only a relatively\n\n 4\n\fsmall amount of illicit material compared to the average child pornography offender.\n\nAccording to Ross’s counsel, the district court should have considered all of these factors\n\nwhen calculating Ross’s term of confinement.\n\n Upon hearing arguments from both the Government and Ross, the district court\n\nimposed a sentence of 120 months to be served consecutive to his state court term of\n\nconfinement. The district court explained that it found Ross’s arguments unpersuasive\n\nand stated that “the Government’s recommendation is appropriate and that’s my sentence\n\nand the reason for it.” J.A. 63. After the district court pronounced Ross’s sentence, the\n\nGovernment requested the court to explain its basis for the sentence under the 18 U.S.C.\n\n§ 3553(a) factors. J.A. 63-64. The district court provided the following explanation:\n\n Well, I mean, it’s obviously [sic] the offense is a serious one. In terms of\n specific deterrence, I am concerned about the lack of remorse while even if\n there was remorse, there is a body of statistical evidence that—well, I’m\n not going to say that, but that I believe it’s a specific deterrence, requires\n the sentence I’m imposing. I did not find that the guidelines are so flawed\n as to essentially have no sentence at all. And in terms of general\n deterrence, I think that the sentence I’m imposing is required.\n\nJ.A. 64. In addition, the district court imposed a lifetime of supervised release. The\n\nspecial conditions of his supervised release prohibit Ross from using “computer systems,\n\nInternet-capable devices and/or similar electronic devices at any location (including\n\nemployment or educational program) without the prior written approval” of the probation\n\nofficer, and from owning, using, possessing, viewing, or reading any pornographic\n\nmaterials, as defined in 18 U.S.C. § 2256(2). J.A. 79.\n\n\n\n\n 5\n\f III.\n\n Under the standard set forth in Gall v. United States, a sentence is reviewed for\n\nboth procedural and substantive reasonableness. 552 U.S. 38, 51 (2007). In the instant\n\ncase, procedural reasonableness is at issue. In determining procedural reasonableness,\n\nthis Court considers whether the district court properly calculated the defendant’s\n\nadvisory guidelines range, gave the parties an opportunity to argue for an appropriate\n\nsentence, considered the 18 U.S.C. § 3553(a) factors, and sufficiently explained the\n\nselected sentence. Id. at 49-51. We do not require the district court to “robotically tick\n\nthrough § 3553(a)’s every subsection, particularly when imposing a within-Guidelines\n\nsentence.” United States v. Powell, 650 F.3d 388, 395 (4th Cir. 2011) (internal citation\n\nand quotation marks omitted). Nevertheless, the district court must provide some\n\nindividualized assessment “justifying the sentence imposed and rejection of arguments\n\nfor a higher or lower sentence based on § 3553.” United States v. Lynn, 592 F.3d 572,\n\n584 (4th Cir. 2010). We will first turn to the procedural unreasonableness of Ross’s term\n\nof confinement and then to similar deficiencies pertaining to Ross’s special conditions of\n\nsupervised release.\n\n\n\n IV.\n\n Ross challenged his term of confinement at his sentencing hearing and therefore\n\nthis Court reviews the reasonableness of the term under “a deferential abuse-of-discretion\n\nstandard.” United States v. Cox, 744 F.3d 305, 308 (4th Cir. 2014). Under the law of this\n\ncircuit a district court must address or consider all non-frivolous reasons presented for\n\n 6\n\fimposing a different sentence and explain why he has rejected those arguments. United\n\nStates v. Blue, 877 F.3d 513, 518 (4th Cir. 2017); Slappy, 872 F.3d 202, 207 (4th Cir.\n\n2017) (internal citation and quotation marks omitted). Here, the district court did not\n\nfollow circuit precedent during Ross’s sentencing proceedings when determining his term\n\nof confinement. Indeed, the district court did not address or consider any of the\n\nnumerous non-frivolous arguments advanced by Ross’s counsel requesting a lower and\n\nconcurrent sentence. This Court has previously held that “[t]he adequacy of the\n\nsentencing court’s explanation depends on the complexity of each case. There is no\n\nmechanical approach to our sentencing review. The appropriateness of brevity or length,\n\nconsciousness or detail, when to write, what to say, depends upon the circumstances.”\n\nBlue, 877 F.3d at 518 (internal quotation marks and citations omitted). Here, it is\n\nundisputable that the sentencing court provided an insufficient explanation of its sentence\n\nand did not provide an “individualized assessment” of important mitigation evidence. Id.\n\nAn individualized assessment requires “that district courts consider the defendant’s\n\nnonfrivolous arguments for a downward departure, impose an individualized sentence\n\nbased on the characteristics of the defendant and the facts of the case, and explain the\n\nsentence chosen.” Id.\n\n As an initial matter, the district court did not provide an individualized assessment\n\nregarding important mitigation evidence related to Ross’s mental health. The district\n\ncourt noted that Ross lacked remorse but did not address his counsel’s arguments that his\n\nmental health issues, such as schizoid personality disorder, adjustment disorder, and an\n\nunspecified neurodevelopmental disorder, caused him to appear to lack remorse.\n\n 7\n\fMoreover, the district court did not address counsel’s arguments about how Ross’s\n\nmental health issues caused him to pursue litigation strategies that were contrary to his\n\nown interest and consequently raised his sentencing exposure. Finally, the district court\n\ndid not address Ross’s history of gainful employment, his role as a caretaker for his aging\n\nmother, and the relatively small amount of illicit material found in his computer as\n\nmitigating factors when calculating his term of confinement.\n\n The district court’s post-sentencing commentary is non-responsive to Ross’s\n\narguments and violates the legal standards for procedural reasonableness. The Supreme\n\nCourt makes clear that the district court must sufficiently address the parties’ arguments\n\nand provide an explanation for its sentence for this Court to engage in “meaningful\n\nappellate review.” Gall, 552 U.S. at 50. Although we have held that it is sometimes\n\npossible to discern a sentencing court’s rationale from the context surrounding its\n\ndecision, United States v. Montes-Pineda, 445 F.3d 375, 381 (4th Cir. 2006), an appellate\n\ncourt nonetheless “may not guess at the district court’s rationale, searching the record for\n\nstatements by the Government or defense counsel or for any other clues that might\n\nexplain a sentence,” United States v. Carter, 564 F.3d 325, 329-30 (4th Cir. 2009). The\n\ncomments made by the district court require this Court to impermissibly speculate as to\n\nthe reason for the district court’s sentencing decision.\n\n Contrary to the Government’s position, it is not harmless error that the district\n\ncourt did not explain its justification for Ross’s term of confinement. “For a procedural\n\nsentencing error to be harmless, the government must prove that the error did not have a\n\nsubstantial and injurious effect or influence on the result.” Lynn, 592 F.3d at 585\n\n 8\n\f(internal citation and quotation marks omitted). This Court cannot look at the district\n\ncourt’s comments and determine that the explicit consideration of Ross’s various\n\nmitigating arguments would not have affected the ultimate term of confinement imposed.\n\nFor instance, the district court mentioned that Ross lacked remorse when discussing its\n\nrationale for Ross’s term of confinement. But the record contains significant evidence of\n\nRoss’s mental health challenges as they affect his ability to show remorse. Given this\n\nrecord evidence, Ross’s demeanor arguably reflects mental health disorders and not a\n\ncallousness or denial of responsibility. The district court could have conceivably given\n\nRoss a different sentence if it had considered his non-frivolous mitigation arguments.\n\nThe district court had an obligation to specifically address Ross’s non-frivolous\n\narguments. It did not do so here. As noted at oral argument, even the Government\n\nnoticed that the district court did not provide a sufficient explanation and asked for\n\nclarification. Nonetheless, the district court cannot meet its responsibility through\n\nbroadly referring to the § 3553(a) factors in lieu of addressing the parties’ non-frivolous\n\narguments.\n\n\n\n V.\n\n The requirement that the district court adequately explain Ross’s term of\n\nconfinement similarly applies to the special conditions of his supervised release. United\n\nStates v. Armel, 585 F.3d 182, 186 (4th Cir. 2009). Ross did not challenge the special\n\nconditions of supervised release before the district court and concedes that this Court\n\n\n\n 9\n\fshould apply a plain-error standard of review. 2 United States v. Wesley, 81 F.3d 482, 484\n\n(4th Cir. 1996) (explaining that we reverse on plain error if the district court erred, the\n\nerror was plain, and the error affected the defendant’s substantial rights). Plain errors\n\nexist “if the settled law of the Supreme Court or this circuit establishes that an error has\n\noccurred.” United States v. Ramirez-Castillo, 748 F.3d 205, 215 (4th Cir. 2014).\n\n In imposing the conditions of supervised release, the district court at the\n\nsentencing hearing said, “I will place you on supervised release for life subject to the\n\ngeneral conditions and special conditions set forth in the recommended conditions of\n\nsupervision.” J.A. 63. The district court did not explain why Ross was given any of the\n\nspecial conditions for life. This lack of explanation contravenes the law of this circuit\n\nand constitutes plain error. Armel, 585 F.3d at 186. This error is not harmless. It is the\n\nsettled law of this circuit that Ross has a right to know why he faces special conditions\n\nthat will forever modify the course of his life, and the district court’s silence violated his\n\nrights. Id. This Court cannot look at the district court’s comments and ascertain its\n\nrationale for imposing very restrictive special conditions for the duration of Ross’s life.\n\n\n\n\n 2\n The parties briefed the special conditions of supervised release argument only\nunder the plain-error standard. Recent circuit precedent suggests, however, that the abuse\nof discretion standard should now apply because Ross challenged the term of\nconfinement and thus preserved his challenge to the special conditions imposed as part of\nhis supervised release. United States v. Ketter, 908 F.3d 61, 66 (4th Cir. 2018) (adopting\na unitary approach to sentencing under which the term of confinement and term of\nsupervised release constitute the same sentence for purposes of appellate review). Ross is\nentitled to relief under either standard.\n\n\n 10\n\fIt is procedurally unreasonable to impose special conditions for the remainder of Ross’s\n\nlife without providing an explanation or rationale for their justification. 3\n\n\n\n\n VI.\n\n In conclusion, given that the district court failed to address Ross’s non-frivolous\n\nmitigation arguments and to properly explain its rationale for his term of confinement and\n\nhis special conditions, we vacate his sentence and remand so that the district court may\n\nprovide a sufficient explanation for the significant deprivation of liberty Ross faces as a\n\nresult of his criminal conduct. This Court makes no assessment regarding the fairness or\n\npropriety of Ross’s term of confinement or special conditions of supervised release.\n\n\n\n VACATED AND REMANDED\n\n\n\n\n 3\n Given that this Court is vacating Ross’s sentence regarding both the term of\nconfinement and special conditions of supervised release, this Court need not address\nRoss’s remaining arguments regarding the propriety of his special conditions.\n\n 11\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Carl Javan ROSS, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-14\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-4242\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nCARL JAVAN ROSS,\\n\\n Defendant - Appellant.\\n\\n\\nAppeal from the United States District Court for the District of Maryland, at Baltimore.\\nJ. Frederick Motz, Senior District Judge. (1:16-cr-00020-JFM)\\n\\n\\nArgued: November 1, 2018 Decided: January 14, 2019\\n\\n\\nBefore GREGORY, Chief Judge, NIEMEYER, and HARRIS, Circuit Judges.\\n\\n\\nVacated and remanded by published opinion. Chief Judge Gregory wrote the opinion, in\\nwhich Judge Niemeyer and Judge Harris joined.\\n\\n\\nARGUED: Paresh S. Patel, OFFICE OF THE FEDERAL PUBLIC DEFENDER,\\nGreenbelt, Maryland, for Appellant. Paul E. Budlow, OFFICE OF THE UNITED\\nSTATES ATTORNEY, Baltimore, Maryland, for Appellee. ON BRIEF: James Wyda,\\nFederal Public Defender, Baltimore, Maryland, Joanna Silver, Appellate Attorney,\\nOFFICE OF THE FEDERAL PUBLIC DEFENDER, Greenbelt, Maryland, for\\nAppellant. Stephen M. Schenning, Acting United States Attorney, Paul Riley, Assistant\\nUnited States Attorney, OFFICE OF THE UNITED STATES ATTORNEY, Baltimore,\\nMaryland, for Appellee.\\n\\fGREGORY, Chief Judge:\\n\\n Defendant-Appellant Carl Javan Ross appeals his sentence, which the district\\n\\ncourt imposed after Ross was convicted of two counts in violation of 18 U.S.C.\\n\\n§ 2252(a)(2), and one count in violation of 18 U.S.C. § 2252(a)(4)(b). Ross contends the\\n\\ndistrict court did not explain why it imposed his term of confinement and did not address\\n\\nhis non-frivolous arguments in favor of a lower sentence. These omissions render his\\n\\nsentence procedurally unreasonable, according to Ross. In addition, Ross argues the\\n\\ndistrict court committed procedural error with its imposition of special conditions of\\n\\nsupervised release. We agree, and for the reasons that follow, we vacate Ross’s sentence\\n\\nand remand for resentencing.\\n\\n\\n\\n I.\\n\\n On December 7, 2016, a jury convicted Ross of two counts of receipt of child\\n\\npornography, in violation of 18 U.S.C. § 2252(a)(2), and one count of possession of child\\n\\npornography in violation of 18 U.S.C. § 2252(a)(4)(b). The United States Probation\\n\\nOffice filed a Presentence Investigation Report (“PSR”) that included a recommended\\n\\nterm of confinement and recommended special conditions of supervised released. The\\n\\nPSR calculated Ross’s final offense level as 35 and included various enhancements\\n\\nreflecting the repugnant nature of the materials in his possession. J.A. 92-93. The PSR\\n\\ncalculated Ross’s Criminal History Category as II given that he had a prior state court\\n\\n\\n\\n\\n 2\\n\\fconviction for a sexual offense involving a minor. 1 J.A. 94. The Government and Ross\\n\\nboth submitted sentencing memoranda.\\n\\n The district court held a sentencing hearing and adopted the PSR’s advisory\\n\\nGuidelines range: 188 months to 235 months in prison. The district court ordered a term\\n\\nof confinement of 120 months as to each count, to run concurrently with each other but\\n\\nconsecutive to his state court sentence. J.A. 63. The district court placed Ross on\\n\\nsupervised release for the rest of his life “subject to the special conditions set forth in the\\n\\nrecommended conditions of supervision.” Id. Ross timely appealed. We have\\n\\njurisdiction under 28 U.S.C. § 1291.\\n\\n\\n\\n II.\\n\\n At the sentencing hearing, the Government asked the district court to impose a\\n\\nterm of confinement of 120 months to be served consecutive to his 120-months state\\n\\ncourt term of confinement instead of Ross’s requested 60-month mandatory minimum\\n\\nsentence which he wanted to run concurrently to his state court sentence. The\\n\\nGovernment argued Ross’s request resulted in “essentially no sentence” and “absolutely\\n\\nzero impact, zero additional punishment as a result of the conduct in this case.” J.A. 17.\\n\\nAccording to the Government, the gravity of Ross’s conduct justified a longer and non-\\n\\nconcurrent sentence and his state court conviction constituted evidence of Ross’s threat to\\n\\nthe public. The Government highlighted that Ross deleted much of the illegal material he\\n\\n 1\\n While awaiting trial in his federal case, Ross received a state court term of\\nconfinement of 240 months, with 120 months suspended. J.A. 93.\\n\\n 3\\n\\fpossessed in order to avoid detection, still denied participating in the conduct that gave\\n\\nrise to his state court conviction and generally lacked remorse for his actions.\\n\\n Counsel for Ross replied that the Government’s sentencing position essentially\\n\\namounted to an above-Guidelines sentence because it would result in two separate 120-\\n\\nmonth terms of confinement that run consecutively. Counsel argued the district court\\n\\nshould consider his state court term of confinement when calculating his sentence. In\\n\\naddition, Ross’s counsel argued that felony convictions relating to sexual offenses are\\n\\nalready very punitive and that the lifelong social stigma Ross faces justified his request\\n\\nfor a 60-month concurrent sentence. Ross’s counsel defended his requested sentence\\n\\ngiven the stringent demands of supervised release he will face and the likelihood of his\\n\\nrecidivism if he violates his terms.\\n\\n Additionally, Ross’s counsel further explained while Ross did not appear\\n\\nremorseful, his demeanor reflected his mental health challenges and not a lack of\\n\\nremorse. Counsel presented Ross’s psychological forensic report, which explained\\n\\nRoss’s diagnosis of schizoid personality disorder, adjustment disorder, and an unspecified\\n\\nneurodevelopmental disorder. These conditions should have been considered in\\n\\nmitigation, according to Ross’s counsel. For instance, counsel asserted Ross’s mental\\n\\ndisorder caused Ross to insist on going to trial in his state court case against the advice of\\n\\nhis lawyer. Ross’s counsel further indicated that Ross’s mental health issues similarly\\n\\ncaused him to elect to go to trial instead of pleading guilty in his federal case as well,\\n\\nleading to increased exposure to criminal penalties. Ross’s counsel argued that Ross\\n\\nmaintained gainful employment, cared for his aging mother and had only a relatively\\n\\n 4\\n\\fsmall amount of illicit material compared to the average child pornography offender.\\n\\nAccording to Ross’s counsel, the district court should have considered all of these factors\\n\\nwhen calculating Ross’s term of confinement.\\n\\n Upon hearing arguments from both the Government and Ross, the district court\\n\\nimposed a sentence of 120 months to be served consecutive to his state court term of\\n\\nconfinement. The district court explained that it found Ross’s arguments unpersuasive\\n\\nand stated that “the Government’s recommendation is appropriate and that’s my sentence\\n\\nand the reason for it.” J.A. 63. After the district court pronounced Ross’s sentence, the\\n\\nGovernment requested the court to explain its basis for the sentence under the 18 U.S.C.\\n\\n§ 3553(a) factors. J.A. 63-64. The district court provided the following explanation:\\n\\n Well, I mean, it’s obviously [sic] the offense is a serious one. In terms of\\n specific deterrence, I am concerned about the lack of remorse while even if\\n there was remorse, there is a body of statistical evidence that—well, I’m\\n not going to say that, but that I believe it’s a specific deterrence, requires\\n the sentence I’m imposing. I did not find that the guidelines are so flawed\\n as to essentially have no sentence at all. And in terms of general\\n deterrence, I think that the sentence I’m imposing is required.\\n\\nJ.A. 64. In addition, the district court imposed a lifetime of supervised release. The\\n\\nspecial conditions of his supervised release prohibit Ross from using “computer systems,\\n\\nInternet-capable devices and/or similar electronic devices at any location (including\\n\\nemployment or educational program) without the prior written approval” of the probation\\n\\nofficer, and from owning, using, possessing, viewing, or reading any pornographic\\n\\nmaterials, as defined in 18 U.S.C. § 2256(2). J.A. 79.\\n\\n\\n\\n\\n 5\\n\\f III.\\n\\n Under the standard set forth in Gall v. United States, a sentence is reviewed for\\n\\nboth procedural and substantive reasonableness. 552 U.S. 38, 51 (2007). In the instant\\n\\ncase, procedural reasonableness is at issue. In determining procedural reasonableness,\\n\\nthis Court considers whether the district court properly calculated the defendant’s\\n\\nadvisory guidelines range, gave the parties an opportunity to argue for an appropriate\\n\\nsentence, considered the 18 U.S.C. § 3553(a) factors, and sufficiently explained the\\n\\nselected sentence. Id. at 49-51. We do not require the district court to “robotically tick\\n\\nthrough § 3553(a)’s every subsection, particularly when imposing a within-Guidelines\\n\\nsentence.” United States v. Powell, 650 F.3d 388, 395 (4th Cir. 2011) (internal citation\\n\\nand quotation marks omitted). Nevertheless, the district court must provide some\\n\\nindividualized assessment “justifying the sentence imposed and rejection of arguments\\n\\nfor a higher or lower sentence based on § 3553.” United States v. Lynn, 592 F.3d 572,\\n\\n584 (4th Cir. 2010). We will first turn to the procedural unreasonableness of Ross’s term\\n\\nof confinement and then to similar deficiencies pertaining to Ross’s special conditions of\\n\\nsupervised release.\\n\\n\\n\\n IV.\\n\\n Ross challenged his term of confinement at his sentencing hearing and therefore\\n\\nthis Court reviews the reasonableness of the term under “a deferential abuse-of-discretion\\n\\nstandard.” United States v. Cox, 744 F.3d 305, 308 (4th Cir. 2014). Under the law of this\\n\\ncircuit a district court must address or consider all non-frivolous reasons presented for\\n\\n 6\\n\\fimposing a different sentence and explain why he has rejected those arguments. United\\n\\nStates v. Blue, 877 F.3d 513, 518 (4th Cir. 2017); Slappy, 872 F.3d 202, 207 (4th Cir.\\n\\n2017) (internal citation and quotation marks omitted). Here, the district court did not\\n\\nfollow circuit precedent during Ross’s sentencing proceedings when determining his term\\n\\nof confinement. Indeed, the district court did not address or consider any of the\\n\\nnumerous non-frivolous arguments advanced by Ross’s counsel requesting a lower and\\n\\nconcurrent sentence. This Court has previously held that “[t]he adequacy of the\\n\\nsentencing court’s explanation depends on the complexity of each case. There is no\\n\\nmechanical approach to our sentencing review. The appropriateness of brevity or length,\\n\\nconsciousness or detail, when to write, what to say, depends upon the circumstances.”\\n\\nBlue, 877 F.3d at 518 (internal quotation marks and citations omitted). Here, it is\\n\\nundisputable that the sentencing court provided an insufficient explanation of its sentence\\n\\nand did not provide an “individualized assessment” of important mitigation evidence. Id.\\n\\nAn individualized assessment requires “that district courts consider the defendant’s\\n\\nnonfrivolous arguments for a downward departure, impose an individualized sentence\\n\\nbased on the characteristics of the defendant and the facts of the case, and explain the\\n\\nsentence chosen.” Id.\\n\\n As an initial matter, the district court did not provide an individualized assessment\\n\\nregarding important mitigation evidence related to Ross’s mental health. The district\\n\\ncourt noted that Ross lacked remorse but did not address his counsel’s arguments that his\\n\\nmental health issues, such as schizoid personality disorder, adjustment disorder, and an\\n\\nunspecified neurodevelopmental disorder, caused him to appear to lack remorse.\\n\\n 7\\n\\fMoreover, the district court did not address counsel’s arguments about how Ross’s\\n\\nmental health issues caused him to pursue litigation strategies that were contrary to his\\n\\nown interest and consequently raised his sentencing exposure. Finally, the district court\\n\\ndid not address Ross’s history of gainful employment, his role as a caretaker for his aging\\n\\nmother, and the relatively small amount of illicit material found in his computer as\\n\\nmitigating factors when calculating his term of confinement.\\n\\n The district court’s post-sentencing commentary is non-responsive to Ross’s\\n\\narguments and violates the legal standards for procedural reasonableness. The Supreme\\n\\nCourt makes clear that the district court must sufficiently address the parties’ arguments\\n\\nand provide an explanation for its sentence for this Court to engage in “meaningful\\n\\nappellate review.” Gall, 552 U.S. at 50. Although we have held that it is sometimes\\n\\npossible to discern a sentencing court’s rationale from the context surrounding its\\n\\ndecision, United States v. Montes-Pineda, 445 F.3d 375, 381 (4th Cir. 2006), an appellate\\n\\ncourt nonetheless “may not guess at the district court’s rationale, searching the record for\\n\\nstatements by the Government or defense counsel or for any other clues that might\\n\\nexplain a sentence,” United States v. Carter, 564 F.3d 325, 329-30 (4th Cir. 2009). The\\n\\ncomments made by the district court require this Court to impermissibly speculate as to\\n\\nthe reason for the district court’s sentencing decision.\\n\\n Contrary to the Government’s position, it is not harmless error that the district\\n\\ncourt did not explain its justification for Ross’s term of confinement. “For a procedural\\n\\nsentencing error to be harmless, the government must prove that the error did not have a\\n\\nsubstantial and injurious effect or influence on the result.” Lynn, 592 F.3d at 585\\n\\n 8\\n\\f(internal citation and quotation marks omitted). This Court cannot look at the district\\n\\ncourt’s comments and determine that the explicit consideration of Ross’s various\\n\\nmitigating arguments would not have affected the ultimate term of confinement imposed.\\n\\nFor instance, the district court mentioned that Ross lacked remorse when discussing its\\n\\nrationale for Ross’s term of confinement. But the record contains significant evidence of\\n\\nRoss’s mental health challenges as they affect his ability to show remorse. Given this\\n\\nrecord evidence, Ross’s demeanor arguably reflects mental health disorders and not a\\n\\ncallousness or denial of responsibility. The district court could have conceivably given\\n\\nRoss a different sentence if it had considered his non-frivolous mitigation arguments.\\n\\nThe district court had an obligation to specifically address Ross’s non-frivolous\\n\\narguments. It did not do so here. As noted at oral argument, even the Government\\n\\nnoticed that the district court did not provide a sufficient explanation and asked for\\n\\nclarification. Nonetheless, the district court cannot meet its responsibility through\\n\\nbroadly referring to the § 3553(a) factors in lieu of addressing the parties’ non-frivolous\\n\\narguments.\\n\\n\\n\\n V.\\n\\n The requirement that the district court adequately explain Ross’s term of\\n\\nconfinement similarly applies to the special conditions of his supervised release. United\\n\\nStates v. Armel, 585 F.3d 182, 186 (4th Cir. 2009). Ross did not challenge the special\\n\\nconditions of supervised release before the district court and concedes that this Court\\n\\n\\n\\n 9\\n\\fshould apply a plain-error standard of review. 2 United States v. Wesley, 81 F.3d 482, 484\\n\\n(4th Cir. 1996) (explaining that we reverse on plain error if the district court erred, the\\n\\nerror was plain, and the error affected the defendant’s substantial rights). Plain errors\\n\\nexist “if the settled law of the Supreme Court or this circuit establishes that an error has\\n\\noccurred.” United States v. Ramirez-Castillo, 748 F.3d 205, 215 (4th Cir. 2014).\\n\\n In imposing the conditions of supervised release, the district court at the\\n\\nsentencing hearing said, “I will place you on supervised release for life subject to the\\n\\ngeneral conditions and special conditions set forth in the recommended conditions of\\n\\nsupervision.” J.A. 63. The district court did not explain why Ross was given any of the\\n\\nspecial conditions for life. This lack of explanation contravenes the law of this circuit\\n\\nand constitutes plain error. Armel, 585 F.3d at 186. This error is not harmless. It is the\\n\\nsettled law of this circuit that Ross has a right to know why he faces special conditions\\n\\nthat will forever modify the course of his life, and the district court’s silence violated his\\n\\nrights. Id. This Court cannot look at the district court’s comments and ascertain its\\n\\nrationale for imposing very restrictive special conditions for the duration of Ross’s life.\\n\\n\\n\\n\\n 2\\n The parties briefed the special conditions of supervised release argument only\\nunder the plain-error standard. Recent circuit precedent suggests, however, that the abuse\\nof discretion standard should now apply because Ross challenged the term of\\nconfinement and thus preserved his challenge to the special conditions imposed as part of\\nhis supervised release. United States v. Ketter, 908 F.3d 61, 66 (4th Cir. 2018) (adopting\\na unitary approach to sentencing under which the term of confinement and term of\\nsupervised release constitute the same sentence for purposes of appellate review). Ross is\\nentitled to relief under either standard.\\n\\n\\n 10\\n\\fIt is procedurally unreasonable to impose special conditions for the remainder of Ross’s\\n\\nlife without providing an explanation or rationale for their justification. 3\\n\\n\\n\\n\\n VI.\\n\\n In conclusion, given that the district court failed to address Ross’s non-frivolous\\n\\nmitigation arguments and to properly explain its rationale for his term of confinement and\\n\\nhis special conditions, we vacate his sentence and remand so that the district court may\\n\\nprovide a sufficient explanation for the significant deprivation of liberty Ross faces as a\\n\\nresult of his criminal conduct. This Court makes no assessment regarding the fairness or\\n\\npropriety of Ross’s term of confinement or special conditions of supervised release.\\n\\n\\n\\n VACATED AND REMANDED\\n\\n\\n\\n\\n 3\\n Given that this Court is vacating Ross’s sentence regarding both the term of\\nconfinement and special conditions of supervised release, this Court need not address\\nRoss’s remaining arguments regarding the propriety of his special conditions.\\n\\n 11\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":93,"cells":{"id":{"kind":"number","value":4581301,"string":"4,581,301"},"name":{"kind":"string","value":"MINNIELAND PRIVATE DAY SCHOOL, INC., a Virginia Corporation, Plaintiff - Appellee, v. APPLIED UNDERWRITERS CAPTIVE RISK ASSURANCE COMPANY, INC., Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"Minnieland Private Day Sch., Inc. v. Applied Underwriters Captive Risk Assurance Co."},"decision_date":{"kind":"string","value":"2019-01-14"},"docket_number":{"kind":"string","value":"17-2385"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Gregory, Motz, Wynn\", \"parties\": \"\", \"opinions\": [{\"author\": \"Affirmed by published opinion. Chief Judge Gregory wrote the opinion, in which Judge\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-2385\\n\\n\\nMINNIELAND PRIVATE DAY SCHOOL, INC., a Virginia corporation,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nAPPLIED UNDERWRITERS CAPTIVE RISK ASSURANCE COMPANY, INC.,\\n\\n Defendant - Appellant.\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. Anthony John Trenga, District Judge. (1:15-cv-01695-AJT-IDD)\\n\\n\\nArgued: October 30, 2018 Decided: January 14, 2019\\n\\n\\nBefore GREGORY, Chief Judge, MOTZ, and WYNN, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Chief Judge Gregory wrote the opinion, in which Judge\\nMotz and Judge Wynn joined.\\n\\n\\nARGUED: Daniel William Olivas, LEWIS, THOMASON, KING, KRIEG &\\nWALDROP, P.C., Nashville, Tennessee, for Appellant. James Scott Krein, KREIN\\nLAW FRIM, Prince William, Virginia, for Appellee. ON BRIEF: R. Dale Bay,\\nRyan N. Clark, LEWIS, THOMASON, KING, KRIEG & WALDROP, P.C., Nashville,\\nTennessee, for Appellant.\\n\\fGREGORY, Chief Judge:\\n\\n Appellant Applied Underwriters Captive Risk Assurance Company, Inc.\\n\\n(“AUCRA”) comes to us for the second time in this case, appealing the district court’s\\n\\ndetermination that a Reinsurance Participation Agreement (“RPA”) executed by it and\\n\\nAppellee Minnieland Private Day School is an insurance contract under Virginia law.\\n\\nThe RPA, executed in connection with Minnieland’s purchase of workers’ compensation\\n\\ninsurance, contains an arbitration clause. In the district court, AUCRA moved to compel\\n\\narbitration in accordance with the RPA’s terms. In opposing arbitration, Minnieland\\n\\nasserted that the RPA is an insurance contract for purposes of Virginia Code § 38.2–312,\\n\\nwhich renders void arbitration clauses contained in insurance contracts. The district court\\n\\ndenied AUCRA’s motion to compel arbitration, finding that AUCRA was judicially\\n\\nestopped from arguing that the RPA is not an insurance contract. We reversed that\\n\\ndetermination, concluding that AUCRA was not estopped from making its argument, and\\n\\nremanded to allow the parties to brief fully the issue of whether the RPA is an insurance\\n\\ncontract for purposes of Virginia Code § 38.2–312. On remand, the district court held\\n\\nthat the RPA is indeed an insurance contract and that the RPA’s arbitration clause is void\\n\\nas a matter of law. AUCRA now appeals that determination.\\n\\n For the reasons set forth below, we conclude that the RPA is an insurance contract\\n\\nfor purposes of Virginia Code § 38.2–312. We therefore affirm.\\n\\n\\n\\n\\n 2\\n\\f I.\\n\\n A.\\n\\n This case involves a workers’ compensation insurance program that Minnieland\\n\\npurchased from AUCRA and its affiliated entities. Under Virginia law, workers’\\n\\ncompensation insurance is “insurance against the legal liability of any employer for the\\n\\ndeath or disablement of, or injury to, his or its employee whether imposed by common\\n\\nlaw or by statute, or assumed by contract.” Va. Code § 38.2–119. Workers’\\n\\ncompensation insurance coverage is required of “[e]very employer subject to” Virginia’s\\n\\nworkers’ compensation statute. Va. Code § 65.2–800(A); Redifer v. Chester, 720 S.E.2d\\n\\n66, 67–68 (Va. 2012).\\n\\n In general, workers’ compensation insurance is typically provided in one of two\\n\\ntypes of policies: a guaranteed cost policy or a retrospective rating plan. Under a\\n\\nguaranteed cost policy, the premiums are fixed and usually do not change over the term\\n\\nof the policy. Steven Plitt, Daniel Maldonado, Joshua D. Rogers, & Jordan R. Plitt, 2\\n\\nCouch on Insurance § 69:10 (3d ed. 1995). In many states, these plans are the only plans\\n\\nlawfully available to small and mid-sized employers. Retrospective rating plans, on the\\n\\nother hand, usually require an advance premium deposit with the insurer and then provide\\n\\nthat the insurer, at some specified time, will compute the actual premium based on the\\n\\ninsured’s actual loss experience or total payroll during a set period of time. Id. § 69:16;\\n\\nsee Va. Code § 38.2–1901 (defining “retrospective rating plan” as “a rating plan that\\n\\nadjusts the premium for the insurance to which it applies on the basis of losses incurred\\n\\nduring the period covered by that insurance”). The insured is then either issued a refund\\n\\n 3\\n\\fif the actual premium is lower than the premium deposit paid or required to pay the\\n\\ndifference if the actual premium exceeds the deposited amount.\\n\\n At issue in this appeal is Applied Underwriters, Inc.’s EquityComp program, an\\n\\ninnovative program of workers’ compensation insurance that offers small and mid-sized\\n\\nemployers the benefits of both a guaranteed cost policy and a retrospective rating plan in\\n\\none insurance program. The EquityComp program provides employers with guaranteed\\n\\ncost workers’ compensation insurance at the same time that they enjoy the benefits—and\\n\\nare subject to the risks—of a retrospective rating plan. See J.A. 404 (explaining that this\\n\\nRPA allows small and mid-sized employers to “in effect, have a retrospective rating plan\\n\\n. . . even though, in fact, the insured has Guaranteed Cost insurance coverage with the\\n\\ninsurance carrier”). 1 The program is so novel that it has been patented.\\n\\n Under the program, various insurance companies affiliated with Applied\\n\\nUnderwriters, Inc. have entered into a reinsurance pooling agreement. The pooled\\n\\ncompanies provide workers’ compensation insurance coverage to employers and also\\n\\nmutually reinsure each other’s insurance business. A layer of reinsurance is also\\n\\nprovided by AUCRA, a wholly owned subsidiary of Applied Underwriters, Inc. AUCRA\\n\\nin turn enters into RPAs with EquityComp customers, under the terms of which each\\n\\ncustomer pays into a segregated “cell” or account that is then used to fund AUCRA’s\\n\\nliabilities. In essence, EquityComp customers participate in underwriting the risk of their\\n\\nown workers’ compensation insurance policies.\\n\\n 1\\n Citations to the “J.A.” refer to the Joint Appendix filed by the parties in this\\nappeal.\\n\\n 4\\n\\f In theory, an EquityComp customer can save costs on its workers’ compensation\\n\\ninsurance through a refund of monies deposited into its segregated cell if its workers’\\n\\ncompensation insurance claims are kept low during the term of the RPA. As detailed\\n\\nbelow, however, Minnieland was unable to reap this benefit.\\n\\n B.\\n\\n Minnieland provides education and childcare services in Virginia and is subject to\\n\\nthe workers’ compensation laws and requirements of the state. Va. Code § 65.2–800(A).\\n\\n On January 14, 2013, Minnieland bought into the EquityComp program.\\n\\nMinnieland executed a Request to Bind Coverages and Services (“Binder”), by which\\n\\nMinnieland “request[ed] that Applied Underwriters, Inc. through its affiliates and/or\\n\\nsubsidiaries . . . cause to be issued to [Minnieland] one or more workers’ compensation\\n\\ninsurance policies . . . subject to [Minnieland] executing the . . . [RPA].” J.A. 40. At the\\n\\nsame time, Minnieland executed an RPA. The RPA had a term of three years and\\n\\nprovided that one or more “Issuing Insurers”—all of which were entities affiliated with\\n\\nApplied Underwriters, Inc.—would issue workers’ compensation insurance policies to\\n\\nMinnieland. The RPA also established that Minnieland would share in the profits and\\n\\nlosses associated with its policies through its “segregated protected cell.” Applied Risk\\n\\nServices, Inc. (“ARS”), another subsidiary of Applied Underwriters, Inc., was designated\\n\\nas the billing agent for both AUCRA and the Issuing Insurers. Schedule 1 of the RPA\\n\\nsets forth various formulae for calculating premiums and losses under the RPA and\\n\\ninsurance policies.\\n\\n\\n\\n 5\\n\\f The day after Minnieland executed the EquityComp documents, the RPA went\\n\\ninto effect, as did the first of what would become three consecutive one-year Virginia\\n\\nworkers’ compensation insurance policies, the last of which was to expire on January 15,\\n\\n2016. The first policy listed the estimated annual premium as $589,163. The second and\\n\\nthird policies listed the estimated annual premiums as $642,333 and $706,160,\\n\\nrespectively. The policies were produced by ARS and insured by Continental Indemnity\\n\\nCompany (“CNI”), another affiliate of Applied Underwriters, Inc.\\n\\n According to the complaint, at no time was AUCRA licensed to sell insurance in\\n\\nVirginia, and the RPA has not been approved by the Virginia Workers’ Compensation\\n\\nCommission.\\n\\n For the first 33 of the 36 months during which the RPA was active, AUCRA\\n\\ncharged, and Minnieland paid, an average of $58,810 per month in premiums. In\\n\\nNovember 2015, however, the premium charged to Minnieland increased drastically to\\n\\n$471,213, a 1167% increase from the October 2015 premium and a 801% increase over\\n\\nthe first 33 months’ average. Despite Minnieland’s requests, AUCRA refused to disclose\\n\\nthe basis on which it assessed the November 2015 premium. Minnieland nonetheless\\n\\npaid the November premium.\\n\\n AUCRA billed Minnieland a similarly high premium of $414,604 for December\\n\\n2015. AUCRA once again refused to disclose the basis for the increased premium, and\\n\\nMinnieland did not pay the December premium.\\n\\n\\n\\n\\n 6\\n\\f On December 16, 2015, AUCRA 2 faxed Minnieland notice that it was terminating\\n\\nMinnieland’s EquityComp program, including the RPA and insurance coverage, effective\\n\\nDecember 27, 2015. The reason provided for the termination of coverage was “Non-\\n\\nPayment of Premium; Client has an outstanding balance.”\\n\\n C.\\n\\n On December 24, 2015, Minnieland filed suit against AUCRA in the Eastern\\n\\nDistrict of Virginia. Minnieland alleged that AUCRA is not authorized or licensed to act\\n\\nas an insurance company under Virginia law; that the RPA is an “insurance contract” and\\n\\nnot a “reinsurance” agreement; and that AUCRA misrepresented the EquityComp\\n\\nprogram, and the RPA specifically, to circumvent Virginia insurance and workers’\\n\\ncompensation laws. Minnieland sought (1) a declaration that the RPA constitutes an\\n\\ninsurance contract and is void because of AUCRA’s failure to comply with Virginia law;\\n\\n(2) a declaration of the amount, if any, that Minnieland owes under the RPA; and (3) a\\n\\ndeclaration that the premiums, deposits, and charges assessed to Minnieland by AUCRA\\n\\nwere excessive. Minnieland also sought damages for fraud and breach of contract.\\n\\n On January 18, 2016, AUCRA filed a demand for arbitration with the American\\n\\nArbitration Association, invoking the RPA’s arbitration provisions. That demand sought\\n\\npayment from Minnieland of a total of $342,358 that AUCRA claimed it was owed under\\n\\nthe RPA and EquityComp program.\\n\\n 2\\n The complaint alleges that AUCRA sent the notice. The letter is printed on\\n“Applied Underwriters” letterhead and does not specify if the sender is AUCRA or\\nApplied Underwriters, Inc. J.A. 52. The document attached to the letter indicates that it\\nwas “produced by” ARS. J.A. 53.\\n\\n 7\\n\\f AUCRA also moved the district court to dismiss Minnieland’s complaint and\\n\\ncompel arbitration under the RPA’s arbitration clause. In opposing the motion to compel\\n\\narbitration, Minnieland argued that the RPA is an insurance contract. As such,\\n\\nMinnieland argued, the arbitration clause is void because it is prohibited by Virginia\\n\\nCode § 38.2–312.\\n\\n On March 17, 2016, the district court granted in part and denied in part AUCRA’s\\n\\nmotion. The district court determined that the RPA’s arbitration clause calls for\\n\\narbitration of the threshold question of whether the RPA is an insurance contract such\\n\\nthat Virginia’s insurance statute, which reverse-preempts the Federal Arbitration Act\\n\\n(“FAA”), applies. Accordingly, the court ordered the parties to submit that question to\\n\\nthe arbitrator.\\n\\n A week later, the district court granted Minnieland’s motion for reconsideration of\\n\\nthe court’s March 17, 2016 order. The district court again concluded that the threshold\\n\\nissue of arbitrability was for the arbitrator to determine. The district court nonetheless\\n\\nstayed its March 17 order and requested supplemental briefing on Minnieland’s\\n\\ncontention that AUCRA was judicially estopped from arguing that the RPA is not an\\n\\ninsurance contract.\\n\\n The parties briefed the judicial estoppel issue, and the district court heard\\n\\nargument on AUCRA’s motion to compel arbitration. The district court denied the\\n\\nmotion to compel, concluding that the four elements of judicial estoppel were met such\\n\\nthat AUCRA was estopped from arguing that the RPA is not an insurance contract. See\\n\\n\\n\\n 8\\n\\fLowery v. Stovall, 92 F.3d 219, 223–24 (4th Cir. 1996) (discussing the elements of\\n\\njudicial estoppel).\\n\\n AUCRA appealed that order. On appeal, we affirmed in part and reversed in part.\\n\\nMinnieland Private Day Sch., Inc. v. Applied Underwriters Captive Risk Assurance Co.,\\n\\nInc., 867 F.3d 449 (4th Cir. 2017), cert. denied, 138 S. Ct. 926 (2018). We concluded\\n\\nthat Virginia Code § 38.2–312 “renders invalid delegation provisions in putative\\n\\ninsurance contracts governed by Virginia law, at least to the extent such delegation\\n\\nprovisions endow an arbitrator, as opposed to a court, with exclusive authority to\\n\\ndetermine whether the contract at issue constitutes an ‘insurance contract’ for purposes of\\n\\nVirginia law.” Id. at 456. Therefore, we affirmed the district court’s denial of the motion\\n\\nto compel arbitration. Id. at 457. We also concluded that AUCRA was not judicially\\n\\nestopped from arguing that the RPA is not an insurance contract under Virginia law. Id.\\n\\nat 458–59. Because the parties had not had the opportunity to brief fully the issue of\\n\\nwhether the RPA is an insurance contract under Virginia law, we remanded the matter to\\n\\nthe district court. Id. at 459.\\n\\n On remand, the district court ruled in an oral opinion that the RPA is an insurance\\n\\ncontract. As the district court explained:\\n\\n Under this arrangement, Minnieland and AUCRA\\n entered into a contract as a result of which Minnieland\\n received workmen’s compensation coverage through an\\n insurance policy in exchange for premiums that were paid for\\n that coverage.\\n\\n AUCRA’s position rests entirely on parsing this\\n transaction to the point of being completely disassociated\\n with the realities of the overall transaction. So the Court\\n\\n 9\\n\\f concludes that it’s an insurance contract for the purposes of\\n 38.2–312 as the Fourth Circuit has already determined. 3\\n\\nJ.A. 1073–74. Accordingly, the district court denied the motion to compel arbitration,\\n\\nfinding that “any arbitration provisions pertaining to any disputes under [the RPA] are\\n\\nvoid.” J.A. 1074.\\n\\n AUCRA appeals the district court’s denial of its motion to compel arbitration.\\n\\n\\n\\n II.\\n\\n We review de novo a district court’s order denying a motion to compel arbitration\\n\\nunder the FAA. Noohi v. Toll Bros., Inc., 708 F.3d 599, 605 (4th Cir. 2013). “At the\\n\\nsame time, we give due regard to the federal policy favoring arbitration and resolve ‘any\\n\\ndoubts concerning the scope of arbitrable issues . . . in favor of arbitration.’” Hill v.\\n\\nPeoplesoft USA, Inc., 412 F.3d 540, 543 (4th Cir. 2005) (citation omitted).\\n\\n In determining whether a dispute is arbitrable, we “apply ordinary state-law\\n\\nprinciples that govern the formation of contracts and the federal substantive law of\\n\\narbitrability.” Id. (internal citations and quotation marks omitted). Because this matter\\n\\n\\n\\n 3\\n In our prior opinion, we did not determine that the RPA is in fact an insurance\\ncontract. Rather, we affirmed the district court’s denial of AUCRA’s motion to compel\\narbitration on the grounds that Virginia Code § 38.2–312 “renders void delegation\\nprovisions in putative insurance contracts—at least to the extent such provisions\\nauthorize an arbitrator to resolve whether the contract at issue constitutes an ‘insurance\\ncontract.’” Minnieland, 867 F.3d at 457. Recognizing that the parties had not had the\\nopportunity to brief and argue the issue of whether the RPA is an insurance contract\\nunder Virginia law, we remanded this matter to the district court for consideration of that\\nissue.\\n\\n 10\\n\\finvolves the question of whether the RPA is an insurance contract for purposes of the\\n\\nVirginia Code, we look to Virginia law, which the parties agree applies in this case. 4\\n\\n\\n\\n III.\\n\\n A.\\n\\n We begin by addressing AUCRA’s argument that the district court ignored this\\n\\nCourt’s “narrow” mandate and improperly considered the entire program of workers’\\n\\ncompensation insurance—rather than only the RPA—in determining that the RPA is an\\n\\ninsurance contract under Virginia law. Opening Br. 23–26. AUCRA points out that the\\n\\ncomplaint names only AUCRA as a defendant, not CNI (the policy issuer), Applied\\n\\nUnderwriters, Inc. (the parent company), or Applied Risk Services (the billing agent). Id.\\n\\nat 25 (citing J.A. 1). AUCRA also relies on the fact that Minnieland’s claims are\\n\\npredicated on the RPA alone. Id. (citing J.A. 11–22). In light of this narrow focus of\\n\\nMinnieland’s suit and our “narrow mandate” to determine whether “the RPA is an\\n\\ninsurance contract under Virginia law,” AUCRA asserts that the district court should\\n\\n 4\\n We note that the RPA provides that it “shall be exclusively governed by and\\nconstrued in accordance with the laws of Nebraska and any matter concerning this\\nAgreement that is not subject to [arbitration] shall be resolved exclusively by the courts\\nof Nebraska without reference to its conflict of laws.” J.A. 34 (§ 16). The question of\\nwhether the contract itself is an insurance contract for purposes of Virginia Code § 38.2–\\n312, however, is a matter of Virginia law, and both parties brief the issue on appeal under\\nVirginia law. See, e.g., Opening Br. 28–34; Resp. Br. 13, 18–22. Because the parties\\nagree that Virginia law applies, we need not inquire further into the choice-of-law\\nquestions, and Virginia law controls the analysis. Cosey v. Prudential Ins. Co. of Am.,\\n735 F.3d 161, 169 n.7 (4th Cir. 2013) (citing Am. Fuel Corp. v. Utah Energy Dev. Co.,\\n122 F.3d 130, 134 (2d Cir. 1997)). We also note that AUCRA has not invoked the\\nRPA’s forum selection clause.\\n\\n 11\\n\\fhave considered only the RPA, not the workers’ compensation insurance transaction as a\\n\\nwhole. Id. at 25–26.\\n\\n Nothing in our prior opinion suggests that we intended to preclude any evaluation\\n\\nof whether the RPA’s terms are the complete terms of the parties’ agreement or whether\\n\\nthe RPA’s terms should be construed as integrated with the terms of the other\\n\\nEquityComp agreements. Our mandate was indeed limited to the RPA. However, on the\\n\\nprevious appeal, we were concerned only with the RPA because the RPA contains the\\n\\narbitration provision at issue. Because we remanded for consideration of whether the\\n\\nRPA is an “insurance contract” under Virginia law, the district court was faced with the\\n\\ninitial question of whether the RPA is in fact a standalone contract or is simply one part\\n\\nof an integrated contract. See Hitachi Credit Am. Corp. v. Signet Bank, 166 F.3d 614,\\n\\n626 (4th Cir. 1999) (“A contract may be contained in several instruments, and they may\\n\\nbe read together as one instrument [i]f made at the same time and in relation to the same\\n\\nsubject matter.” (alteration in original) (internal citations and quotation marks omitted)).\\n\\nOnly after the court made that threshold determination could it then determine the nature\\n\\nof the contract. Therefore, the district court did not ignore our previous mandate by\\n\\nlooking at the EquityComp program as a whole.\\n\\n B.\\n\\n 1.\\n\\n Having concluded that the district court did not violate our prior mandate, we turn\\n\\nto the issue at the heart of this appeal: whether the RPA is an insurance contract for\\n\\npurposes of Virginia Code § 38.2–312. Under Virginia law, “[w]here two papers are\\n\\n 12\\n\\fexecuted at the same time or contemporaneously between the same parties, in reference\\n\\nto the same subject matter, they must be regarded as parts of one transaction, and receive\\n\\nthe same construction as if their several provisions were in one and the same instrument.”\\n\\nCountryside Orthopaedics, P.C. v. Peyton, 541 S.E.2d 279, 284 (Va. 2001) (alteration in\\n\\noriginal) (citations omitted). “To construe two instruments as one, reference in one\\n\\ninstrument to the other need not be explicit; ‘it is sufficient if it is fairly traceable.’”\\n\\nHitachi Credit, 166 F.3d at 626 (quoting Tex. Co. v. Northup, 153 S.E. 659, 662 (Va.\\n\\n1930)). While “a court is not required to construe two documents as one contract just\\n\\nbecause they are executed at the same time and concern the same subject matter[,] [t]he\\n\\ncourt must give effect to the intent of the parties.” Id. (citing Am. Realty Tr. v. Chase\\n\\nManhattan Bank, N.A., 281 S.E.2d 825, 831 (Va. 1981)).\\n\\n The Virginia courts have yet to address whether a contract similar to the RPA,\\n\\nexecuted during an insurance transaction, comprises part of the insurance contract. The\\n\\nVirginia Supreme Court, however, has taken a rather expansive view of what constitutes\\n\\na single integrated contract. In Daugherty v. Diment, the Virginia Supreme Court made\\n\\nclear that, “[w]here a business transaction is based upon more than one document\\n\\nexecuted by the parties, the documents will be construed together to determine the intent\\n\\nof the parties; each document will be employed to ascertain the meaning intended to be\\n\\nexpressed by the others.” 385 S.E.2d 572, 574 (Va. 1989) (citing Am. Realty Tr., 281\\n\\nS.E.2d at 830).\\n\\n The Virginia Supreme Court has since applied Daugherty’s rule regularly to\\n\\ntransactions involving multiple written agreements. In Musselman v. Glass Works, LLC,\\n\\n 13\\n\\ffor example, the Virginia Supreme Court held that an asset purchase agreement and a\\n\\nnon-competition agreement executed at the same time “formed an integrated business\\n\\ntransaction.” 533 S.E.2d 919, 921 (Va. 2000). The purchase agreement provided that the\\n\\npurchase price was payable in various payments, including a deposit, a sum certain at\\n\\nclosing, a secured promissory note to the sellers, and a total of $60,000 to be paid\\n\\npursuant to three non-competition agreements. Id. at 920. The Virginia Supreme Court\\n\\nrejected an argument that the non-competition agreements were separate, personal service\\n\\ncontracts. Id. at 921. Instead, the court determined that the four contracts formed an\\n\\nintegrated contract because the sum due under the non-competition agreements was\\n\\nexplicitly part of the purchase price of the business under the purchase agreement. Id.\\n\\n The Virginia Supreme Court has also found that agreements not executed by the\\n\\nsame parties may nonetheless constitute an integrated contract. In Countryside\\n\\nOrthopaedics, for instance, the court found an integrated contract comprised of four\\n\\nagreements: two employment agreements executed by Countryside Orthopaedics and\\n\\ntwo respective physicians, a Stock Purchase Agreement executed by the physicians, and a\\n\\nStockholders’ Agreement executed by all three parties. 541 S.E.2d at 284. The court\\n\\nheld that these documents constituted a single transaction despite the fact that each of the\\n\\ncontracts was not signed by all three parties because “all the parties knew about the\\n\\nagreements and executed them at the same time as part of a single transaction to\\n\\naccomplish an agreed purpose.” Id. The court was also persuaded by the fact that “some\\n\\nof the agreements contain[ed] explicit references to the other agreements.” Id. at 285.\\n\\n\\n\\n 14\\n\\f Also instructive is Parr v. Alderwoods Grp., Inc., 604 S.E.2d 431 (Va. 2004). The\\n\\ntransaction at issue in that case involved four agreements: an asset purchase agreement, a\\n\\nnon-competition agreement, a lease, and a management agreement. Id. at 432. In\\n\\nreviewing the agreements, the Virginia Supreme Court rejected the argument that the\\n\\nmanagement agreement was “a contract separate and apart from” the asset purchase\\n\\nagreement. Id. at 435. The court found that the management agreement and asset\\n\\npurchase agreement should be construed “as a single integrated contract” because they\\n\\ncross-referenced each other and contained certain provisions written in identical\\n\\nlanguage. Id. The court explained that those references “reflect[ed] the parties’\\n\\nknowledge and understanding of the interrelationship between the contracts and\\n\\nprovide[d] strong support for the proposition that the parties intended that the documents\\n\\nconstitute a single transaction.” Id. The court further reasoned that, although the four\\n\\ncontracts “identified discrete acts required of the parties,” the contracts all shared the\\n\\nsame result and purpose. Id. Also relevant was the fact that the provisions of the\\n\\nmanagement agreement “could not be performed” without the acquisition of the business\\n\\nthrough the purchase agreement and the lease of the property. Id. As the court stated,\\n\\n“[t]he absence of any one of the agreements would frustrate the purpose of the\\n\\ntransaction.” Id.\\n\\n Moreover, it is well-established that insurance may be sold and purchased by way\\n\\nof more than the pages of the policy itself. See 2 Couch on Insurance § 21:21\\n\\n(“Endorsements, riders, marginal references, and other similar writings are a part of the\\n\\ncontract of insurance and are to be read and construed with the policy proper.”). Counsel\\n\\n 15\\n\\ffor AUCRA conceded during oral argument that an insurance contract is broader than an\\n\\ninsurance policy and that a policy endorsement, for example, would be considered part of\\n\\nthe insurance contract.\\n\\n 2.\\n\\n With these principles in mind, we examine the relationship between the Binder,\\n\\nRPA, and the CNI workers’ compensation insurance policies. Both the RPA and the first\\n\\nCNI policy went into effect on the same day, one day after Minnieland executed the\\n\\nBinder and RPA. Issuance of the policy was expressly conditioned on Minnieland’s prior\\n\\nexecution of the RPA. Therefore, as contemplated by the parties, execution of the RPA\\n\\nwould temporally precede issuance of the insurance policy. See Seabulk Offshore, Ltd. v.\\n\\nAm. Home Assurance Co., 377 F.3d 408, 419 (4th Cir. 2004) (“Under Virginia law, a\\n\\ncontract is made when the last act to complete it is performed, and in the context of an\\n\\ninsurance policy, the last act is the delivery of the policy to the insured.” (citation\\n\\nomitted)). And the entire program went into effect at the same time, on January 15, 2013.\\n\\n The subject matter of the documents is also the same: the workers’ compensation\\n\\ninsurance issued to Minnieland, including the manner in which the payroll, premiums,\\n\\nand losses in connection with the insurance coverage would be calculated and how the\\n\\nrisk would be distributed. The Binder represented Minnieland’s acceptance of the\\n\\nEquityComp program, and through the Binder, Minnieland requested that Applied\\n\\nUnderwriters, Inc. “through its affiliates and/or subsidiaries . . . cause to be issued”\\n\\nworkers’ compensation insurance coverage to Minnieland. J.A. 40. The RPA also\\n\\ndiscusses the insurance coverage; it notes that workers’ compensation insurance coverage\\n\\n 16\\n\\f“will be provided” to Minnieland by “one or more of the Issuing Insurers,” defined as\\n\\naffiliates of Applied Underwriters, Inc. J.A. 30–31. The RPA establishes Minnieland’s\\n\\nparticipation in a segregated cell to be funded in part by “a portion of the premium and\\n\\nlosses” under the RPA. J.A. 30. The premium and losses are calculated pursuant to the\\n\\nRPA’s Schedule 1. Id. And Schedule 1 “applies . . . to all payroll, premium, and losses\\n\\noccurring under the [CNI workers’ compensation insurance] Policies.” J.A. 36.\\n\\n The documents also internally reference each other and set forth each other’s\\n\\nterms. The Binder formally requests the issuance of workers’ compensation insurance\\n\\ncoverage subject to Minnieland’s execution of the RPA. The RPA references the\\n\\nworkers’ compensation policies explicitly, and Minnieland was required to execute the\\n\\nRPA before those policies would issue. Schedule 1 of the RPA establishes the manner in\\n\\nwhich Minnieland’s fees for the EquityComp program as a whole would be calculated.\\n\\nThat is, Schedule 1 applies to all premiums and losses under the actual insurance policies.\\n\\nIn fact, the billing statements for Minnieland’s participation in the EquityComp program\\n\\nshow that Minnieland was charged a single “pay-in amount” each month for the\\n\\n“Workers’ Compensation Program.” J.A. 45, 47, 49 (emphasis added). The RPA also\\n\\nwaives Minnieland’s right to choose deductibles for its workers’ compensation insurance\\n\\npolicies, and the Binder acknowledges that waiver. See J.A. 31 (§ 5), 40.\\n\\n The RPA and insurance policies are linked in other ways as well. The RPA\\n\\nprovides that its early cancellation terms apply if any one of the insurance policies is\\n\\ncancelled prior to the end of the RPA’s three-year term. J.A. 31 (§ 4). The RPA also\\n\\nprovides that Minnieland and AUCRA’s obligations under the RPA survive the active\\n\\n 17\\n\\fterm of the RPA “and shall be extinguished only when [AUCRA] no longer has any\\n\\npotential or actual liability to the Issuing Insurers with respect to the [workers’\\n\\ncompensation insurance] Policies.” J.A. 31 (§ 7). The RPA additionally provides that, in\\n\\nthe event Minnieland defaults under the RPA “or under any other agreement with any\\n\\naffiliates of [AUCRA] (Affiliated Agreements),” AUCRA “may take all reasonable steps\\n\\nto protect its and its affiliates’ interests.” J.A. 31 (§ 9). The RPA goes on to state that\\n\\n“[t]he parties hereto shall have the right . . . to offset or recoup any balances due from one\\n\\nto the other under [the RPA] or any Affiliated Agreements.” Id. Those Affiliated\\n\\nAgreements would include the insurance policies issued by CNI, an AUCRA affiliate.\\n\\nThe RPA also sets forth the terms that apply if CNI were required to provide workers’\\n\\ncompensation insurance coverage outside of the active term of the RPA. J.A. 31 (§ 4).\\n\\n These explicit internal references, interrelated terms, and shared subject matter are\\n\\nstrong evidence that the parties intended these documents to be part of one integrated\\n\\ntransaction. See Countryside Orthopaedics, 541 S.E.2d at 285; Musselman, 533 S.E.2d at\\n\\n921.\\n\\n To be sure, the documents were not executed by the same parties. The Binder was\\n\\nsigned by Minnieland as an acceptance of the EquityComp program proposal apparently\\n\\ndrafted by ARS, a subsidiary of Applied Underwriters, Inc., to whom the EquityComp\\n\\ntrademark is registered. See J.A. 23 (defining “we” as Applied Risk Services). The RPA\\n\\nwas executed between Minnieland and AUCRA, another subsidiary of Applied\\n\\nUnderwriters, Inc. J.A. 30. And the insurance policies were produced by Applied Risk\\n\\n\\n\\n 18\\n\\fServices, Inc., another subsidiary of Applied Underwriters, Inc., with CNI, yet another\\n\\nApplied Underwriters, Inc. subsidiary, as the insuring entity. J.A. 42–44.\\n\\n Nonetheless, the EquityComp program is promoted and sold as “[o]ne unified\\n\\nprogram for your business needs across all states” provided by Applied Underwriters,\\n\\nInc., “a premier financial services group of companies with leading experience in the\\n\\ncasualty insurance, reinsurance and business services disciplines.” J.A. 24–25 (emphases\\n\\nadded). The EquityComp program is marketed as being “effected through a separate\\n\\nreinsurance transaction issued in conjunction with a fully insured, guaranteed cost,\\n\\nworkers’ compensation policy.” J.A. 24. In fact, the Producer’s Quote Transmittal sent\\n\\nto the agent who brokered this deal for Minnieland expressly stated that the program\\n\\nproposed to Minnieland was “valid only if presented prior to expiration, in its original\\n\\nform, and in its entirety without modification.” J.A. 29 (emphasis added). And the\\n\\nBinder makes clear that insurance coverage was conditioned on execution of the RPA.\\n\\nTherefore, absent execution of the RPA, the insurance coverage would not have been\\n\\noffered as proposed. See Nat’l Convention Servs., LLC v. Applied Underwriters Captive\\n\\nRisk Assurance Co., Inc., 239 F. Supp. 3d 761, 786 (S.D.N.Y. 2017) (examining the\\n\\nworkers’ compensation insurance program offered by AUCRA and its affiliates and\\n\\nnoting that the RPA “would serve no purpose” without the approved guaranteed cost\\n\\ninsurance policies and that “it is plausible that the two can be treated as one\\n\\nundertaking”); see also Parr, 604 S.E.2d at 435 (finding integrated contract where one\\n\\ncontract’s terms could not be performed in the absence of other contracts).\\n\\n\\n\\n 19\\n\\f Additionally, the RPA contemplates that its terms will apply to AUCRA’s\\n\\naffiliates. The RPA provides that “[n]othing in this Agreement, expressed or implied, is\\n\\nintended to confer upon any party, other than the parties hereto and their affiliates,\\n\\nsuccessors and assigns, any rights, remedies, obligations or liabilities under or by reason\\n\\nof this Agreement, except as expressly provided herein.” J.A. 35 (§ 19) (emphasis\\n\\nadded). The RPA also provides that “[a]ll existing obligations from each party to the\\n\\nother or to third parties shall remain in force as of the expiration of the Active Term until\\n\\nthis Agreement is terminated.” J.A. 31 (§ 4) (emphasis added). These provisions further\\n\\nsuggest that Minnieland and AUCRA intended the RPA to be part of an integrated\\n\\ntransaction with AUCRA’s affiliates. See Countryside Orthopaedics, 541 S.E.2d at 284.\\n\\n During oral argument, counsel for AUCRA highlighted that, despite the RPA’s\\n\\nSchedule 1, the RPA does not charge “premiums”; it merely explains what happens to the\\n\\npremiums that are paid under the policies. This, however, does not render the RPA a\\n\\nstandalone contract. Instead, it lends support to Minnieland’s argument that the RPA and\\n\\nthe CNI policies must be read as one integrated contract. The policies set forth an\\n\\nestimated annual premium that is not subject to the RPA’s Schedule 1 calculations. J.A.\\n\\n42–44. The policies also contain a Short Rate Cancelation Policyholder Notice that\\n\\nexplains how the final premium will be calculated if the policies are cancelled by\\n\\nMinnieland. J.A. 761–63. The RPA’s Schedule 1, on the other hand, purports to\\n\\nestablish the total fee to be paid by Minnieland for the EquityComp program as well as\\n\\nany early cancellation fee that may be due. J.A. 36–37.\\n\\n\\n\\n 20\\n\\f Schedule 1’s calculations, however, incorporate the provisions of the CNI policies.\\n\\nSchedule 1 states that it “applies as of the Effective Date [January 15, 2013] to all\\n\\npayroll, premium, and losses occurring under the Policies.” J.A. 36. Schedule 1 explains\\n\\nthat “[a]n amount equal to the premium earned under the Policies in excess of the Loss\\n\\nPick Containment Amount multiplied by the applicable Exposure Group Adjustment\\n\\nFactor multiplied by the Allocation Factor listed in Table B, will be allocated to the\\n\\nParticipant’s cell.” J.A. 36 (§ 2). Thus, although Minnieland was billed one monthly fee\\n\\nfor the EquityComp program, the premium amount set forth in the policies was part of\\n\\nthat monthly fee and was included in calculating the total amount that would be due\\n\\nunder the program as a whole. Absent the CNI policies, the calculations in Schedule 1—\\n\\nincluding the amount to be allocated to Minnieland’s segregated cell—would be\\n\\nimpossible to make.\\n\\n The early cancellation provision of the RPA also depends on the cancellation\\n\\nprovisions of the CNI policies. The RPA’s early cancellation provision applies if either\\n\\nMinnieland cancels the RPA or if any of the insurance policies are “cancelled or non-\\n\\nrenewed prior to the end of the Active Term” of the RPA. J.A. 31 (§ 4). That\\n\\ncancellation policy, described in Schedule 1, states that certain of the factors used to\\n\\ncalculate premiums and losses will be increased in the event of early cancellation and that\\n\\nMinnieland will be required to pay, among other things, “any remaining premium,\\n\\nincluding short rate penalties, due under the Policies.” J.A. 37 (§ 6) (emphasis added).\\n\\nThose “short rate penalties” are the early termination provisions of the insurance policies.\\n\\nSee, e.g., J.A. 761 (“Short Rate Cancelation Policyholder Notice”). And the short rate\\n\\n 21\\n\\fpenalties apply when the policy is cancelled by Minnieland. Id. Therefore, when the\\n\\nshort rate cancellation provisions of the policies apply, they are another integer of the\\n\\nformula used under the RPA to calculate the total amount due under the EquityComp\\n\\nprogram. In the absence of the CNI policy terms, the RPA’s Schedule 1 calculations and\\n\\nearly cancellation provisions make no sense. See Musselman, 533 S.E.2d at 921.\\n\\n We do not ignore that Minnieland chose to sue only AUCRA and to base its\\n\\nclaims only on the RPA. However, because the RPA was but one component of an\\n\\nintegrated insurance sale, we must examine the related documents and the relationship\\n\\nbetween the affiliated entities. Daugherty, 385 S.E.2d at 574. In the absence of the CNI\\n\\npolicies, the RPA would have been pointless and nonsensical; and in the absence of the\\n\\nRPA, there would have been no insurance coverage. Nothing in the record suggests that\\n\\nMinnieland could have simply paid the premiums listed in the CNI policies, without\\n\\npaying the amounts set forth in the RPA’s Schedule 1, and maintained its workers’\\n\\ncompensation coverage; the RPA expressly provides for the opposite result. Because the\\n\\nEquityComp program was marketed and sold as a package deal, Minnieland’s failure to\\n\\nexecute the RPA would have frustrated the purpose of the transaction. See Parr, 604\\n\\nS.E.2d at 435.\\n\\n In sum, the documents, considered together, show that the purpose of the Binder,\\n\\nRPA, and CNI policies was one: to provide Minnieland with workers’ compensation\\n\\ninsurance coverage while allowing Minnieland the opportunity to keep its insurance costs\\n\\nlow by sharing in the underwriting risk. We need not determine specifically whether the\\n\\nRPA constitutes a policy endorsement or rider. Regardless of the label that may attach,\\n\\n 22\\n\\fthe RPA and insurance policies constitute an integrated transaction and must be read as\\n\\none contract.\\n\\n C.\\n\\n Having determined the scope of the contract at issue, we must now decide whether\\n\\nthe integrated contract is a contract of insurance under Virginia Code § 38.2–312. The\\n\\nVirginia Code does not define “insurance contract.” It does define “insurance,” however,\\n\\nas “the business of transferring risk by contract wherein a person, for a consideration,\\n\\nundertakes (i) to indemnify another person, (ii) to pay or provide a specified or\\n\\nascertainable amount of money, or (iii) to provide a benefit or service upon the\\n\\noccurrence of a determinable risk contingency.” Va. Code § 38.2–100. The Code also\\n\\nlists the required terms of “[e]ach insurance policy or contract”:\\n\\n 1. The names of the parties to the contract;\\n\\n 2. The subject of the insurance;\\n\\n 3. The risks insured against;\\n\\n 4. The time the insurance takes effect and, except in the case\\n of group insurance, title insurance, and insurance written\\n under perpetual policies, the period during which the\\n insurance is to continue;\\n\\n 5. A statement of the premium, except in the case of group\\n insurance and title insurance; and\\n\\n 6. The conditions pertaining to the insurance.\\n\\nVa. Code § 38.2–305. 5\\n\\n\\n 5\\n Minnieland cites to Virginia common law for the essential terms of an insurance\\ncontract. See Resp. Br. 20–21; Grp. Hospitalization Med. Serv., Inc. v. Smith, 372 S.E.2d\\n(Continued)\\n 23\\n\\f Neither party argues that the terms of the CNI policies themselves fail to meet the\\n\\nstatutory requirements for insurance contracts. In fact, AUCRA acknowledges that the\\n\\nCNI policies meet Virginia’s requirements. Opening Br. 7 n.3. Construing the CNI\\n\\npolicy terms as integrated with those of the RPA, as though the terms of each were\\n\\nwritten in a single document, Countryside Orthopaedics, 541 S.E.2d at 284, it becomes\\n\\nclear that the contract at issue is an “insurance contract” under Virginia law.\\n\\nAccordingly, the district court properly determined that the RPA is an insurance contract\\n\\nfor the purposes of Virginia Code § 38.2–312.\\n\\n D.\\n\\n We note, as Minnieland does, that we are not the first to determine that the\\n\\nprogram marketed by Applied Underwriters, Inc. is insurance. In fact, several state\\n\\ninsurance commissioners have determined that the EquityComp program and its sister\\n\\nprogram, SolutionOne, are not only subject to insurance regulations, but also violate\\n\\nthose regulations. For example, the Vermont Department of Financial Regulation has\\n\\nbarred Applied Underwriters, Inc. from selling the RPA in conjunction with guaranteed\\n\\n\\n159, 160 (Va. 1988) (listing “essential terms” of insurance contract as: “(1) the subject\\nmatter to be insured; (2) the risk insured against; (3) the commencement and period of the\\nrisk undertaken by the insurer; (4) the amount of insurance; and (5) the premium and time\\nat which it is to be paid” (citation omitted)). AUCRA argues that, since the addition of\\nthe definition of “insurance” to the Virginia Code in 2001, this common law definition is\\nno longer controlling. Opening Br. 32–33. The Virginia Supreme Court has not applied\\nthe common-law definition in connection with the statutory definition of “insurance.”\\nHowever, the common-law elements are essentially the same as the statutory\\nrequirements for every insurance policy. Therefore, an evaluation of the contract at issue\\nunder either the statutory factors or the common-law definition should yield the same\\nresult.\\n\\n 24\\n\\fcost insurance policies in Vermont after concluding that the RPA “de facto operated as a\\n\\nretrospective rating plan, replacing [CNI’s] guaranteed-cost workers’ compensation\\n\\ninsurance policy with an unfiled, unapproved retrospective rating plan.” J.A. 233.\\n\\nSimilarly, the Wisconsin Office of the Commissioner of Insurance entered into an\\n\\nagreement with ARS and CNI that they will “cease and desist from marketing, binding,\\n\\nissuing and renewing SolutionOne and EquityComp policies and any similarly designed\\n\\npolicies and programs that involve side agreements that affect the terms of the workers’\\n\\ncompensation policy, including but not limited to reinsurance agreements.” J.A. 375.\\n\\nThe California Insurance Commissioner likewise found that the EquityComp program\\n\\nand its RPA violate the California Insurance Code. See Decision and Order, In the\\n\\nMatter of the Appeal of Shasta Linen Supply, Inc., No. AHB-WCA-14-31 (Dep’t of Ins.,\\n\\nState of Cal. June 20, 2016), http://www.insurance.ca.gov/0250-insurers/0500-legal-\\n\\ninfo/0600-decision-ruling/0100-precedential/upload/ShastaLinenSupplyInc.pdf.\\n\\n Other courts faced with the RPA and similar related documents have also\\n\\nsuggested that the program marketed by Applied Underwriters, including the RPA, is\\n\\ninsurance. See, e.g., Nat’l Convention Servs., 239 F. Supp. 3d at 786 (observing that the\\n\\nRPA and guaranteed cost policies “plausibly serve the common purpose of providing\\n\\nworkers’ compensation insurance at rates that are affected by loss experience”); Nielsen\\n\\nContracting, Inc. v. Applied Underwriters, Inc., 22 Cal. App. 5th 1096, 1116–17 (Cal. Ct.\\n\\nApp. 2018) (determining that the RPA’s provisions were meant to replace those of the\\n\\ninsurance policies and that the Applied Underwriters affiliated entities were “so\\n\\nenmeshed” and “intertwined” that the RPA and insurance policies should be considered\\n\\n 25\\n\\ftogether); Citizens of Humanity, LLC v. Applied Underwriters Captive Risk Assurance\\n\\nCo., Inc., 909 N.W.2d 614, 632 (Neb.) (stating that “the RPA has the hallmarks of a\\n\\nretrospective rating plan” and concluding that the RPA is an “agreement concerning or\\n\\nrelating to an insurance policy” under Nebraska law), cert. denied, 139 S. Ct. 274 (2018).\\n\\n While each of these other jurisdictions has evaluated the RPA under different laws\\n\\nand for different purposes, the general consensus has consistently been that the RPA is\\n\\nsubject to insurance regulations. We join that consensus in holding that the RPA at issue\\n\\nhere is an insurance contract under Virginia law. Because arbitration provisions in\\n\\ninsurance contracts are void under Virginia law, Va. Code § 38.2–312, AUCRA must\\n\\nface Minnieland’s claims in court.\\n\\n\\n\\n IV.\\n\\n For these reasons, we affirm the judgment of the district court.\\n\\n\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 26\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4358554/\", \"author_raw\": \"Affirmed by published opinion. Chief Judge Gregory wrote the opinion, in which Judge\"}]}"},"judge1":{"kind":"string","value":"GREGORY"},"judge2":{"kind":"string","value":"MOTZ"},"judge3":{"kind":"string","value":"WYNN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4581301/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: MINNIELAND PRIVATE DAY SCHOOL, INC., a Virginia Corporation, Plaintiff - Appellee, v. APPLIED UNDERWRITERS CAPTIVE RISK ASSURANCE COMPANY, INC., Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-14\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-2385\n\n\nMINNIELAND PRIVATE DAY SCHOOL, INC., a Virginia corporation,\n\n Plaintiff - Appellee,\n\n v.\n\nAPPLIED UNDERWRITERS CAPTIVE RISK ASSURANCE COMPANY, INC.,\n\n Defendant - Appellant.\n\n\nAppeal from the United States District Court for the Eastern District of Virginia, at\nAlexandria. Anthony John Trenga, District Judge. (1:15-cv-01695-AJT-IDD)\n\n\nArgued: October 30, 2018 Decided: January 14, 2019\n\n\nBefore GREGORY, Chief Judge, MOTZ, and WYNN, Circuit Judges.\n\n\nAffirmed by published opinion. Chief Judge Gregory wrote the opinion, in which Judge\nMotz and Judge Wynn joined.\n\n\nARGUED: Daniel William Olivas, LEWIS, THOMASON, KING, KRIEG &\nWALDROP, P.C., Nashville, Tennessee, for Appellant. James Scott Krein, KREIN\nLAW FRIM, Prince William, Virginia, for Appellee. ON BRIEF: R. Dale Bay,\nRyan N. Clark, LEWIS, THOMASON, KING, KRIEG & WALDROP, P.C., Nashville,\nTennessee, for Appellant.\n\fGREGORY, Chief Judge:\n\n Appellant Applied Underwriters Captive Risk Assurance Company, Inc.\n\n(“AUCRA”) comes to us for the second time in this case, appealing the district court’s\n\ndetermination that a Reinsurance Participation Agreement (“RPA”) executed by it and\n\nAppellee Minnieland Private Day School is an insurance contract under Virginia law.\n\nThe RPA, executed in connection with Minnieland’s purchase of workers’ compensation\n\ninsurance, contains an arbitration clause. In the district court, AUCRA moved to compel\n\narbitration in accordance with the RPA’s terms. In opposing arbitration, Minnieland\n\nasserted that the RPA is an insurance contract for purposes of Virginia Code § 38.2–312,\n\nwhich renders void arbitration clauses contained in insurance contracts. The district court\n\ndenied AUCRA’s motion to compel arbitration, finding that AUCRA was judicially\n\nestopped from arguing that the RPA is not an insurance contract. We reversed that\n\ndetermination, concluding that AUCRA was not estopped from making its argument, and\n\nremanded to allow the parties to brief fully the issue of whether the RPA is an insurance\n\ncontract for purposes of Virginia Code § 38.2–312. On remand, the district court held\n\nthat the RPA is indeed an insurance contract and that the RPA’s arbitration clause is void\n\nas a matter of law. AUCRA now appeals that determination.\n\n For the reasons set forth below, we conclude that the RPA is an insurance contract\n\nfor purposes of Virginia Code § 38.2–312. We therefore affirm.\n\n\n\n\n 2\n\f I.\n\n A.\n\n This case involves a workers’ compensation insurance program that Minnieland\n\npurchased from AUCRA and its affiliated entities. Under Virginia law, workers’\n\ncompensation insurance is “insurance against the legal liability of any employer for the\n\ndeath or disablement of, or injury to, his or its employee whether imposed by common\n\nlaw or by statute, or assumed by contract.” Va. Code § 38.2–119. Workers’\n\ncompensation insurance coverage is required of “[e]very employer subject to” Virginia’s\n\nworkers’ compensation statute. Va. Code § 65.2–800(A); Redifer v. Chester, 720 S.E.2d\n\n66, 67–68 (Va. 2012).\n\n In general, workers’ compensation insurance is typically provided in one of two\n\ntypes of policies: a guaranteed cost policy or a retrospective rating plan. Under a\n\nguaranteed cost policy, the premiums are fixed and usually do not change over the term\n\nof the policy. Steven Plitt, Daniel Maldonado, Joshua D. Rogers, & Jordan R. Plitt, 2\n\nCouch on Insurance § 69:10 (3d ed. 1995). In many states, these plans are the only plans\n\nlawfully available to small and mid-sized employers. Retrospective rating plans, on the\n\nother hand, usually require an advance premium deposit with the insurer and then provide\n\nthat the insurer, at some specified time, will compute the actual premium based on the\n\ninsured’s actual loss experience or total payroll during a set period of time. Id. § 69:16;\n\nsee Va. Code § 38.2–1901 (defining “retrospective rating plan” as “a rating plan that\n\nadjusts the premium for the insurance to which it applies on the basis of losses incurred\n\nduring the period covered by that insurance”). The insured is then either issued a refund\n\n 3\n\fif the actual premium is lower than the premium deposit paid or required to pay the\n\ndifference if the actual premium exceeds the deposited amount.\n\n At issue in this appeal is Applied Underwriters, Inc.’s EquityComp program, an\n\ninnovative program of workers’ compensation insurance that offers small and mid-sized\n\nemployers the benefits of both a guaranteed cost policy and a retrospective rating plan in\n\none insurance program. The EquityComp program provides employers with guaranteed\n\ncost workers’ compensation insurance at the same time that they enjoy the benefits—and\n\nare subject to the risks—of a retrospective rating plan. See J.A. 404 (explaining that this\n\nRPA allows small and mid-sized employers to “in effect, have a retrospective rating plan\n\n. . . even though, in fact, the insured has Guaranteed Cost insurance coverage with the\n\ninsurance carrier”). 1 The program is so novel that it has been patented.\n\n Under the program, various insurance companies affiliated with Applied\n\nUnderwriters, Inc. have entered into a reinsurance pooling agreement. The pooled\n\ncompanies provide workers’ compensation insurance coverage to employers and also\n\nmutually reinsure each other’s insurance business. A layer of reinsurance is also\n\nprovided by AUCRA, a wholly owned subsidiary of Applied Underwriters, Inc. AUCRA\n\nin turn enters into RPAs with EquityComp customers, under the terms of which each\n\ncustomer pays into a segregated “cell” or account that is then used to fund AUCRA’s\n\nliabilities. In essence, EquityComp customers participate in underwriting the risk of their\n\nown workers’ compensation insurance policies.\n\n 1\n Citations to the “J.A.” refer to the Joint Appendix filed by the parties in this\nappeal.\n\n 4\n\f In theory, an EquityComp customer can save costs on its workers’ compensation\n\ninsurance through a refund of monies deposited into its segregated cell if its workers’\n\ncompensation insurance claims are kept low during the term of the RPA. As detailed\n\nbelow, however, Minnieland was unable to reap this benefit.\n\n B.\n\n Minnieland provides education and childcare services in Virginia and is subject to\n\nthe workers’ compensation laws and requirements of the state. Va. Code § 65.2–800(A).\n\n On January 14, 2013, Minnieland bought into the EquityComp program.\n\nMinnieland executed a Request to Bind Coverages and Services (“Binder”), by which\n\nMinnieland “request[ed] that Applied Underwriters, Inc. through its affiliates and/or\n\nsubsidiaries . . . cause to be issued to [Minnieland] one or more workers’ compensation\n\ninsurance policies . . . subject to [Minnieland] executing the . . . [RPA].” J.A. 40. At the\n\nsame time, Minnieland executed an RPA. The RPA had a term of three years and\n\nprovided that one or more “Issuing Insurers”—all of which were entities affiliated with\n\nApplied Underwriters, Inc.—would issue workers’ compensation insurance policies to\n\nMinnieland. The RPA also established that Minnieland would share in the profits and\n\nlosses associated with its policies through its “segregated protected cell.” Applied Risk\n\nServices, Inc. (“ARS”), another subsidiary of Applied Underwriters, Inc., was designated\n\nas the billing agent for both AUCRA and the Issuing Insurers. Schedule 1 of the RPA\n\nsets forth various formulae for calculating premiums and losses under the RPA and\n\ninsurance policies.\n\n\n\n 5\n\f The day after Minnieland executed the EquityComp documents, the RPA went\n\ninto effect, as did the first of what would become three consecutive one-year Virginia\n\nworkers’ compensation insurance policies, the last of which was to expire on January 15,\n\n2016. The first policy listed the estimated annual premium as $589,163. The second and\n\nthird policies listed the estimated annual premiums as $642,333 and $706,160,\n\nrespectively. The policies were produced by ARS and insured by Continental Indemnity\n\nCompany (“CNI”), another affiliate of Applied Underwriters, Inc.\n\n According to the complaint, at no time was AUCRA licensed to sell insurance in\n\nVirginia, and the RPA has not been approved by the Virginia Workers’ Compensation\n\nCommission.\n\n For the first 33 of the 36 months during which the RPA was active, AUCRA\n\ncharged, and Minnieland paid, an average of $58,810 per month in premiums. In\n\nNovember 2015, however, the premium charged to Minnieland increased drastically to\n\n$471,213, a 1167% increase from the October 2015 premium and a 801% increase over\n\nthe first 33 months’ average. Despite Minnieland’s requests, AUCRA refused to disclose\n\nthe basis on which it assessed the November 2015 premium. Minnieland nonetheless\n\npaid the November premium.\n\n AUCRA billed Minnieland a similarly high premium of $414,604 for December\n\n2015. AUCRA once again refused to disclose the basis for the increased premium, and\n\nMinnieland did not pay the December premium.\n\n\n\n\n 6\n\f On December 16, 2015, AUCRA 2 faxed Minnieland notice that it was terminating\n\nMinnieland’s EquityComp program, including the RPA and insurance coverage, effective\n\nDecember 27, 2015. The reason provided for the termination of coverage was “Non-\n\nPayment of Premium; Client has an outstanding balance.”\n\n C.\n\n On December 24, 2015, Minnieland filed suit against AUCRA in the Eastern\n\nDistrict of Virginia. Minnieland alleged that AUCRA is not authorized or licensed to act\n\nas an insurance company under Virginia law; that the RPA is an “insurance contract” and\n\nnot a “reinsurance” agreement; and that AUCRA misrepresented the EquityComp\n\nprogram, and the RPA specifically, to circumvent Virginia insurance and workers’\n\ncompensation laws. Minnieland sought (1) a declaration that the RPA constitutes an\n\ninsurance contract and is void because of AUCRA’s failure to comply with Virginia law;\n\n(2) a declaration of the amount, if any, that Minnieland owes under the RPA; and (3) a\n\ndeclaration that the premiums, deposits, and charges assessed to Minnieland by AUCRA\n\nwere excessive. Minnieland also sought damages for fraud and breach of contract.\n\n On January 18, 2016, AUCRA filed a demand for arbitration with the American\n\nArbitration Association, invoking the RPA’s arbitration provisions. That demand sought\n\npayment from Minnieland of a total of $342,358 that AUCRA claimed it was owed under\n\nthe RPA and EquityComp program.\n\n 2\n The complaint alleges that AUCRA sent the notice. The letter is printed on\n“Applied Underwriters” letterhead and does not specify if the sender is AUCRA or\nApplied Underwriters, Inc. J.A. 52. The document attached to the letter indicates that it\nwas “produced by” ARS. J.A. 53.\n\n 7\n\f AUCRA also moved the district court to dismiss Minnieland’s complaint and\n\ncompel arbitration under the RPA’s arbitration clause. In opposing the motion to compel\n\narbitration, Minnieland argued that the RPA is an insurance contract. As such,\n\nMinnieland argued, the arbitration clause is void because it is prohibited by Virginia\n\nCode § 38.2–312.\n\n On March 17, 2016, the district court granted in part and denied in part AUCRA’s\n\nmotion. The district court determined that the RPA’s arbitration clause calls for\n\narbitration of the threshold question of whether the RPA is an insurance contract such\n\nthat Virginia’s insurance statute, which reverse-preempts the Federal Arbitration Act\n\n(“FAA”), applies. Accordingly, the court ordered the parties to submit that question to\n\nthe arbitrator.\n\n A week later, the district court granted Minnieland’s motion for reconsideration of\n\nthe court’s March 17, 2016 order. The district court again concluded that the threshold\n\nissue of arbitrability was for the arbitrator to determine. The district court nonetheless\n\nstayed its March 17 order and requested supplemental briefing on Minnieland’s\n\ncontention that AUCRA was judicially estopped from arguing that the RPA is not an\n\ninsurance contract.\n\n The parties briefed the judicial estoppel issue, and the district court heard\n\nargument on AUCRA’s motion to compel arbitration. The district court denied the\n\nmotion to compel, concluding that the four elements of judicial estoppel were met such\n\nthat AUCRA was estopped from arguing that the RPA is not an insurance contract. See\n\n\n\n 8\n\fLowery v. Stovall, 92 F.3d 219, 223–24 (4th Cir. 1996) (discussing the elements of\n\njudicial estoppel).\n\n AUCRA appealed that order. On appeal, we affirmed in part and reversed in part.\n\nMinnieland Private Day Sch., Inc. v. Applied Underwriters Captive Risk Assurance Co.,\n\nInc., 867 F.3d 449 (4th Cir. 2017), cert. denied, 138 S. Ct. 926 (2018). We concluded\n\nthat Virginia Code § 38.2–312 “renders invalid delegation provisions in putative\n\ninsurance contracts governed by Virginia law, at least to the extent such delegation\n\nprovisions endow an arbitrator, as opposed to a court, with exclusive authority to\n\ndetermine whether the contract at issue constitutes an ‘insurance contract’ for purposes of\n\nVirginia law.” Id. at 456. Therefore, we affirmed the district court’s denial of the motion\n\nto compel arbitration. Id. at 457. We also concluded that AUCRA was not judicially\n\nestopped from arguing that the RPA is not an insurance contract under Virginia law. Id.\n\nat 458–59. Because the parties had not had the opportunity to brief fully the issue of\n\nwhether the RPA is an insurance contract under Virginia law, we remanded the matter to\n\nthe district court. Id. at 459.\n\n On remand, the district court ruled in an oral opinion that the RPA is an insurance\n\ncontract. As the district court explained:\n\n Under this arrangement, Minnieland and AUCRA\n entered into a contract as a result of which Minnieland\n received workmen’s compensation coverage through an\n insurance policy in exchange for premiums that were paid for\n that coverage.\n\n AUCRA’s position rests entirely on parsing this\n transaction to the point of being completely disassociated\n with the realities of the overall transaction. So the Court\n\n 9\n\f concludes that it’s an insurance contract for the purposes of\n 38.2–312 as the Fourth Circuit has already determined. 3\n\nJ.A. 1073–74. Accordingly, the district court denied the motion to compel arbitration,\n\nfinding that “any arbitration provisions pertaining to any disputes under [the RPA] are\n\nvoid.” J.A. 1074.\n\n AUCRA appeals the district court’s denial of its motion to compel arbitration.\n\n\n\n II.\n\n We review de novo a district court’s order denying a motion to compel arbitration\n\nunder the FAA. Noohi v. Toll Bros., Inc., 708 F.3d 599, 605 (4th Cir. 2013). “At the\n\nsame time, we give due regard to the federal policy favoring arbitration and resolve ‘any\n\ndoubts concerning the scope of arbitrable issues . . . in favor of arbitration.’” Hill v.\n\nPeoplesoft USA, Inc., 412 F.3d 540, 543 (4th Cir. 2005) (citation omitted).\n\n In determining whether a dispute is arbitrable, we “apply ordinary state-law\n\nprinciples that govern the formation of contracts and the federal substantive law of\n\narbitrability.” Id. (internal citations and quotation marks omitted). Because this matter\n\n\n\n 3\n In our prior opinion, we did not determine that the RPA is in fact an insurance\ncontract. Rather, we affirmed the district court’s denial of AUCRA’s motion to compel\narbitration on the grounds that Virginia Code § 38.2–312 “renders void delegation\nprovisions in putative insurance contracts—at least to the extent such provisions\nauthorize an arbitrator to resolve whether the contract at issue constitutes an ‘insurance\ncontract.’” Minnieland, 867 F.3d at 457. Recognizing that the parties had not had the\nopportunity to brief and argue the issue of whether the RPA is an insurance contract\nunder Virginia law, we remanded this matter to the district court for consideration of that\nissue.\n\n 10\n\finvolves the question of whether the RPA is an insurance contract for purposes of the\n\nVirginia Code, we look to Virginia law, which the parties agree applies in this case. 4\n\n\n\n III.\n\n A.\n\n We begin by addressing AUCRA’s argument that the district court ignored this\n\nCourt’s “narrow” mandate and improperly considered the entire program of workers’\n\ncompensation insurance—rather than only the RPA—in determining that the RPA is an\n\ninsurance contract under Virginia law. Opening Br. 23–26. AUCRA points out that the\n\ncomplaint names only AUCRA as a defendant, not CNI (the policy issuer), Applied\n\nUnderwriters, Inc. (the parent company), or Applied Risk Services (the billing agent). Id.\n\nat 25 (citing J.A. 1). AUCRA also relies on the fact that Minnieland’s claims are\n\npredicated on the RPA alone. Id. (citing J.A. 11–22). In light of this narrow focus of\n\nMinnieland’s suit and our “narrow mandate” to determine whether “the RPA is an\n\ninsurance contract under Virginia law,” AUCRA asserts that the district court should\n\n 4\n We note that the RPA provides that it “shall be exclusively governed by and\nconstrued in accordance with the laws of Nebraska and any matter concerning this\nAgreement that is not subject to [arbitration] shall be resolved exclusively by the courts\nof Nebraska without reference to its conflict of laws.” J.A. 34 (§ 16). The question of\nwhether the contract itself is an insurance contract for purposes of Virginia Code § 38.2–\n312, however, is a matter of Virginia law, and both parties brief the issue on appeal under\nVirginia law. See, e.g., Opening Br. 28–34; Resp. Br. 13, 18–22. Because the parties\nagree that Virginia law applies, we need not inquire further into the choice-of-law\nquestions, and Virginia law controls the analysis. Cosey v. Prudential Ins. Co. of Am.,\n735 F.3d 161, 169 n.7 (4th Cir. 2013) (citing Am. Fuel Corp. v. Utah Energy Dev. Co.,\n122 F.3d 130, 134 (2d Cir. 1997)). We also note that AUCRA has not invoked the\nRPA’s forum selection clause.\n\n 11\n\fhave considered only the RPA, not the workers’ compensation insurance transaction as a\n\nwhole. Id. at 25–26.\n\n Nothing in our prior opinion suggests that we intended to preclude any evaluation\n\nof whether the RPA’s terms are the complete terms of the parties’ agreement or whether\n\nthe RPA’s terms should be construed as integrated with the terms of the other\n\nEquityComp agreements. Our mandate was indeed limited to the RPA. However, on the\n\nprevious appeal, we were concerned only with the RPA because the RPA contains the\n\narbitration provision at issue. Because we remanded for consideration of whether the\n\nRPA is an “insurance contract” under Virginia law, the district court was faced with the\n\ninitial question of whether the RPA is in fact a standalone contract or is simply one part\n\nof an integrated contract. See Hitachi Credit Am. Corp. v. Signet Bank, 166 F.3d 614,\n\n626 (4th Cir. 1999) (“A contract may be contained in several instruments, and they may\n\nbe read together as one instrument [i]f made at the same time and in relation to the same\n\nsubject matter.” (alteration in original) (internal citations and quotation marks omitted)).\n\nOnly after the court made that threshold determination could it then determine the nature\n\nof the contract. Therefore, the district court did not ignore our previous mandate by\n\nlooking at the EquityComp program as a whole.\n\n B.\n\n 1.\n\n Having concluded that the district court did not violate our prior mandate, we turn\n\nto the issue at the heart of this appeal: whether the RPA is an insurance contract for\n\npurposes of Virginia Code § 38.2–312. Under Virginia law, “[w]here two papers are\n\n 12\n\fexecuted at the same time or contemporaneously between the same parties, in reference\n\nto the same subject matter, they must be regarded as parts of one transaction, and receive\n\nthe same construction as if their several provisions were in one and the same instrument.”\n\nCountryside Orthopaedics, P.C. v. Peyton, 541 S.E.2d 279, 284 (Va. 2001) (alteration in\n\noriginal) (citations omitted). “To construe two instruments as one, reference in one\n\ninstrument to the other need not be explicit; ‘it is sufficient if it is fairly traceable.’”\n\nHitachi Credit, 166 F.3d at 626 (quoting Tex. Co. v. Northup, 153 S.E. 659, 662 (Va.\n\n1930)). While “a court is not required to construe two documents as one contract just\n\nbecause they are executed at the same time and concern the same subject matter[,] [t]he\n\ncourt must give effect to the intent of the parties.” Id. (citing Am. Realty Tr. v. Chase\n\nManhattan Bank, N.A., 281 S.E.2d 825, 831 (Va. 1981)).\n\n The Virginia courts have yet to address whether a contract similar to the RPA,\n\nexecuted during an insurance transaction, comprises part of the insurance contract. The\n\nVirginia Supreme Court, however, has taken a rather expansive view of what constitutes\n\na single integrated contract. In Daugherty v. Diment, the Virginia Supreme Court made\n\nclear that, “[w]here a business transaction is based upon more than one document\n\nexecuted by the parties, the documents will be construed together to determine the intent\n\nof the parties; each document will be employed to ascertain the meaning intended to be\n\nexpressed by the others.” 385 S.E.2d 572, 574 (Va. 1989) (citing Am. Realty Tr., 281\n\nS.E.2d at 830).\n\n The Virginia Supreme Court has since applied Daugherty’s rule regularly to\n\ntransactions involving multiple written agreements. In Musselman v. Glass Works, LLC,\n\n 13\n\ffor example, the Virginia Supreme Court held that an asset purchase agreement and a\n\nnon-competition agreement executed at the same time “formed an integrated business\n\ntransaction.” 533 S.E.2d 919, 921 (Va. 2000). The purchase agreement provided that the\n\npurchase price was payable in various payments, including a deposit, a sum certain at\n\nclosing, a secured promissory note to the sellers, and a total of $60,000 to be paid\n\npursuant to three non-competition agreements. Id. at 920. The Virginia Supreme Court\n\nrejected an argument that the non-competition agreements were separate, personal service\n\ncontracts. Id. at 921. Instead, the court determined that the four contracts formed an\n\nintegrated contract because the sum due under the non-competition agreements was\n\nexplicitly part of the purchase price of the business under the purchase agreement. Id.\n\n The Virginia Supreme Court has also found that agreements not executed by the\n\nsame parties may nonetheless constitute an integrated contract. In Countryside\n\nOrthopaedics, for instance, the court found an integrated contract comprised of four\n\nagreements: two employment agreements executed by Countryside Orthopaedics and\n\ntwo respective physicians, a Stock Purchase Agreement executed by the physicians, and a\n\nStockholders’ Agreement executed by all three parties. 541 S.E.2d at 284. The court\n\nheld that these documents constituted a single transaction despite the fact that each of the\n\ncontracts was not signed by all three parties because “all the parties knew about the\n\nagreements and executed them at the same time as part of a single transaction to\n\naccomplish an agreed purpose.” Id. The court was also persuaded by the fact that “some\n\nof the agreements contain[ed] explicit references to the other agreements.” Id. at 285.\n\n\n\n 14\n\f Also instructive is Parr v. Alderwoods Grp., Inc., 604 S.E.2d 431 (Va. 2004). The\n\ntransaction at issue in that case involved four agreements: an asset purchase agreement, a\n\nnon-competition agreement, a lease, and a management agreement. Id. at 432. In\n\nreviewing the agreements, the Virginia Supreme Court rejected the argument that the\n\nmanagement agreement was “a contract separate and apart from” the asset purchase\n\nagreement. Id. at 435. The court found that the management agreement and asset\n\npurchase agreement should be construed “as a single integrated contract” because they\n\ncross-referenced each other and contained certain provisions written in identical\n\nlanguage. Id. The court explained that those references “reflect[ed] the parties’\n\nknowledge and understanding of the interrelationship between the contracts and\n\nprovide[d] strong support for the proposition that the parties intended that the documents\n\nconstitute a single transaction.” Id. The court further reasoned that, although the four\n\ncontracts “identified discrete acts required of the parties,” the contracts all shared the\n\nsame result and purpose. Id. Also relevant was the fact that the provisions of the\n\nmanagement agreement “could not be performed” without the acquisition of the business\n\nthrough the purchase agreement and the lease of the property. Id. As the court stated,\n\n“[t]he absence of any one of the agreements would frustrate the purpose of the\n\ntransaction.” Id.\n\n Moreover, it is well-established that insurance may be sold and purchased by way\n\nof more than the pages of the policy itself. See 2 Couch on Insurance § 21:21\n\n(“Endorsements, riders, marginal references, and other similar writings are a part of the\n\ncontract of insurance and are to be read and construed with the policy proper.”). Counsel\n\n 15\n\ffor AUCRA conceded during oral argument that an insurance contract is broader than an\n\ninsurance policy and that a policy endorsement, for example, would be considered part of\n\nthe insurance contract.\n\n 2.\n\n With these principles in mind, we examine the relationship between the Binder,\n\nRPA, and the CNI workers’ compensation insurance policies. Both the RPA and the first\n\nCNI policy went into effect on the same day, one day after Minnieland executed the\n\nBinder and RPA. Issuance of the policy was expressly conditioned on Minnieland’s prior\n\nexecution of the RPA. Therefore, as contemplated by the parties, execution of the RPA\n\nwould temporally precede issuance of the insurance policy. See Seabulk Offshore, Ltd. v.\n\nAm. Home Assurance Co., 377 F.3d 408, 419 (4th Cir. 2004) (“Under Virginia law, a\n\ncontract is made when the last act to complete it is performed, and in the context of an\n\ninsurance policy, the last act is the delivery of the policy to the insured.” (citation\n\nomitted)). And the entire program went into effect at the same time, on January 15, 2013.\n\n The subject matter of the documents is also the same: the workers’ compensation\n\ninsurance issued to Minnieland, including the manner in which the payroll, premiums,\n\nand losses in connection with the insurance coverage would be calculated and how the\n\nrisk would be distributed. The Binder represented Minnieland’s acceptance of the\n\nEquityComp program, and through the Binder, Minnieland requested that Applied\n\nUnderwriters, Inc. “through its affiliates and/or subsidiaries . . . cause to be issued”\n\nworkers’ compensation insurance coverage to Minnieland. J.A. 40. The RPA also\n\ndiscusses the insurance coverage; it notes that workers’ compensation insurance coverage\n\n 16\n\f“will be provided” to Minnieland by “one or more of the Issuing Insurers,” defined as\n\naffiliates of Applied Underwriters, Inc. J.A. 30–31. The RPA establishes Minnieland’s\n\nparticipation in a segregated cell to be funded in part by “a portion of the premium and\n\nlosses” under the RPA. J.A. 30. The premium and losses are calculated pursuant to the\n\nRPA’s Schedule 1. Id. And Schedule 1 “applies . . . to all payroll, premium, and losses\n\noccurring under the [CNI workers’ compensation insurance] Policies.” J.A. 36.\n\n The documents also internally reference each other and set forth each other’s\n\nterms. The Binder formally requests the issuance of workers’ compensation insurance\n\ncoverage subject to Minnieland’s execution of the RPA. The RPA references the\n\nworkers’ compensation policies explicitly, and Minnieland was required to execute the\n\nRPA before those policies would issue. Schedule 1 of the RPA establishes the manner in\n\nwhich Minnieland’s fees for the EquityComp program as a whole would be calculated.\n\nThat is, Schedule 1 applies to all premiums and losses under the actual insurance policies.\n\nIn fact, the billing statements for Minnieland’s participation in the EquityComp program\n\nshow that Minnieland was charged a single “pay-in amount” each month for the\n\n“Workers’ Compensation Program.” J.A. 45, 47, 49 (emphasis added). The RPA also\n\nwaives Minnieland’s right to choose deductibles for its workers’ compensation insurance\n\npolicies, and the Binder acknowledges that waiver. See J.A. 31 (§ 5), 40.\n\n The RPA and insurance policies are linked in other ways as well. The RPA\n\nprovides that its early cancellation terms apply if any one of the insurance policies is\n\ncancelled prior to the end of the RPA’s three-year term. J.A. 31 (§ 4). The RPA also\n\nprovides that Minnieland and AUCRA’s obligations under the RPA survive the active\n\n 17\n\fterm of the RPA “and shall be extinguished only when [AUCRA] no longer has any\n\npotential or actual liability to the Issuing Insurers with respect to the [workers’\n\ncompensation insurance] Policies.” J.A. 31 (§ 7). The RPA additionally provides that, in\n\nthe event Minnieland defaults under the RPA “or under any other agreement with any\n\naffiliates of [AUCRA] (Affiliated Agreements),” AUCRA “may take all reasonable steps\n\nto protect its and its affiliates’ interests.” J.A. 31 (§ 9). The RPA goes on to state that\n\n“[t]he parties hereto shall have the right . . . to offset or recoup any balances due from one\n\nto the other under [the RPA] or any Affiliated Agreements.” Id. Those Affiliated\n\nAgreements would include the insurance policies issued by CNI, an AUCRA affiliate.\n\nThe RPA also sets forth the terms that apply if CNI were required to provide workers’\n\ncompensation insurance coverage outside of the active term of the RPA. J.A. 31 (§ 4).\n\n These explicit internal references, interrelated terms, and shared subject matter are\n\nstrong evidence that the parties intended these documents to be part of one integrated\n\ntransaction. See Countryside Orthopaedics, 541 S.E.2d at 285; Musselman, 533 S.E.2d at\n\n921.\n\n To be sure, the documents were not executed by the same parties. The Binder was\n\nsigned by Minnieland as an acceptance of the EquityComp program proposal apparently\n\ndrafted by ARS, a subsidiary of Applied Underwriters, Inc., to whom the EquityComp\n\ntrademark is registered. See J.A. 23 (defining “we” as Applied Risk Services). The RPA\n\nwas executed between Minnieland and AUCRA, another subsidiary of Applied\n\nUnderwriters, Inc. J.A. 30. And the insurance policies were produced by Applied Risk\n\n\n\n 18\n\fServices, Inc., another subsidiary of Applied Underwriters, Inc., with CNI, yet another\n\nApplied Underwriters, Inc. subsidiary, as the insuring entity. J.A. 42–44.\n\n Nonetheless, the EquityComp program is promoted and sold as “[o]ne unified\n\nprogram for your business needs across all states” provided by Applied Underwriters,\n\nInc., “a premier financial services group of companies with leading experience in the\n\ncasualty insurance, reinsurance and business services disciplines.” J.A. 24–25 (emphases\n\nadded). The EquityComp program is marketed as being “effected through a separate\n\nreinsurance transaction issued in conjunction with a fully insured, guaranteed cost,\n\nworkers’ compensation policy.” J.A. 24. In fact, the Producer’s Quote Transmittal sent\n\nto the agent who brokered this deal for Minnieland expressly stated that the program\n\nproposed to Minnieland was “valid only if presented prior to expiration, in its original\n\nform, and in its entirety without modification.” J.A. 29 (emphasis added). And the\n\nBinder makes clear that insurance coverage was conditioned on execution of the RPA.\n\nTherefore, absent execution of the RPA, the insurance coverage would not have been\n\noffered as proposed. See Nat’l Convention Servs., LLC v. Applied Underwriters Captive\n\nRisk Assurance Co., Inc., 239 F. Supp. 3d 761, 786 (S.D.N.Y. 2017) (examining the\n\nworkers’ compensation insurance program offered by AUCRA and its affiliates and\n\nnoting that the RPA “would serve no purpose” without the approved guaranteed cost\n\ninsurance policies and that “it is plausible that the two can be treated as one\n\nundertaking”); see also Parr, 604 S.E.2d at 435 (finding integrated contract where one\n\ncontract’s terms could not be performed in the absence of other contracts).\n\n\n\n 19\n\f Additionally, the RPA contemplates that its terms will apply to AUCRA’s\n\naffiliates. The RPA provides that “[n]othing in this Agreement, expressed or implied, is\n\nintended to confer upon any party, other than the parties hereto and their affiliates,\n\nsuccessors and assigns, any rights, remedies, obligations or liabilities under or by reason\n\nof this Agreement, except as expressly provided herein.” J.A. 35 (§ 19) (emphasis\n\nadded). The RPA also provides that “[a]ll existing obligations from each party to the\n\nother or to third parties shall remain in force as of the expiration of the Active Term until\n\nthis Agreement is terminated.” J.A. 31 (§ 4) (emphasis added). These provisions further\n\nsuggest that Minnieland and AUCRA intended the RPA to be part of an integrated\n\ntransaction with AUCRA’s affiliates. See Countryside Orthopaedics, 541 S.E.2d at 284.\n\n During oral argument, counsel for AUCRA highlighted that, despite the RPA’s\n\nSchedule 1, the RPA does not charge “premiums”; it merely explains what happens to the\n\npremiums that are paid under the policies. This, however, does not render the RPA a\n\nstandalone contract. Instead, it lends support to Minnieland’s argument that the RPA and\n\nthe CNI policies must be read as one integrated contract. The policies set forth an\n\nestimated annual premium that is not subject to the RPA’s Schedule 1 calculations. J.A.\n\n42–44. The policies also contain a Short Rate Cancelation Policyholder Notice that\n\nexplains how the final premium will be calculated if the policies are cancelled by\n\nMinnieland. J.A. 761–63. The RPA’s Schedule 1, on the other hand, purports to\n\nestablish the total fee to be paid by Minnieland for the EquityComp program as well as\n\nany early cancellation fee that may be due. J.A. 36–37.\n\n\n\n 20\n\f Schedule 1’s calculations, however, incorporate the provisions of the CNI policies.\n\nSchedule 1 states that it “applies as of the Effective Date [January 15, 2013] to all\n\npayroll, premium, and losses occurring under the Policies.” J.A. 36. Schedule 1 explains\n\nthat “[a]n amount equal to the premium earned under the Policies in excess of the Loss\n\nPick Containment Amount multiplied by the applicable Exposure Group Adjustment\n\nFactor multiplied by the Allocation Factor listed in Table B, will be allocated to the\n\nParticipant’s cell.” J.A. 36 (§ 2). Thus, although Minnieland was billed one monthly fee\n\nfor the EquityComp program, the premium amount set forth in the policies was part of\n\nthat monthly fee and was included in calculating the total amount that would be due\n\nunder the program as a whole. Absent the CNI policies, the calculations in Schedule 1—\n\nincluding the amount to be allocated to Minnieland’s segregated cell—would be\n\nimpossible to make.\n\n The early cancellation provision of the RPA also depends on the cancellation\n\nprovisions of the CNI policies. The RPA’s early cancellation provision applies if either\n\nMinnieland cancels the RPA or if any of the insurance policies are “cancelled or non-\n\nrenewed prior to the end of the Active Term” of the RPA. J.A. 31 (§ 4). That\n\ncancellation policy, described in Schedule 1, states that certain of the factors used to\n\ncalculate premiums and losses will be increased in the event of early cancellation and that\n\nMinnieland will be required to pay, among other things, “any remaining premium,\n\nincluding short rate penalties, due under the Policies.” J.A. 37 (§ 6) (emphasis added).\n\nThose “short rate penalties” are the early termination provisions of the insurance policies.\n\nSee, e.g., J.A. 761 (“Short Rate Cancelation Policyholder Notice”). And the short rate\n\n 21\n\fpenalties apply when the policy is cancelled by Minnieland. Id. Therefore, when the\n\nshort rate cancellation provisions of the policies apply, they are another integer of the\n\nformula used under the RPA to calculate the total amount due under the EquityComp\n\nprogram. In the absence of the CNI policy terms, the RPA’s Schedule 1 calculations and\n\nearly cancellation provisions make no sense. See Musselman, 533 S.E.2d at 921.\n\n We do not ignore that Minnieland chose to sue only AUCRA and to base its\n\nclaims only on the RPA. However, because the RPA was but one component of an\n\nintegrated insurance sale, we must examine the related documents and the relationship\n\nbetween the affiliated entities. Daugherty, 385 S.E.2d at 574. In the absence of the CNI\n\npolicies, the RPA would have been pointless and nonsensical; and in the absence of the\n\nRPA, there would have been no insurance coverage. Nothing in the record suggests that\n\nMinnieland could have simply paid the premiums listed in the CNI policies, without\n\npaying the amounts set forth in the RPA’s Schedule 1, and maintained its workers’\n\ncompensation coverage; the RPA expressly provides for the opposite result. Because the\n\nEquityComp program was marketed and sold as a package deal, Minnieland’s failure to\n\nexecute the RPA would have frustrated the purpose of the transaction. See Parr, 604\n\nS.E.2d at 435.\n\n In sum, the documents, considered together, show that the purpose of the Binder,\n\nRPA, and CNI policies was one: to provide Minnieland with workers’ compensation\n\ninsurance coverage while allowing Minnieland the opportunity to keep its insurance costs\n\nlow by sharing in the underwriting risk. We need not determine specifically whether the\n\nRPA constitutes a policy endorsement or rider. Regardless of the label that may attach,\n\n 22\n\fthe RPA and insurance policies constitute an integrated transaction and must be read as\n\none contract.\n\n C.\n\n Having determined the scope of the contract at issue, we must now decide whether\n\nthe integrated contract is a contract of insurance under Virginia Code § 38.2–312. The\n\nVirginia Code does not define “insurance contract.” It does define “insurance,” however,\n\nas “the business of transferring risk by contract wherein a person, for a consideration,\n\nundertakes (i) to indemnify another person, (ii) to pay or provide a specified or\n\nascertainable amount of money, or (iii) to provide a benefit or service upon the\n\noccurrence of a determinable risk contingency.” Va. Code § 38.2–100. The Code also\n\nlists the required terms of “[e]ach insurance policy or contract”:\n\n 1. The names of the parties to the contract;\n\n 2. The subject of the insurance;\n\n 3. The risks insured against;\n\n 4. The time the insurance takes effect and, except in the case\n of group insurance, title insurance, and insurance written\n under perpetual policies, the period during which the\n insurance is to continue;\n\n 5. A statement of the premium, except in the case of group\n insurance and title insurance; and\n\n 6. The conditions pertaining to the insurance.\n\nVa. Code § 38.2–305. 5\n\n\n 5\n Minnieland cites to Virginia common law for the essential terms of an insurance\ncontract. See Resp. Br. 20–21; Grp. Hospitalization Med. Serv., Inc. v. Smith, 372 S.E.2d\n(Continued)\n 23\n\f Neither party argues that the terms of the CNI policies themselves fail to meet the\n\nstatutory requirements for insurance contracts. In fact, AUCRA acknowledges that the\n\nCNI policies meet Virginia’s requirements. Opening Br. 7 n.3. Construing the CNI\n\npolicy terms as integrated with those of the RPA, as though the terms of each were\n\nwritten in a single document, Countryside Orthopaedics, 541 S.E.2d at 284, it becomes\n\nclear that the contract at issue is an “insurance contract” under Virginia law.\n\nAccordingly, the district court properly determined that the RPA is an insurance contract\n\nfor the purposes of Virginia Code § 38.2–312.\n\n D.\n\n We note, as Minnieland does, that we are not the first to determine that the\n\nprogram marketed by Applied Underwriters, Inc. is insurance. In fact, several state\n\ninsurance commissioners have determined that the EquityComp program and its sister\n\nprogram, SolutionOne, are not only subject to insurance regulations, but also violate\n\nthose regulations. For example, the Vermont Department of Financial Regulation has\n\nbarred Applied Underwriters, Inc. from selling the RPA in conjunction with guaranteed\n\n\n159, 160 (Va. 1988) (listing “essential terms” of insurance contract as: “(1) the subject\nmatter to be insured; (2) the risk insured against; (3) the commencement and period of the\nrisk undertaken by the insurer; (4) the amount of insurance; and (5) the premium and time\nat which it is to be paid” (citation omitted)). AUCRA argues that, since the addition of\nthe definition of “insurance” to the Virginia Code in 2001, this common law definition is\nno longer controlling. Opening Br. 32–33. The Virginia Supreme Court has not applied\nthe common-law definition in connection with the statutory definition of “insurance.”\nHowever, the common-law elements are essentially the same as the statutory\nrequirements for every insurance policy. Therefore, an evaluation of the contract at issue\nunder either the statutory factors or the common-law definition should yield the same\nresult.\n\n 24\n\fcost insurance policies in Vermont after concluding that the RPA “de facto operated as a\n\nretrospective rating plan, replacing [CNI’s] guaranteed-cost workers’ compensation\n\ninsurance policy with an unfiled, unapproved retrospective rating plan.” J.A. 233.\n\nSimilarly, the Wisconsin Office of the Commissioner of Insurance entered into an\n\nagreement with ARS and CNI that they will “cease and desist from marketing, binding,\n\nissuing and renewing SolutionOne and EquityComp policies and any similarly designed\n\npolicies and programs that involve side agreements that affect the terms of the workers’\n\ncompensation policy, including but not limited to reinsurance agreements.” J.A. 375.\n\nThe California Insurance Commissioner likewise found that the EquityComp program\n\nand its RPA violate the California Insurance Code. See Decision and Order, In the\n\nMatter of the Appeal of Shasta Linen Supply, Inc., No. AHB-WCA-14-31 (Dep’t of Ins.,\n\nState of Cal. June 20, 2016), http://www.insurance.ca.gov/0250-insurers/0500-legal-\n\ninfo/0600-decision-ruling/0100-precedential/upload/ShastaLinenSupplyInc.pdf.\n\n Other courts faced with the RPA and similar related documents have also\n\nsuggested that the program marketed by Applied Underwriters, including the RPA, is\n\ninsurance. See, e.g., Nat’l Convention Servs., 239 F. Supp. 3d at 786 (observing that the\n\nRPA and guaranteed cost policies “plausibly serve the common purpose of providing\n\nworkers’ compensation insurance at rates that are affected by loss experience”); Nielsen\n\nContracting, Inc. v. Applied Underwriters, Inc., 22 Cal. App. 5th 1096, 1116–17 (Cal. Ct.\n\nApp. 2018) (determining that the RPA’s provisions were meant to replace those of the\n\ninsurance policies and that the Applied Underwriters affiliated entities were “so\n\nenmeshed” and “intertwined” that the RPA and insurance policies should be considered\n\n 25\n\ftogether); Citizens of Humanity, LLC v. Applied Underwriters Captive Risk Assurance\n\nCo., Inc., 909 N.W.2d 614, 632 (Neb.) (stating that “the RPA has the hallmarks of a\n\nretrospective rating plan” and concluding that the RPA is an “agreement concerning or\n\nrelating to an insurance policy” under Nebraska law), cert. denied, 139 S. Ct. 274 (2018).\n\n While each of these other jurisdictions has evaluated the RPA under different laws\n\nand for different purposes, the general consensus has consistently been that the RPA is\n\nsubject to insurance regulations. We join that consensus in holding that the RPA at issue\n\nhere is an insurance contract under Virginia law. Because arbitration provisions in\n\ninsurance contracts are void under Virginia law, Va. Code § 38.2–312, AUCRA must\n\nface Minnieland’s claims in court.\n\n\n\n IV.\n\n For these reasons, we affirm the judgment of the district court.\n\n\n\n AFFIRMED.\n\n\n\n\n 26\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: MINNIELAND PRIVATE DAY SCHOOL, INC., a Virginia Corporation, Plaintiff - Appellee, v. APPLIED UNDERWRITERS CAPTIVE RISK ASSURANCE COMPANY, INC., Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-14\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-2385\\n\\n\\nMINNIELAND PRIVATE DAY SCHOOL, INC., a Virginia corporation,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nAPPLIED UNDERWRITERS CAPTIVE RISK ASSURANCE COMPANY, INC.,\\n\\n Defendant - Appellant.\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. Anthony John Trenga, District Judge. (1:15-cv-01695-AJT-IDD)\\n\\n\\nArgued: October 30, 2018 Decided: January 14, 2019\\n\\n\\nBefore GREGORY, Chief Judge, MOTZ, and WYNN, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Chief Judge Gregory wrote the opinion, in which Judge\\nMotz and Judge Wynn joined.\\n\\n\\nARGUED: Daniel William Olivas, LEWIS, THOMASON, KING, KRIEG &\\nWALDROP, P.C., Nashville, Tennessee, for Appellant. James Scott Krein, KREIN\\nLAW FRIM, Prince William, Virginia, for Appellee. ON BRIEF: R. Dale Bay,\\nRyan N. Clark, LEWIS, THOMASON, KING, KRIEG & WALDROP, P.C., Nashville,\\nTennessee, for Appellant.\\n\\fGREGORY, Chief Judge:\\n\\n Appellant Applied Underwriters Captive Risk Assurance Company, Inc.\\n\\n(“AUCRA”) comes to us for the second time in this case, appealing the district court’s\\n\\ndetermination that a Reinsurance Participation Agreement (“RPA”) executed by it and\\n\\nAppellee Minnieland Private Day School is an insurance contract under Virginia law.\\n\\nThe RPA, executed in connection with Minnieland’s purchase of workers’ compensation\\n\\ninsurance, contains an arbitration clause. In the district court, AUCRA moved to compel\\n\\narbitration in accordance with the RPA’s terms. In opposing arbitration, Minnieland\\n\\nasserted that the RPA is an insurance contract for purposes of Virginia Code § 38.2–312,\\n\\nwhich renders void arbitration clauses contained in insurance contracts. The district court\\n\\ndenied AUCRA’s motion to compel arbitration, finding that AUCRA was judicially\\n\\nestopped from arguing that the RPA is not an insurance contract. We reversed that\\n\\ndetermination, concluding that AUCRA was not estopped from making its argument, and\\n\\nremanded to allow the parties to brief fully the issue of whether the RPA is an insurance\\n\\ncontract for purposes of Virginia Code § 38.2–312. On remand, the district court held\\n\\nthat the RPA is indeed an insurance contract and that the RPA’s arbitration clause is void\\n\\nas a matter of law. AUCRA now appeals that determination.\\n\\n For the reasons set forth below, we conclude that the RPA is an insurance contract\\n\\nfor purposes of Virginia Code § 38.2–312. We therefore affirm.\\n\\n\\n\\n\\n 2\\n\\f I.\\n\\n A.\\n\\n This case involves a workers’ compensation insurance program that Minnieland\\n\\npurchased from AUCRA and its affiliated entities. Under Virginia law, workers’\\n\\ncompensation insurance is “insurance against the legal liability of any employer for the\\n\\ndeath or disablement of, or injury to, his or its employee whether imposed by common\\n\\nlaw or by statute, or assumed by contract.” Va. Code § 38.2–119. Workers’\\n\\ncompensation insurance coverage is required of “[e]very employer subject to” Virginia’s\\n\\nworkers’ compensation statute. Va. Code § 65.2–800(A); Redifer v. Chester, 720 S.E.2d\\n\\n66, 67–68 (Va. 2012).\\n\\n In general, workers’ compensation insurance is typically provided in one of two\\n\\ntypes of policies: a guaranteed cost policy or a retrospective rating plan. Under a\\n\\nguaranteed cost policy, the premiums are fixed and usually do not change over the term\\n\\nof the policy. Steven Plitt, Daniel Maldonado, Joshua D. Rogers, & Jordan R. Plitt, 2\\n\\nCouch on Insurance § 69:10 (3d ed. 1995). In many states, these plans are the only plans\\n\\nlawfully available to small and mid-sized employers. Retrospective rating plans, on the\\n\\nother hand, usually require an advance premium deposit with the insurer and then provide\\n\\nthat the insurer, at some specified time, will compute the actual premium based on the\\n\\ninsured’s actual loss experience or total payroll during a set period of time. Id. § 69:16;\\n\\nsee Va. Code § 38.2–1901 (defining “retrospective rating plan” as “a rating plan that\\n\\nadjusts the premium for the insurance to which it applies on the basis of losses incurred\\n\\nduring the period covered by that insurance”). The insured is then either issued a refund\\n\\n 3\\n\\fif the actual premium is lower than the premium deposit paid or required to pay the\\n\\ndifference if the actual premium exceeds the deposited amount.\\n\\n At issue in this appeal is Applied Underwriters, Inc.’s EquityComp program, an\\n\\ninnovative program of workers’ compensation insurance that offers small and mid-sized\\n\\nemployers the benefits of both a guaranteed cost policy and a retrospective rating plan in\\n\\none insurance program. The EquityComp program provides employers with guaranteed\\n\\ncost workers’ compensation insurance at the same time that they enjoy the benefits—and\\n\\nare subject to the risks—of a retrospective rating plan. See J.A. 404 (explaining that this\\n\\nRPA allows small and mid-sized employers to “in effect, have a retrospective rating plan\\n\\n. . . even though, in fact, the insured has Guaranteed Cost insurance coverage with the\\n\\ninsurance carrier”). 1 The program is so novel that it has been patented.\\n\\n Under the program, various insurance companies affiliated with Applied\\n\\nUnderwriters, Inc. have entered into a reinsurance pooling agreement. The pooled\\n\\ncompanies provide workers’ compensation insurance coverage to employers and also\\n\\nmutually reinsure each other’s insurance business. A layer of reinsurance is also\\n\\nprovided by AUCRA, a wholly owned subsidiary of Applied Underwriters, Inc. AUCRA\\n\\nin turn enters into RPAs with EquityComp customers, under the terms of which each\\n\\ncustomer pays into a segregated “cell” or account that is then used to fund AUCRA’s\\n\\nliabilities. In essence, EquityComp customers participate in underwriting the risk of their\\n\\nown workers’ compensation insurance policies.\\n\\n 1\\n Citations to the “J.A.” refer to the Joint Appendix filed by the parties in this\\nappeal.\\n\\n 4\\n\\f In theory, an EquityComp customer can save costs on its workers’ compensation\\n\\ninsurance through a refund of monies deposited into its segregated cell if its workers’\\n\\ncompensation insurance claims are kept low during the term of the RPA. As detailed\\n\\nbelow, however, Minnieland was unable to reap this benefit.\\n\\n B.\\n\\n Minnieland provides education and childcare services in Virginia and is subject to\\n\\nthe workers’ compensation laws and requirements of the state. Va. Code § 65.2–800(A).\\n\\n On January 14, 2013, Minnieland bought into the EquityComp program.\\n\\nMinnieland executed a Request to Bind Coverages and Services (“Binder”), by which\\n\\nMinnieland “request[ed] that Applied Underwriters, Inc. through its affiliates and/or\\n\\nsubsidiaries . . . cause to be issued to [Minnieland] one or more workers’ compensation\\n\\ninsurance policies . . . subject to [Minnieland] executing the . . . [RPA].” J.A. 40. At the\\n\\nsame time, Minnieland executed an RPA. The RPA had a term of three years and\\n\\nprovided that one or more “Issuing Insurers”—all of which were entities affiliated with\\n\\nApplied Underwriters, Inc.—would issue workers’ compensation insurance policies to\\n\\nMinnieland. The RPA also established that Minnieland would share in the profits and\\n\\nlosses associated with its policies through its “segregated protected cell.” Applied Risk\\n\\nServices, Inc. (“ARS”), another subsidiary of Applied Underwriters, Inc., was designated\\n\\nas the billing agent for both AUCRA and the Issuing Insurers. Schedule 1 of the RPA\\n\\nsets forth various formulae for calculating premiums and losses under the RPA and\\n\\ninsurance policies.\\n\\n\\n\\n 5\\n\\f The day after Minnieland executed the EquityComp documents, the RPA went\\n\\ninto effect, as did the first of what would become three consecutive one-year Virginia\\n\\nworkers’ compensation insurance policies, the last of which was to expire on January 15,\\n\\n2016. The first policy listed the estimated annual premium as $589,163. The second and\\n\\nthird policies listed the estimated annual premiums as $642,333 and $706,160,\\n\\nrespectively. The policies were produced by ARS and insured by Continental Indemnity\\n\\nCompany (“CNI”), another affiliate of Applied Underwriters, Inc.\\n\\n According to the complaint, at no time was AUCRA licensed to sell insurance in\\n\\nVirginia, and the RPA has not been approved by the Virginia Workers’ Compensation\\n\\nCommission.\\n\\n For the first 33 of the 36 months during which the RPA was active, AUCRA\\n\\ncharged, and Minnieland paid, an average of $58,810 per month in premiums. In\\n\\nNovember 2015, however, the premium charged to Minnieland increased drastically to\\n\\n$471,213, a 1167% increase from the October 2015 premium and a 801% increase over\\n\\nthe first 33 months’ average. Despite Minnieland’s requests, AUCRA refused to disclose\\n\\nthe basis on which it assessed the November 2015 premium. Minnieland nonetheless\\n\\npaid the November premium.\\n\\n AUCRA billed Minnieland a similarly high premium of $414,604 for December\\n\\n2015. AUCRA once again refused to disclose the basis for the increased premium, and\\n\\nMinnieland did not pay the December premium.\\n\\n\\n\\n\\n 6\\n\\f On December 16, 2015, AUCRA 2 faxed Minnieland notice that it was terminating\\n\\nMinnieland’s EquityComp program, including the RPA and insurance coverage, effective\\n\\nDecember 27, 2015. The reason provided for the termination of coverage was “Non-\\n\\nPayment of Premium; Client has an outstanding balance.”\\n\\n C.\\n\\n On December 24, 2015, Minnieland filed suit against AUCRA in the Eastern\\n\\nDistrict of Virginia. Minnieland alleged that AUCRA is not authorized or licensed to act\\n\\nas an insurance company under Virginia law; that the RPA is an “insurance contract” and\\n\\nnot a “reinsurance” agreement; and that AUCRA misrepresented the EquityComp\\n\\nprogram, and the RPA specifically, to circumvent Virginia insurance and workers’\\n\\ncompensation laws. Minnieland sought (1) a declaration that the RPA constitutes an\\n\\ninsurance contract and is void because of AUCRA’s failure to comply with Virginia law;\\n\\n(2) a declaration of the amount, if any, that Minnieland owes under the RPA; and (3) a\\n\\ndeclaration that the premiums, deposits, and charges assessed to Minnieland by AUCRA\\n\\nwere excessive. Minnieland also sought damages for fraud and breach of contract.\\n\\n On January 18, 2016, AUCRA filed a demand for arbitration with the American\\n\\nArbitration Association, invoking the RPA’s arbitration provisions. That demand sought\\n\\npayment from Minnieland of a total of $342,358 that AUCRA claimed it was owed under\\n\\nthe RPA and EquityComp program.\\n\\n 2\\n The complaint alleges that AUCRA sent the notice. The letter is printed on\\n“Applied Underwriters” letterhead and does not specify if the sender is AUCRA or\\nApplied Underwriters, Inc. J.A. 52. The document attached to the letter indicates that it\\nwas “produced by” ARS. J.A. 53.\\n\\n 7\\n\\f AUCRA also moved the district court to dismiss Minnieland’s complaint and\\n\\ncompel arbitration under the RPA’s arbitration clause. In opposing the motion to compel\\n\\narbitration, Minnieland argued that the RPA is an insurance contract. As such,\\n\\nMinnieland argued, the arbitration clause is void because it is prohibited by Virginia\\n\\nCode § 38.2–312.\\n\\n On March 17, 2016, the district court granted in part and denied in part AUCRA’s\\n\\nmotion. The district court determined that the RPA’s arbitration clause calls for\\n\\narbitration of the threshold question of whether the RPA is an insurance contract such\\n\\nthat Virginia’s insurance statute, which reverse-preempts the Federal Arbitration Act\\n\\n(“FAA”), applies. Accordingly, the court ordered the parties to submit that question to\\n\\nthe arbitrator.\\n\\n A week later, the district court granted Minnieland’s motion for reconsideration of\\n\\nthe court’s March 17, 2016 order. The district court again concluded that the threshold\\n\\nissue of arbitrability was for the arbitrator to determine. The district court nonetheless\\n\\nstayed its March 17 order and requested supplemental briefing on Minnieland’s\\n\\ncontention that AUCRA was judicially estopped from arguing that the RPA is not an\\n\\ninsurance contract.\\n\\n The parties briefed the judicial estoppel issue, and the district court heard\\n\\nargument on AUCRA’s motion to compel arbitration. The district court denied the\\n\\nmotion to compel, concluding that the four elements of judicial estoppel were met such\\n\\nthat AUCRA was estopped from arguing that the RPA is not an insurance contract. See\\n\\n\\n\\n 8\\n\\fLowery v. Stovall, 92 F.3d 219, 223–24 (4th Cir. 1996) (discussing the elements of\\n\\njudicial estoppel).\\n\\n AUCRA appealed that order. On appeal, we affirmed in part and reversed in part.\\n\\nMinnieland Private Day Sch., Inc. v. Applied Underwriters Captive Risk Assurance Co.,\\n\\nInc., 867 F.3d 449 (4th Cir. 2017), cert. denied, 138 S. Ct. 926 (2018). We concluded\\n\\nthat Virginia Code § 38.2–312 “renders invalid delegation provisions in putative\\n\\ninsurance contracts governed by Virginia law, at least to the extent such delegation\\n\\nprovisions endow an arbitrator, as opposed to a court, with exclusive authority to\\n\\ndetermine whether the contract at issue constitutes an ‘insurance contract’ for purposes of\\n\\nVirginia law.” Id. at 456. Therefore, we affirmed the district court’s denial of the motion\\n\\nto compel arbitration. Id. at 457. We also concluded that AUCRA was not judicially\\n\\nestopped from arguing that the RPA is not an insurance contract under Virginia law. Id.\\n\\nat 458–59. Because the parties had not had the opportunity to brief fully the issue of\\n\\nwhether the RPA is an insurance contract under Virginia law, we remanded the matter to\\n\\nthe district court. Id. at 459.\\n\\n On remand, the district court ruled in an oral opinion that the RPA is an insurance\\n\\ncontract. As the district court explained:\\n\\n Under this arrangement, Minnieland and AUCRA\\n entered into a contract as a result of which Minnieland\\n received workmen’s compensation coverage through an\\n insurance policy in exchange for premiums that were paid for\\n that coverage.\\n\\n AUCRA’s position rests entirely on parsing this\\n transaction to the point of being completely disassociated\\n with the realities of the overall transaction. So the Court\\n\\n 9\\n\\f concludes that it’s an insurance contract for the purposes of\\n 38.2–312 as the Fourth Circuit has already determined. 3\\n\\nJ.A. 1073–74. Accordingly, the district court denied the motion to compel arbitration,\\n\\nfinding that “any arbitration provisions pertaining to any disputes under [the RPA] are\\n\\nvoid.” J.A. 1074.\\n\\n AUCRA appeals the district court’s denial of its motion to compel arbitration.\\n\\n\\n\\n II.\\n\\n We review de novo a district court’s order denying a motion to compel arbitration\\n\\nunder the FAA. Noohi v. Toll Bros., Inc., 708 F.3d 599, 605 (4th Cir. 2013). “At the\\n\\nsame time, we give due regard to the federal policy favoring arbitration and resolve ‘any\\n\\ndoubts concerning the scope of arbitrable issues . . . in favor of arbitration.’” Hill v.\\n\\nPeoplesoft USA, Inc., 412 F.3d 540, 543 (4th Cir. 2005) (citation omitted).\\n\\n In determining whether a dispute is arbitrable, we “apply ordinary state-law\\n\\nprinciples that govern the formation of contracts and the federal substantive law of\\n\\narbitrability.” Id. (internal citations and quotation marks omitted). Because this matter\\n\\n\\n\\n 3\\n In our prior opinion, we did not determine that the RPA is in fact an insurance\\ncontract. Rather, we affirmed the district court’s denial of AUCRA’s motion to compel\\narbitration on the grounds that Virginia Code § 38.2–312 “renders void delegation\\nprovisions in putative insurance contracts—at least to the extent such provisions\\nauthorize an arbitrator to resolve whether the contract at issue constitutes an ‘insurance\\ncontract.’” Minnieland, 867 F.3d at 457. Recognizing that the parties had not had the\\nopportunity to brief and argue the issue of whether the RPA is an insurance contract\\nunder Virginia law, we remanded this matter to the district court for consideration of that\\nissue.\\n\\n 10\\n\\finvolves the question of whether the RPA is an insurance contract for purposes of the\\n\\nVirginia Code, we look to Virginia law, which the parties agree applies in this case. 4\\n\\n\\n\\n III.\\n\\n A.\\n\\n We begin by addressing AUCRA’s argument that the district court ignored this\\n\\nCourt’s “narrow” mandate and improperly considered the entire program of workers’\\n\\ncompensation insurance—rather than only the RPA—in determining that the RPA is an\\n\\ninsurance contract under Virginia law. Opening Br. 23–26. AUCRA points out that the\\n\\ncomplaint names only AUCRA as a defendant, not CNI (the policy issuer), Applied\\n\\nUnderwriters, Inc. (the parent company), or Applied Risk Services (the billing agent). Id.\\n\\nat 25 (citing J.A. 1). AUCRA also relies on the fact that Minnieland’s claims are\\n\\npredicated on the RPA alone. Id. (citing J.A. 11–22). In light of this narrow focus of\\n\\nMinnieland’s suit and our “narrow mandate” to determine whether “the RPA is an\\n\\ninsurance contract under Virginia law,” AUCRA asserts that the district court should\\n\\n 4\\n We note that the RPA provides that it “shall be exclusively governed by and\\nconstrued in accordance with the laws of Nebraska and any matter concerning this\\nAgreement that is not subject to [arbitration] shall be resolved exclusively by the courts\\nof Nebraska without reference to its conflict of laws.” J.A. 34 (§ 16). The question of\\nwhether the contract itself is an insurance contract for purposes of Virginia Code § 38.2–\\n312, however, is a matter of Virginia law, and both parties brief the issue on appeal under\\nVirginia law. See, e.g., Opening Br. 28–34; Resp. Br. 13, 18–22. Because the parties\\nagree that Virginia law applies, we need not inquire further into the choice-of-law\\nquestions, and Virginia law controls the analysis. Cosey v. Prudential Ins. Co. of Am.,\\n735 F.3d 161, 169 n.7 (4th Cir. 2013) (citing Am. Fuel Corp. v. Utah Energy Dev. Co.,\\n122 F.3d 130, 134 (2d Cir. 1997)). We also note that AUCRA has not invoked the\\nRPA’s forum selection clause.\\n\\n 11\\n\\fhave considered only the RPA, not the workers’ compensation insurance transaction as a\\n\\nwhole. Id. at 25–26.\\n\\n Nothing in our prior opinion suggests that we intended to preclude any evaluation\\n\\nof whether the RPA’s terms are the complete terms of the parties’ agreement or whether\\n\\nthe RPA’s terms should be construed as integrated with the terms of the other\\n\\nEquityComp agreements. Our mandate was indeed limited to the RPA. However, on the\\n\\nprevious appeal, we were concerned only with the RPA because the RPA contains the\\n\\narbitration provision at issue. Because we remanded for consideration of whether the\\n\\nRPA is an “insurance contract” under Virginia law, the district court was faced with the\\n\\ninitial question of whether the RPA is in fact a standalone contract or is simply one part\\n\\nof an integrated contract. See Hitachi Credit Am. Corp. v. Signet Bank, 166 F.3d 614,\\n\\n626 (4th Cir. 1999) (“A contract may be contained in several instruments, and they may\\n\\nbe read together as one instrument [i]f made at the same time and in relation to the same\\n\\nsubject matter.” (alteration in original) (internal citations and quotation marks omitted)).\\n\\nOnly after the court made that threshold determination could it then determine the nature\\n\\nof the contract. Therefore, the district court did not ignore our previous mandate by\\n\\nlooking at the EquityComp program as a whole.\\n\\n B.\\n\\n 1.\\n\\n Having concluded that the district court did not violate our prior mandate, we turn\\n\\nto the issue at the heart of this appeal: whether the RPA is an insurance contract for\\n\\npurposes of Virginia Code § 38.2–312. Under Virginia law, “[w]here two papers are\\n\\n 12\\n\\fexecuted at the same time or contemporaneously between the same parties, in reference\\n\\nto the same subject matter, they must be regarded as parts of one transaction, and receive\\n\\nthe same construction as if their several provisions were in one and the same instrument.”\\n\\nCountryside Orthopaedics, P.C. v. Peyton, 541 S.E.2d 279, 284 (Va. 2001) (alteration in\\n\\noriginal) (citations omitted). “To construe two instruments as one, reference in one\\n\\ninstrument to the other need not be explicit; ‘it is sufficient if it is fairly traceable.’”\\n\\nHitachi Credit, 166 F.3d at 626 (quoting Tex. Co. v. Northup, 153 S.E. 659, 662 (Va.\\n\\n1930)). While “a court is not required to construe two documents as one contract just\\n\\nbecause they are executed at the same time and concern the same subject matter[,] [t]he\\n\\ncourt must give effect to the intent of the parties.” Id. (citing Am. Realty Tr. v. Chase\\n\\nManhattan Bank, N.A., 281 S.E.2d 825, 831 (Va. 1981)).\\n\\n The Virginia courts have yet to address whether a contract similar to the RPA,\\n\\nexecuted during an insurance transaction, comprises part of the insurance contract. The\\n\\nVirginia Supreme Court, however, has taken a rather expansive view of what constitutes\\n\\na single integrated contract. In Daugherty v. Diment, the Virginia Supreme Court made\\n\\nclear that, “[w]here a business transaction is based upon more than one document\\n\\nexecuted by the parties, the documents will be construed together to determine the intent\\n\\nof the parties; each document will be employed to ascertain the meaning intended to be\\n\\nexpressed by the others.” 385 S.E.2d 572, 574 (Va. 1989) (citing Am. Realty Tr., 281\\n\\nS.E.2d at 830).\\n\\n The Virginia Supreme Court has since applied Daugherty’s rule regularly to\\n\\ntransactions involving multiple written agreements. In Musselman v. Glass Works, LLC,\\n\\n 13\\n\\ffor example, the Virginia Supreme Court held that an asset purchase agreement and a\\n\\nnon-competition agreement executed at the same time “formed an integrated business\\n\\ntransaction.” 533 S.E.2d 919, 921 (Va. 2000). The purchase agreement provided that the\\n\\npurchase price was payable in various payments, including a deposit, a sum certain at\\n\\nclosing, a secured promissory note to the sellers, and a total of $60,000 to be paid\\n\\npursuant to three non-competition agreements. Id. at 920. The Virginia Supreme Court\\n\\nrejected an argument that the non-competition agreements were separate, personal service\\n\\ncontracts. Id. at 921. Instead, the court determined that the four contracts formed an\\n\\nintegrated contract because the sum due under the non-competition agreements was\\n\\nexplicitly part of the purchase price of the business under the purchase agreement. Id.\\n\\n The Virginia Supreme Court has also found that agreements not executed by the\\n\\nsame parties may nonetheless constitute an integrated contract. In Countryside\\n\\nOrthopaedics, for instance, the court found an integrated contract comprised of four\\n\\nagreements: two employment agreements executed by Countryside Orthopaedics and\\n\\ntwo respective physicians, a Stock Purchase Agreement executed by the physicians, and a\\n\\nStockholders’ Agreement executed by all three parties. 541 S.E.2d at 284. The court\\n\\nheld that these documents constituted a single transaction despite the fact that each of the\\n\\ncontracts was not signed by all three parties because “all the parties knew about the\\n\\nagreements and executed them at the same time as part of a single transaction to\\n\\naccomplish an agreed purpose.” Id. The court was also persuaded by the fact that “some\\n\\nof the agreements contain[ed] explicit references to the other agreements.” Id. at 285.\\n\\n\\n\\n 14\\n\\f Also instructive is Parr v. Alderwoods Grp., Inc., 604 S.E.2d 431 (Va. 2004). The\\n\\ntransaction at issue in that case involved four agreements: an asset purchase agreement, a\\n\\nnon-competition agreement, a lease, and a management agreement. Id. at 432. In\\n\\nreviewing the agreements, the Virginia Supreme Court rejected the argument that the\\n\\nmanagement agreement was “a contract separate and apart from” the asset purchase\\n\\nagreement. Id. at 435. The court found that the management agreement and asset\\n\\npurchase agreement should be construed “as a single integrated contract” because they\\n\\ncross-referenced each other and contained certain provisions written in identical\\n\\nlanguage. Id. The court explained that those references “reflect[ed] the parties’\\n\\nknowledge and understanding of the interrelationship between the contracts and\\n\\nprovide[d] strong support for the proposition that the parties intended that the documents\\n\\nconstitute a single transaction.” Id. The court further reasoned that, although the four\\n\\ncontracts “identified discrete acts required of the parties,” the contracts all shared the\\n\\nsame result and purpose. Id. Also relevant was the fact that the provisions of the\\n\\nmanagement agreement “could not be performed” without the acquisition of the business\\n\\nthrough the purchase agreement and the lease of the property. Id. As the court stated,\\n\\n“[t]he absence of any one of the agreements would frustrate the purpose of the\\n\\ntransaction.” Id.\\n\\n Moreover, it is well-established that insurance may be sold and purchased by way\\n\\nof more than the pages of the policy itself. See 2 Couch on Insurance § 21:21\\n\\n(“Endorsements, riders, marginal references, and other similar writings are a part of the\\n\\ncontract of insurance and are to be read and construed with the policy proper.”). Counsel\\n\\n 15\\n\\ffor AUCRA conceded during oral argument that an insurance contract is broader than an\\n\\ninsurance policy and that a policy endorsement, for example, would be considered part of\\n\\nthe insurance contract.\\n\\n 2.\\n\\n With these principles in mind, we examine the relationship between the Binder,\\n\\nRPA, and the CNI workers’ compensation insurance policies. Both the RPA and the first\\n\\nCNI policy went into effect on the same day, one day after Minnieland executed the\\n\\nBinder and RPA. Issuance of the policy was expressly conditioned on Minnieland’s prior\\n\\nexecution of the RPA. Therefore, as contemplated by the parties, execution of the RPA\\n\\nwould temporally precede issuance of the insurance policy. See Seabulk Offshore, Ltd. v.\\n\\nAm. Home Assurance Co., 377 F.3d 408, 419 (4th Cir. 2004) (“Under Virginia law, a\\n\\ncontract is made when the last act to complete it is performed, and in the context of an\\n\\ninsurance policy, the last act is the delivery of the policy to the insured.” (citation\\n\\nomitted)). And the entire program went into effect at the same time, on January 15, 2013.\\n\\n The subject matter of the documents is also the same: the workers’ compensation\\n\\ninsurance issued to Minnieland, including the manner in which the payroll, premiums,\\n\\nand losses in connection with the insurance coverage would be calculated and how the\\n\\nrisk would be distributed. The Binder represented Minnieland’s acceptance of the\\n\\nEquityComp program, and through the Binder, Minnieland requested that Applied\\n\\nUnderwriters, Inc. “through its affiliates and/or subsidiaries . . . cause to be issued”\\n\\nworkers’ compensation insurance coverage to Minnieland. J.A. 40. The RPA also\\n\\ndiscusses the insurance coverage; it notes that workers’ compensation insurance coverage\\n\\n 16\\n\\f“will be provided” to Minnieland by “one or more of the Issuing Insurers,” defined as\\n\\naffiliates of Applied Underwriters, Inc. J.A. 30–31. The RPA establishes Minnieland’s\\n\\nparticipation in a segregated cell to be funded in part by “a portion of the premium and\\n\\nlosses” under the RPA. J.A. 30. The premium and losses are calculated pursuant to the\\n\\nRPA’s Schedule 1. Id. And Schedule 1 “applies . . . to all payroll, premium, and losses\\n\\noccurring under the [CNI workers’ compensation insurance] Policies.” J.A. 36.\\n\\n The documents also internally reference each other and set forth each other’s\\n\\nterms. The Binder formally requests the issuance of workers’ compensation insurance\\n\\ncoverage subject to Minnieland’s execution of the RPA. The RPA references the\\n\\nworkers’ compensation policies explicitly, and Minnieland was required to execute the\\n\\nRPA before those policies would issue. Schedule 1 of the RPA establishes the manner in\\n\\nwhich Minnieland’s fees for the EquityComp program as a whole would be calculated.\\n\\nThat is, Schedule 1 applies to all premiums and losses under the actual insurance policies.\\n\\nIn fact, the billing statements for Minnieland’s participation in the EquityComp program\\n\\nshow that Minnieland was charged a single “pay-in amount” each month for the\\n\\n“Workers’ Compensation Program.” J.A. 45, 47, 49 (emphasis added). The RPA also\\n\\nwaives Minnieland’s right to choose deductibles for its workers’ compensation insurance\\n\\npolicies, and the Binder acknowledges that waiver. See J.A. 31 (§ 5), 40.\\n\\n The RPA and insurance policies are linked in other ways as well. The RPA\\n\\nprovides that its early cancellation terms apply if any one of the insurance policies is\\n\\ncancelled prior to the end of the RPA’s three-year term. J.A. 31 (§ 4). The RPA also\\n\\nprovides that Minnieland and AUCRA’s obligations under the RPA survive the active\\n\\n 17\\n\\fterm of the RPA “and shall be extinguished only when [AUCRA] no longer has any\\n\\npotential or actual liability to the Issuing Insurers with respect to the [workers’\\n\\ncompensation insurance] Policies.” J.A. 31 (§ 7). The RPA additionally provides that, in\\n\\nthe event Minnieland defaults under the RPA “or under any other agreement with any\\n\\naffiliates of [AUCRA] (Affiliated Agreements),” AUCRA “may take all reasonable steps\\n\\nto protect its and its affiliates’ interests.” J.A. 31 (§ 9). The RPA goes on to state that\\n\\n“[t]he parties hereto shall have the right . . . to offset or recoup any balances due from one\\n\\nto the other under [the RPA] or any Affiliated Agreements.” Id. Those Affiliated\\n\\nAgreements would include the insurance policies issued by CNI, an AUCRA affiliate.\\n\\nThe RPA also sets forth the terms that apply if CNI were required to provide workers’\\n\\ncompensation insurance coverage outside of the active term of the RPA. J.A. 31 (§ 4).\\n\\n These explicit internal references, interrelated terms, and shared subject matter are\\n\\nstrong evidence that the parties intended these documents to be part of one integrated\\n\\ntransaction. See Countryside Orthopaedics, 541 S.E.2d at 285; Musselman, 533 S.E.2d at\\n\\n921.\\n\\n To be sure, the documents were not executed by the same parties. The Binder was\\n\\nsigned by Minnieland as an acceptance of the EquityComp program proposal apparently\\n\\ndrafted by ARS, a subsidiary of Applied Underwriters, Inc., to whom the EquityComp\\n\\ntrademark is registered. See J.A. 23 (defining “we” as Applied Risk Services). The RPA\\n\\nwas executed between Minnieland and AUCRA, another subsidiary of Applied\\n\\nUnderwriters, Inc. J.A. 30. And the insurance policies were produced by Applied Risk\\n\\n\\n\\n 18\\n\\fServices, Inc., another subsidiary of Applied Underwriters, Inc., with CNI, yet another\\n\\nApplied Underwriters, Inc. subsidiary, as the insuring entity. J.A. 42–44.\\n\\n Nonetheless, the EquityComp program is promoted and sold as “[o]ne unified\\n\\nprogram for your business needs across all states” provided by Applied Underwriters,\\n\\nInc., “a premier financial services group of companies with leading experience in the\\n\\ncasualty insurance, reinsurance and business services disciplines.” J.A. 24–25 (emphases\\n\\nadded). The EquityComp program is marketed as being “effected through a separate\\n\\nreinsurance transaction issued in conjunction with a fully insured, guaranteed cost,\\n\\nworkers’ compensation policy.” J.A. 24. In fact, the Producer’s Quote Transmittal sent\\n\\nto the agent who brokered this deal for Minnieland expressly stated that the program\\n\\nproposed to Minnieland was “valid only if presented prior to expiration, in its original\\n\\nform, and in its entirety without modification.” J.A. 29 (emphasis added). And the\\n\\nBinder makes clear that insurance coverage was conditioned on execution of the RPA.\\n\\nTherefore, absent execution of the RPA, the insurance coverage would not have been\\n\\noffered as proposed. See Nat’l Convention Servs., LLC v. Applied Underwriters Captive\\n\\nRisk Assurance Co., Inc., 239 F. Supp. 3d 761, 786 (S.D.N.Y. 2017) (examining the\\n\\nworkers’ compensation insurance program offered by AUCRA and its affiliates and\\n\\nnoting that the RPA “would serve no purpose” without the approved guaranteed cost\\n\\ninsurance policies and that “it is plausible that the two can be treated as one\\n\\nundertaking”); see also Parr, 604 S.E.2d at 435 (finding integrated contract where one\\n\\ncontract’s terms could not be performed in the absence of other contracts).\\n\\n\\n\\n 19\\n\\f Additionally, the RPA contemplates that its terms will apply to AUCRA’s\\n\\naffiliates. The RPA provides that “[n]othing in this Agreement, expressed or implied, is\\n\\nintended to confer upon any party, other than the parties hereto and their affiliates,\\n\\nsuccessors and assigns, any rights, remedies, obligations or liabilities under or by reason\\n\\nof this Agreement, except as expressly provided herein.” J.A. 35 (§ 19) (emphasis\\n\\nadded). The RPA also provides that “[a]ll existing obligations from each party to the\\n\\nother or to third parties shall remain in force as of the expiration of the Active Term until\\n\\nthis Agreement is terminated.” J.A. 31 (§ 4) (emphasis added). These provisions further\\n\\nsuggest that Minnieland and AUCRA intended the RPA to be part of an integrated\\n\\ntransaction with AUCRA’s affiliates. See Countryside Orthopaedics, 541 S.E.2d at 284.\\n\\n During oral argument, counsel for AUCRA highlighted that, despite the RPA’s\\n\\nSchedule 1, the RPA does not charge “premiums”; it merely explains what happens to the\\n\\npremiums that are paid under the policies. This, however, does not render the RPA a\\n\\nstandalone contract. Instead, it lends support to Minnieland’s argument that the RPA and\\n\\nthe CNI policies must be read as one integrated contract. The policies set forth an\\n\\nestimated annual premium that is not subject to the RPA’s Schedule 1 calculations. J.A.\\n\\n42–44. The policies also contain a Short Rate Cancelation Policyholder Notice that\\n\\nexplains how the final premium will be calculated if the policies are cancelled by\\n\\nMinnieland. J.A. 761–63. The RPA’s Schedule 1, on the other hand, purports to\\n\\nestablish the total fee to be paid by Minnieland for the EquityComp program as well as\\n\\nany early cancellation fee that may be due. J.A. 36–37.\\n\\n\\n\\n 20\\n\\f Schedule 1’s calculations, however, incorporate the provisions of the CNI policies.\\n\\nSchedule 1 states that it “applies as of the Effective Date [January 15, 2013] to all\\n\\npayroll, premium, and losses occurring under the Policies.” J.A. 36. Schedule 1 explains\\n\\nthat “[a]n amount equal to the premium earned under the Policies in excess of the Loss\\n\\nPick Containment Amount multiplied by the applicable Exposure Group Adjustment\\n\\nFactor multiplied by the Allocation Factor listed in Table B, will be allocated to the\\n\\nParticipant’s cell.” J.A. 36 (§ 2). Thus, although Minnieland was billed one monthly fee\\n\\nfor the EquityComp program, the premium amount set forth in the policies was part of\\n\\nthat monthly fee and was included in calculating the total amount that would be due\\n\\nunder the program as a whole. Absent the CNI policies, the calculations in Schedule 1—\\n\\nincluding the amount to be allocated to Minnieland’s segregated cell—would be\\n\\nimpossible to make.\\n\\n The early cancellation provision of the RPA also depends on the cancellation\\n\\nprovisions of the CNI policies. The RPA’s early cancellation provision applies if either\\n\\nMinnieland cancels the RPA or if any of the insurance policies are “cancelled or non-\\n\\nrenewed prior to the end of the Active Term” of the RPA. J.A. 31 (§ 4). That\\n\\ncancellation policy, described in Schedule 1, states that certain of the factors used to\\n\\ncalculate premiums and losses will be increased in the event of early cancellation and that\\n\\nMinnieland will be required to pay, among other things, “any remaining premium,\\n\\nincluding short rate penalties, due under the Policies.” J.A. 37 (§ 6) (emphasis added).\\n\\nThose “short rate penalties” are the early termination provisions of the insurance policies.\\n\\nSee, e.g., J.A. 761 (“Short Rate Cancelation Policyholder Notice”). And the short rate\\n\\n 21\\n\\fpenalties apply when the policy is cancelled by Minnieland. Id. Therefore, when the\\n\\nshort rate cancellation provisions of the policies apply, they are another integer of the\\n\\nformula used under the RPA to calculate the total amount due under the EquityComp\\n\\nprogram. In the absence of the CNI policy terms, the RPA’s Schedule 1 calculations and\\n\\nearly cancellation provisions make no sense. See Musselman, 533 S.E.2d at 921.\\n\\n We do not ignore that Minnieland chose to sue only AUCRA and to base its\\n\\nclaims only on the RPA. However, because the RPA was but one component of an\\n\\nintegrated insurance sale, we must examine the related documents and the relationship\\n\\nbetween the affiliated entities. Daugherty, 385 S.E.2d at 574. In the absence of the CNI\\n\\npolicies, the RPA would have been pointless and nonsensical; and in the absence of the\\n\\nRPA, there would have been no insurance coverage. Nothing in the record suggests that\\n\\nMinnieland could have simply paid the premiums listed in the CNI policies, without\\n\\npaying the amounts set forth in the RPA’s Schedule 1, and maintained its workers’\\n\\ncompensation coverage; the RPA expressly provides for the opposite result. Because the\\n\\nEquityComp program was marketed and sold as a package deal, Minnieland’s failure to\\n\\nexecute the RPA would have frustrated the purpose of the transaction. See Parr, 604\\n\\nS.E.2d at 435.\\n\\n In sum, the documents, considered together, show that the purpose of the Binder,\\n\\nRPA, and CNI policies was one: to provide Minnieland with workers’ compensation\\n\\ninsurance coverage while allowing Minnieland the opportunity to keep its insurance costs\\n\\nlow by sharing in the underwriting risk. We need not determine specifically whether the\\n\\nRPA constitutes a policy endorsement or rider. Regardless of the label that may attach,\\n\\n 22\\n\\fthe RPA and insurance policies constitute an integrated transaction and must be read as\\n\\none contract.\\n\\n C.\\n\\n Having determined the scope of the contract at issue, we must now decide whether\\n\\nthe integrated contract is a contract of insurance under Virginia Code § 38.2–312. The\\n\\nVirginia Code does not define “insurance contract.” It does define “insurance,” however,\\n\\nas “the business of transferring risk by contract wherein a person, for a consideration,\\n\\nundertakes (i) to indemnify another person, (ii) to pay or provide a specified or\\n\\nascertainable amount of money, or (iii) to provide a benefit or service upon the\\n\\noccurrence of a determinable risk contingency.” Va. Code § 38.2–100. The Code also\\n\\nlists the required terms of “[e]ach insurance policy or contract”:\\n\\n 1. The names of the parties to the contract;\\n\\n 2. The subject of the insurance;\\n\\n 3. The risks insured against;\\n\\n 4. The time the insurance takes effect and, except in the case\\n of group insurance, title insurance, and insurance written\\n under perpetual policies, the period during which the\\n insurance is to continue;\\n\\n 5. A statement of the premium, except in the case of group\\n insurance and title insurance; and\\n\\n 6. The conditions pertaining to the insurance.\\n\\nVa. Code § 38.2–305. 5\\n\\n\\n 5\\n Minnieland cites to Virginia common law for the essential terms of an insurance\\ncontract. See Resp. Br. 20–21; Grp. Hospitalization Med. Serv., Inc. v. Smith, 372 S.E.2d\\n(Continued)\\n 23\\n\\f Neither party argues that the terms of the CNI policies themselves fail to meet the\\n\\nstatutory requirements for insurance contracts. In fact, AUCRA acknowledges that the\\n\\nCNI policies meet Virginia’s requirements. Opening Br. 7 n.3. Construing the CNI\\n\\npolicy terms as integrated with those of the RPA, as though the terms of each were\\n\\nwritten in a single document, Countryside Orthopaedics, 541 S.E.2d at 284, it becomes\\n\\nclear that the contract at issue is an “insurance contract” under Virginia law.\\n\\nAccordingly, the district court properly determined that the RPA is an insurance contract\\n\\nfor the purposes of Virginia Code § 38.2–312.\\n\\n D.\\n\\n We note, as Minnieland does, that we are not the first to determine that the\\n\\nprogram marketed by Applied Underwriters, Inc. is insurance. In fact, several state\\n\\ninsurance commissioners have determined that the EquityComp program and its sister\\n\\nprogram, SolutionOne, are not only subject to insurance regulations, but also violate\\n\\nthose regulations. For example, the Vermont Department of Financial Regulation has\\n\\nbarred Applied Underwriters, Inc. from selling the RPA in conjunction with guaranteed\\n\\n\\n159, 160 (Va. 1988) (listing “essential terms” of insurance contract as: “(1) the subject\\nmatter to be insured; (2) the risk insured against; (3) the commencement and period of the\\nrisk undertaken by the insurer; (4) the amount of insurance; and (5) the premium and time\\nat which it is to be paid” (citation omitted)). AUCRA argues that, since the addition of\\nthe definition of “insurance” to the Virginia Code in 2001, this common law definition is\\nno longer controlling. Opening Br. 32–33. The Virginia Supreme Court has not applied\\nthe common-law definition in connection with the statutory definition of “insurance.”\\nHowever, the common-law elements are essentially the same as the statutory\\nrequirements for every insurance policy. Therefore, an evaluation of the contract at issue\\nunder either the statutory factors or the common-law definition should yield the same\\nresult.\\n\\n 24\\n\\fcost insurance policies in Vermont after concluding that the RPA “de facto operated as a\\n\\nretrospective rating plan, replacing [CNI’s] guaranteed-cost workers’ compensation\\n\\ninsurance policy with an unfiled, unapproved retrospective rating plan.” J.A. 233.\\n\\nSimilarly, the Wisconsin Office of the Commissioner of Insurance entered into an\\n\\nagreement with ARS and CNI that they will “cease and desist from marketing, binding,\\n\\nissuing and renewing SolutionOne and EquityComp policies and any similarly designed\\n\\npolicies and programs that involve side agreements that affect the terms of the workers’\\n\\ncompensation policy, including but not limited to reinsurance agreements.” J.A. 375.\\n\\nThe California Insurance Commissioner likewise found that the EquityComp program\\n\\nand its RPA violate the California Insurance Code. See Decision and Order, In the\\n\\nMatter of the Appeal of Shasta Linen Supply, Inc., No. AHB-WCA-14-31 (Dep’t of Ins.,\\n\\nState of Cal. June 20, 2016), http://www.insurance.ca.gov/0250-insurers/0500-legal-\\n\\ninfo/0600-decision-ruling/0100-precedential/upload/ShastaLinenSupplyInc.pdf.\\n\\n Other courts faced with the RPA and similar related documents have also\\n\\nsuggested that the program marketed by Applied Underwriters, including the RPA, is\\n\\ninsurance. See, e.g., Nat’l Convention Servs., 239 F. Supp. 3d at 786 (observing that the\\n\\nRPA and guaranteed cost policies “plausibly serve the common purpose of providing\\n\\nworkers’ compensation insurance at rates that are affected by loss experience”); Nielsen\\n\\nContracting, Inc. v. Applied Underwriters, Inc., 22 Cal. App. 5th 1096, 1116–17 (Cal. Ct.\\n\\nApp. 2018) (determining that the RPA’s provisions were meant to replace those of the\\n\\ninsurance policies and that the Applied Underwriters affiliated entities were “so\\n\\nenmeshed” and “intertwined” that the RPA and insurance policies should be considered\\n\\n 25\\n\\ftogether); Citizens of Humanity, LLC v. Applied Underwriters Captive Risk Assurance\\n\\nCo., Inc., 909 N.W.2d 614, 632 (Neb.) (stating that “the RPA has the hallmarks of a\\n\\nretrospective rating plan” and concluding that the RPA is an “agreement concerning or\\n\\nrelating to an insurance policy” under Nebraska law), cert. denied, 139 S. Ct. 274 (2018).\\n\\n While each of these other jurisdictions has evaluated the RPA under different laws\\n\\nand for different purposes, the general consensus has consistently been that the RPA is\\n\\nsubject to insurance regulations. We join that consensus in holding that the RPA at issue\\n\\nhere is an insurance contract under Virginia law. Because arbitration provisions in\\n\\ninsurance contracts are void under Virginia law, Va. Code § 38.2–312, AUCRA must\\n\\nface Minnieland’s claims in court.\\n\\n\\n\\n IV.\\n\\n For these reasons, we affirm the judgment of the district court.\\n\\n\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 26\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":94,"cells":{"id":{"kind":"number","value":4581303,"string":"4,581,303"},"name":{"kind":"string","value":"APPALACHIAN VOICES; Chesapeake Climate Action Network; Sierra Club; Wild Virginia, Inc. ; Cowpasture River Preservation Association; Friends of Buckingham ; Highlanders for Responsible Development; Jackson River Preservation Association ; Potomac Riverkeeper, D/B/A Potomac Riverkeeper Network, Inc. ; Shenandoah Riverkeeper, a Program of Potomac Riverkeeper Network; Shenandoah Valley Battlefields Foundation ; Shenandoah Valley Network; Virginia Wilderness Committee, Petitioners, v. STATE WATER CONTROL BOARD ; David K. Paylor, Director, Virginia Department of Environmental Quality ; Robert Dunn, Chair of the State Water Control Board; Virginia Department of Environmental Quality ; Melanie D. Davenport, Director, Water Permitting Division, Virginia Department of Environmental Quality, Respondents, Atlantic Coast Pipeline LLC, Intervenor. Chesapeake Bay Foundation, Incorporated; Robert Whitescarver; Jeanne Hoffman, Petitioners, v. State Water Control Board ; Melanie D. Davenport, Director, Water Permitting Division, Virginia Department of Environmental Quality ; Robert Dunn, Chair of the State Water Control Board; Virginia Department of Environmental Quality ; David K. Paylor, Director, Virginia Department of Environmental Quality, Respondents, Atlantic Coast Pipeline LLC, Intervenor."},"name_abbreviation":{"kind":"string","value":"Appalachian Voices v. State Water Control Board"},"decision_date":{"kind":"string","value":"2019-01-14"},"docket_number":{"kind":"string","value":"18-1077; 18-1079"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Gregory, Wynn, Thacker\", \"parties\": \"\", \"opinions\": [{\"author\": \"Petition for review denied by published opinion. Chief Judge Gregory wrote the opinion\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1077\\n\\n\\nAPPALACHIAN VOICES; CHESAPEAKE CLIMATE ACTION NETWORK;\\nSIERRA CLUB; WILD VIRGINIA, INC.; COWPASTURE RIVER\\nPRESERVATION ASSOCIATION; FRIENDS OF BUCKINGHAM;\\nHIGHLANDERS FOR RESPONSIBLE DEVELOPMENT; JACKSON RIVER\\nPRESERVATION ASSOCIATION; POTOMAC RIVERKEEPER, d/b/a Potomac\\nRiverkeeper Network, Inc.; SHENANDOAH RIVERKEEPER, a program of\\nPotomac Riverkeeper Network; SHENANDOAH VALLEY BATTLEFIELDS\\nFOUNDATION; SHENANDOAH VALLEY NETWORK; VIRGINIA\\nWILDERNESS COMMITTEE,\\n\\n Petitioners,\\n\\n v.\\n\\nSTATE WATER CONTROL BOARD; DAVID K. PAYLOR, Director, Virginia\\nDepartment of Environmental Quality; ROBERT DUNN, Chair of the State Water\\nControl Board; VIRGINIA DEPARTMENT OF ENVIRONMENTAL QUALITY;\\nMELANIE D. DAVENPORT, Director, Water Permitting Division, Virginia\\nDepartment of Environmental Quality,\\n\\n Respondents,\\n\\nATLANTIC COAST PIPELINE LLC,\\n\\n Intervenor.\\n\\n\\n No. 18-1079\\n\\n\\nCHESAPEAKE BAY FOUNDATION, INCORPORATED; ROBERT WHITESCARVER;\\nJEANNE HOFFMAN,\\n\\n Petitioners,\\n\\f v.\\n\\nSTATE WATER CONTROL BOARD; MELANIE D. DAVENPORT, Director,\\nWater Permitting Division, Virginia Department of Environmental Quality;\\nROBERT DUNN, Chair of the State Water Control Board; VIRGINIA\\nDEPARTMENT OF ENVIRONMENTAL QUALITY; DAVID K. PAYLOR,\\nDirector, Virginia Department of Environmental Quality,\\n\\n Respondents,\\n\\nATLANTIC COAST PIPELINE LLC,\\n\\n Intervenor.\\n\\n\\nOn Petition for Review of an Order of the Federal Energy Regulatory Commission.\\n(17-002)\\n\\n\\nArgued: September 28, 2018 Decided: January 14, 2019\\n\\n\\nBefore GREGORY, Chief Judge, WYNN, and THACKER, Circuit Judges\\n\\n\\nPetition for review denied by published opinion. Chief Judge Gregory wrote the opinion,\\nin which Judge Wynn and Judge Thacker joined.\\n\\n\\nARGUED: Benjamin Alan Luckett, APPALACHIAN MOUNTAIN ADVOCATES,\\nLewisburg, West Virginia, for Petitioners. Toby Jay Heytens, OFFICE OF THE\\nATTORNEY GENERAL OF VIRGINIA, Richmond, Virginia, for\\nRespondents. Brooks Meredith Smith, TROUTMAN SANDERS LLP, Richmond,\\nVirginia, for Intervenor. ON BRIEF: Gregory Buppert, Charmayne G. Staloff,\\nJonathan M. Gendzier, SOUTHERN ENVIRONMENTAL LAW CENTER,\\nCharlottesville, Virginia, for Petitioners Cowpasture River Preservation Association,\\nFriends of Buckingham, Highlanders for Responsible Development, Jackson River\\nPreservation Association, Inc., Potomac Riverkeeper, Inc., Shenandoah Riverkeeper,\\nShenandoah Valley Battlefields Foundation, Shenandoah Valley Network, and Virginia\\nWilderness Committee. Joseph M. Lovett, APPALACHIAN MOUNTAIN\\nADVOCATES, Lewisburg, West Virginia, for Petitioners Appalachian Voices,\\nChesapeake Climate Action Network, Sierra Club, and Wild Virginia. Jon Alan Mueller,\\n\\n 2\\n\\fMargaret L. Sanner, Ariel Solaski, CHESAPEAKE BAY FOUNDATION, INC.,\\nAnnapolis, Maryland, for Petitioners Chesapeake Bay Foundation, Inc., Jeanne Hoffman,\\nand Robert Whitescarver. Mark R. Herring, Attorney General, Stephen A. Cobb,\\nDeputy Attorney General, Donald D. Anderson, Senior Assistant Attorney General,\\nJ. Duncan Pitchford, Assistant Attorney General, David C. Grandis, Assistant Attorney\\nGeneral, Matthew R. McGuire, Deputy Solicitor General, OFFICE OF THE\\nATTORNEY GENERAL OF VIRGINIA, Richmond, Virginia, for Respondents.\\nAndrea W. Wortzel, TROUTMAN SANDERS LLP, Richmond, Virginia, for Intervenor.\\n\\n\\n\\n\\n 3\\n\\fGREGORY, Chief Judge:\\n\\n Pursuant to Section 401 of the Clean Water Act (“CWA”), the Virginia State\\n\\nWater Control Board (“Board”) certified that it had reasonable assurance that activities\\n\\nrelated to the construction of a natural gas pipeline would not degrade the state’s water\\n\\nresources. Environmental groups and their individual members disagreed with this\\n\\ncertification, and they petitioned this Court to review the Board’s decision. Because we\\n\\nconclude that the Board’s Section 401 Certification for upland areas was not arbitrary and\\n\\ncapricious, we deny the petition for review.\\n\\n\\n\\n I.\\n\\n The Atlantic Coast Pipeline (“ACP”), a project developed and overseen by\\n\\nAtlantic Coast Pipeline LLC (“Atlantic”), is a proposed interstate natural gas pipeline,\\n\\nconstructed by Atlantic, that will be approximately 604 miles long and 42 inches in\\n\\ndiameter and will carry natural gas from Harrison County, West Virginia, to the eastern\\n\\nportions of Virginia and North Carolina. Approximately 307 miles of the ACP would\\n\\ntraverse the Commonwealth of Virginia. There are a total of 890 water body crossings\\n\\nlocations in Virginia, and the route of the ACP encompasses 74 migratory fish spawning\\n\\nwaters or their tributaries. The proposed ACP access roads will intersect 89 Virginia\\n\\nrivers and streams and will require the clearing of thousands of acres in Virginia. To\\n\\nobtain approval for construction, Atlantic had to comply with the following federal and\\n\\nstate laws and regulations relevant to this appeal.\\n\\n\\n\\n 4\\n\\f II.\\n\\n As an initial matter, Atlantic had to comply with the Natural Gas Act (“NGA”).\\n\\nUnder the NGA, a party is required to obtain authorization from the Federal Energy\\n\\nRegulatory Commission (“FERC”) in the form of a certificate of public convenience and\\n\\nnecessity to build or operate a natural gas pipeline. Upon receipt of an application for\\n\\nsuch a certificate, FERC undertakes a review of the environmental impacts of the\\n\\nproposed project under the National Environmental Policy Act (“NEPA”) and the NGA.\\n\\n42 U.S.C. §§ 4321 et seq.; 15 U.S.C. §§ 717 et seq. FERC accepts input from the public\\n\\nand then produces an environmental impact statement (“EIS”). Functioning as a “lead\\n\\nagency,” FERC coordinates the required authorizations, including Virginia’s water\\n\\nquality certification under the CWA. See 15 U.S.C. § 717n(b).\\n\\n Because the pipeline project involves the discharge of fill and dredged materials\\n\\ninto waterways and wetlands, Atlantic needed to obtain not only a certificate of public\\n\\nconvenience and necessity from FERC, but also a Section 404 CWA authorization from\\n\\nthe U.S. Army Corps of Engineers (“Army Corps”). See 33 U.S.C. § 1344(a); AES\\n\\nSparrows Point LNG, LLC v. Wilson, 589 F.3d 721, 724 (4th Cir. 2009). The Army\\n\\nCorps provided the authorization necessary for the ACP through issuing Nationwide\\n\\nPermit 12, which covers “activities required for the construction, maintenance, repair,\\n\\nand removal of utilities lines and associated facilities in waters of the United States.” See\\n\\n33 U.S.C. 1344(e)(1) (allowing the Secretary of the Army to issue permits on a\\n\\n“nationwide basis for any category of activities involving discharges of dredged or fill\\n\\nmaterial if the Secretary determines that the activities in such category are similar in\\n\\n 5\\n\\fnature, will cause only minimal adverse environmental effects when performed\\n\\nseparately, and will have only minimal cumulative adverse effect on the environment”).\\n\\n\\n\\n III.\\n\\n Atlantic was also required to obtain a Section 401 Certification. The NGA allows\\n\\nstates to regulate the environmental impacts of pipelines under the CWA. Delaware\\n\\nRiverkeeper Network v. Secretary Pa. Dep’t of Envtl. Prot., 833 F.3d 360, 368 (3d Cir.\\n\\n2016) (citing 15 U.S.C. § 717b(d)). Virginia exercises this regulatory authority through\\n\\nthe Board. See Va. Code § 62.1-44.15. Pursuant to Virginia law, the Board wields broad\\n\\npowers regarding regulatory matters impacting water quality in Virginia, and Section 401\\n\\nCertifications fall under its authority. Id. The Virginia Department of Environmental\\n\\nQuality (“DEQ”) serves as the Board’s staff, and the Board may assign DEQ tasks and\\n\\ndelegate DEQ the authority to make decisions. See Va. Code Ann. § 62.1-44.14. We\\n\\nwill refer to the Board and DEQ together as “the State Agencies” when their actions are\\n\\nin concert.\\n\\n Under the Virginia Water Protection (“VWP”) Program, the Board, after soliciting\\n\\nand considering public comment and consulting with relevant agencies, may issue a\\n\\nVWP permit “if it has determined that the proposed activity is consistent with the\\n\\nprovisions of the Clean Water Act and the State Water Control Law and will protect in-\\n\\nstream beneficial uses.” Va. Code Ann. § 62.1-44.15:20(B). The Board may also certify\\n\\na nationwide Corps permit, such as Nationwide Permit 12, as meeting these requirements\\n\\nso long as the permit meets specified criteria. See 9 Va. Admin. Code 25-210-130(H).\\n\\n 6\\n\\fSpecifically, Section 401 states “[a]ny applicant for a Federal license or permit to conduct\\n\\nany activity . . . which may result in any discharge into the navigable waters” must seek\\n\\n“a certification from the State in which the discharge originates . . . that any such\\n\\ndischarge will comply with the applicable provisions” of the CWA. 33 U.S.C.\\n\\n§ 1341(a)(1). In addition, Section 401 states, “[n]o license or permit shall be granted if\\n\\ncertification has been denied by the State.” Id. If the state grants the Section 401\\n\\nCertification — whether with or without conditions — it must contain “[a] statement that\\n\\nthere is a reasonable assurance that the activity will be conducted in a manner which will\\n\\nnot violate applicable water quality standards.” 40 C.F.R. § 121.2(a)(3); see PUD No. 1\\n\\nof Jefferson Cty. v. Washington Dep’t of Ecology, 511 U.S. 700, 712 (1994). In addition,\\n\\nthe regulations allow for Virginia to consider activities that impact the upland areas that\\n\\nmay have the potential to affect water quality but do not fall under the scope of a VWP\\n\\npermit when the pipeline is over 36 inches inside diameter. Va. Code § 62.1-44.15:80.\\n\\n\\n\\n IV.\\n\\n Atlantic applied for the certificate of public convenience and necessity from FERC\\n\\nand Section 404 authorization from the Army Corps in September 2015. Atlantic filed an\\n\\namendment to its FERC certificate application in March 2016. In October 2017, FERC\\n\\nissued the certificate to Atlantic to construct and operate the pipeline. On April 7, 2017,\\n\\nthe DEQ issued a Section 401 Certification for the wetland, river, and streams crossings\\n\\nas covered in the Section 404 Nationwide Permit 12. In May 2017, the DEQ explained\\n\\nthat the Section 401 Certification for the Pipeline would entail two separate parts: (1) the\\n\\n 7\\n\\fcertification for the Army Corps Nationwide Permit 12, issued in April, applying to the\\n\\nPipeline’s wetland, river, and streams crossings (the “Wetlands and Streams\\n\\nCertification”), and (2) an additional Section 401 Certification review process to evaluate\\n\\nthe “upland” impacts of the Pipeline, terrestrial areas that are not covered by the Army\\n\\nCorps Permit (the “Upland Certification”). Specifically, the Upland Certification would\\n\\n“include all proposed upland activities associated with the construction, operation,\\n\\nmaintenance, and repair of the pipeline, any components thereof or appurtenances\\n\\nthereto, and related access roads and rights-of-way as well as certain project related\\n\\nsurface water withdrawals.” J.A 1083.\\n\\n On November 9, 2017, the DEQ recommended that the Board approve a Section\\n\\n401 Upland Certification of the project. On December 20, 2017, the Board issued the\\n\\nUpland Certification for the ACP with conditions. This Certification was distinct from\\n\\nthe Wetlands and Steams Certification. This Upland Certification provided that it “shall\\n\\nbe effective only following submission, review and final approval as required by law of\\n\\nthe Karst Mitigation Plan, Annual Standards and Specifications, and Erosion and\\n\\nSediment Control Plans and Storm Water Management Plans, and a report to the Board\\n\\nand the public by DEQ on the adequacy of these materials.” J.A. 29.\\n\\n Petitioners timely filed two petitions for review of the Certification on January 18,\\n\\n2018. The petitions were consolidated by court order on January 31, 2018. We possess\\n\\njurisdiction to review the Board’s Section 401 Upland Certification pursuant to 15 U.S.C.\\n\\n§ 717r(d)(1).\\n\\n\\n\\n 8\\n\\f The petitioners contend the Board’s issuance of the Section 401 Upland\\n\\nCertification was arbitrary and capricious and should be vacated for four reasons: (1) the\\n\\nState Agencies effectively invalidated their own finding of reasonable assurance when it\\n\\nvoted to reopen the comment period on the Section 401 Certification of the Army Corps\\n\\nof Engineers Nationwide Permit 12; (2) the State Agencies arbitrarily and capriciously\\n\\nfailed to assess the combined impacts on water quality that would result from multiple\\n\\nareas of construction activities within individual watershed areas; (3) the State Agencies\\n\\narbitrarily and capriciously failed to conduct an adequate antidegradation review; and (4)\\n\\nthe State Agencies arbitrarily and capriciously failed to ensure that the water quality in\\n\\nkarst geology regions would be protected. Respondents and intervenor in turn deny that\\n\\nthe State Agencies acted arbitrarily and capriciously and argue that the petitioners lack\\n\\nstanding to bring this petition.\\n\\n On April 12, 2018, the Board approved a second 30-day public comment period\\n\\nrelated to the Wetlands and Steams Certification. On August 21, 2018, the Board heard a\\n\\npresentation from the DEQ summarizing the public comment period and denied a motion\\n\\nto reevaluate this contested Certification.\\n\\n\\n\\n V.\\n\\n The respondents and intervenor argue as an initial matter that petitioners do not\\n\\nhave standing to litigate this petition for review. Spokeo, Inc. v. Robins, 136 S. Ct. 1540,\\n\\n1547 (2016) (quoting Lujan v. Defenders of Wildlife, 504 U.S. 555, 560-61 (1992))\\n\\n(Article III standing requires (1) an injury-in-fact (2) that is fairly traceable to the\\n\\n 9\\n\\fchallenged conduct of the defendant, and (3) that is likely to be redressed through a\\n\\nfavorable judicial decision). We disagree.\\n\\n This Court has previously rejected respondents’ and intervenor’s arguments on\\n\\nstanding. Sierra Club v. State Water Control Bd., 898 F.3d 383, 400-02 (4th Cir. 2018).\\n\\nPetitioners have established an injury-in-fact even though the State Agencies could\\n\\nchoose to waive certification. We have previously held that the denial of an opportunity,\\n\\nin this case, to have the project vetoed or have additional restrictions can constitute an\\n\\ninjury-in-fact. Id. at 401. In addition, petitioners successfully establish traceability and\\n\\nredressability given that we could vacate the Board’s decision and determine that its\\n\\ndecision was not based on a reasonable assurance and instead was arbitrary and\\n\\ncapricious. Petitioners’ injuries could be remedied if the Board required Atlantic to take\\n\\nadditional measures that would address petitioners’ grievances. In our previous decision\\n\\nwe held petitioners established traceability and redressability in this very context. Id.\\n\\nPetitioners have demonstrated the requirements for standing.\\n\\n\\n\\n VI.\\n\\n We review Virginia’s Section 401 Certification under the standards set forth in the\\n\\nAdministrative Procedures Act (“APA”). See AES Sparrows Point LNG, LLC v. Wilson,\\n\\n589 F.3d 721, 727 (4th Cir. 2009). 1 This Court applies the arbitrary and capricious\\n\\n\\n 1\\n Asserting that the APA is not applicable to actions by State Agencies,\\nrespondents argue that Va. Code § 2.2-4027 establishes the applicable standard of review.\\nThat statute provides that issues of fact shall be decided based on “whether there was\\n(Continued)\\n 10\\n\\fstandard of the APA to the State Agencies’ challenged findings and conclusions. Sierra\\n\\nClub, 898 F.3d at 403.\\n\\n To survive review under the arbitrary and capricious standard, an agency decision\\n\\nmust show that the agency examined “the relevant data and articulate[d] a satisfactory\\n\\nexplanation for its action including a ‘rational connection between the facts found and the\\n\\nchoice made.’” Motor Vehicle Mfrs. Ass’n of U.S., Inc. v. State Farm Mut. Auto Ins. Co.,\\n\\n463 U.S. 29, 43 (1983) (quoting Burlington Truck Lines v. United States, 371 U.S. 156,\\n\\n168 (1962)).\\n\\n Agency action is arbitrary and capricious if the agency relies on factors that\\n Congress did not intend for it to consider, entirely ignores important aspects\\n of the problem, explains its decision in a manner contrary to the evidence\\n before it, or reaches a decision that is so implausible that it cannot be\\n ascribed to a difference in view.\\n\\nBedford Cty. Mem’l Hosp. v. Health & Human Servs., 769 F.2d 1017, 1022 (4th Cir.\\n\\n1985) (citing Motor Vehicle Mfrs. Ass’n, 463 U.S. at 43). This Circuit has held that\\n\\n [r]eview under this standard is highly deferential, with a presumption in\\n favor of finding the agency action valid. Especially in matters involving\\n not just simple findings of fact but complex predictions based on special\\n expertise, a reviewing court must generally be at its most deferential. In\\n determining whether agency action was arbitrary or capricious, the court\\n must consider whether the agency considered the relevant factors and\\n whether a clear error of judgment was made. Although this inquiry into the\\n facts is to be searching and careful, the ultimate standard of review is a\\n narrow one. The court is not empowered to substitute its judgment for that\\n of the agency. Deference is due where the agency has examined the\\n\\n\\n\\n\\nsubstantial evidence in the agency record to support the agency decision.” As we did in\\nSierra Club, we decline to resolve this issue because petitioners’ claims fail even under\\nthe substantial evidence standard. 898 F.3d at 403 n.13.\\n\\n 11\\n\\f relevant data and provided an explanation of its decision that includes a\\n rational connection between the facts found and the choice made.\\n\\nOhio Valley Envtl. Coal. v. Aracoma Coal Co., 556 F.3d 177, 192 (4th Cir. 2009)\\n\\n(internal quotation marks and citations omitted). Nonetheless, if a state agency’s Section\\n\\n401 certification is found to be arbitrary and capricious, the Court must vacate the\\n\\ncertification. 5 U.S.C. § 706(2)(A).\\n\\n\\n\\n VII.\\n\\n A.\\n\\n Turning to petitioners’ first argument, we hold that the decision to reopen the\\n\\ncomment period did not render the State Agencies’ Section 401 Upland Certification\\n\\narbitrary and capricious. The comment period was re-opened for the Wetlands and\\n\\nStreams Certification and not the Upland Certification at issue in this case. In any event,\\n\\nthe Wetlands and Streams Certification was not ultimately revoked.\\n\\n B.\\n\\n Moving to the petitioners’ second argument, we conclude that the State Agencies’\\n\\ndecision not to conduct a combined effect analysis does not render their issuance of a\\n\\nSection 401 Upland Certification arbitrary and capricious for three reasons.\\n\\n First, the Section 401 Upland Certification in question deals with project-related\\n\\nactivities taking place in upland areas. The Upland Certification supplemented the FERC\\n\\ncertificate and the prior Wetland and Streams Certification of the Army Corps’\\n\\nNationwide Permit 12 regarding waterways and utility line crossings. As the State\\n\\n\\n 12\\n\\fAgencies explained, “the conditions in the proposed additional 401 Certification are in\\n\\naddition to any other Federal or State permit or regulatory requirements including the\\n\\nexpressed conditions imposed by FERC.” J.A. 1059. The Upland Certification in\\n\\nquestion is not designed to function as a stand-alone document, comprehensively\\n\\ncovering all pieces of relevant data and potentialities. For example, record evidence\\n\\navailable to the State Agencies explains, “while the impacts to jurisdictional waters\\n\\nauthorized by the Corps under Section 404 of the Clean Water Act are separate from\\n\\nupland activities that are the subject of this Certification, the Corps also analyzed the\\n\\ncumulative effects of linear utility projects and found that the individual and cumulative\\n\\nadverse effects on the aquatic environment resulting from the activities authorized by the\\n\\nNationwide Permit 12 will be no more than minimal and each crossing is a single and\\n\\ncomplete project.” J.A. 999. The Army Corps examined cumulative impacts, and it\\n\\nwould be redundant and inefficient for the State Agencies to duplicate these efforts. The\\n\\nUpland Certification works in conjunction with other regulatory tools and cannot be\\n\\njudged in a void, and it supplements other pieces of the regulatory framework. It is not\\n\\nrequired to cover combined effect analysis because other parts of the regulatory process\\n\\nsufficiently address that subject matter. The State Agencies in the current appeal used\\n\\ntheir resources to issue the Upland Certification to fill an information gap regarding the\\n\\nimpact of upland activities, which were not typically covered under prior CWA\\n\\ncertifications. The State Agencies properly made a unique contribution instead of\\n\\nduplicating the efforts of other regulatory bodies as petitioners’ request. See Sierra Club,\\n\\n898 F.3d at 407.\\n\\n 13\\n\\f Second, State Agencies have broad discretion when developing the criteria for\\n\\ntheir Section 401 Certification. The only requirement imposed by the regulations is that\\n\\nStates must establish procedures for public notice when there are applications for\\n\\ncertification, and to the extent deemed appropriate, procedures for public hearings in\\n\\nconnection with specific applications. 33 U.S.C. § 1341(a)(1). Nonetheless, nothing in\\n\\nSection 401 restricts states to a single certificate proceeding, and Section 401 does not\\n\\nrequire states to undertake a single cumulative review of all possible impacts in a single\\n\\ncertification.\\n\\n Petitioners’ rely on two federal regulations in arguing that a cumulative review is\\n\\nrequired, 40 C.F.R. § 230.7(a) and 40 C.F.R. § 230.11(g)(1), but those regulations impose\\n\\nduties—including a duty to make factual determinations and consider cumulative\\n\\neffects—on the Army Corps under Section 404, not on states under Section 401.\\n\\nMoreover, petitioners contend that two cases require State Agencies to take into account\\n\\ncombined effects lest their decisions be rendered arbitrary and capricious. See Klamath-\\n\\nSiskiyou Wildlands Ctr. v. BLM, 387 F.3d 989, 993 (9th Cir. 2004); Idaho Rivers United\\n\\nv. Probert, Case No.: 3:16-102, 2016 U.S. Dist. LEXIS 63767, at *32-34. Furthermore,\\n\\npetitioners invoke the Supreme Court’s decision in Motor Vehicles Manufacturers\\n\\nAssociation v. State Farm Mutual Automobile Ins. Co., to argue that all “relevant data”\\n\\nmust be considered. 463 U.S. 29, 43 (1983). We conclude, however, that both the\\n\\nKlamath-Siskiyou Wildlands and Idaho Rivers United cases are distinguishable and\\n\\nunpersuasive because in those cases the Bureau of Land Management and the Forest\\n\\nService, respectively, faced violations under NEPA, not the CWA. Klamath-Siskiyou\\n\\n 14\\n\\fWildlands Ctr., 387 F.3d at 993–94; Idaho Rivers United, 2016 U.S. Dist. LEXIS 63767,\\n\\nat *33. Unlike the CWA, NEPA requires a cumulative effects analysis, and thus cases\\n\\ndecided under NEPA are not dispositive authority here. Furthermore, Motor Vehicle\\n\\nManufacturers Association, which deals with the National Highway Traffic Safety\\n\\nAdministration, does not mention cumulative effects or the CWA, and thus the case does\\n\\nnot stand for the proposition that the CWA should be broadened to encompass a\\n\\ncombined impact analysis.\\n\\n Finally, the State Agencies’ failure to explicitly consider the combined effects of\\n\\nmultiple areas of construction within individual watersheds such as the Chesapeake Bay\\n\\nwatershed and the Chesapeake Bay Total Maximum Daily Load (“Bay TMDL”) did not\\n\\nrender their decision arbitrary and capricious. 2 As an initial matter, despite petitioners’\\n\\npreferences, there are no express regulations that require the State Agencies to consider\\n\\nthe combined effects of individual watersheds. In addition, the Ninth Circuit has\\n\\nexplained that TMDLs like the Chesapeake Bay TMDL are “primarily informational\\n\\ntools that allow states to proceed from the identification of water requiring additional\\n\\nplanning to the required plans.” Pronsolino v. Nastri, 291 F. 3d 1123, 1129 (9th Cir.\\n\\n2002). Moreover, TMDLs do not give rise to an independent legal obligation.\\n\\nPronsolino, 291 F.3d 1123, 1140. Consequently, the Chesapeake TMDL does not\\n\\nconstitute a regulatory mandate that the State Agencies were required to address before\\n\\nissuing the Section 401 Upland Certification. Furthermore, protection measures for the\\n\\n 2\\n The Bay TMDL is a federal-state partnership that monitors the water quality\\nstandards in the Chesapeake Bay and its related tributaries. J.A. 888.\\n\\n 15\\n\\fChesapeake Bay TMDL are offered through other tools such as the FERC EIS and the\\n\\nStorm Water Prevention Plan. J.A. 664-665; 1138-1140.\\n\\n The State Agencies more than satisfied their obligations by reviewing upland\\n\\nactivities as well as stream and wetland crossings. The Board’s decisions are not\\n\\nrendered arbitrary and capricious because it did not conduct an independent review of the\\n\\ncumulative effects on water quality within individual watersheds, even if this was\\n\\npetitioners’ preference. To deem an agency action arbitrary and capricious their decision\\n\\nmust be “so implausible that it could not be ascribed to a difference in view or the\\n\\nproduct of agency expertise.” State Farm Mut. Auto. Ins. Co., 463 U.S. at 43. The lack\\n\\nof an explicit combined effect analysis in the Section 401 Upland Certification does not\\n\\nrise to this level, especially given that there are other regulatory tools that were utilized to\\n\\nconsider those impacts.\\n\\n C.\\n\\n 1.\\n\\n Turning to petitioners’ third argument, we do not find that the State Agencies’\\n\\nreasonable assurance determination to be arbitrary and capricious simply because they\\n\\nrelied on existing Virginia water quality standards and regulations to effectively address\\n\\nconcerns regarding water quality deterioration.\\n\\n Under the CWA, “states have the primary role in promulgating water quality\\n\\nstandards.” Piney Run Preservation Ass’n v. County Comm’rs of Carroll Cty., 268 F.3d\\n\\n255, 265 n.9 (4th Cir. 2001). States must initially classify the uses for which their water\\n\\nis to be protected and then determine the necessary level of water quality for their\\n\\n 16\\n\\fpreferred uses. See NRDC v. EPA, 16 F.3d 1395, 1400 (4th Cir. 1993). Virginia’s water-\\n\\nquality policy is relevant in two respects: its narrative water-quality criterion and its anti-\\n\\ndegradation policy.\\n\\n Virginia’s water-quality criterion mandates that “State waters . . . shall be free\\n\\nfrom substances attributable to . . . waste in concentrations, amounts, or combinations\\n\\nwhich contravene established standards or interfere directly or indirectly with designated\\n\\nuses of such water or which are inimical or harmful to human, animal, plant, or aquatic\\n\\nlife.” 9 Va. Admin. Code § 25-260-20(A). The regulation explains that any substance\\n\\n“that produce[s] . . . turbidity” is a substance to be controlled. Id. The regulation\\n\\nprovides examples of “turbidity” such as floating debris, oil, and other materials that are\\n\\nsuspended solids in a body of water.\\n\\n In addition, Virginia’s antidegradation policy shall be applied whenever any\\n\\nactivity is proposed that has the potential to affect existing surface water quality. 9 Va.\\n\\nAdmin. Code § 25-260-30(A). The antidegradation policy classifies Virginia’s water into\\n\\nthree tiers and provides differing levels of protection based on the water’s tier. See 9 Va.\\n\\nAdmin. Code § 25-260-30(A).\\n\\n The Policy defines Tier 3 waters as “exceptional”; these waters “shall be\\n\\nmaintained and protected to prevent permanent or long-term degradation or impairment.”\\n\\n9 Va. Admin. Code § 25-260-30(A)(3)(b)(1). The policy specifically provides that “[n]o\\n\\nnew, additional, or increased discharge of sewage, industrial wastes or other pollution\\n\\ninto [Tier 3 waters] shall be allowed.” 9 Va. Admin. Code § 25-260-30(A)(3)(b)(2).\\n\\nNonetheless, “[a]ctivities causing temporary sources of pollution may be allowed in [Tier\\n\\n 17\\n\\f3 waters] even if degradation may be expected to temporarily occur provided that after a\\n\\nminimal period of time the waters are returned or restored to conditions equal to or better\\n\\nthan those existing just prior to the temporary source of pollution.” 9 Va. Admin. Code\\n\\n§ 25-260-30(A)(3)(b)(3).\\n\\n The Policy defines Tier 2 waters as those that “exceed water quality standards.” 9\\n\\nVa. Admin. Code § 25-260-30(A)(2). The protection for these waters and their quality\\n\\nare lower and the regulation states that the quality of Tier 2 waters “shall be maintained\\n\\nand protected unless the board finds . . . that allowing lower water quality is necessary to\\n\\naccommodate important economic or social development in the area in which the waters\\n\\nare located.” 9 Va. Admin. Code § 25-260-30(A)(2).\\n\\n Last, Tier 1 waters constitute all Virginia waters that are not designated Tier 2 or\\n\\nTier 3. The regulation classifying the level of protection for these waters’ states,\\n\\n“existing in-stream water uses and the level of water quality necessary to protect the\\n\\nexisting uses shall be maintained and protected.” 9 Va. Admin. Code § 25-260-30(A)(1).\\n\\n In Virginia a project may be permitted under a Construction General Permit. 9\\n\\nVa. Admin. Code § 25-880-70 Part II. The Construction General Permit incorporates the\\n\\nrequirements of two other state laws, the Virginia Storm Water Management (“VSM”)\\n\\nLaw, Va. Code § 62.1-44.15:24 et seq., and the Virginia Erosion and Sediment Control\\n\\n(“VESC”) Law, Va. Code § 62.1-44.15:51, et seq.\\n\\n The CWA has an exemption for natural gas pipeline construction projects and\\n\\ntherefore Virginia’s regulatory scheme diverges from the federal environmental\\n\\nprotections. See 33 U.S.C. § 1342(I)(2). Consequently, Virginia still regulates natural\\n\\n 18\\n\\fgas pipeline projects through its Annual Standards and Specifications (“AS&S”)\\n\\nProgram. See Va. Code § 62.1-44.15:55(D). The AS&S program requires a project\\n\\ndeveloper to submit annual standards and specifications for DEQ’s review and approval.\\n\\nSee 9 Va. Admin. Code § 25-870-170(A). Through this program Virginia ensures that\\n\\nprojects will meet the same requirements imposed on other projects subject to the\\n\\nVirginia Construction General Permit. See 9 Va. Admin. Code § 25-870-170(A).\\n\\nNonetheless, once DEQ approves a developer’s annual standards and specifications as\\n\\nsatisfying the requirements of the VSM and VESC, the entity generally need not submit\\n\\nsite-specific VSM and VESC plans to DEQ for approval. See Va. Code § 62.1-\\n\\n44.15:55(D). This allows the projects to become more self-regulating.\\n\\n Typically, ensuring an activity’s compliance with water quality standards requires\\n\\nan antidegradation review. See Nat. Res. Def. Council, Inc. v. EPA, 16 F.3d 1395, 1400\\n\\n(4th Cir. 1993); see also 40 C.F.R. § 131.12 (requiring states to develop and adopt a\\n\\nstatewide antidegradation policy). The CWA’s antidegradation policy requires that state\\n\\nstandards be “sufficient to maintain existing beneficial uses of navigable waters,\\n\\npreventing further degradation.” 33 U.S.C. § 1313(d). State antidegradation policies\\n\\nmust be consistent with 40 C.F.R. § 131.12(a), and must protect existing uses, maintain\\n\\nthe existing quality of high-quality waters unless degradation is justified by important\\n\\nsocioeconomic development, and prohibit degradation of national resource waters. Id.\\n\\n§ 131.12(a).\\n\\n\\n\\n\\n 19\\n\\f 2.\\n\\n We do not find that the State Agencies’ failure to conduct a separate\\n\\nantidegradation review before issuing its Upland Certification renders their decision\\n\\narbitrary and capricious for two reasons.\\n\\n First, in Virginia, the AS&S program requires a project developer to submit annual\\n\\nstandards and specifications for DEQ’s review and approval, thereby ensuring that\\n\\nprojects will meet the same requirements that would apply were they covered by the\\n\\nVirginia Construction General Permit. See 9 Va. Admin. Code § 25-870-170(A). The\\n\\nAS&S also incorporate all the requirements of EPA’s Construction General Permit. J.A.\\n\\n1124-1125. The AS&S in this case were developed over eighteen months and represent a\\n\\nthorough process of development, revision and refinement to ensure that the ACP meet\\n\\nthe technical and legal requirements for Virginia. J.A. 1087. Both federal and state\\n\\nregulators have concluded that application of technical requirements like those in the\\n\\nAS&S “will not result in a lowering of water quality,” which renders the individualized\\n\\nreview the petitioners suggest “unnecessary.” J.A. 11. There is no indication that these\\n\\nAS&S fail to protect water quality in Virginia. To the contrary, these regulations have\\n\\nbeen found as a matter of law to protect water quality in Virginia. See Kelble v.\\n\\nCommonwealth, Case No. CL 14-762, at 4-5 (Richmond Cir. Ct. Apr. 10, 2017).\\n\\n Second, State Agencies did not have to conduct a separate antidegradation review\\n\\nbecause the impact on sediment on the water would only be temporary. Under FERC’s\\n\\nfinal EIS, it was determined that any water quality impacts stemming from construction\\n\\nwould be temporary. J.A. 623. Even with respect to Tier 3 waters, the policy states that\\n\\n 20\\n\\f“[a]ctivities causing temporary sources of pollution may be allowed in [Tier 3] waters . . .\\n\\neven if degradation may be expected to occur provided that after a minimal period of\\n\\ntime the waters are returned or restored to conditions equal to or better that those existing\\n\\njust prior to the temporary source of pollution.” 9 Va. Admin. Code 25-260-\\n\\n30A(3)(b)(3). Even in the most protected state waters, Virginia does not consider\\n\\ntemporary sources of pollution, such as the construction of the ACP, to violate\\n\\nantidegradation policies.\\n\\n Thus, nothing was arbitrary and capricious about the State Agencies’ decision not\\n\\nto conduct a separate antidegradation review.\\n\\n D.\\n\\n Turning to the final challenge raised by petitioners, we find that the State\\n\\nAgencies’ treatment of karst terrain was not arbitrary or capricious because of the\\n\\nconditions imposed on the Section 401 Upland Certification.\\n\\n Karst geology refers to geological formations of soluble limestone bedrock that\\n\\ncreates underground water flow systems where the rocks have dissolved and created\\n\\nsinkholes, caves and underground springs and rivers. J.A. 669. The constitution of these\\n\\nareas presents additional environmental considerations for pipeline construction\\n\\nincluding, sinkhole collapse, sinkhole flooding and associated groundwater\\n\\ncontamination. J.A. 904-905.\\n\\n The record demonstrates that the State Agencies took petitioners’ concerns\\n\\nregarding karst geology into consideration. J.A. 31. Virginia’s Section 401 Upland\\n\\nCertification contains five specific requirements concerning the protection of karst\\n\\n 21\\n\\fterrain. J.A. 31-32. First, Atlantic must provide the State an addendum to a 51-page\\n\\nKarst Survey Report prior to any land disturbing activities. J.A. 212-237; J.A. 31.\\n\\nSecond, Atlantic must follow the Karst Terrain Assessment, Construction, Monitoring,\\n\\nand Mitigation Plan. J.A. 31. This plan allows for route adjustments to avoid karst\\n\\nterrain. J.A. 1001. Third, based on the conditions in the Section 401 Upland\\n\\nCertification, Atlantic must conduct contingency planning in order to address any\\n\\naccidental spills or releases during construction on karst terrain. Fourth, water surveys\\n\\nregarding drinkable water in karst regions are required under the Section 401 Upland\\n\\nCertification. J.A. 31. Finally, Atlantic has a liability of five million dollars to cover the\\n\\ncost of any impacts to private water supplies, which encompasses karst regions. J.A. 32.\\n\\n Reliance on these conditions, even the prospective ones, does not render the State\\n\\nAgencies’ issuance of the Section 401 Upland Certification arbitrary and capricious. See\\n\\nPort of Seattle v. Pollution Control Hearings Bd., 90 P.3d 659, 677 (Wash. 2004)\\n\\n(holding regulators did not act arbitrarily or capriciously by basing reasonable assurance\\n\\n“on future submissions of revised plans, reports, and studies, so long as their\\n\\nimplementation and anticipated outcome meet the reasonable assurance test”).\\n\\n Moreover, the mere existence of risk to karst geology does not render the State\\n\\nAgencies’ decision to issue the Section 401 Upland Certification arbitrary and capricious.\\n\\nBased on the information in the record, this Court finds that the State Agencies had\\n\\nreasonable assurance that karst regions would be protected given the conditions imposed\\n\\non the Section 401 Upland Certification. We “see no purpose we would serve by\\n\\nstepping in and second-guessing the analytical methods Virginia deemed appropriate to\\n\\n 22\\n\\fprovide it with reasonable assurance that its water quality would be protected.” Sierra\\n\\nClub., 898 F.3d at 407.\\n\\n\\n\\n VIII.\\n\\n Governmental agencies can always take additional steps to increase the protection\\n\\nof the environment. But that is not the applicable legal standard this Court utilizes when\\n\\nreviewing a state agency’s issuance of a Section 401 Certification. We must determine\\n\\n“whether the agency considered the relevant factors and whether a clear error of\\n\\njudgment was made.” Ohio Valley Envtl. Coal., 556 F.3d 177, 192. There is no\\n\\nindication that the State Agencies did not consider relevant factors or that they clearly\\n\\nmade an error of judgment. In conclusion, because we find that the State Agencies did\\n\\nnot act arbitrarily and capriciously in issuing the Section 401 Upland Certification, we\\n\\ndeny the petition for review.\\n\\n\\n\\n PETITION FOR REVIEW DENIED\\n\\n\\n\\n\\n 23\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4358556/\", \"author_raw\": \"Petition for review denied by published opinion. Chief Judge Gregory wrote the opinion\"}]}"},"judge1":{"kind":"string","value":"GREGORY"},"judge2":{"kind":"string","value":"WYNN"},"judge3":{"kind":"string","value":"THACKER"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4581303/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: APPALACHIAN VOICES; Chesapeake Climate Action Network; Sierra Club; Wild Virginia, Inc. ; Cowpasture River Preservation Association; Friends of Buckingham ; Highlanders for Responsible Development; Jackson River Preservation Association ; Potomac Riverkeeper, D/B/A Potomac Riverkeeper Network, Inc. ; Shenandoah Riverkeeper, a Program of Potomac Riverkeeper Network; Shenandoah Valley Battlefields Foundation ; Shenandoah Valley Network; Virginia Wilderness Committee, Petitioners, v. STATE WATER CONTROL BOARD ; David K. Paylor, Director, Virginia Department of Environmental Quality ; Robert Dunn, Chair of the State Water Control Board; Virginia Department of Environmental Quality ; Melanie D. Davenport, Director, Water Permitting Division, Virginia Department of Environmental Quality, Respondents, Atlantic Coast Pipeline LLC, Intervenor. Chesapeake Bay Foundation, Incorporated; Robert Whitescarver; Jeanne Hoffman, Petitioners, v. State Water Control Board ; Melanie D. Davenport, Director, Water Permitting Division, Virginia Department of Environmental Quality ; Robert Dunn, Chair of the State Water Control Board; Virginia Department of Environmental Quality ; David K. Paylor, Director, Virginia Department of Environmental Quality, Respondents, Atlantic Coast Pipeline LLC, Intervenor.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-14\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1077\n\n\nAPPALACHIAN VOICES; CHESAPEAKE CLIMATE ACTION NETWORK;\nSIERRA CLUB; WILD VIRGINIA, INC.; COWPASTURE RIVER\nPRESERVATION ASSOCIATION; FRIENDS OF BUCKINGHAM;\nHIGHLANDERS FOR RESPONSIBLE DEVELOPMENT; JACKSON RIVER\nPRESERVATION ASSOCIATION; POTOMAC RIVERKEEPER, d/b/a Potomac\nRiverkeeper Network, Inc.; SHENANDOAH RIVERKEEPER, a program of\nPotomac Riverkeeper Network; SHENANDOAH VALLEY BATTLEFIELDS\nFOUNDATION; SHENANDOAH VALLEY NETWORK; VIRGINIA\nWILDERNESS COMMITTEE,\n\n Petitioners,\n\n v.\n\nSTATE WATER CONTROL BOARD; DAVID K. PAYLOR, Director, Virginia\nDepartment of Environmental Quality; ROBERT DUNN, Chair of the State Water\nControl Board; VIRGINIA DEPARTMENT OF ENVIRONMENTAL QUALITY;\nMELANIE D. DAVENPORT, Director, Water Permitting Division, Virginia\nDepartment of Environmental Quality,\n\n Respondents,\n\nATLANTIC COAST PIPELINE LLC,\n\n Intervenor.\n\n\n No. 18-1079\n\n\nCHESAPEAKE BAY FOUNDATION, INCORPORATED; ROBERT WHITESCARVER;\nJEANNE HOFFMAN,\n\n Petitioners,\n\f v.\n\nSTATE WATER CONTROL BOARD; MELANIE D. DAVENPORT, Director,\nWater Permitting Division, Virginia Department of Environmental Quality;\nROBERT DUNN, Chair of the State Water Control Board; VIRGINIA\nDEPARTMENT OF ENVIRONMENTAL QUALITY; DAVID K. PAYLOR,\nDirector, Virginia Department of Environmental Quality,\n\n Respondents,\n\nATLANTIC COAST PIPELINE LLC,\n\n Intervenor.\n\n\nOn Petition for Review of an Order of the Federal Energy Regulatory Commission.\n(17-002)\n\n\nArgued: September 28, 2018 Decided: January 14, 2019\n\n\nBefore GREGORY, Chief Judge, WYNN, and THACKER, Circuit Judges\n\n\nPetition for review denied by published opinion. Chief Judge Gregory wrote the opinion,\nin which Judge Wynn and Judge Thacker joined.\n\n\nARGUED: Benjamin Alan Luckett, APPALACHIAN MOUNTAIN ADVOCATES,\nLewisburg, West Virginia, for Petitioners. Toby Jay Heytens, OFFICE OF THE\nATTORNEY GENERAL OF VIRGINIA, Richmond, Virginia, for\nRespondents. Brooks Meredith Smith, TROUTMAN SANDERS LLP, Richmond,\nVirginia, for Intervenor. ON BRIEF: Gregory Buppert, Charmayne G. Staloff,\nJonathan M. Gendzier, SOUTHERN ENVIRONMENTAL LAW CENTER,\nCharlottesville, Virginia, for Petitioners Cowpasture River Preservation Association,\nFriends of Buckingham, Highlanders for Responsible Development, Jackson River\nPreservation Association, Inc., Potomac Riverkeeper, Inc., Shenandoah Riverkeeper,\nShenandoah Valley Battlefields Foundation, Shenandoah Valley Network, and Virginia\nWilderness Committee. Joseph M. Lovett, APPALACHIAN MOUNTAIN\nADVOCATES, Lewisburg, West Virginia, for Petitioners Appalachian Voices,\nChesapeake Climate Action Network, Sierra Club, and Wild Virginia. Jon Alan Mueller,\n\n 2\n\fMargaret L. Sanner, Ariel Solaski, CHESAPEAKE BAY FOUNDATION, INC.,\nAnnapolis, Maryland, for Petitioners Chesapeake Bay Foundation, Inc., Jeanne Hoffman,\nand Robert Whitescarver. Mark R. Herring, Attorney General, Stephen A. Cobb,\nDeputy Attorney General, Donald D. Anderson, Senior Assistant Attorney General,\nJ. Duncan Pitchford, Assistant Attorney General, David C. Grandis, Assistant Attorney\nGeneral, Matthew R. McGuire, Deputy Solicitor General, OFFICE OF THE\nATTORNEY GENERAL OF VIRGINIA, Richmond, Virginia, for Respondents.\nAndrea W. Wortzel, TROUTMAN SANDERS LLP, Richmond, Virginia, for Intervenor.\n\n\n\n\n 3\n\fGREGORY, Chief Judge:\n\n Pursuant to Section 401 of the Clean Water Act (“CWA”), the Virginia State\n\nWater Control Board (“Board”) certified that it had reasonable assurance that activities\n\nrelated to the construction of a natural gas pipeline would not degrade the state’s water\n\nresources. Environmental groups and their individual members disagreed with this\n\ncertification, and they petitioned this Court to review the Board’s decision. Because we\n\nconclude that the Board’s Section 401 Certification for upland areas was not arbitrary and\n\ncapricious, we deny the petition for review.\n\n\n\n I.\n\n The Atlantic Coast Pipeline (“ACP”), a project developed and overseen by\n\nAtlantic Coast Pipeline LLC (“Atlantic”), is a proposed interstate natural gas pipeline,\n\nconstructed by Atlantic, that will be approximately 604 miles long and 42 inches in\n\ndiameter and will carry natural gas from Harrison County, West Virginia, to the eastern\n\nportions of Virginia and North Carolina. Approximately 307 miles of the ACP would\n\ntraverse the Commonwealth of Virginia. There are a total of 890 water body crossings\n\nlocations in Virginia, and the route of the ACP encompasses 74 migratory fish spawning\n\nwaters or their tributaries. The proposed ACP access roads will intersect 89 Virginia\n\nrivers and streams and will require the clearing of thousands of acres in Virginia. To\n\nobtain approval for construction, Atlantic had to comply with the following federal and\n\nstate laws and regulations relevant to this appeal.\n\n\n\n 4\n\f II.\n\n As an initial matter, Atlantic had to comply with the Natural Gas Act (“NGA”).\n\nUnder the NGA, a party is required to obtain authorization from the Federal Energy\n\nRegulatory Commission (“FERC”) in the form of a certificate of public convenience and\n\nnecessity to build or operate a natural gas pipeline. Upon receipt of an application for\n\nsuch a certificate, FERC undertakes a review of the environmental impacts of the\n\nproposed project under the National Environmental Policy Act (“NEPA”) and the NGA.\n\n42 U.S.C. §§ 4321 et seq.; 15 U.S.C. §§ 717 et seq. FERC accepts input from the public\n\nand then produces an environmental impact statement (“EIS”). Functioning as a “lead\n\nagency,” FERC coordinates the required authorizations, including Virginia’s water\n\nquality certification under the CWA. See 15 U.S.C. § 717n(b).\n\n Because the pipeline project involves the discharge of fill and dredged materials\n\ninto waterways and wetlands, Atlantic needed to obtain not only a certificate of public\n\nconvenience and necessity from FERC, but also a Section 404 CWA authorization from\n\nthe U.S. Army Corps of Engineers (“Army Corps”). See 33 U.S.C. § 1344(a); AES\n\nSparrows Point LNG, LLC v. Wilson, 589 F.3d 721, 724 (4th Cir. 2009). The Army\n\nCorps provided the authorization necessary for the ACP through issuing Nationwide\n\nPermit 12, which covers “activities required for the construction, maintenance, repair,\n\nand removal of utilities lines and associated facilities in waters of the United States.” See\n\n33 U.S.C. 1344(e)(1) (allowing the Secretary of the Army to issue permits on a\n\n“nationwide basis for any category of activities involving discharges of dredged or fill\n\nmaterial if the Secretary determines that the activities in such category are similar in\n\n 5\n\fnature, will cause only minimal adverse environmental effects when performed\n\nseparately, and will have only minimal cumulative adverse effect on the environment”).\n\n\n\n III.\n\n Atlantic was also required to obtain a Section 401 Certification. The NGA allows\n\nstates to regulate the environmental impacts of pipelines under the CWA. Delaware\n\nRiverkeeper Network v. Secretary Pa. Dep’t of Envtl. Prot., 833 F.3d 360, 368 (3d Cir.\n\n2016) (citing 15 U.S.C. § 717b(d)). Virginia exercises this regulatory authority through\n\nthe Board. See Va. Code § 62.1-44.15. Pursuant to Virginia law, the Board wields broad\n\npowers regarding regulatory matters impacting water quality in Virginia, and Section 401\n\nCertifications fall under its authority. Id. The Virginia Department of Environmental\n\nQuality (“DEQ”) serves as the Board’s staff, and the Board may assign DEQ tasks and\n\ndelegate DEQ the authority to make decisions. See Va. Code Ann. § 62.1-44.14. We\n\nwill refer to the Board and DEQ together as “the State Agencies” when their actions are\n\nin concert.\n\n Under the Virginia Water Protection (“VWP”) Program, the Board, after soliciting\n\nand considering public comment and consulting with relevant agencies, may issue a\n\nVWP permit “if it has determined that the proposed activity is consistent with the\n\nprovisions of the Clean Water Act and the State Water Control Law and will protect in-\n\nstream beneficial uses.” Va. Code Ann. § 62.1-44.15:20(B). The Board may also certify\n\na nationwide Corps permit, such as Nationwide Permit 12, as meeting these requirements\n\nso long as the permit meets specified criteria. See 9 Va. Admin. Code 25-210-130(H).\n\n 6\n\fSpecifically, Section 401 states “[a]ny applicant for a Federal license or permit to conduct\n\nany activity . . . which may result in any discharge into the navigable waters” must seek\n\n“a certification from the State in which the discharge originates . . . that any such\n\ndischarge will comply with the applicable provisions” of the CWA. 33 U.S.C.\n\n§ 1341(a)(1). In addition, Section 401 states, “[n]o license or permit shall be granted if\n\ncertification has been denied by the State.” Id. If the state grants the Section 401\n\nCertification — whether with or without conditions — it must contain “[a] statement that\n\nthere is a reasonable assurance that the activity will be conducted in a manner which will\n\nnot violate applicable water quality standards.” 40 C.F.R. § 121.2(a)(3); see PUD No. 1\n\nof Jefferson Cty. v. Washington Dep’t of Ecology, 511 U.S. 700, 712 (1994). In addition,\n\nthe regulations allow for Virginia to consider activities that impact the upland areas that\n\nmay have the potential to affect water quality but do not fall under the scope of a VWP\n\npermit when the pipeline is over 36 inches inside diameter. Va. Code § 62.1-44.15:80.\n\n\n\n IV.\n\n Atlantic applied for the certificate of public convenience and necessity from FERC\n\nand Section 404 authorization from the Army Corps in September 2015. Atlantic filed an\n\namendment to its FERC certificate application in March 2016. In October 2017, FERC\n\nissued the certificate to Atlantic to construct and operate the pipeline. On April 7, 2017,\n\nthe DEQ issued a Section 401 Certification for the wetland, river, and streams crossings\n\nas covered in the Section 404 Nationwide Permit 12. In May 2017, the DEQ explained\n\nthat the Section 401 Certification for the Pipeline would entail two separate parts: (1) the\n\n 7\n\fcertification for the Army Corps Nationwide Permit 12, issued in April, applying to the\n\nPipeline’s wetland, river, and streams crossings (the “Wetlands and Streams\n\nCertification”), and (2) an additional Section 401 Certification review process to evaluate\n\nthe “upland” impacts of the Pipeline, terrestrial areas that are not covered by the Army\n\nCorps Permit (the “Upland Certification”). Specifically, the Upland Certification would\n\n“include all proposed upland activities associated with the construction, operation,\n\nmaintenance, and repair of the pipeline, any components thereof or appurtenances\n\nthereto, and related access roads and rights-of-way as well as certain project related\n\nsurface water withdrawals.” J.A 1083.\n\n On November 9, 2017, the DEQ recommended that the Board approve a Section\n\n401 Upland Certification of the project. On December 20, 2017, the Board issued the\n\nUpland Certification for the ACP with conditions. This Certification was distinct from\n\nthe Wetlands and Steams Certification. This Upland Certification provided that it “shall\n\nbe effective only following submission, review and final approval as required by law of\n\nthe Karst Mitigation Plan, Annual Standards and Specifications, and Erosion and\n\nSediment Control Plans and Storm Water Management Plans, and a report to the Board\n\nand the public by DEQ on the adequacy of these materials.” J.A. 29.\n\n Petitioners timely filed two petitions for review of the Certification on January 18,\n\n2018. The petitions were consolidated by court order on January 31, 2018. We possess\n\njurisdiction to review the Board’s Section 401 Upland Certification pursuant to 15 U.S.C.\n\n§ 717r(d)(1).\n\n\n\n 8\n\f The petitioners contend the Board’s issuance of the Section 401 Upland\n\nCertification was arbitrary and capricious and should be vacated for four reasons: (1) the\n\nState Agencies effectively invalidated their own finding of reasonable assurance when it\n\nvoted to reopen the comment period on the Section 401 Certification of the Army Corps\n\nof Engineers Nationwide Permit 12; (2) the State Agencies arbitrarily and capriciously\n\nfailed to assess the combined impacts on water quality that would result from multiple\n\nareas of construction activities within individual watershed areas; (3) the State Agencies\n\narbitrarily and capriciously failed to conduct an adequate antidegradation review; and (4)\n\nthe State Agencies arbitrarily and capriciously failed to ensure that the water quality in\n\nkarst geology regions would be protected. Respondents and intervenor in turn deny that\n\nthe State Agencies acted arbitrarily and capriciously and argue that the petitioners lack\n\nstanding to bring this petition.\n\n On April 12, 2018, the Board approved a second 30-day public comment period\n\nrelated to the Wetlands and Steams Certification. On August 21, 2018, the Board heard a\n\npresentation from the DEQ summarizing the public comment period and denied a motion\n\nto reevaluate this contested Certification.\n\n\n\n V.\n\n The respondents and intervenor argue as an initial matter that petitioners do not\n\nhave standing to litigate this petition for review. Spokeo, Inc. v. Robins, 136 S. Ct. 1540,\n\n1547 (2016) (quoting Lujan v. Defenders of Wildlife, 504 U.S. 555, 560-61 (1992))\n\n(Article III standing requires (1) an injury-in-fact (2) that is fairly traceable to the\n\n 9\n\fchallenged conduct of the defendant, and (3) that is likely to be redressed through a\n\nfavorable judicial decision). We disagree.\n\n This Court has previously rejected respondents’ and intervenor’s arguments on\n\nstanding. Sierra Club v. State Water Control Bd., 898 F.3d 383, 400-02 (4th Cir. 2018).\n\nPetitioners have established an injury-in-fact even though the State Agencies could\n\nchoose to waive certification. We have previously held that the denial of an opportunity,\n\nin this case, to have the project vetoed or have additional restrictions can constitute an\n\ninjury-in-fact. Id. at 401. In addition, petitioners successfully establish traceability and\n\nredressability given that we could vacate the Board’s decision and determine that its\n\ndecision was not based on a reasonable assurance and instead was arbitrary and\n\ncapricious. Petitioners’ injuries could be remedied if the Board required Atlantic to take\n\nadditional measures that would address petitioners’ grievances. In our previous decision\n\nwe held petitioners established traceability and redressability in this very context. Id.\n\nPetitioners have demonstrated the requirements for standing.\n\n\n\n VI.\n\n We review Virginia’s Section 401 Certification under the standards set forth in the\n\nAdministrative Procedures Act (“APA”). See AES Sparrows Point LNG, LLC v. Wilson,\n\n589 F.3d 721, 727 (4th Cir. 2009). 1 This Court applies the arbitrary and capricious\n\n\n 1\n Asserting that the APA is not applicable to actions by State Agencies,\nrespondents argue that Va. Code § 2.2-4027 establishes the applicable standard of review.\nThat statute provides that issues of fact shall be decided based on “whether there was\n(Continued)\n 10\n\fstandard of the APA to the State Agencies’ challenged findings and conclusions. Sierra\n\nClub, 898 F.3d at 403.\n\n To survive review under the arbitrary and capricious standard, an agency decision\n\nmust show that the agency examined “the relevant data and articulate[d] a satisfactory\n\nexplanation for its action including a ‘rational connection between the facts found and the\n\nchoice made.’” Motor Vehicle Mfrs. Ass’n of U.S., Inc. v. State Farm Mut. Auto Ins. Co.,\n\n463 U.S. 29, 43 (1983) (quoting Burlington Truck Lines v. United States, 371 U.S. 156,\n\n168 (1962)).\n\n Agency action is arbitrary and capricious if the agency relies on factors that\n Congress did not intend for it to consider, entirely ignores important aspects\n of the problem, explains its decision in a manner contrary to the evidence\n before it, or reaches a decision that is so implausible that it cannot be\n ascribed to a difference in view.\n\nBedford Cty. Mem’l Hosp. v. Health & Human Servs., 769 F.2d 1017, 1022 (4th Cir.\n\n1985) (citing Motor Vehicle Mfrs. Ass’n, 463 U.S. at 43). This Circuit has held that\n\n [r]eview under this standard is highly deferential, with a presumption in\n favor of finding the agency action valid. Especially in matters involving\n not just simple findings of fact but complex predictions based on special\n expertise, a reviewing court must generally be at its most deferential. In\n determining whether agency action was arbitrary or capricious, the court\n must consider whether the agency considered the relevant factors and\n whether a clear error of judgment was made. Although this inquiry into the\n facts is to be searching and careful, the ultimate standard of review is a\n narrow one. The court is not empowered to substitute its judgment for that\n of the agency. Deference is due where the agency has examined the\n\n\n\n\nsubstantial evidence in the agency record to support the agency decision.” As we did in\nSierra Club, we decline to resolve this issue because petitioners’ claims fail even under\nthe substantial evidence standard. 898 F.3d at 403 n.13.\n\n 11\n\f relevant data and provided an explanation of its decision that includes a\n rational connection between the facts found and the choice made.\n\nOhio Valley Envtl. Coal. v. Aracoma Coal Co., 556 F.3d 177, 192 (4th Cir. 2009)\n\n(internal quotation marks and citations omitted). Nonetheless, if a state agency’s Section\n\n401 certification is found to be arbitrary and capricious, the Court must vacate the\n\ncertification. 5 U.S.C. § 706(2)(A).\n\n\n\n VII.\n\n A.\n\n Turning to petitioners’ first argument, we hold that the decision to reopen the\n\ncomment period did not render the State Agencies’ Section 401 Upland Certification\n\narbitrary and capricious. The comment period was re-opened for the Wetlands and\n\nStreams Certification and not the Upland Certification at issue in this case. In any event,\n\nthe Wetlands and Streams Certification was not ultimately revoked.\n\n B.\n\n Moving to the petitioners’ second argument, we conclude that the State Agencies’\n\ndecision not to conduct a combined effect analysis does not render their issuance of a\n\nSection 401 Upland Certification arbitrary and capricious for three reasons.\n\n First, the Section 401 Upland Certification in question deals with project-related\n\nactivities taking place in upland areas. The Upland Certification supplemented the FERC\n\ncertificate and the prior Wetland and Streams Certification of the Army Corps’\n\nNationwide Permit 12 regarding waterways and utility line crossings. As the State\n\n\n 12\n\fAgencies explained, “the conditions in the proposed additional 401 Certification are in\n\naddition to any other Federal or State permit or regulatory requirements including the\n\nexpressed conditions imposed by FERC.” J.A. 1059. The Upland Certification in\n\nquestion is not designed to function as a stand-alone document, comprehensively\n\ncovering all pieces of relevant data and potentialities. For example, record evidence\n\navailable to the State Agencies explains, “while the impacts to jurisdictional waters\n\nauthorized by the Corps under Section 404 of the Clean Water Act are separate from\n\nupland activities that are the subject of this Certification, the Corps also analyzed the\n\ncumulative effects of linear utility projects and found that the individual and cumulative\n\nadverse effects on the aquatic environment resulting from the activities authorized by the\n\nNationwide Permit 12 will be no more than minimal and each crossing is a single and\n\ncomplete project.” J.A. 999. The Army Corps examined cumulative impacts, and it\n\nwould be redundant and inefficient for the State Agencies to duplicate these efforts. The\n\nUpland Certification works in conjunction with other regulatory tools and cannot be\n\njudged in a void, and it supplements other pieces of the regulatory framework. It is not\n\nrequired to cover combined effect analysis because other parts of the regulatory process\n\nsufficiently address that subject matter. The State Agencies in the current appeal used\n\ntheir resources to issue the Upland Certification to fill an information gap regarding the\n\nimpact of upland activities, which were not typically covered under prior CWA\n\ncertifications. The State Agencies properly made a unique contribution instead of\n\nduplicating the efforts of other regulatory bodies as petitioners’ request. See Sierra Club,\n\n898 F.3d at 407.\n\n 13\n\f Second, State Agencies have broad discretion when developing the criteria for\n\ntheir Section 401 Certification. The only requirement imposed by the regulations is that\n\nStates must establish procedures for public notice when there are applications for\n\ncertification, and to the extent deemed appropriate, procedures for public hearings in\n\nconnection with specific applications. 33 U.S.C. § 1341(a)(1). Nonetheless, nothing in\n\nSection 401 restricts states to a single certificate proceeding, and Section 401 does not\n\nrequire states to undertake a single cumulative review of all possible impacts in a single\n\ncertification.\n\n Petitioners’ rely on two federal regulations in arguing that a cumulative review is\n\nrequired, 40 C.F.R. § 230.7(a) and 40 C.F.R. § 230.11(g)(1), but those regulations impose\n\nduties—including a duty to make factual determinations and consider cumulative\n\neffects—on the Army Corps under Section 404, not on states under Section 401.\n\nMoreover, petitioners contend that two cases require State Agencies to take into account\n\ncombined effects lest their decisions be rendered arbitrary and capricious. See Klamath-\n\nSiskiyou Wildlands Ctr. v. BLM, 387 F.3d 989, 993 (9th Cir. 2004); Idaho Rivers United\n\nv. Probert, Case No.: 3:16-102, 2016 U.S. Dist. LEXIS 63767, at *32-34. Furthermore,\n\npetitioners invoke the Supreme Court’s decision in Motor Vehicles Manufacturers\n\nAssociation v. State Farm Mutual Automobile Ins. Co., to argue that all “relevant data”\n\nmust be considered. 463 U.S. 29, 43 (1983). We conclude, however, that both the\n\nKlamath-Siskiyou Wildlands and Idaho Rivers United cases are distinguishable and\n\nunpersuasive because in those cases the Bureau of Land Management and the Forest\n\nService, respectively, faced violations under NEPA, not the CWA. Klamath-Siskiyou\n\n 14\n\fWildlands Ctr., 387 F.3d at 993–94; Idaho Rivers United, 2016 U.S. Dist. LEXIS 63767,\n\nat *33. Unlike the CWA, NEPA requires a cumulative effects analysis, and thus cases\n\ndecided under NEPA are not dispositive authority here. Furthermore, Motor Vehicle\n\nManufacturers Association, which deals with the National Highway Traffic Safety\n\nAdministration, does not mention cumulative effects or the CWA, and thus the case does\n\nnot stand for the proposition that the CWA should be broadened to encompass a\n\ncombined impact analysis.\n\n Finally, the State Agencies’ failure to explicitly consider the combined effects of\n\nmultiple areas of construction within individual watersheds such as the Chesapeake Bay\n\nwatershed and the Chesapeake Bay Total Maximum Daily Load (“Bay TMDL”) did not\n\nrender their decision arbitrary and capricious. 2 As an initial matter, despite petitioners’\n\npreferences, there are no express regulations that require the State Agencies to consider\n\nthe combined effects of individual watersheds. In addition, the Ninth Circuit has\n\nexplained that TMDLs like the Chesapeake Bay TMDL are “primarily informational\n\ntools that allow states to proceed from the identification of water requiring additional\n\nplanning to the required plans.” Pronsolino v. Nastri, 291 F. 3d 1123, 1129 (9th Cir.\n\n2002). Moreover, TMDLs do not give rise to an independent legal obligation.\n\nPronsolino, 291 F.3d 1123, 1140. Consequently, the Chesapeake TMDL does not\n\nconstitute a regulatory mandate that the State Agencies were required to address before\n\nissuing the Section 401 Upland Certification. Furthermore, protection measures for the\n\n 2\n The Bay TMDL is a federal-state partnership that monitors the water quality\nstandards in the Chesapeake Bay and its related tributaries. J.A. 888.\n\n 15\n\fChesapeake Bay TMDL are offered through other tools such as the FERC EIS and the\n\nStorm Water Prevention Plan. J.A. 664-665; 1138-1140.\n\n The State Agencies more than satisfied their obligations by reviewing upland\n\nactivities as well as stream and wetland crossings. The Board’s decisions are not\n\nrendered arbitrary and capricious because it did not conduct an independent review of the\n\ncumulative effects on water quality within individual watersheds, even if this was\n\npetitioners’ preference. To deem an agency action arbitrary and capricious their decision\n\nmust be “so implausible that it could not be ascribed to a difference in view or the\n\nproduct of agency expertise.” State Farm Mut. Auto. Ins. Co., 463 U.S. at 43. The lack\n\nof an explicit combined effect analysis in the Section 401 Upland Certification does not\n\nrise to this level, especially given that there are other regulatory tools that were utilized to\n\nconsider those impacts.\n\n C.\n\n 1.\n\n Turning to petitioners’ third argument, we do not find that the State Agencies’\n\nreasonable assurance determination to be arbitrary and capricious simply because they\n\nrelied on existing Virginia water quality standards and regulations to effectively address\n\nconcerns regarding water quality deterioration.\n\n Under the CWA, “states have the primary role in promulgating water quality\n\nstandards.” Piney Run Preservation Ass’n v. County Comm’rs of Carroll Cty., 268 F.3d\n\n255, 265 n.9 (4th Cir. 2001). States must initially classify the uses for which their water\n\nis to be protected and then determine the necessary level of water quality for their\n\n 16\n\fpreferred uses. See NRDC v. EPA, 16 F.3d 1395, 1400 (4th Cir. 1993). Virginia’s water-\n\nquality policy is relevant in two respects: its narrative water-quality criterion and its anti-\n\ndegradation policy.\n\n Virginia’s water-quality criterion mandates that “State waters . . . shall be free\n\nfrom substances attributable to . . . waste in concentrations, amounts, or combinations\n\nwhich contravene established standards or interfere directly or indirectly with designated\n\nuses of such water or which are inimical or harmful to human, animal, plant, or aquatic\n\nlife.” 9 Va. Admin. Code § 25-260-20(A). The regulation explains that any substance\n\n“that produce[s] . . . turbidity” is a substance to be controlled. Id. The regulation\n\nprovides examples of “turbidity” such as floating debris, oil, and other materials that are\n\nsuspended solids in a body of water.\n\n In addition, Virginia’s antidegradation policy shall be applied whenever any\n\nactivity is proposed that has the potential to affect existing surface water quality. 9 Va.\n\nAdmin. Code § 25-260-30(A). The antidegradation policy classifies Virginia’s water into\n\nthree tiers and provides differing levels of protection based on the water’s tier. See 9 Va.\n\nAdmin. Code § 25-260-30(A).\n\n The Policy defines Tier 3 waters as “exceptional”; these waters “shall be\n\nmaintained and protected to prevent permanent or long-term degradation or impairment.”\n\n9 Va. Admin. Code § 25-260-30(A)(3)(b)(1). The policy specifically provides that “[n]o\n\nnew, additional, or increased discharge of sewage, industrial wastes or other pollution\n\ninto [Tier 3 waters] shall be allowed.” 9 Va. Admin. Code § 25-260-30(A)(3)(b)(2).\n\nNonetheless, “[a]ctivities causing temporary sources of pollution may be allowed in [Tier\n\n 17\n\f3 waters] even if degradation may be expected to temporarily occur provided that after a\n\nminimal period of time the waters are returned or restored to conditions equal to or better\n\nthan those existing just prior to the temporary source of pollution.” 9 Va. Admin. Code\n\n§ 25-260-30(A)(3)(b)(3).\n\n The Policy defines Tier 2 waters as those that “exceed water quality standards.” 9\n\nVa. Admin. Code § 25-260-30(A)(2). The protection for these waters and their quality\n\nare lower and the regulation states that the quality of Tier 2 waters “shall be maintained\n\nand protected unless the board finds . . . that allowing lower water quality is necessary to\n\naccommodate important economic or social development in the area in which the waters\n\nare located.” 9 Va. Admin. Code § 25-260-30(A)(2).\n\n Last, Tier 1 waters constitute all Virginia waters that are not designated Tier 2 or\n\nTier 3. The regulation classifying the level of protection for these waters’ states,\n\n“existing in-stream water uses and the level of water quality necessary to protect the\n\nexisting uses shall be maintained and protected.” 9 Va. Admin. Code § 25-260-30(A)(1).\n\n In Virginia a project may be permitted under a Construction General Permit. 9\n\nVa. Admin. Code § 25-880-70 Part II. The Construction General Permit incorporates the\n\nrequirements of two other state laws, the Virginia Storm Water Management (“VSM”)\n\nLaw, Va. Code § 62.1-44.15:24 et seq., and the Virginia Erosion and Sediment Control\n\n(“VESC”) Law, Va. Code § 62.1-44.15:51, et seq.\n\n The CWA has an exemption for natural gas pipeline construction projects and\n\ntherefore Virginia’s regulatory scheme diverges from the federal environmental\n\nprotections. See 33 U.S.C. § 1342(I)(2). Consequently, Virginia still regulates natural\n\n 18\n\fgas pipeline projects through its Annual Standards and Specifications (“AS&S”)\n\nProgram. See Va. Code § 62.1-44.15:55(D). The AS&S program requires a project\n\ndeveloper to submit annual standards and specifications for DEQ’s review and approval.\n\nSee 9 Va. Admin. Code § 25-870-170(A). Through this program Virginia ensures that\n\nprojects will meet the same requirements imposed on other projects subject to the\n\nVirginia Construction General Permit. See 9 Va. Admin. Code § 25-870-170(A).\n\nNonetheless, once DEQ approves a developer’s annual standards and specifications as\n\nsatisfying the requirements of the VSM and VESC, the entity generally need not submit\n\nsite-specific VSM and VESC plans to DEQ for approval. See Va. Code § 62.1-\n\n44.15:55(D). This allows the projects to become more self-regulating.\n\n Typically, ensuring an activity’s compliance with water quality standards requires\n\nan antidegradation review. See Nat. Res. Def. Council, Inc. v. EPA, 16 F.3d 1395, 1400\n\n(4th Cir. 1993); see also 40 C.F.R. § 131.12 (requiring states to develop and adopt a\n\nstatewide antidegradation policy). The CWA’s antidegradation policy requires that state\n\nstandards be “sufficient to maintain existing beneficial uses of navigable waters,\n\npreventing further degradation.” 33 U.S.C. § 1313(d). State antidegradation policies\n\nmust be consistent with 40 C.F.R. § 131.12(a), and must protect existing uses, maintain\n\nthe existing quality of high-quality waters unless degradation is justified by important\n\nsocioeconomic development, and prohibit degradation of national resource waters. Id.\n\n§ 131.12(a).\n\n\n\n\n 19\n\f 2.\n\n We do not find that the State Agencies’ failure to conduct a separate\n\nantidegradation review before issuing its Upland Certification renders their decision\n\narbitrary and capricious for two reasons.\n\n First, in Virginia, the AS&S program requires a project developer to submit annual\n\nstandards and specifications for DEQ’s review and approval, thereby ensuring that\n\nprojects will meet the same requirements that would apply were they covered by the\n\nVirginia Construction General Permit. See 9 Va. Admin. Code § 25-870-170(A). The\n\nAS&S also incorporate all the requirements of EPA’s Construction General Permit. J.A.\n\n1124-1125. The AS&S in this case were developed over eighteen months and represent a\n\nthorough process of development, revision and refinement to ensure that the ACP meet\n\nthe technical and legal requirements for Virginia. J.A. 1087. Both federal and state\n\nregulators have concluded that application of technical requirements like those in the\n\nAS&S “will not result in a lowering of water quality,” which renders the individualized\n\nreview the petitioners suggest “unnecessary.” J.A. 11. There is no indication that these\n\nAS&S fail to protect water quality in Virginia. To the contrary, these regulations have\n\nbeen found as a matter of law to protect water quality in Virginia. See Kelble v.\n\nCommonwealth, Case No. CL 14-762, at 4-5 (Richmond Cir. Ct. Apr. 10, 2017).\n\n Second, State Agencies did not have to conduct a separate antidegradation review\n\nbecause the impact on sediment on the water would only be temporary. Under FERC’s\n\nfinal EIS, it was determined that any water quality impacts stemming from construction\n\nwould be temporary. J.A. 623. Even with respect to Tier 3 waters, the policy states that\n\n 20\n\f“[a]ctivities causing temporary sources of pollution may be allowed in [Tier 3] waters . . .\n\neven if degradation may be expected to occur provided that after a minimal period of\n\ntime the waters are returned or restored to conditions equal to or better that those existing\n\njust prior to the temporary source of pollution.” 9 Va. Admin. Code 25-260-\n\n30A(3)(b)(3). Even in the most protected state waters, Virginia does not consider\n\ntemporary sources of pollution, such as the construction of the ACP, to violate\n\nantidegradation policies.\n\n Thus, nothing was arbitrary and capricious about the State Agencies’ decision not\n\nto conduct a separate antidegradation review.\n\n D.\n\n Turning to the final challenge raised by petitioners, we find that the State\n\nAgencies’ treatment of karst terrain was not arbitrary or capricious because of the\n\nconditions imposed on the Section 401 Upland Certification.\n\n Karst geology refers to geological formations of soluble limestone bedrock that\n\ncreates underground water flow systems where the rocks have dissolved and created\n\nsinkholes, caves and underground springs and rivers. J.A. 669. The constitution of these\n\nareas presents additional environmental considerations for pipeline construction\n\nincluding, sinkhole collapse, sinkhole flooding and associated groundwater\n\ncontamination. J.A. 904-905.\n\n The record demonstrates that the State Agencies took petitioners’ concerns\n\nregarding karst geology into consideration. J.A. 31. Virginia’s Section 401 Upland\n\nCertification contains five specific requirements concerning the protection of karst\n\n 21\n\fterrain. J.A. 31-32. First, Atlantic must provide the State an addendum to a 51-page\n\nKarst Survey Report prior to any land disturbing activities. J.A. 212-237; J.A. 31.\n\nSecond, Atlantic must follow the Karst Terrain Assessment, Construction, Monitoring,\n\nand Mitigation Plan. J.A. 31. This plan allows for route adjustments to avoid karst\n\nterrain. J.A. 1001. Third, based on the conditions in the Section 401 Upland\n\nCertification, Atlantic must conduct contingency planning in order to address any\n\naccidental spills or releases during construction on karst terrain. Fourth, water surveys\n\nregarding drinkable water in karst regions are required under the Section 401 Upland\n\nCertification. J.A. 31. Finally, Atlantic has a liability of five million dollars to cover the\n\ncost of any impacts to private water supplies, which encompasses karst regions. J.A. 32.\n\n Reliance on these conditions, even the prospective ones, does not render the State\n\nAgencies’ issuance of the Section 401 Upland Certification arbitrary and capricious. See\n\nPort of Seattle v. Pollution Control Hearings Bd., 90 P.3d 659, 677 (Wash. 2004)\n\n(holding regulators did not act arbitrarily or capriciously by basing reasonable assurance\n\n“on future submissions of revised plans, reports, and studies, so long as their\n\nimplementation and anticipated outcome meet the reasonable assurance test”).\n\n Moreover, the mere existence of risk to karst geology does not render the State\n\nAgencies’ decision to issue the Section 401 Upland Certification arbitrary and capricious.\n\nBased on the information in the record, this Court finds that the State Agencies had\n\nreasonable assurance that karst regions would be protected given the conditions imposed\n\non the Section 401 Upland Certification. We “see no purpose we would serve by\n\nstepping in and second-guessing the analytical methods Virginia deemed appropriate to\n\n 22\n\fprovide it with reasonable assurance that its water quality would be protected.” Sierra\n\nClub., 898 F.3d at 407.\n\n\n\n VIII.\n\n Governmental agencies can always take additional steps to increase the protection\n\nof the environment. But that is not the applicable legal standard this Court utilizes when\n\nreviewing a state agency’s issuance of a Section 401 Certification. We must determine\n\n“whether the agency considered the relevant factors and whether a clear error of\n\njudgment was made.” Ohio Valley Envtl. Coal., 556 F.3d 177, 192. There is no\n\nindication that the State Agencies did not consider relevant factors or that they clearly\n\nmade an error of judgment. In conclusion, because we find that the State Agencies did\n\nnot act arbitrarily and capriciously in issuing the Section 401 Upland Certification, we\n\ndeny the petition for review.\n\n\n\n PETITION FOR REVIEW DENIED\n\n\n\n\n 23\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: APPALACHIAN VOICES; Chesapeake Climate Action Network; Sierra Club; Wild Virginia, Inc. ; Cowpasture River Preservation Association; Friends of Buckingham ; Highlanders for Responsible Development; Jackson River Preservation Association ; Potomac Riverkeeper, D/B/A Potomac Riverkeeper Network, Inc. ; Shenandoah Riverkeeper, a Program of Potomac Riverkeeper Network; Shenandoah Valley Battlefields Foundation ; Shenandoah Valley Network; Virginia Wilderness Committee, Petitioners, v. STATE WATER CONTROL BOARD ; David K. Paylor, Director, Virginia Department of Environmental Quality ; Robert Dunn, Chair of the State Water Control Board; Virginia Department of Environmental Quality ; Melanie D. Davenport, Director, Water Permitting Division, Virginia Department of Environmental Quality, Respondents, Atlantic Coast Pipeline LLC, Intervenor. Chesapeake Bay Foundation, Incorporated; Robert Whitescarver; Jeanne Hoffman, Petitioners, v. State Water Control Board ; Melanie D. Davenport, Director, Water Permitting Division, Virginia Department of Environmental Quality ; Robert Dunn, Chair of the State Water Control Board; Virginia Department of Environmental Quality ; David K. Paylor, Director, Virginia Department of Environmental Quality, Respondents, Atlantic Coast Pipeline LLC, Intervenor.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-14\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1077\\n\\n\\nAPPALACHIAN VOICES; CHESAPEAKE CLIMATE ACTION NETWORK;\\nSIERRA CLUB; WILD VIRGINIA, INC.; COWPASTURE RIVER\\nPRESERVATION ASSOCIATION; FRIENDS OF BUCKINGHAM;\\nHIGHLANDERS FOR RESPONSIBLE DEVELOPMENT; JACKSON RIVER\\nPRESERVATION ASSOCIATION; POTOMAC RIVERKEEPER, d/b/a Potomac\\nRiverkeeper Network, Inc.; SHENANDOAH RIVERKEEPER, a program of\\nPotomac Riverkeeper Network; SHENANDOAH VALLEY BATTLEFIELDS\\nFOUNDATION; SHENANDOAH VALLEY NETWORK; VIRGINIA\\nWILDERNESS COMMITTEE,\\n\\n Petitioners,\\n\\n v.\\n\\nSTATE WATER CONTROL BOARD; DAVID K. PAYLOR, Director, Virginia\\nDepartment of Environmental Quality; ROBERT DUNN, Chair of the State Water\\nControl Board; VIRGINIA DEPARTMENT OF ENVIRONMENTAL QUALITY;\\nMELANIE D. DAVENPORT, Director, Water Permitting Division, Virginia\\nDepartment of Environmental Quality,\\n\\n Respondents,\\n\\nATLANTIC COAST PIPELINE LLC,\\n\\n Intervenor.\\n\\n\\n No. 18-1079\\n\\n\\nCHESAPEAKE BAY FOUNDATION, INCORPORATED; ROBERT WHITESCARVER;\\nJEANNE HOFFMAN,\\n\\n Petitioners,\\n\\f v.\\n\\nSTATE WATER CONTROL BOARD; MELANIE D. DAVENPORT, Director,\\nWater Permitting Division, Virginia Department of Environmental Quality;\\nROBERT DUNN, Chair of the State Water Control Board; VIRGINIA\\nDEPARTMENT OF ENVIRONMENTAL QUALITY; DAVID K. PAYLOR,\\nDirector, Virginia Department of Environmental Quality,\\n\\n Respondents,\\n\\nATLANTIC COAST PIPELINE LLC,\\n\\n Intervenor.\\n\\n\\nOn Petition for Review of an Order of the Federal Energy Regulatory Commission.\\n(17-002)\\n\\n\\nArgued: September 28, 2018 Decided: January 14, 2019\\n\\n\\nBefore GREGORY, Chief Judge, WYNN, and THACKER, Circuit Judges\\n\\n\\nPetition for review denied by published opinion. Chief Judge Gregory wrote the opinion,\\nin which Judge Wynn and Judge Thacker joined.\\n\\n\\nARGUED: Benjamin Alan Luckett, APPALACHIAN MOUNTAIN ADVOCATES,\\nLewisburg, West Virginia, for Petitioners. Toby Jay Heytens, OFFICE OF THE\\nATTORNEY GENERAL OF VIRGINIA, Richmond, Virginia, for\\nRespondents. Brooks Meredith Smith, TROUTMAN SANDERS LLP, Richmond,\\nVirginia, for Intervenor. ON BRIEF: Gregory Buppert, Charmayne G. Staloff,\\nJonathan M. Gendzier, SOUTHERN ENVIRONMENTAL LAW CENTER,\\nCharlottesville, Virginia, for Petitioners Cowpasture River Preservation Association,\\nFriends of Buckingham, Highlanders for Responsible Development, Jackson River\\nPreservation Association, Inc., Potomac Riverkeeper, Inc., Shenandoah Riverkeeper,\\nShenandoah Valley Battlefields Foundation, Shenandoah Valley Network, and Virginia\\nWilderness Committee. Joseph M. Lovett, APPALACHIAN MOUNTAIN\\nADVOCATES, Lewisburg, West Virginia, for Petitioners Appalachian Voices,\\nChesapeake Climate Action Network, Sierra Club, and Wild Virginia. Jon Alan Mueller,\\n\\n 2\\n\\fMargaret L. Sanner, Ariel Solaski, CHESAPEAKE BAY FOUNDATION, INC.,\\nAnnapolis, Maryland, for Petitioners Chesapeake Bay Foundation, Inc., Jeanne Hoffman,\\nand Robert Whitescarver. Mark R. Herring, Attorney General, Stephen A. Cobb,\\nDeputy Attorney General, Donald D. Anderson, Senior Assistant Attorney General,\\nJ. Duncan Pitchford, Assistant Attorney General, David C. Grandis, Assistant Attorney\\nGeneral, Matthew R. McGuire, Deputy Solicitor General, OFFICE OF THE\\nATTORNEY GENERAL OF VIRGINIA, Richmond, Virginia, for Respondents.\\nAndrea W. Wortzel, TROUTMAN SANDERS LLP, Richmond, Virginia, for Intervenor.\\n\\n\\n\\n\\n 3\\n\\fGREGORY, Chief Judge:\\n\\n Pursuant to Section 401 of the Clean Water Act (“CWA”), the Virginia State\\n\\nWater Control Board (“Board”) certified that it had reasonable assurance that activities\\n\\nrelated to the construction of a natural gas pipeline would not degrade the state’s water\\n\\nresources. Environmental groups and their individual members disagreed with this\\n\\ncertification, and they petitioned this Court to review the Board’s decision. Because we\\n\\nconclude that the Board’s Section 401 Certification for upland areas was not arbitrary and\\n\\ncapricious, we deny the petition for review.\\n\\n\\n\\n I.\\n\\n The Atlantic Coast Pipeline (“ACP”), a project developed and overseen by\\n\\nAtlantic Coast Pipeline LLC (“Atlantic”), is a proposed interstate natural gas pipeline,\\n\\nconstructed by Atlantic, that will be approximately 604 miles long and 42 inches in\\n\\ndiameter and will carry natural gas from Harrison County, West Virginia, to the eastern\\n\\nportions of Virginia and North Carolina. Approximately 307 miles of the ACP would\\n\\ntraverse the Commonwealth of Virginia. There are a total of 890 water body crossings\\n\\nlocations in Virginia, and the route of the ACP encompasses 74 migratory fish spawning\\n\\nwaters or their tributaries. The proposed ACP access roads will intersect 89 Virginia\\n\\nrivers and streams and will require the clearing of thousands of acres in Virginia. To\\n\\nobtain approval for construction, Atlantic had to comply with the following federal and\\n\\nstate laws and regulations relevant to this appeal.\\n\\n\\n\\n 4\\n\\f II.\\n\\n As an initial matter, Atlantic had to comply with the Natural Gas Act (“NGA”).\\n\\nUnder the NGA, a party is required to obtain authorization from the Federal Energy\\n\\nRegulatory Commission (“FERC”) in the form of a certificate of public convenience and\\n\\nnecessity to build or operate a natural gas pipeline. Upon receipt of an application for\\n\\nsuch a certificate, FERC undertakes a review of the environmental impacts of the\\n\\nproposed project under the National Environmental Policy Act (“NEPA”) and the NGA.\\n\\n42 U.S.C. §§ 4321 et seq.; 15 U.S.C. §§ 717 et seq. FERC accepts input from the public\\n\\nand then produces an environmental impact statement (“EIS”). Functioning as a “lead\\n\\nagency,” FERC coordinates the required authorizations, including Virginia’s water\\n\\nquality certification under the CWA. See 15 U.S.C. § 717n(b).\\n\\n Because the pipeline project involves the discharge of fill and dredged materials\\n\\ninto waterways and wetlands, Atlantic needed to obtain not only a certificate of public\\n\\nconvenience and necessity from FERC, but also a Section 404 CWA authorization from\\n\\nthe U.S. Army Corps of Engineers (“Army Corps”). See 33 U.S.C. § 1344(a); AES\\n\\nSparrows Point LNG, LLC v. Wilson, 589 F.3d 721, 724 (4th Cir. 2009). The Army\\n\\nCorps provided the authorization necessary for the ACP through issuing Nationwide\\n\\nPermit 12, which covers “activities required for the construction, maintenance, repair,\\n\\nand removal of utilities lines and associated facilities in waters of the United States.” See\\n\\n33 U.S.C. 1344(e)(1) (allowing the Secretary of the Army to issue permits on a\\n\\n“nationwide basis for any category of activities involving discharges of dredged or fill\\n\\nmaterial if the Secretary determines that the activities in such category are similar in\\n\\n 5\\n\\fnature, will cause only minimal adverse environmental effects when performed\\n\\nseparately, and will have only minimal cumulative adverse effect on the environment”).\\n\\n\\n\\n III.\\n\\n Atlantic was also required to obtain a Section 401 Certification. The NGA allows\\n\\nstates to regulate the environmental impacts of pipelines under the CWA. Delaware\\n\\nRiverkeeper Network v. Secretary Pa. Dep’t of Envtl. Prot., 833 F.3d 360, 368 (3d Cir.\\n\\n2016) (citing 15 U.S.C. § 717b(d)). Virginia exercises this regulatory authority through\\n\\nthe Board. See Va. Code § 62.1-44.15. Pursuant to Virginia law, the Board wields broad\\n\\npowers regarding regulatory matters impacting water quality in Virginia, and Section 401\\n\\nCertifications fall under its authority. Id. The Virginia Department of Environmental\\n\\nQuality (“DEQ”) serves as the Board’s staff, and the Board may assign DEQ tasks and\\n\\ndelegate DEQ the authority to make decisions. See Va. Code Ann. § 62.1-44.14. We\\n\\nwill refer to the Board and DEQ together as “the State Agencies” when their actions are\\n\\nin concert.\\n\\n Under the Virginia Water Protection (“VWP”) Program, the Board, after soliciting\\n\\nand considering public comment and consulting with relevant agencies, may issue a\\n\\nVWP permit “if it has determined that the proposed activity is consistent with the\\n\\nprovisions of the Clean Water Act and the State Water Control Law and will protect in-\\n\\nstream beneficial uses.” Va. Code Ann. § 62.1-44.15:20(B). The Board may also certify\\n\\na nationwide Corps permit, such as Nationwide Permit 12, as meeting these requirements\\n\\nso long as the permit meets specified criteria. See 9 Va. Admin. Code 25-210-130(H).\\n\\n 6\\n\\fSpecifically, Section 401 states “[a]ny applicant for a Federal license or permit to conduct\\n\\nany activity . . . which may result in any discharge into the navigable waters” must seek\\n\\n“a certification from the State in which the discharge originates . . . that any such\\n\\ndischarge will comply with the applicable provisions” of the CWA. 33 U.S.C.\\n\\n§ 1341(a)(1). In addition, Section 401 states, “[n]o license or permit shall be granted if\\n\\ncertification has been denied by the State.” Id. If the state grants the Section 401\\n\\nCertification — whether with or without conditions — it must contain “[a] statement that\\n\\nthere is a reasonable assurance that the activity will be conducted in a manner which will\\n\\nnot violate applicable water quality standards.” 40 C.F.R. § 121.2(a)(3); see PUD No. 1\\n\\nof Jefferson Cty. v. Washington Dep’t of Ecology, 511 U.S. 700, 712 (1994). In addition,\\n\\nthe regulations allow for Virginia to consider activities that impact the upland areas that\\n\\nmay have the potential to affect water quality but do not fall under the scope of a VWP\\n\\npermit when the pipeline is over 36 inches inside diameter. Va. Code § 62.1-44.15:80.\\n\\n\\n\\n IV.\\n\\n Atlantic applied for the certificate of public convenience and necessity from FERC\\n\\nand Section 404 authorization from the Army Corps in September 2015. Atlantic filed an\\n\\namendment to its FERC certificate application in March 2016. In October 2017, FERC\\n\\nissued the certificate to Atlantic to construct and operate the pipeline. On April 7, 2017,\\n\\nthe DEQ issued a Section 401 Certification for the wetland, river, and streams crossings\\n\\nas covered in the Section 404 Nationwide Permit 12. In May 2017, the DEQ explained\\n\\nthat the Section 401 Certification for the Pipeline would entail two separate parts: (1) the\\n\\n 7\\n\\fcertification for the Army Corps Nationwide Permit 12, issued in April, applying to the\\n\\nPipeline’s wetland, river, and streams crossings (the “Wetlands and Streams\\n\\nCertification”), and (2) an additional Section 401 Certification review process to evaluate\\n\\nthe “upland” impacts of the Pipeline, terrestrial areas that are not covered by the Army\\n\\nCorps Permit (the “Upland Certification”). Specifically, the Upland Certification would\\n\\n“include all proposed upland activities associated with the construction, operation,\\n\\nmaintenance, and repair of the pipeline, any components thereof or appurtenances\\n\\nthereto, and related access roads and rights-of-way as well as certain project related\\n\\nsurface water withdrawals.” J.A 1083.\\n\\n On November 9, 2017, the DEQ recommended that the Board approve a Section\\n\\n401 Upland Certification of the project. On December 20, 2017, the Board issued the\\n\\nUpland Certification for the ACP with conditions. This Certification was distinct from\\n\\nthe Wetlands and Steams Certification. This Upland Certification provided that it “shall\\n\\nbe effective only following submission, review and final approval as required by law of\\n\\nthe Karst Mitigation Plan, Annual Standards and Specifications, and Erosion and\\n\\nSediment Control Plans and Storm Water Management Plans, and a report to the Board\\n\\nand the public by DEQ on the adequacy of these materials.” J.A. 29.\\n\\n Petitioners timely filed two petitions for review of the Certification on January 18,\\n\\n2018. The petitions were consolidated by court order on January 31, 2018. We possess\\n\\njurisdiction to review the Board’s Section 401 Upland Certification pursuant to 15 U.S.C.\\n\\n§ 717r(d)(1).\\n\\n\\n\\n 8\\n\\f The petitioners contend the Board’s issuance of the Section 401 Upland\\n\\nCertification was arbitrary and capricious and should be vacated for four reasons: (1) the\\n\\nState Agencies effectively invalidated their own finding of reasonable assurance when it\\n\\nvoted to reopen the comment period on the Section 401 Certification of the Army Corps\\n\\nof Engineers Nationwide Permit 12; (2) the State Agencies arbitrarily and capriciously\\n\\nfailed to assess the combined impacts on water quality that would result from multiple\\n\\nareas of construction activities within individual watershed areas; (3) the State Agencies\\n\\narbitrarily and capriciously failed to conduct an adequate antidegradation review; and (4)\\n\\nthe State Agencies arbitrarily and capriciously failed to ensure that the water quality in\\n\\nkarst geology regions would be protected. Respondents and intervenor in turn deny that\\n\\nthe State Agencies acted arbitrarily and capriciously and argue that the petitioners lack\\n\\nstanding to bring this petition.\\n\\n On April 12, 2018, the Board approved a second 30-day public comment period\\n\\nrelated to the Wetlands and Steams Certification. On August 21, 2018, the Board heard a\\n\\npresentation from the DEQ summarizing the public comment period and denied a motion\\n\\nto reevaluate this contested Certification.\\n\\n\\n\\n V.\\n\\n The respondents and intervenor argue as an initial matter that petitioners do not\\n\\nhave standing to litigate this petition for review. Spokeo, Inc. v. Robins, 136 S. Ct. 1540,\\n\\n1547 (2016) (quoting Lujan v. Defenders of Wildlife, 504 U.S. 555, 560-61 (1992))\\n\\n(Article III standing requires (1) an injury-in-fact (2) that is fairly traceable to the\\n\\n 9\\n\\fchallenged conduct of the defendant, and (3) that is likely to be redressed through a\\n\\nfavorable judicial decision). We disagree.\\n\\n This Court has previously rejected respondents’ and intervenor’s arguments on\\n\\nstanding. Sierra Club v. State Water Control Bd., 898 F.3d 383, 400-02 (4th Cir. 2018).\\n\\nPetitioners have established an injury-in-fact even though the State Agencies could\\n\\nchoose to waive certification. We have previously held that the denial of an opportunity,\\n\\nin this case, to have the project vetoed or have additional restrictions can constitute an\\n\\ninjury-in-fact. Id. at 401. In addition, petitioners successfully establish traceability and\\n\\nredressability given that we could vacate the Board’s decision and determine that its\\n\\ndecision was not based on a reasonable assurance and instead was arbitrary and\\n\\ncapricious. Petitioners’ injuries could be remedied if the Board required Atlantic to take\\n\\nadditional measures that would address petitioners’ grievances. In our previous decision\\n\\nwe held petitioners established traceability and redressability in this very context. Id.\\n\\nPetitioners have demonstrated the requirements for standing.\\n\\n\\n\\n VI.\\n\\n We review Virginia’s Section 401 Certification under the standards set forth in the\\n\\nAdministrative Procedures Act (“APA”). See AES Sparrows Point LNG, LLC v. Wilson,\\n\\n589 F.3d 721, 727 (4th Cir. 2009). 1 This Court applies the arbitrary and capricious\\n\\n\\n 1\\n Asserting that the APA is not applicable to actions by State Agencies,\\nrespondents argue that Va. Code § 2.2-4027 establishes the applicable standard of review.\\nThat statute provides that issues of fact shall be decided based on “whether there was\\n(Continued)\\n 10\\n\\fstandard of the APA to the State Agencies’ challenged findings and conclusions. Sierra\\n\\nClub, 898 F.3d at 403.\\n\\n To survive review under the arbitrary and capricious standard, an agency decision\\n\\nmust show that the agency examined “the relevant data and articulate[d] a satisfactory\\n\\nexplanation for its action including a ‘rational connection between the facts found and the\\n\\nchoice made.’” Motor Vehicle Mfrs. Ass’n of U.S., Inc. v. State Farm Mut. Auto Ins. Co.,\\n\\n463 U.S. 29, 43 (1983) (quoting Burlington Truck Lines v. United States, 371 U.S. 156,\\n\\n168 (1962)).\\n\\n Agency action is arbitrary and capricious if the agency relies on factors that\\n Congress did not intend for it to consider, entirely ignores important aspects\\n of the problem, explains its decision in a manner contrary to the evidence\\n before it, or reaches a decision that is so implausible that it cannot be\\n ascribed to a difference in view.\\n\\nBedford Cty. Mem’l Hosp. v. Health & Human Servs., 769 F.2d 1017, 1022 (4th Cir.\\n\\n1985) (citing Motor Vehicle Mfrs. Ass’n, 463 U.S. at 43). This Circuit has held that\\n\\n [r]eview under this standard is highly deferential, with a presumption in\\n favor of finding the agency action valid. Especially in matters involving\\n not just simple findings of fact but complex predictions based on special\\n expertise, a reviewing court must generally be at its most deferential. In\\n determining whether agency action was arbitrary or capricious, the court\\n must consider whether the agency considered the relevant factors and\\n whether a clear error of judgment was made. Although this inquiry into the\\n facts is to be searching and careful, the ultimate standard of review is a\\n narrow one. The court is not empowered to substitute its judgment for that\\n of the agency. Deference is due where the agency has examined the\\n\\n\\n\\n\\nsubstantial evidence in the agency record to support the agency decision.” As we did in\\nSierra Club, we decline to resolve this issue because petitioners’ claims fail even under\\nthe substantial evidence standard. 898 F.3d at 403 n.13.\\n\\n 11\\n\\f relevant data and provided an explanation of its decision that includes a\\n rational connection between the facts found and the choice made.\\n\\nOhio Valley Envtl. Coal. v. Aracoma Coal Co., 556 F.3d 177, 192 (4th Cir. 2009)\\n\\n(internal quotation marks and citations omitted). Nonetheless, if a state agency’s Section\\n\\n401 certification is found to be arbitrary and capricious, the Court must vacate the\\n\\ncertification. 5 U.S.C. § 706(2)(A).\\n\\n\\n\\n VII.\\n\\n A.\\n\\n Turning to petitioners’ first argument, we hold that the decision to reopen the\\n\\ncomment period did not render the State Agencies’ Section 401 Upland Certification\\n\\narbitrary and capricious. The comment period was re-opened for the Wetlands and\\n\\nStreams Certification and not the Upland Certification at issue in this case. In any event,\\n\\nthe Wetlands and Streams Certification was not ultimately revoked.\\n\\n B.\\n\\n Moving to the petitioners’ second argument, we conclude that the State Agencies’\\n\\ndecision not to conduct a combined effect analysis does not render their issuance of a\\n\\nSection 401 Upland Certification arbitrary and capricious for three reasons.\\n\\n First, the Section 401 Upland Certification in question deals with project-related\\n\\nactivities taking place in upland areas. The Upland Certification supplemented the FERC\\n\\ncertificate and the prior Wetland and Streams Certification of the Army Corps’\\n\\nNationwide Permit 12 regarding waterways and utility line crossings. As the State\\n\\n\\n 12\\n\\fAgencies explained, “the conditions in the proposed additional 401 Certification are in\\n\\naddition to any other Federal or State permit or regulatory requirements including the\\n\\nexpressed conditions imposed by FERC.” J.A. 1059. The Upland Certification in\\n\\nquestion is not designed to function as a stand-alone document, comprehensively\\n\\ncovering all pieces of relevant data and potentialities. For example, record evidence\\n\\navailable to the State Agencies explains, “while the impacts to jurisdictional waters\\n\\nauthorized by the Corps under Section 404 of the Clean Water Act are separate from\\n\\nupland activities that are the subject of this Certification, the Corps also analyzed the\\n\\ncumulative effects of linear utility projects and found that the individual and cumulative\\n\\nadverse effects on the aquatic environment resulting from the activities authorized by the\\n\\nNationwide Permit 12 will be no more than minimal and each crossing is a single and\\n\\ncomplete project.” J.A. 999. The Army Corps examined cumulative impacts, and it\\n\\nwould be redundant and inefficient for the State Agencies to duplicate these efforts. The\\n\\nUpland Certification works in conjunction with other regulatory tools and cannot be\\n\\njudged in a void, and it supplements other pieces of the regulatory framework. It is not\\n\\nrequired to cover combined effect analysis because other parts of the regulatory process\\n\\nsufficiently address that subject matter. The State Agencies in the current appeal used\\n\\ntheir resources to issue the Upland Certification to fill an information gap regarding the\\n\\nimpact of upland activities, which were not typically covered under prior CWA\\n\\ncertifications. The State Agencies properly made a unique contribution instead of\\n\\nduplicating the efforts of other regulatory bodies as petitioners’ request. See Sierra Club,\\n\\n898 F.3d at 407.\\n\\n 13\\n\\f Second, State Agencies have broad discretion when developing the criteria for\\n\\ntheir Section 401 Certification. The only requirement imposed by the regulations is that\\n\\nStates must establish procedures for public notice when there are applications for\\n\\ncertification, and to the extent deemed appropriate, procedures for public hearings in\\n\\nconnection with specific applications. 33 U.S.C. § 1341(a)(1). Nonetheless, nothing in\\n\\nSection 401 restricts states to a single certificate proceeding, and Section 401 does not\\n\\nrequire states to undertake a single cumulative review of all possible impacts in a single\\n\\ncertification.\\n\\n Petitioners’ rely on two federal regulations in arguing that a cumulative review is\\n\\nrequired, 40 C.F.R. § 230.7(a) and 40 C.F.R. § 230.11(g)(1), but those regulations impose\\n\\nduties—including a duty to make factual determinations and consider cumulative\\n\\neffects—on the Army Corps under Section 404, not on states under Section 401.\\n\\nMoreover, petitioners contend that two cases require State Agencies to take into account\\n\\ncombined effects lest their decisions be rendered arbitrary and capricious. See Klamath-\\n\\nSiskiyou Wildlands Ctr. v. BLM, 387 F.3d 989, 993 (9th Cir. 2004); Idaho Rivers United\\n\\nv. Probert, Case No.: 3:16-102, 2016 U.S. Dist. LEXIS 63767, at *32-34. Furthermore,\\n\\npetitioners invoke the Supreme Court’s decision in Motor Vehicles Manufacturers\\n\\nAssociation v. State Farm Mutual Automobile Ins. Co., to argue that all “relevant data”\\n\\nmust be considered. 463 U.S. 29, 43 (1983). We conclude, however, that both the\\n\\nKlamath-Siskiyou Wildlands and Idaho Rivers United cases are distinguishable and\\n\\nunpersuasive because in those cases the Bureau of Land Management and the Forest\\n\\nService, respectively, faced violations under NEPA, not the CWA. Klamath-Siskiyou\\n\\n 14\\n\\fWildlands Ctr., 387 F.3d at 993–94; Idaho Rivers United, 2016 U.S. Dist. LEXIS 63767,\\n\\nat *33. Unlike the CWA, NEPA requires a cumulative effects analysis, and thus cases\\n\\ndecided under NEPA are not dispositive authority here. Furthermore, Motor Vehicle\\n\\nManufacturers Association, which deals with the National Highway Traffic Safety\\n\\nAdministration, does not mention cumulative effects or the CWA, and thus the case does\\n\\nnot stand for the proposition that the CWA should be broadened to encompass a\\n\\ncombined impact analysis.\\n\\n Finally, the State Agencies’ failure to explicitly consider the combined effects of\\n\\nmultiple areas of construction within individual watersheds such as the Chesapeake Bay\\n\\nwatershed and the Chesapeake Bay Total Maximum Daily Load (“Bay TMDL”) did not\\n\\nrender their decision arbitrary and capricious. 2 As an initial matter, despite petitioners’\\n\\npreferences, there are no express regulations that require the State Agencies to consider\\n\\nthe combined effects of individual watersheds. In addition, the Ninth Circuit has\\n\\nexplained that TMDLs like the Chesapeake Bay TMDL are “primarily informational\\n\\ntools that allow states to proceed from the identification of water requiring additional\\n\\nplanning to the required plans.” Pronsolino v. Nastri, 291 F. 3d 1123, 1129 (9th Cir.\\n\\n2002). Moreover, TMDLs do not give rise to an independent legal obligation.\\n\\nPronsolino, 291 F.3d 1123, 1140. Consequently, the Chesapeake TMDL does not\\n\\nconstitute a regulatory mandate that the State Agencies were required to address before\\n\\nissuing the Section 401 Upland Certification. Furthermore, protection measures for the\\n\\n 2\\n The Bay TMDL is a federal-state partnership that monitors the water quality\\nstandards in the Chesapeake Bay and its related tributaries. J.A. 888.\\n\\n 15\\n\\fChesapeake Bay TMDL are offered through other tools such as the FERC EIS and the\\n\\nStorm Water Prevention Plan. J.A. 664-665; 1138-1140.\\n\\n The State Agencies more than satisfied their obligations by reviewing upland\\n\\nactivities as well as stream and wetland crossings. The Board’s decisions are not\\n\\nrendered arbitrary and capricious because it did not conduct an independent review of the\\n\\ncumulative effects on water quality within individual watersheds, even if this was\\n\\npetitioners’ preference. To deem an agency action arbitrary and capricious their decision\\n\\nmust be “so implausible that it could not be ascribed to a difference in view or the\\n\\nproduct of agency expertise.” State Farm Mut. Auto. Ins. Co., 463 U.S. at 43. The lack\\n\\nof an explicit combined effect analysis in the Section 401 Upland Certification does not\\n\\nrise to this level, especially given that there are other regulatory tools that were utilized to\\n\\nconsider those impacts.\\n\\n C.\\n\\n 1.\\n\\n Turning to petitioners’ third argument, we do not find that the State Agencies’\\n\\nreasonable assurance determination to be arbitrary and capricious simply because they\\n\\nrelied on existing Virginia water quality standards and regulations to effectively address\\n\\nconcerns regarding water quality deterioration.\\n\\n Under the CWA, “states have the primary role in promulgating water quality\\n\\nstandards.” Piney Run Preservation Ass’n v. County Comm’rs of Carroll Cty., 268 F.3d\\n\\n255, 265 n.9 (4th Cir. 2001). States must initially classify the uses for which their water\\n\\nis to be protected and then determine the necessary level of water quality for their\\n\\n 16\\n\\fpreferred uses. See NRDC v. EPA, 16 F.3d 1395, 1400 (4th Cir. 1993). Virginia’s water-\\n\\nquality policy is relevant in two respects: its narrative water-quality criterion and its anti-\\n\\ndegradation policy.\\n\\n Virginia’s water-quality criterion mandates that “State waters . . . shall be free\\n\\nfrom substances attributable to . . . waste in concentrations, amounts, or combinations\\n\\nwhich contravene established standards or interfere directly or indirectly with designated\\n\\nuses of such water or which are inimical or harmful to human, animal, plant, or aquatic\\n\\nlife.” 9 Va. Admin. Code § 25-260-20(A). The regulation explains that any substance\\n\\n“that produce[s] . . . turbidity” is a substance to be controlled. Id. The regulation\\n\\nprovides examples of “turbidity” such as floating debris, oil, and other materials that are\\n\\nsuspended solids in a body of water.\\n\\n In addition, Virginia’s antidegradation policy shall be applied whenever any\\n\\nactivity is proposed that has the potential to affect existing surface water quality. 9 Va.\\n\\nAdmin. Code § 25-260-30(A). The antidegradation policy classifies Virginia’s water into\\n\\nthree tiers and provides differing levels of protection based on the water’s tier. See 9 Va.\\n\\nAdmin. Code § 25-260-30(A).\\n\\n The Policy defines Tier 3 waters as “exceptional”; these waters “shall be\\n\\nmaintained and protected to prevent permanent or long-term degradation or impairment.”\\n\\n9 Va. Admin. Code § 25-260-30(A)(3)(b)(1). The policy specifically provides that “[n]o\\n\\nnew, additional, or increased discharge of sewage, industrial wastes or other pollution\\n\\ninto [Tier 3 waters] shall be allowed.” 9 Va. Admin. Code § 25-260-30(A)(3)(b)(2).\\n\\nNonetheless, “[a]ctivities causing temporary sources of pollution may be allowed in [Tier\\n\\n 17\\n\\f3 waters] even if degradation may be expected to temporarily occur provided that after a\\n\\nminimal period of time the waters are returned or restored to conditions equal to or better\\n\\nthan those existing just prior to the temporary source of pollution.” 9 Va. Admin. Code\\n\\n§ 25-260-30(A)(3)(b)(3).\\n\\n The Policy defines Tier 2 waters as those that “exceed water quality standards.” 9\\n\\nVa. Admin. Code § 25-260-30(A)(2). The protection for these waters and their quality\\n\\nare lower and the regulation states that the quality of Tier 2 waters “shall be maintained\\n\\nand protected unless the board finds . . . that allowing lower water quality is necessary to\\n\\naccommodate important economic or social development in the area in which the waters\\n\\nare located.” 9 Va. Admin. Code § 25-260-30(A)(2).\\n\\n Last, Tier 1 waters constitute all Virginia waters that are not designated Tier 2 or\\n\\nTier 3. The regulation classifying the level of protection for these waters’ states,\\n\\n“existing in-stream water uses and the level of water quality necessary to protect the\\n\\nexisting uses shall be maintained and protected.” 9 Va. Admin. Code § 25-260-30(A)(1).\\n\\n In Virginia a project may be permitted under a Construction General Permit. 9\\n\\nVa. Admin. Code § 25-880-70 Part II. The Construction General Permit incorporates the\\n\\nrequirements of two other state laws, the Virginia Storm Water Management (“VSM”)\\n\\nLaw, Va. Code § 62.1-44.15:24 et seq., and the Virginia Erosion and Sediment Control\\n\\n(“VESC”) Law, Va. Code § 62.1-44.15:51, et seq.\\n\\n The CWA has an exemption for natural gas pipeline construction projects and\\n\\ntherefore Virginia’s regulatory scheme diverges from the federal environmental\\n\\nprotections. See 33 U.S.C. § 1342(I)(2). Consequently, Virginia still regulates natural\\n\\n 18\\n\\fgas pipeline projects through its Annual Standards and Specifications (“AS&S”)\\n\\nProgram. See Va. Code § 62.1-44.15:55(D). The AS&S program requires a project\\n\\ndeveloper to submit annual standards and specifications for DEQ’s review and approval.\\n\\nSee 9 Va. Admin. Code § 25-870-170(A). Through this program Virginia ensures that\\n\\nprojects will meet the same requirements imposed on other projects subject to the\\n\\nVirginia Construction General Permit. See 9 Va. Admin. Code § 25-870-170(A).\\n\\nNonetheless, once DEQ approves a developer’s annual standards and specifications as\\n\\nsatisfying the requirements of the VSM and VESC, the entity generally need not submit\\n\\nsite-specific VSM and VESC plans to DEQ for approval. See Va. Code § 62.1-\\n\\n44.15:55(D). This allows the projects to become more self-regulating.\\n\\n Typically, ensuring an activity’s compliance with water quality standards requires\\n\\nan antidegradation review. See Nat. Res. Def. Council, Inc. v. EPA, 16 F.3d 1395, 1400\\n\\n(4th Cir. 1993); see also 40 C.F.R. § 131.12 (requiring states to develop and adopt a\\n\\nstatewide antidegradation policy). The CWA’s antidegradation policy requires that state\\n\\nstandards be “sufficient to maintain existing beneficial uses of navigable waters,\\n\\npreventing further degradation.” 33 U.S.C. § 1313(d). State antidegradation policies\\n\\nmust be consistent with 40 C.F.R. § 131.12(a), and must protect existing uses, maintain\\n\\nthe existing quality of high-quality waters unless degradation is justified by important\\n\\nsocioeconomic development, and prohibit degradation of national resource waters. Id.\\n\\n§ 131.12(a).\\n\\n\\n\\n\\n 19\\n\\f 2.\\n\\n We do not find that the State Agencies’ failure to conduct a separate\\n\\nantidegradation review before issuing its Upland Certification renders their decision\\n\\narbitrary and capricious for two reasons.\\n\\n First, in Virginia, the AS&S program requires a project developer to submit annual\\n\\nstandards and specifications for DEQ’s review and approval, thereby ensuring that\\n\\nprojects will meet the same requirements that would apply were they covered by the\\n\\nVirginia Construction General Permit. See 9 Va. Admin. Code § 25-870-170(A). The\\n\\nAS&S also incorporate all the requirements of EPA’s Construction General Permit. J.A.\\n\\n1124-1125. The AS&S in this case were developed over eighteen months and represent a\\n\\nthorough process of development, revision and refinement to ensure that the ACP meet\\n\\nthe technical and legal requirements for Virginia. J.A. 1087. Both federal and state\\n\\nregulators have concluded that application of technical requirements like those in the\\n\\nAS&S “will not result in a lowering of water quality,” which renders the individualized\\n\\nreview the petitioners suggest “unnecessary.” J.A. 11. There is no indication that these\\n\\nAS&S fail to protect water quality in Virginia. To the contrary, these regulations have\\n\\nbeen found as a matter of law to protect water quality in Virginia. See Kelble v.\\n\\nCommonwealth, Case No. CL 14-762, at 4-5 (Richmond Cir. Ct. Apr. 10, 2017).\\n\\n Second, State Agencies did not have to conduct a separate antidegradation review\\n\\nbecause the impact on sediment on the water would only be temporary. Under FERC’s\\n\\nfinal EIS, it was determined that any water quality impacts stemming from construction\\n\\nwould be temporary. J.A. 623. Even with respect to Tier 3 waters, the policy states that\\n\\n 20\\n\\f“[a]ctivities causing temporary sources of pollution may be allowed in [Tier 3] waters . . .\\n\\neven if degradation may be expected to occur provided that after a minimal period of\\n\\ntime the waters are returned or restored to conditions equal to or better that those existing\\n\\njust prior to the temporary source of pollution.” 9 Va. Admin. Code 25-260-\\n\\n30A(3)(b)(3). Even in the most protected state waters, Virginia does not consider\\n\\ntemporary sources of pollution, such as the construction of the ACP, to violate\\n\\nantidegradation policies.\\n\\n Thus, nothing was arbitrary and capricious about the State Agencies’ decision not\\n\\nto conduct a separate antidegradation review.\\n\\n D.\\n\\n Turning to the final challenge raised by petitioners, we find that the State\\n\\nAgencies’ treatment of karst terrain was not arbitrary or capricious because of the\\n\\nconditions imposed on the Section 401 Upland Certification.\\n\\n Karst geology refers to geological formations of soluble limestone bedrock that\\n\\ncreates underground water flow systems where the rocks have dissolved and created\\n\\nsinkholes, caves and underground springs and rivers. J.A. 669. The constitution of these\\n\\nareas presents additional environmental considerations for pipeline construction\\n\\nincluding, sinkhole collapse, sinkhole flooding and associated groundwater\\n\\ncontamination. J.A. 904-905.\\n\\n The record demonstrates that the State Agencies took petitioners’ concerns\\n\\nregarding karst geology into consideration. J.A. 31. Virginia’s Section 401 Upland\\n\\nCertification contains five specific requirements concerning the protection of karst\\n\\n 21\\n\\fterrain. J.A. 31-32. First, Atlantic must provide the State an addendum to a 51-page\\n\\nKarst Survey Report prior to any land disturbing activities. J.A. 212-237; J.A. 31.\\n\\nSecond, Atlantic must follow the Karst Terrain Assessment, Construction, Monitoring,\\n\\nand Mitigation Plan. J.A. 31. This plan allows for route adjustments to avoid karst\\n\\nterrain. J.A. 1001. Third, based on the conditions in the Section 401 Upland\\n\\nCertification, Atlantic must conduct contingency planning in order to address any\\n\\naccidental spills or releases during construction on karst terrain. Fourth, water surveys\\n\\nregarding drinkable water in karst regions are required under the Section 401 Upland\\n\\nCertification. J.A. 31. Finally, Atlantic has a liability of five million dollars to cover the\\n\\ncost of any impacts to private water supplies, which encompasses karst regions. J.A. 32.\\n\\n Reliance on these conditions, even the prospective ones, does not render the State\\n\\nAgencies’ issuance of the Section 401 Upland Certification arbitrary and capricious. See\\n\\nPort of Seattle v. Pollution Control Hearings Bd., 90 P.3d 659, 677 (Wash. 2004)\\n\\n(holding regulators did not act arbitrarily or capriciously by basing reasonable assurance\\n\\n“on future submissions of revised plans, reports, and studies, so long as their\\n\\nimplementation and anticipated outcome meet the reasonable assurance test”).\\n\\n Moreover, the mere existence of risk to karst geology does not render the State\\n\\nAgencies’ decision to issue the Section 401 Upland Certification arbitrary and capricious.\\n\\nBased on the information in the record, this Court finds that the State Agencies had\\n\\nreasonable assurance that karst regions would be protected given the conditions imposed\\n\\non the Section 401 Upland Certification. We “see no purpose we would serve by\\n\\nstepping in and second-guessing the analytical methods Virginia deemed appropriate to\\n\\n 22\\n\\fprovide it with reasonable assurance that its water quality would be protected.” Sierra\\n\\nClub., 898 F.3d at 407.\\n\\n\\n\\n VIII.\\n\\n Governmental agencies can always take additional steps to increase the protection\\n\\nof the environment. But that is not the applicable legal standard this Court utilizes when\\n\\nreviewing a state agency’s issuance of a Section 401 Certification. We must determine\\n\\n“whether the agency considered the relevant factors and whether a clear error of\\n\\njudgment was made.” Ohio Valley Envtl. Coal., 556 F.3d 177, 192. There is no\\n\\nindication that the State Agencies did not consider relevant factors or that they clearly\\n\\nmade an error of judgment. In conclusion, because we find that the State Agencies did\\n\\nnot act arbitrarily and capriciously in issuing the Section 401 Upland Certification, we\\n\\ndeny the petition for review.\\n\\n\\n\\n PETITION FOR REVIEW DENIED\\n\\n\\n\\n\\n 23\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":95,"cells":{"id":{"kind":"number","value":4582070,"string":"4,582,070"},"name":{"kind":"string","value":"John S. BENNETT, Plaintiff - Appellant, v. James GARNER; Virtus Consulting, LLC, Defendants - Appellees."},"name_abbreviation":{"kind":"string","value":"John Bennett v. James Garner"},"decision_date":{"kind":"string","value":"2019-01-16"},"docket_number":{"kind":"string","value":"18-1531"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Keenan, Floyd, Thacker\", \"parties\": \"\", \"opinions\": [{\"author\": \"BARBARA MILANO KEENAN, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1531\\n\\n\\nJOHN S. BENNETT,\\n\\n Plaintiff - Appellant,\\n\\n v.\\n\\nJAMES GARNER; VIRTUS CONSULTING, LLC,\\n\\n Defendants - Appellees.\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. Claude M. Hilton, Senior District Judge. (1:17-cv-00574-CMH-TCB)\\n\\n\\nArgued: December 13, 2018 Decided: January 16, 2019\\n\\n\\nBefore KEENAN, FLOYD, and THACKER, Circuit Judges.\\n\\n\\nVacated and remanded by published opinion. Judge Keenan wrote the opinion, in which\\nJudge Floyd and Judge Thacker joined.\\n\\n\\nARGUED: Kevin M. O’Donnell, HENRY & O’DONNELL, PC, Alexandria, Virginia,\\nfor Appellant. Thomas Wayne Biggs II, DYCIO & BIGGS, Fairfax, Virginia, for\\nAppellees. ON BRIEF: Jeffery T. Martin, Jr., HENRY & O’DONNELL, PC,\\nAlexandria, Virginia, for Appellant. Daniel F. Izzo, DYCIO & BIGGS, Fairfax,\\nVirginia, for Appellees.\\n\\fBARBARA MILANO KEENAN, Circuit Judge:\\n\\n John S. Bennett appeals from the district court’s award of summary judgment in\\n\\nfavor of his former employer, Virtus Consulting, LLC (Virtus), and its owner, James\\n\\nGarner (collectively, the defendants), in Bennett’s action seeking to collect on a state\\n\\ncourt judgment entered against the defendants. The district court held that Bennett’s\\n\\nclaims were precluded under Virginia’s doctrine of res judicata.\\n\\n Upon our review, we conclude that Bennett’s claims are not precluded, because\\n\\nBennett could not have brought those claims at the time of his earlier litigation.\\n\\nAccordingly, we vacate the district court’s judgment and remand for further proceedings.\\n\\n\\n\\n I.\\n\\n We present the facts in the light most favorable to Bennett, the nonmoving party,\\n\\nand draw all reasonable inferences in his favor. Rosetta Stone Ltd. v. Google, Inc., 676\\n\\nF.3d 144, 150 (4th Cir. 2012) (citation omitted). Virtus is a Virginia limited liability\\n\\ncompany that provides consulting services to various financial institutions. Garner is the\\n\\nowner and sole member of Virtus. Bennett was employed by Virtus and worked as the\\n\\nprincipal contact for one of Virtus’ largest clients.\\n\\n In 2012, Garner began negotiations to sell Virtus’ assets to the Solomon Edwards\\n\\nGroup (SEG). Around the same time, the defendants and Bennett signed an agreement,\\n\\nin which Bennett agreed to assist in the sale in exchange for “sharing [in the] proceeds”\\n\\nfrom the sale (the Bennett Agreement). Under the Bennett Agreement, once the sale to\\n\\nSEG successfully closed, Bennett would receive a fixed cash payment made in quarterly\\n\\n 2\\n\\finstallments. The parties also agreed that Bennett potentially could receive two annual\\n\\n“earn out” payments, depending on whether SEG and Garner achieved certain revenue\\n\\ntargets in the two years following the sale.\\n\\n The sale of Virtus’ assets to SEG successfully closed around the end of September\\n\\n2012. In accordance with the Bennett Agreement, Garner made the first two quarterly\\n\\ninstallment payments to Bennett. But, in April 2013, the defendants ceased making any\\n\\nfurther payments, claiming that Bennett had breached his obligations under the\\n\\nagreement. Bennett, however, maintained that he was entitled to the remaining\\n\\ninstallment payments and the “earn out” payments.\\n\\n The parties submitted their dispute to an arbitrator as required by the arbitration\\n\\nclause in the Bennett Agreement. During the arbitration proceedings, the defendants\\n\\nprovided Bennett documents describing the structure of the SEG sale but did not produce\\n\\nany of Virtus’ financial records or bank statements. In response to a request seeking\\n\\nthose financial records, the defendants stipulated that the Bennett Agreement was\\n\\nproperly executed and that the performance metrics triggering the “earn out” payments\\n\\nhad been “met in full.”\\n\\n In September 2014, the arbitrator ordered Virtus to pay Bennett $387,500. Under\\n\\nthe terms of the Bennett Agreement, the arbitrator held Garner jointly and severally liable\\n\\nfor $125,000 of that award. The award was confirmed by a Virginia circuit court and\\n\\nreduced to a judgment. Although Garner paid the portion of the award for which he\\n\\npersonally was liable, Virtus failed to pay the remaining $262,500.\\n\\n\\n\\n 3\\n\\f After the arbitration award was confirmed, Bennett obtained Virtus’ bank\\n\\nstatements. These statements showed that shortly before the SEG sale closed, Garner had\\n\\ntransferred substantially all of Virtus’ cash reserves to himself. Further, Bennett learned\\n\\nthat the SEG sale had been structured to divert all cash and other consideration from the\\n\\nsale to Garner personally. For instance, equity stock in SEG that was supposed to\\n\\ntransfer to Virtus as part of the sale was instead listed in Garner’s name and reported as\\n\\npart of Garner’s personal tax returns. Thus, Virtus lacked sufficient assets to satisfy\\n\\nBennett’s judgment.\\n\\n In May 2017, Bennett initiated the present action in the district court seeking to\\n\\ncollect on his judgment. He asserted four claims against the defendants: (1) fraudulent\\n\\nconveyance, in violation of Virginia Code § 55-80; (2) voluntary transfer, in violation of\\n\\nVirginia Code § 55-81 (together, the fraudulent transfer claims); (3) a claim seeking to\\n\\n“pierce the corporate veil” and recover the judgment amount directly from Garner (the\\n\\nalter-ego claim); and (4) fraud in the inducement. The district court granted the\\n\\ndefendants’ motion for summary judgment, concluding that Bennett’s fraudulent transfer\\n\\nclaims and alter-ego claim were precluded under Virginia’s doctrine of res judicata. 1\\n\\nThis appeal followed.\\n\\n\\n\\n\\n 1\\n The district court also awarded the defendants summary judgment on Bennett’s\\nfraud in the inducement claim, concluding that it was barred by the two-year statute of\\nlimitations governing fraud claims, Va. Code § 8.01-243(A). Bennett does not contest\\nthe dismissal of the fraud in the inducement claim.\\n\\n\\n 4\\n\\f II.\\n\\n We review de novo the district court’s award of summary judgment. Rosetta\\n\\nStone Ltd., 676 F.3d at 150.\\n\\n A.\\n\\n Before addressing the parties’ arguments, we begin by reviewing the applicable\\n\\nprinciples of res judicata. In considering the preclusive effect of an earlier state court\\n\\njudgment on a new claim, we apply the “preclusion law of the State in which judgment\\n\\nwas rendered.” In re Genesys Data Techs., Inc., 204 F.3d 124, 127 (4th Cir. 2000)\\n\\n(quoting Marrese v. Am. Acad. of Orthopedic Surgeons, 470 U.S. 373, 380 (1985)).\\n\\nHere, the arbitration award was confirmed and reduced to a judgment by a Virginia court.\\n\\nWe therefore apply Virginia’s principles of res judicata.\\n\\n In Virginia, res judicata 2 is governed by Rule 1:6 of the Rules of the Supreme\\n\\nCourt of Virginia, which states in relevant part:\\n\\n A party whose claim for relief arising from identified conduct, a\\n transaction, or an occurrence, is decided on the merits by a final judgment,\\n shall be forever barred from prosecuting any second or subsequent civil\\n action against the same opposing party or parties on any claim or cause of\\n action that arises from that same conduct, transaction or occurrence,\\n whether or not the legal theory or rights asserted in the second or\\n subsequent action were raised in the prior lawsuit, and regardless of the\\n legal elements or the evidence upon which any claims in the prior\\n proceeding depended, or the particular remedies sought.\\n\\n\\n\\n\\n 2\\n Although Virginia’s res judicata doctrine encompasses both claim preclusion and\\nissue preclusion, here we use the term “res judicata” to refer to claim preclusion only.\\nSee Funny Guy, LLC v. Lecego, LLC, 795 S.E.2d 887, 890 (Va. 2017).\\n\\n 5\\n\\fVa. Sup. Ct. R. 1:6(a). Under this rule, “a final judgment forecloses ‘successive litigation\\n\\nof the very same claim, whether or not relitigation of the claim raises the same issues as\\n\\nthe earlier suit.’” Lee v. Spoden, 776 S.E.2d 798, 803 (Va. 2015) (quoting Taylor v.\\n\\nSturgell, 553 U.S. 880, 892 (2008)). Parties, therefore, may not relitigate “the same\\n\\ncause of action or any part thereof which could have been litigated in the previous\\n\\naction.” D’Ambrosio v. Wolf, 809 S.E.2d 625, 628 (Va. 2018) (citation omitted). Stated\\n\\nsimply, res judicata operates to prevent a party from getting a “second bite of the apple”\\n\\nwith respect to wrongs arising from a single dispute. See Funny Guy, LLC v. Lecego,\\n\\nLLC, 795 S.E.2d 887, 890 (Va. 2017) (“The law should afford one full, fair hearing\\n\\nrelating to a particular problem—but not two.” (citation omitted)).\\n\\n While ostensibly a broad proposition, res judicata nonetheless is limited by\\n\\nlongstanding principles. For instance, claims brought solely to execute on a judgment are\\n\\ngenerally not precluded by prior litigation that resulted in that judgment. See State Farm\\n\\nMut. Auto. Ins. Co. v. Kelly, 380 S.E.2d 654, 655 n.2 (Va. 1989); see also Restatement 2d\\n\\nJudgments § 18(c). Similarly, res judicata does “not bar a claim that does not accrue\\n\\nprior to the litigation triggering the bar.” Funny Guy, 795 S.E.2d at 900 (emphasis\\n\\nadded). A party is not precluded from bringing a claim that he was unable to bring in the\\n\\ninitial litigation, regardless whether that claim constitutes part of the same “conduct,\\n\\ntransaction, or occurrence.” D’Ambrosio, 809 S.E.2d at 628; Funny Guy, 795 S.E.2d at\\n\\n890 (“Determining which claims should have been brought in earlier litigation largely\\n\\ndepends on which claims could have been brought.” (citation omitted)); see also Lawlor\\n\\nv. Nat’l Screen Serv. Corp., 349 U.S. 322, 328 (1955) (explaining that although an earlier\\n\\n 6\\n\\fjudgment “precludes recovery on claims arising prior to its entry, it cannot be given the\\n\\neffect of extinguishing claims which did not even then exist”). With these principles in\\n\\nmind, we turn to consider the parties’ arguments.\\n\\n B.\\n\\n As the parties asserting res judicata, the defendants bear the burden of showing\\n\\nthat it is more likely than not that Bennett’s claims should be precluded by the prior\\n\\njudgment. D’Ambrosio, 809 S.E.2d at 628. The defendants argue, as they did in the\\n\\ndistrict court, that because Bennett had knowledge of the structure of the SEG sale at the\\n\\ntime of the arbitration, Bennett could have raised both his fraudulent transfer and alter-\\n\\nego claims during those proceedings. Accordingly, the defendants contend that under\\n\\nVirginia’s doctrine of res judicata, Bennett must have brought those claims during the\\n\\narbitration proceedings.\\n\\n In response, Bennett generally maintains that his claims are brought solely in\\n\\nexecution of his state court judgment. That is, instead of seeking to “relitigate” the\\n\\ndefendants’ liability under the Bennett Agreement, Bennett argues that his fraudulent\\n\\ntransfer claims were an attempt to collect on the judgment he is owed and could not have\\n\\nbeen brought before the judgment was entered. With respect to his alter-ego claim,\\n\\nBennett similarly argues that he could not have maintained that claim before obtaining\\n\\nthe judgment against Virtus. We agree with Bennett and address each argument in turn.\\n\\n 1.\\n\\n We begin by considering the question whether Bennett could have raised his\\n\\nfraudulent transfer claims during the arbitration proceedings. Actions brought under\\n\\n 7\\n\\fVirginia’s fraudulent conveyance statute, Va. Code § 55-80, and the state’s voluntary\\n\\ntransfer statute, Va. Code § 55-81, assist creditors in collecting on a judgment or other\\n\\ndebt. See La Bella Dona Skin Care, Inc. v. Belle Femme Enters., LLC, 805 S.E.2d 399,\\n\\n406 (Va. 2017); Balzer & Assocs., Inc. v. The Lakes on 360, Inc., 463 S.E.2d 453, 455-56\\n\\n(Va. 1995). Such actions do not impose liability on the participants in a fraudulent\\n\\nconveyance, but merely unwind “transactions designed to place a debtor’s assets beyond\\n\\nhis creditors’ reach.” La Bella Dona, 805 S.E.2d at 404, 406; see also Mills v. Miller\\n\\nHarness Co., 326 S.E.2d 665, 667 (Va. 1985) (concluding that Virginia Code § 55-80\\n\\ndoes not authorize a court “to award an in personam judgment when a fraudulent\\n\\nconveyance is set aside”). Indeed, Virginia law expressly permits actions under both\\n\\nSections 55-80 and 55-81 to be brought after the entry of a judgment. Va. Code § 55-\\n\\n82.2 (“The court shall have the authority to set aside a fraudulent conveyance or\\n\\nvoluntary transfer pursuant to § 55-80 or § 55-81 during an action brought by a creditor\\n\\nto execute on a judgment.” (emphasis added)). Thus, actions to void wrongful transfers\\n\\nare remedies designed to “return[] the fraudulently conveyed assets to the transferor.” La\\n\\nBella Dona, 805 S.E.2d at 406.\\n\\n In the present case, the disputes that the parties submitted to arbitration focused on\\n\\nthe issue whether Bennett was entitled to receive the remaining payments under the\\n\\nBennett Agreement. Thus, the arbitration served only to establish the parties’ respective\\n\\nobligations and liability under the Bennett Agreement.\\n\\n In contrast, Bennett’s fraudulent transfer claims allege that Virtus depleted its\\n\\ncorporate assets and made improper conveyances to Garner to prevent Bennett from\\n\\n 8\\n\\fcollecting on the arbitration award and judgment. Bennett does not advance any new\\n\\nlegal “theories of recovery” on which either defendant could be held liable under the\\n\\nBennett Agreement. Cf. Funny Guy, 795 S.E.2d at 897-98 (holding that, under principles\\n\\nof res judicata, “alternative theories of recovery” cannot be raised in consecutive\\n\\nlawsuits). Nor does he seek damages beyond the outstanding $262,500 judgment, the\\n\\nprecise amount awarded in arbitration. Although the alleged wrongful transfers took\\n\\nplace around the same time as the SEG sale, those transfers were immaterial to the\\n\\nquestion whether either Bennett or the defendants had breached the Bennett Agreement.\\n\\nThus, Bennett is not seeking a “second bite of the apple” with respect to the amount he is\\n\\nowed. See id. Rather, he seeks only to unwind the allegedly improper transfers from\\n\\nVirtus to Garner so that Virtus can satisfy the existing judgment. 3\\n\\n Furthermore, we observe that had Bennett claimed that the defendants were\\n\\nattempting to defraud him by transferring assets, before he proved that he was entitled to\\n\\npayments under the Bennett Agreement, those fraudulent transfer claims would have\\n\\nbeen premature. At the time of the arbitration proceedings, Bennett did not have\\n\\n\\n 3\\n The defendants incorrectly rely on the Supreme Court of Virginia’s decision in\\nPrice v. Hawkins, 439 S.E.2d 382 (Va. 1994), to argue that Bennett’s fraudulent\\nconveyance claim under Virginia Code § 55-80 is meant to impose liability on Garner. In\\nPrice, the court allowed an in personam judgment to be awarded against recipients of\\nfraudulent transfers when the wrongfully transferred property was only cash. Id. at 385.\\nThis narrowly crafted exception was designed to prevent a defrauded creditor from being\\nleft without a remedy, because cash “cannot be easily located for attachment or levy.” La\\nBella Dona, 805 S.E.2d at 406 (describing the exception in Price). However, the\\nSupreme Court of Virginia has since clarified that the Price exception does not “impose\\nliability upon the grantee[,]” but merely unwinds “the transfer of the cash in the grantee’s\\npockets.” Id.\\n\\n 9\\n\\fsufficient information about Virtus’ financial condition to allege a fraudulent conveyance\\n\\nor voluntary transfer. Neither defendant disclosed any financial records or bank\\n\\nstatements to Bennett during the arbitration. Indeed, as noted above, rather than produce\\n\\nsuch documents, the defendants stipulated that the financial benchmarks in the Bennett\\n\\nAgreement had been “met in full.”\\n\\n It was not until Virtus failed to satisfy the judgment rendered against it, and\\n\\nBennett received Virtus’ relevant financial records, that he learned that Virtus had no\\n\\nremaining assets from which it could pay the judgment. These financial documents also\\n\\ndisclosed the recipient of Virtus’ transferred assets and the nature of such transfers,\\n\\nallowing Bennett to properly plead his fraudulent transfer claims. Thus, it was only after\\n\\nthe state court judgment was entered that Bennett would have had “actual notice” of any\\n\\npotential fraudulent transfer claims. Cf. Luria v. Bd. of Dirs. of Westbriar Condo. Unit\\n\\nOwners Ass’n, 672 S.E.2d 837, 840 (Va. 2009) (recognizing that, while a judgment is not\\n\\nrequired to bring a fraudulent conveyance claim, a plaintiff must have “actual notice of a\\n\\nspecific potential claim” to be considered a “creditor” under Virginia Code § 55-80).\\n\\n On these facts, we hold that Bennett could not have brought his fraudulent transfer\\n\\nclaims in the arbitration proceedings. To conclude otherwise essentially would have\\n\\nrequired Bennett to be clairvoyant. Under the defendants’ logic, a plaintiff in Bennett’s\\n\\nposition would have had to amend his original complaint, adding claims of fraudulent\\n\\nconveyance whenever he suspected that the defendant was moving money to avoid\\n\\npaying a potential judgment. Otherwise, the plaintiff would risk having those claims\\n\\nbarred in a later action to collect on that judgment. In other words, Bennett would have\\n\\n 10\\n\\fhad to try to enforce his judgment before the judgment was awarded. We decline to\\n\\ninterpret Virginia’s res judicata law in a manner that would lead to such untenable results.\\n\\nSee State Water Control Bd. v. Smithfield Foods, Inc., 542 S.E.2d 766, 769 (Va. 2001)\\n\\n(“The doctrine [of res judicata] protects litigants from multiple lawsuits, conserves\\n\\njudicial resources, and fosters certainty and reliance in legal relationships.” (emphasis\\n\\nadded)). Therefore, we hold that Bennett’s fraudulent transfer claims are not precluded\\n\\nunder Virginia’s res judicata doctrine.\\n\\n 2.\\n\\n With respect to Bennett’s alter-ego claim, we similarly conclude that the claim\\n\\ncould not have been brought before the state court judgment was entered against Virtus.\\n\\nWhen an individual uses a corporate form to “disguise wrongs, obscure fraud, or conceal\\n\\ncrime,” Virginia law permits a plaintiff to pierce the corporate veil and to impose liability\\n\\ndirectly on the individual as the “alter ego” of the corporation. Cheatle v. Rudd’s\\n\\nSwimming Pool Supply Co., 360 S.E.2d 828, 831 (Va. 1987). However, before bringing\\n\\nan action to pierce the corporate veil, the plaintiff must “first obtain[] a judgment against\\n\\nthe corporation.” Dana v. 313 Freemason, 587 S.E.2d 548, 553 (Va. 2003). Because\\n\\nBennett was required to obtain a judgment against Virtus before bringing his alter-ego\\n\\nclaim, this claim had not yet accrued at the time of the arbitration proceedings.\\n\\nAccordingly, we hold that Bennett’s alter-ego claim also is not precluded under\\n\\nVirginia’s doctrine of res judicata. See D’Ambrosio, 809 S.E.2d at 628.\\n\\n\\n\\n III.\\n\\n 11\\n\\f For these reasons, we hold that Bennett’s fraudulent transfer claims and his alter-\\n\\nego claim are not precluded under Virginia law by res judicata. 4 Accordingly, we vacate\\n\\nthe district court’s award of summary judgment in favor of the defendants and remand the\\n\\ncase to the district court for further proceedings.\\n\\n VACATED AND REMANDED\\n\\n\\n\\n\\n 4\\n Bennett also asks us to enter summary judgment in his favor on his fraudulent\\ntransfer claims. Because the district court held that Bennett’s action was barred by res\\njudicata, the court did not rule on the merits of Bennett’s claims. We decline to consider\\nthose issues in the first instance. See Graham v. Gagnon, 831 F.3d 176, 189 (4th Cir.\\n2016).\\n\\n 12\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4359323/\", \"author_raw\": \"BARBARA MILANO KEENAN, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"KEENAN"},"judge2":{"kind":"string","value":"FLOYD"},"judge3":{"kind":"string","value":"THACKER"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4582070/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: John S. BENNETT, Plaintiff - Appellant, v. James GARNER; Virtus Consulting, LLC, Defendants - Appellees.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-16\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1531\n\n\nJOHN S. BENNETT,\n\n Plaintiff - Appellant,\n\n v.\n\nJAMES GARNER; VIRTUS CONSULTING, LLC,\n\n Defendants - Appellees.\n\n\nAppeal from the United States District Court for the Eastern District of Virginia, at\nAlexandria. Claude M. Hilton, Senior District Judge. (1:17-cv-00574-CMH-TCB)\n\n\nArgued: December 13, 2018 Decided: January 16, 2019\n\n\nBefore KEENAN, FLOYD, and THACKER, Circuit Judges.\n\n\nVacated and remanded by published opinion. Judge Keenan wrote the opinion, in which\nJudge Floyd and Judge Thacker joined.\n\n\nARGUED: Kevin M. O’Donnell, HENRY & O’DONNELL, PC, Alexandria, Virginia,\nfor Appellant. Thomas Wayne Biggs II, DYCIO & BIGGS, Fairfax, Virginia, for\nAppellees. ON BRIEF: Jeffery T. Martin, Jr., HENRY & O’DONNELL, PC,\nAlexandria, Virginia, for Appellant. Daniel F. Izzo, DYCIO & BIGGS, Fairfax,\nVirginia, for Appellees.\n\fBARBARA MILANO KEENAN, Circuit Judge:\n\n John S. Bennett appeals from the district court’s award of summary judgment in\n\nfavor of his former employer, Virtus Consulting, LLC (Virtus), and its owner, James\n\nGarner (collectively, the defendants), in Bennett’s action seeking to collect on a state\n\ncourt judgment entered against the defendants. The district court held that Bennett’s\n\nclaims were precluded under Virginia’s doctrine of res judicata.\n\n Upon our review, we conclude that Bennett’s claims are not precluded, because\n\nBennett could not have brought those claims at the time of his earlier litigation.\n\nAccordingly, we vacate the district court’s judgment and remand for further proceedings.\n\n\n\n I.\n\n We present the facts in the light most favorable to Bennett, the nonmoving party,\n\nand draw all reasonable inferences in his favor. Rosetta Stone Ltd. v. Google, Inc., 676\n\nF.3d 144, 150 (4th Cir. 2012) (citation omitted). Virtus is a Virginia limited liability\n\ncompany that provides consulting services to various financial institutions. Garner is the\n\nowner and sole member of Virtus. Bennett was employed by Virtus and worked as the\n\nprincipal contact for one of Virtus’ largest clients.\n\n In 2012, Garner began negotiations to sell Virtus’ assets to the Solomon Edwards\n\nGroup (SEG). Around the same time, the defendants and Bennett signed an agreement,\n\nin which Bennett agreed to assist in the sale in exchange for “sharing [in the] proceeds”\n\nfrom the sale (the Bennett Agreement). Under the Bennett Agreement, once the sale to\n\nSEG successfully closed, Bennett would receive a fixed cash payment made in quarterly\n\n 2\n\finstallments. The parties also agreed that Bennett potentially could receive two annual\n\n“earn out” payments, depending on whether SEG and Garner achieved certain revenue\n\ntargets in the two years following the sale.\n\n The sale of Virtus’ assets to SEG successfully closed around the end of September\n\n2012. In accordance with the Bennett Agreement, Garner made the first two quarterly\n\ninstallment payments to Bennett. But, in April 2013, the defendants ceased making any\n\nfurther payments, claiming that Bennett had breached his obligations under the\n\nagreement. Bennett, however, maintained that he was entitled to the remaining\n\ninstallment payments and the “earn out” payments.\n\n The parties submitted their dispute to an arbitrator as required by the arbitration\n\nclause in the Bennett Agreement. During the arbitration proceedings, the defendants\n\nprovided Bennett documents describing the structure of the SEG sale but did not produce\n\nany of Virtus’ financial records or bank statements. In response to a request seeking\n\nthose financial records, the defendants stipulated that the Bennett Agreement was\n\nproperly executed and that the performance metrics triggering the “earn out” payments\n\nhad been “met in full.”\n\n In September 2014, the arbitrator ordered Virtus to pay Bennett $387,500. Under\n\nthe terms of the Bennett Agreement, the arbitrator held Garner jointly and severally liable\n\nfor $125,000 of that award. The award was confirmed by a Virginia circuit court and\n\nreduced to a judgment. Although Garner paid the portion of the award for which he\n\npersonally was liable, Virtus failed to pay the remaining $262,500.\n\n\n\n 3\n\f After the arbitration award was confirmed, Bennett obtained Virtus’ bank\n\nstatements. These statements showed that shortly before the SEG sale closed, Garner had\n\ntransferred substantially all of Virtus’ cash reserves to himself. Further, Bennett learned\n\nthat the SEG sale had been structured to divert all cash and other consideration from the\n\nsale to Garner personally. For instance, equity stock in SEG that was supposed to\n\ntransfer to Virtus as part of the sale was instead listed in Garner’s name and reported as\n\npart of Garner’s personal tax returns. Thus, Virtus lacked sufficient assets to satisfy\n\nBennett’s judgment.\n\n In May 2017, Bennett initiated the present action in the district court seeking to\n\ncollect on his judgment. He asserted four claims against the defendants: (1) fraudulent\n\nconveyance, in violation of Virginia Code § 55-80; (2) voluntary transfer, in violation of\n\nVirginia Code § 55-81 (together, the fraudulent transfer claims); (3) a claim seeking to\n\n“pierce the corporate veil” and recover the judgment amount directly from Garner (the\n\nalter-ego claim); and (4) fraud in the inducement. The district court granted the\n\ndefendants’ motion for summary judgment, concluding that Bennett’s fraudulent transfer\n\nclaims and alter-ego claim were precluded under Virginia’s doctrine of res judicata. 1\n\nThis appeal followed.\n\n\n\n\n 1\n The district court also awarded the defendants summary judgment on Bennett’s\nfraud in the inducement claim, concluding that it was barred by the two-year statute of\nlimitations governing fraud claims, Va. Code § 8.01-243(A). Bennett does not contest\nthe dismissal of the fraud in the inducement claim.\n\n\n 4\n\f II.\n\n We review de novo the district court’s award of summary judgment. Rosetta\n\nStone Ltd., 676 F.3d at 150.\n\n A.\n\n Before addressing the parties’ arguments, we begin by reviewing the applicable\n\nprinciples of res judicata. In considering the preclusive effect of an earlier state court\n\njudgment on a new claim, we apply the “preclusion law of the State in which judgment\n\nwas rendered.” In re Genesys Data Techs., Inc., 204 F.3d 124, 127 (4th Cir. 2000)\n\n(quoting Marrese v. Am. Acad. of Orthopedic Surgeons, 470 U.S. 373, 380 (1985)).\n\nHere, the arbitration award was confirmed and reduced to a judgment by a Virginia court.\n\nWe therefore apply Virginia’s principles of res judicata.\n\n In Virginia, res judicata 2 is governed by Rule 1:6 of the Rules of the Supreme\n\nCourt of Virginia, which states in relevant part:\n\n A party whose claim for relief arising from identified conduct, a\n transaction, or an occurrence, is decided on the merits by a final judgment,\n shall be forever barred from prosecuting any second or subsequent civil\n action against the same opposing party or parties on any claim or cause of\n action that arises from that same conduct, transaction or occurrence,\n whether or not the legal theory or rights asserted in the second or\n subsequent action were raised in the prior lawsuit, and regardless of the\n legal elements or the evidence upon which any claims in the prior\n proceeding depended, or the particular remedies sought.\n\n\n\n\n 2\n Although Virginia’s res judicata doctrine encompasses both claim preclusion and\nissue preclusion, here we use the term “res judicata” to refer to claim preclusion only.\nSee Funny Guy, LLC v. Lecego, LLC, 795 S.E.2d 887, 890 (Va. 2017).\n\n 5\n\fVa. Sup. Ct. R. 1:6(a). Under this rule, “a final judgment forecloses ‘successive litigation\n\nof the very same claim, whether or not relitigation of the claim raises the same issues as\n\nthe earlier suit.’” Lee v. Spoden, 776 S.E.2d 798, 803 (Va. 2015) (quoting Taylor v.\n\nSturgell, 553 U.S. 880, 892 (2008)). Parties, therefore, may not relitigate “the same\n\ncause of action or any part thereof which could have been litigated in the previous\n\naction.” D’Ambrosio v. Wolf, 809 S.E.2d 625, 628 (Va. 2018) (citation omitted). Stated\n\nsimply, res judicata operates to prevent a party from getting a “second bite of the apple”\n\nwith respect to wrongs arising from a single dispute. See Funny Guy, LLC v. Lecego,\n\nLLC, 795 S.E.2d 887, 890 (Va. 2017) (“The law should afford one full, fair hearing\n\nrelating to a particular problem—but not two.” (citation omitted)).\n\n While ostensibly a broad proposition, res judicata nonetheless is limited by\n\nlongstanding principles. For instance, claims brought solely to execute on a judgment are\n\ngenerally not precluded by prior litigation that resulted in that judgment. See State Farm\n\nMut. Auto. Ins. Co. v. Kelly, 380 S.E.2d 654, 655 n.2 (Va. 1989); see also Restatement 2d\n\nJudgments § 18(c). Similarly, res judicata does “not bar a claim that does not accrue\n\nprior to the litigation triggering the bar.” Funny Guy, 795 S.E.2d at 900 (emphasis\n\nadded). A party is not precluded from bringing a claim that he was unable to bring in the\n\ninitial litigation, regardless whether that claim constitutes part of the same “conduct,\n\ntransaction, or occurrence.” D’Ambrosio, 809 S.E.2d at 628; Funny Guy, 795 S.E.2d at\n\n890 (“Determining which claims should have been brought in earlier litigation largely\n\ndepends on which claims could have been brought.” (citation omitted)); see also Lawlor\n\nv. Nat’l Screen Serv. Corp., 349 U.S. 322, 328 (1955) (explaining that although an earlier\n\n 6\n\fjudgment “precludes recovery on claims arising prior to its entry, it cannot be given the\n\neffect of extinguishing claims which did not even then exist”). With these principles in\n\nmind, we turn to consider the parties’ arguments.\n\n B.\n\n As the parties asserting res judicata, the defendants bear the burden of showing\n\nthat it is more likely than not that Bennett’s claims should be precluded by the prior\n\njudgment. D’Ambrosio, 809 S.E.2d at 628. The defendants argue, as they did in the\n\ndistrict court, that because Bennett had knowledge of the structure of the SEG sale at the\n\ntime of the arbitration, Bennett could have raised both his fraudulent transfer and alter-\n\nego claims during those proceedings. Accordingly, the defendants contend that under\n\nVirginia’s doctrine of res judicata, Bennett must have brought those claims during the\n\narbitration proceedings.\n\n In response, Bennett generally maintains that his claims are brought solely in\n\nexecution of his state court judgment. That is, instead of seeking to “relitigate” the\n\ndefendants’ liability under the Bennett Agreement, Bennett argues that his fraudulent\n\ntransfer claims were an attempt to collect on the judgment he is owed and could not have\n\nbeen brought before the judgment was entered. With respect to his alter-ego claim,\n\nBennett similarly argues that he could not have maintained that claim before obtaining\n\nthe judgment against Virtus. We agree with Bennett and address each argument in turn.\n\n 1.\n\n We begin by considering the question whether Bennett could have raised his\n\nfraudulent transfer claims during the arbitration proceedings. Actions brought under\n\n 7\n\fVirginia’s fraudulent conveyance statute, Va. Code § 55-80, and the state’s voluntary\n\ntransfer statute, Va. Code § 55-81, assist creditors in collecting on a judgment or other\n\ndebt. See La Bella Dona Skin Care, Inc. v. Belle Femme Enters., LLC, 805 S.E.2d 399,\n\n406 (Va. 2017); Balzer & Assocs., Inc. v. The Lakes on 360, Inc., 463 S.E.2d 453, 455-56\n\n(Va. 1995). Such actions do not impose liability on the participants in a fraudulent\n\nconveyance, but merely unwind “transactions designed to place a debtor’s assets beyond\n\nhis creditors’ reach.” La Bella Dona, 805 S.E.2d at 404, 406; see also Mills v. Miller\n\nHarness Co., 326 S.E.2d 665, 667 (Va. 1985) (concluding that Virginia Code § 55-80\n\ndoes not authorize a court “to award an in personam judgment when a fraudulent\n\nconveyance is set aside”). Indeed, Virginia law expressly permits actions under both\n\nSections 55-80 and 55-81 to be brought after the entry of a judgment. Va. Code § 55-\n\n82.2 (“The court shall have the authority to set aside a fraudulent conveyance or\n\nvoluntary transfer pursuant to § 55-80 or § 55-81 during an action brought by a creditor\n\nto execute on a judgment.” (emphasis added)). Thus, actions to void wrongful transfers\n\nare remedies designed to “return[] the fraudulently conveyed assets to the transferor.” La\n\nBella Dona, 805 S.E.2d at 406.\n\n In the present case, the disputes that the parties submitted to arbitration focused on\n\nthe issue whether Bennett was entitled to receive the remaining payments under the\n\nBennett Agreement. Thus, the arbitration served only to establish the parties’ respective\n\nobligations and liability under the Bennett Agreement.\n\n In contrast, Bennett’s fraudulent transfer claims allege that Virtus depleted its\n\ncorporate assets and made improper conveyances to Garner to prevent Bennett from\n\n 8\n\fcollecting on the arbitration award and judgment. Bennett does not advance any new\n\nlegal “theories of recovery” on which either defendant could be held liable under the\n\nBennett Agreement. Cf. Funny Guy, 795 S.E.2d at 897-98 (holding that, under principles\n\nof res judicata, “alternative theories of recovery” cannot be raised in consecutive\n\nlawsuits). Nor does he seek damages beyond the outstanding $262,500 judgment, the\n\nprecise amount awarded in arbitration. Although the alleged wrongful transfers took\n\nplace around the same time as the SEG sale, those transfers were immaterial to the\n\nquestion whether either Bennett or the defendants had breached the Bennett Agreement.\n\nThus, Bennett is not seeking a “second bite of the apple” with respect to the amount he is\n\nowed. See id. Rather, he seeks only to unwind the allegedly improper transfers from\n\nVirtus to Garner so that Virtus can satisfy the existing judgment. 3\n\n Furthermore, we observe that had Bennett claimed that the defendants were\n\nattempting to defraud him by transferring assets, before he proved that he was entitled to\n\npayments under the Bennett Agreement, those fraudulent transfer claims would have\n\nbeen premature. At the time of the arbitration proceedings, Bennett did not have\n\n\n 3\n The defendants incorrectly rely on the Supreme Court of Virginia’s decision in\nPrice v. Hawkins, 439 S.E.2d 382 (Va. 1994), to argue that Bennett’s fraudulent\nconveyance claim under Virginia Code § 55-80 is meant to impose liability on Garner. In\nPrice, the court allowed an in personam judgment to be awarded against recipients of\nfraudulent transfers when the wrongfully transferred property was only cash. Id. at 385.\nThis narrowly crafted exception was designed to prevent a defrauded creditor from being\nleft without a remedy, because cash “cannot be easily located for attachment or levy.” La\nBella Dona, 805 S.E.2d at 406 (describing the exception in Price). However, the\nSupreme Court of Virginia has since clarified that the Price exception does not “impose\nliability upon the grantee[,]” but merely unwinds “the transfer of the cash in the grantee’s\npockets.” Id.\n\n 9\n\fsufficient information about Virtus’ financial condition to allege a fraudulent conveyance\n\nor voluntary transfer. Neither defendant disclosed any financial records or bank\n\nstatements to Bennett during the arbitration. Indeed, as noted above, rather than produce\n\nsuch documents, the defendants stipulated that the financial benchmarks in the Bennett\n\nAgreement had been “met in full.”\n\n It was not until Virtus failed to satisfy the judgment rendered against it, and\n\nBennett received Virtus’ relevant financial records, that he learned that Virtus had no\n\nremaining assets from which it could pay the judgment. These financial documents also\n\ndisclosed the recipient of Virtus’ transferred assets and the nature of such transfers,\n\nallowing Bennett to properly plead his fraudulent transfer claims. Thus, it was only after\n\nthe state court judgment was entered that Bennett would have had “actual notice” of any\n\npotential fraudulent transfer claims. Cf. Luria v. Bd. of Dirs. of Westbriar Condo. Unit\n\nOwners Ass’n, 672 S.E.2d 837, 840 (Va. 2009) (recognizing that, while a judgment is not\n\nrequired to bring a fraudulent conveyance claim, a plaintiff must have “actual notice of a\n\nspecific potential claim” to be considered a “creditor” under Virginia Code § 55-80).\n\n On these facts, we hold that Bennett could not have brought his fraudulent transfer\n\nclaims in the arbitration proceedings. To conclude otherwise essentially would have\n\nrequired Bennett to be clairvoyant. Under the defendants’ logic, a plaintiff in Bennett’s\n\nposition would have had to amend his original complaint, adding claims of fraudulent\n\nconveyance whenever he suspected that the defendant was moving money to avoid\n\npaying a potential judgment. Otherwise, the plaintiff would risk having those claims\n\nbarred in a later action to collect on that judgment. In other words, Bennett would have\n\n 10\n\fhad to try to enforce his judgment before the judgment was awarded. We decline to\n\ninterpret Virginia’s res judicata law in a manner that would lead to such untenable results.\n\nSee State Water Control Bd. v. Smithfield Foods, Inc., 542 S.E.2d 766, 769 (Va. 2001)\n\n(“The doctrine [of res judicata] protects litigants from multiple lawsuits, conserves\n\njudicial resources, and fosters certainty and reliance in legal relationships.” (emphasis\n\nadded)). Therefore, we hold that Bennett’s fraudulent transfer claims are not precluded\n\nunder Virginia’s res judicata doctrine.\n\n 2.\n\n With respect to Bennett’s alter-ego claim, we similarly conclude that the claim\n\ncould not have been brought before the state court judgment was entered against Virtus.\n\nWhen an individual uses a corporate form to “disguise wrongs, obscure fraud, or conceal\n\ncrime,” Virginia law permits a plaintiff to pierce the corporate veil and to impose liability\n\ndirectly on the individual as the “alter ego” of the corporation. Cheatle v. Rudd’s\n\nSwimming Pool Supply Co., 360 S.E.2d 828, 831 (Va. 1987). However, before bringing\n\nan action to pierce the corporate veil, the plaintiff must “first obtain[] a judgment against\n\nthe corporation.” Dana v. 313 Freemason, 587 S.E.2d 548, 553 (Va. 2003). Because\n\nBennett was required to obtain a judgment against Virtus before bringing his alter-ego\n\nclaim, this claim had not yet accrued at the time of the arbitration proceedings.\n\nAccordingly, we hold that Bennett’s alter-ego claim also is not precluded under\n\nVirginia’s doctrine of res judicata. See D’Ambrosio, 809 S.E.2d at 628.\n\n\n\n III.\n\n 11\n\f For these reasons, we hold that Bennett’s fraudulent transfer claims and his alter-\n\nego claim are not precluded under Virginia law by res judicata. 4 Accordingly, we vacate\n\nthe district court’s award of summary judgment in favor of the defendants and remand the\n\ncase to the district court for further proceedings.\n\n VACATED AND REMANDED\n\n\n\n\n 4\n Bennett also asks us to enter summary judgment in his favor on his fraudulent\ntransfer claims. Because the district court held that Bennett’s action was barred by res\njudicata, the court did not rule on the merits of Bennett’s claims. We decline to consider\nthose issues in the first instance. See Graham v. Gagnon, 831 F.3d 176, 189 (4th Cir.\n2016).\n\n 12\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: John S. BENNETT, Plaintiff - Appellant, v. James GARNER; Virtus Consulting, LLC, Defendants - Appellees.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-16\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1531\\n\\n\\nJOHN S. BENNETT,\\n\\n Plaintiff - Appellant,\\n\\n v.\\n\\nJAMES GARNER; VIRTUS CONSULTING, LLC,\\n\\n Defendants - Appellees.\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. Claude M. Hilton, Senior District Judge. (1:17-cv-00574-CMH-TCB)\\n\\n\\nArgued: December 13, 2018 Decided: January 16, 2019\\n\\n\\nBefore KEENAN, FLOYD, and THACKER, Circuit Judges.\\n\\n\\nVacated and remanded by published opinion. Judge Keenan wrote the opinion, in which\\nJudge Floyd and Judge Thacker joined.\\n\\n\\nARGUED: Kevin M. O’Donnell, HENRY & O’DONNELL, PC, Alexandria, Virginia,\\nfor Appellant. Thomas Wayne Biggs II, DYCIO & BIGGS, Fairfax, Virginia, for\\nAppellees. ON BRIEF: Jeffery T. Martin, Jr., HENRY & O’DONNELL, PC,\\nAlexandria, Virginia, for Appellant. Daniel F. Izzo, DYCIO & BIGGS, Fairfax,\\nVirginia, for Appellees.\\n\\fBARBARA MILANO KEENAN, Circuit Judge:\\n\\n John S. Bennett appeals from the district court’s award of summary judgment in\\n\\nfavor of his former employer, Virtus Consulting, LLC (Virtus), and its owner, James\\n\\nGarner (collectively, the defendants), in Bennett’s action seeking to collect on a state\\n\\ncourt judgment entered against the defendants. The district court held that Bennett’s\\n\\nclaims were precluded under Virginia’s doctrine of res judicata.\\n\\n Upon our review, we conclude that Bennett’s claims are not precluded, because\\n\\nBennett could not have brought those claims at the time of his earlier litigation.\\n\\nAccordingly, we vacate the district court’s judgment and remand for further proceedings.\\n\\n\\n\\n I.\\n\\n We present the facts in the light most favorable to Bennett, the nonmoving party,\\n\\nand draw all reasonable inferences in his favor. Rosetta Stone Ltd. v. Google, Inc., 676\\n\\nF.3d 144, 150 (4th Cir. 2012) (citation omitted). Virtus is a Virginia limited liability\\n\\ncompany that provides consulting services to various financial institutions. Garner is the\\n\\nowner and sole member of Virtus. Bennett was employed by Virtus and worked as the\\n\\nprincipal contact for one of Virtus’ largest clients.\\n\\n In 2012, Garner began negotiations to sell Virtus’ assets to the Solomon Edwards\\n\\nGroup (SEG). Around the same time, the defendants and Bennett signed an agreement,\\n\\nin which Bennett agreed to assist in the sale in exchange for “sharing [in the] proceeds”\\n\\nfrom the sale (the Bennett Agreement). Under the Bennett Agreement, once the sale to\\n\\nSEG successfully closed, Bennett would receive a fixed cash payment made in quarterly\\n\\n 2\\n\\finstallments. The parties also agreed that Bennett potentially could receive two annual\\n\\n“earn out” payments, depending on whether SEG and Garner achieved certain revenue\\n\\ntargets in the two years following the sale.\\n\\n The sale of Virtus’ assets to SEG successfully closed around the end of September\\n\\n2012. In accordance with the Bennett Agreement, Garner made the first two quarterly\\n\\ninstallment payments to Bennett. But, in April 2013, the defendants ceased making any\\n\\nfurther payments, claiming that Bennett had breached his obligations under the\\n\\nagreement. Bennett, however, maintained that he was entitled to the remaining\\n\\ninstallment payments and the “earn out” payments.\\n\\n The parties submitted their dispute to an arbitrator as required by the arbitration\\n\\nclause in the Bennett Agreement. During the arbitration proceedings, the defendants\\n\\nprovided Bennett documents describing the structure of the SEG sale but did not produce\\n\\nany of Virtus’ financial records or bank statements. In response to a request seeking\\n\\nthose financial records, the defendants stipulated that the Bennett Agreement was\\n\\nproperly executed and that the performance metrics triggering the “earn out” payments\\n\\nhad been “met in full.”\\n\\n In September 2014, the arbitrator ordered Virtus to pay Bennett $387,500. Under\\n\\nthe terms of the Bennett Agreement, the arbitrator held Garner jointly and severally liable\\n\\nfor $125,000 of that award. The award was confirmed by a Virginia circuit court and\\n\\nreduced to a judgment. Although Garner paid the portion of the award for which he\\n\\npersonally was liable, Virtus failed to pay the remaining $262,500.\\n\\n\\n\\n 3\\n\\f After the arbitration award was confirmed, Bennett obtained Virtus’ bank\\n\\nstatements. These statements showed that shortly before the SEG sale closed, Garner had\\n\\ntransferred substantially all of Virtus’ cash reserves to himself. Further, Bennett learned\\n\\nthat the SEG sale had been structured to divert all cash and other consideration from the\\n\\nsale to Garner personally. For instance, equity stock in SEG that was supposed to\\n\\ntransfer to Virtus as part of the sale was instead listed in Garner’s name and reported as\\n\\npart of Garner’s personal tax returns. Thus, Virtus lacked sufficient assets to satisfy\\n\\nBennett’s judgment.\\n\\n In May 2017, Bennett initiated the present action in the district court seeking to\\n\\ncollect on his judgment. He asserted four claims against the defendants: (1) fraudulent\\n\\nconveyance, in violation of Virginia Code § 55-80; (2) voluntary transfer, in violation of\\n\\nVirginia Code § 55-81 (together, the fraudulent transfer claims); (3) a claim seeking to\\n\\n“pierce the corporate veil” and recover the judgment amount directly from Garner (the\\n\\nalter-ego claim); and (4) fraud in the inducement. The district court granted the\\n\\ndefendants’ motion for summary judgment, concluding that Bennett’s fraudulent transfer\\n\\nclaims and alter-ego claim were precluded under Virginia’s doctrine of res judicata. 1\\n\\nThis appeal followed.\\n\\n\\n\\n\\n 1\\n The district court also awarded the defendants summary judgment on Bennett’s\\nfraud in the inducement claim, concluding that it was barred by the two-year statute of\\nlimitations governing fraud claims, Va. Code § 8.01-243(A). Bennett does not contest\\nthe dismissal of the fraud in the inducement claim.\\n\\n\\n 4\\n\\f II.\\n\\n We review de novo the district court’s award of summary judgment. Rosetta\\n\\nStone Ltd., 676 F.3d at 150.\\n\\n A.\\n\\n Before addressing the parties’ arguments, we begin by reviewing the applicable\\n\\nprinciples of res judicata. In considering the preclusive effect of an earlier state court\\n\\njudgment on a new claim, we apply the “preclusion law of the State in which judgment\\n\\nwas rendered.” In re Genesys Data Techs., Inc., 204 F.3d 124, 127 (4th Cir. 2000)\\n\\n(quoting Marrese v. Am. Acad. of Orthopedic Surgeons, 470 U.S. 373, 380 (1985)).\\n\\nHere, the arbitration award was confirmed and reduced to a judgment by a Virginia court.\\n\\nWe therefore apply Virginia’s principles of res judicata.\\n\\n In Virginia, res judicata 2 is governed by Rule 1:6 of the Rules of the Supreme\\n\\nCourt of Virginia, which states in relevant part:\\n\\n A party whose claim for relief arising from identified conduct, a\\n transaction, or an occurrence, is decided on the merits by a final judgment,\\n shall be forever barred from prosecuting any second or subsequent civil\\n action against the same opposing party or parties on any claim or cause of\\n action that arises from that same conduct, transaction or occurrence,\\n whether or not the legal theory or rights asserted in the second or\\n subsequent action were raised in the prior lawsuit, and regardless of the\\n legal elements or the evidence upon which any claims in the prior\\n proceeding depended, or the particular remedies sought.\\n\\n\\n\\n\\n 2\\n Although Virginia’s res judicata doctrine encompasses both claim preclusion and\\nissue preclusion, here we use the term “res judicata” to refer to claim preclusion only.\\nSee Funny Guy, LLC v. Lecego, LLC, 795 S.E.2d 887, 890 (Va. 2017).\\n\\n 5\\n\\fVa. Sup. Ct. R. 1:6(a). Under this rule, “a final judgment forecloses ‘successive litigation\\n\\nof the very same claim, whether or not relitigation of the claim raises the same issues as\\n\\nthe earlier suit.’” Lee v. Spoden, 776 S.E.2d 798, 803 (Va. 2015) (quoting Taylor v.\\n\\nSturgell, 553 U.S. 880, 892 (2008)). Parties, therefore, may not relitigate “the same\\n\\ncause of action or any part thereof which could have been litigated in the previous\\n\\naction.” D’Ambrosio v. Wolf, 809 S.E.2d 625, 628 (Va. 2018) (citation omitted). Stated\\n\\nsimply, res judicata operates to prevent a party from getting a “second bite of the apple”\\n\\nwith respect to wrongs arising from a single dispute. See Funny Guy, LLC v. Lecego,\\n\\nLLC, 795 S.E.2d 887, 890 (Va. 2017) (“The law should afford one full, fair hearing\\n\\nrelating to a particular problem—but not two.” (citation omitted)).\\n\\n While ostensibly a broad proposition, res judicata nonetheless is limited by\\n\\nlongstanding principles. For instance, claims brought solely to execute on a judgment are\\n\\ngenerally not precluded by prior litigation that resulted in that judgment. See State Farm\\n\\nMut. Auto. Ins. Co. v. Kelly, 380 S.E.2d 654, 655 n.2 (Va. 1989); see also Restatement 2d\\n\\nJudgments § 18(c). Similarly, res judicata does “not bar a claim that does not accrue\\n\\nprior to the litigation triggering the bar.” Funny Guy, 795 S.E.2d at 900 (emphasis\\n\\nadded). A party is not precluded from bringing a claim that he was unable to bring in the\\n\\ninitial litigation, regardless whether that claim constitutes part of the same “conduct,\\n\\ntransaction, or occurrence.” D’Ambrosio, 809 S.E.2d at 628; Funny Guy, 795 S.E.2d at\\n\\n890 (“Determining which claims should have been brought in earlier litigation largely\\n\\ndepends on which claims could have been brought.” (citation omitted)); see also Lawlor\\n\\nv. Nat’l Screen Serv. Corp., 349 U.S. 322, 328 (1955) (explaining that although an earlier\\n\\n 6\\n\\fjudgment “precludes recovery on claims arising prior to its entry, it cannot be given the\\n\\neffect of extinguishing claims which did not even then exist”). With these principles in\\n\\nmind, we turn to consider the parties’ arguments.\\n\\n B.\\n\\n As the parties asserting res judicata, the defendants bear the burden of showing\\n\\nthat it is more likely than not that Bennett’s claims should be precluded by the prior\\n\\njudgment. D’Ambrosio, 809 S.E.2d at 628. The defendants argue, as they did in the\\n\\ndistrict court, that because Bennett had knowledge of the structure of the SEG sale at the\\n\\ntime of the arbitration, Bennett could have raised both his fraudulent transfer and alter-\\n\\nego claims during those proceedings. Accordingly, the defendants contend that under\\n\\nVirginia’s doctrine of res judicata, Bennett must have brought those claims during the\\n\\narbitration proceedings.\\n\\n In response, Bennett generally maintains that his claims are brought solely in\\n\\nexecution of his state court judgment. That is, instead of seeking to “relitigate” the\\n\\ndefendants’ liability under the Bennett Agreement, Bennett argues that his fraudulent\\n\\ntransfer claims were an attempt to collect on the judgment he is owed and could not have\\n\\nbeen brought before the judgment was entered. With respect to his alter-ego claim,\\n\\nBennett similarly argues that he could not have maintained that claim before obtaining\\n\\nthe judgment against Virtus. We agree with Bennett and address each argument in turn.\\n\\n 1.\\n\\n We begin by considering the question whether Bennett could have raised his\\n\\nfraudulent transfer claims during the arbitration proceedings. Actions brought under\\n\\n 7\\n\\fVirginia’s fraudulent conveyance statute, Va. Code § 55-80, and the state’s voluntary\\n\\ntransfer statute, Va. Code § 55-81, assist creditors in collecting on a judgment or other\\n\\ndebt. See La Bella Dona Skin Care, Inc. v. Belle Femme Enters., LLC, 805 S.E.2d 399,\\n\\n406 (Va. 2017); Balzer & Assocs., Inc. v. The Lakes on 360, Inc., 463 S.E.2d 453, 455-56\\n\\n(Va. 1995). Such actions do not impose liability on the participants in a fraudulent\\n\\nconveyance, but merely unwind “transactions designed to place a debtor’s assets beyond\\n\\nhis creditors’ reach.” La Bella Dona, 805 S.E.2d at 404, 406; see also Mills v. Miller\\n\\nHarness Co., 326 S.E.2d 665, 667 (Va. 1985) (concluding that Virginia Code § 55-80\\n\\ndoes not authorize a court “to award an in personam judgment when a fraudulent\\n\\nconveyance is set aside”). Indeed, Virginia law expressly permits actions under both\\n\\nSections 55-80 and 55-81 to be brought after the entry of a judgment. Va. Code § 55-\\n\\n82.2 (“The court shall have the authority to set aside a fraudulent conveyance or\\n\\nvoluntary transfer pursuant to § 55-80 or § 55-81 during an action brought by a creditor\\n\\nto execute on a judgment.” (emphasis added)). Thus, actions to void wrongful transfers\\n\\nare remedies designed to “return[] the fraudulently conveyed assets to the transferor.” La\\n\\nBella Dona, 805 S.E.2d at 406.\\n\\n In the present case, the disputes that the parties submitted to arbitration focused on\\n\\nthe issue whether Bennett was entitled to receive the remaining payments under the\\n\\nBennett Agreement. Thus, the arbitration served only to establish the parties’ respective\\n\\nobligations and liability under the Bennett Agreement.\\n\\n In contrast, Bennett’s fraudulent transfer claims allege that Virtus depleted its\\n\\ncorporate assets and made improper conveyances to Garner to prevent Bennett from\\n\\n 8\\n\\fcollecting on the arbitration award and judgment. Bennett does not advance any new\\n\\nlegal “theories of recovery” on which either defendant could be held liable under the\\n\\nBennett Agreement. Cf. Funny Guy, 795 S.E.2d at 897-98 (holding that, under principles\\n\\nof res judicata, “alternative theories of recovery” cannot be raised in consecutive\\n\\nlawsuits). Nor does he seek damages beyond the outstanding $262,500 judgment, the\\n\\nprecise amount awarded in arbitration. Although the alleged wrongful transfers took\\n\\nplace around the same time as the SEG sale, those transfers were immaterial to the\\n\\nquestion whether either Bennett or the defendants had breached the Bennett Agreement.\\n\\nThus, Bennett is not seeking a “second bite of the apple” with respect to the amount he is\\n\\nowed. See id. Rather, he seeks only to unwind the allegedly improper transfers from\\n\\nVirtus to Garner so that Virtus can satisfy the existing judgment. 3\\n\\n Furthermore, we observe that had Bennett claimed that the defendants were\\n\\nattempting to defraud him by transferring assets, before he proved that he was entitled to\\n\\npayments under the Bennett Agreement, those fraudulent transfer claims would have\\n\\nbeen premature. At the time of the arbitration proceedings, Bennett did not have\\n\\n\\n 3\\n The defendants incorrectly rely on the Supreme Court of Virginia’s decision in\\nPrice v. Hawkins, 439 S.E.2d 382 (Va. 1994), to argue that Bennett’s fraudulent\\nconveyance claim under Virginia Code § 55-80 is meant to impose liability on Garner. In\\nPrice, the court allowed an in personam judgment to be awarded against recipients of\\nfraudulent transfers when the wrongfully transferred property was only cash. Id. at 385.\\nThis narrowly crafted exception was designed to prevent a defrauded creditor from being\\nleft without a remedy, because cash “cannot be easily located for attachment or levy.” La\\nBella Dona, 805 S.E.2d at 406 (describing the exception in Price). However, the\\nSupreme Court of Virginia has since clarified that the Price exception does not “impose\\nliability upon the grantee[,]” but merely unwinds “the transfer of the cash in the grantee’s\\npockets.” Id.\\n\\n 9\\n\\fsufficient information about Virtus’ financial condition to allege a fraudulent conveyance\\n\\nor voluntary transfer. Neither defendant disclosed any financial records or bank\\n\\nstatements to Bennett during the arbitration. Indeed, as noted above, rather than produce\\n\\nsuch documents, the defendants stipulated that the financial benchmarks in the Bennett\\n\\nAgreement had been “met in full.”\\n\\n It was not until Virtus failed to satisfy the judgment rendered against it, and\\n\\nBennett received Virtus’ relevant financial records, that he learned that Virtus had no\\n\\nremaining assets from which it could pay the judgment. These financial documents also\\n\\ndisclosed the recipient of Virtus’ transferred assets and the nature of such transfers,\\n\\nallowing Bennett to properly plead his fraudulent transfer claims. Thus, it was only after\\n\\nthe state court judgment was entered that Bennett would have had “actual notice” of any\\n\\npotential fraudulent transfer claims. Cf. Luria v. Bd. of Dirs. of Westbriar Condo. Unit\\n\\nOwners Ass’n, 672 S.E.2d 837, 840 (Va. 2009) (recognizing that, while a judgment is not\\n\\nrequired to bring a fraudulent conveyance claim, a plaintiff must have “actual notice of a\\n\\nspecific potential claim” to be considered a “creditor” under Virginia Code § 55-80).\\n\\n On these facts, we hold that Bennett could not have brought his fraudulent transfer\\n\\nclaims in the arbitration proceedings. To conclude otherwise essentially would have\\n\\nrequired Bennett to be clairvoyant. Under the defendants’ logic, a plaintiff in Bennett’s\\n\\nposition would have had to amend his original complaint, adding claims of fraudulent\\n\\nconveyance whenever he suspected that the defendant was moving money to avoid\\n\\npaying a potential judgment. Otherwise, the plaintiff would risk having those claims\\n\\nbarred in a later action to collect on that judgment. In other words, Bennett would have\\n\\n 10\\n\\fhad to try to enforce his judgment before the judgment was awarded. We decline to\\n\\ninterpret Virginia’s res judicata law in a manner that would lead to such untenable results.\\n\\nSee State Water Control Bd. v. Smithfield Foods, Inc., 542 S.E.2d 766, 769 (Va. 2001)\\n\\n(“The doctrine [of res judicata] protects litigants from multiple lawsuits, conserves\\n\\njudicial resources, and fosters certainty and reliance in legal relationships.” (emphasis\\n\\nadded)). Therefore, we hold that Bennett’s fraudulent transfer claims are not precluded\\n\\nunder Virginia’s res judicata doctrine.\\n\\n 2.\\n\\n With respect to Bennett’s alter-ego claim, we similarly conclude that the claim\\n\\ncould not have been brought before the state court judgment was entered against Virtus.\\n\\nWhen an individual uses a corporate form to “disguise wrongs, obscure fraud, or conceal\\n\\ncrime,” Virginia law permits a plaintiff to pierce the corporate veil and to impose liability\\n\\ndirectly on the individual as the “alter ego” of the corporation. Cheatle v. Rudd’s\\n\\nSwimming Pool Supply Co., 360 S.E.2d 828, 831 (Va. 1987). However, before bringing\\n\\nan action to pierce the corporate veil, the plaintiff must “first obtain[] a judgment against\\n\\nthe corporation.” Dana v. 313 Freemason, 587 S.E.2d 548, 553 (Va. 2003). Because\\n\\nBennett was required to obtain a judgment against Virtus before bringing his alter-ego\\n\\nclaim, this claim had not yet accrued at the time of the arbitration proceedings.\\n\\nAccordingly, we hold that Bennett’s alter-ego claim also is not precluded under\\n\\nVirginia’s doctrine of res judicata. See D’Ambrosio, 809 S.E.2d at 628.\\n\\n\\n\\n III.\\n\\n 11\\n\\f For these reasons, we hold that Bennett’s fraudulent transfer claims and his alter-\\n\\nego claim are not precluded under Virginia law by res judicata. 4 Accordingly, we vacate\\n\\nthe district court’s award of summary judgment in favor of the defendants and remand the\\n\\ncase to the district court for further proceedings.\\n\\n VACATED AND REMANDED\\n\\n\\n\\n\\n 4\\n Bennett also asks us to enter summary judgment in his favor on his fraudulent\\ntransfer claims. Because the district court held that Bennett’s action was barred by res\\njudicata, the court did not rule on the merits of Bennett’s claims. We decline to consider\\nthose issues in the first instance. See Graham v. Gagnon, 831 F.3d 176, 189 (4th Cir.\\n2016).\\n\\n 12\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":96,"cells":{"id":{"kind":"number","value":4582072,"string":"4,582,072"},"name":{"kind":"string","value":"The CITY OF NEW YORK; The City of Philadelphia; The City and County of San Francisco, Plaintiffs - Appellants, v. the UNITED STATES DEPARTMENT OF DEFENSE; The United States Department of the Air Force; The United States Department of the Navy; The United States Department of the Army; James N. Mattis, in His Official Capacity as United States Secretary of Defense; Heather A. Wilson, in Her Official Capacity as United States Secretary of the Air Force; Richard v. Spencer, in His Official Capacity as United States Secretary of the Navy; Dr. Mark T. Esper, in His Official Capacity as United States Secretary of the Army; Dermot F. O'Reilly, in His Official Capacity as Director of the Defense Criminal Investigative Service; Colonel Kirk B. Stabler, in His Official Capacity as Commander of the Air Force Office of Special Investigations; Andrew L. Traver, in His Official Capacity as Director of the Naval Criminal Investigative Service; Major General David P. Glaser, in His Official Capacity as Commanding General of the United States Army Criminal Investigation Command; Rear Admiral John B. Nowell, in His Official Capacity as Commander of the Navy Personnel Command and Deputy Chief of Naval Personnel, Defendants - Appellees."},"name_abbreviation":{"kind":"string","value":"City of N.Y. v. U.S. Dep't of Def."},"decision_date":{"kind":"string","value":"2019-01-16"},"docket_number":{"kind":"string","value":"18-1699"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Wilkinson, Agee, Thacker\", \"parties\": \"\", \"opinions\": [{\"author\": \"WILKINSON, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1699\\n\\n\\nTHE CITY OF NEW YORK; THE CITY OF PHILADELPHIA; THE CITY AND\\nCOUNTY OF SAN FRANCISCO,\\n\\n Plaintiffs – Appellants,\\n\\n v.\\n\\nTHE UNITED STATES DEPARTMENT OF DEFENSE; THE UNITED STATES\\nDEPARTMENT OF THE AIR FORCE; THE UNITED STATES DEPARTMENT\\nOF THE NAVY; THE UNITED STATES DEPARTMENT OF THE ARMY;\\nJAMES N. MATTIS, in his official capacity as United States Secretary of Defense;\\nHEATHER A. WILSON, in her official capacity as United States Secretary of the\\nAir Force; RICHARD V. SPENCER, in his official capacity as United States\\nSecretary of the Navy; DR. MARK T. ESPER, in his official capacity as United\\nStates Secretary of the Army; DERMOT F. O'REILLY, in his official capacity as\\nDirector of the Defense Criminal Investigative Service; COLONEL KIRK B.\\nSTABLER, in his official capacity as Commander of the Air Force Office of\\nSpecial Investigations; ANDREW L. TRAVER, in his official capacity as Director\\nof the Naval Criminal Investigative Service; MAJOR GENERAL DAVID P.\\nGLASER, in his official capacity as Commanding General of the United States\\nArmy Criminal Investigation Command; REAR ADMIRAL JOHN B. NOWELL,\\nin his official capacity as Commander of the Navy Personnel Command and\\nDeputy Chief of Naval Personnel,\\n\\n Defendants - Appellees.\\n\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. Claude M. Hilton, Senior District Judge. (1:17-cv-01464-CMH-MSN)\\n\\n\\nArgued: December 11, 2018 Decided: January 16, 2019\\n\\fBefore WILKINSON, AGEE, and THACKER, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Wilkinson wrote the opinion, in which Judge Agee\\nand Judge Thacker joined.\\n\\n\\nARGUED: Matthew Jeffrey MacLean, PILLSBURY WINTHROP SHAW PITTMAN\\nLLP, Washington, D.C., for Appellants. Tyce R. Walters, UNITED STATES\\nDEPARTMENT OF JUSTICE, Washington, D.C., for Appellees. ON BRIEF: Laura B.\\nLoBue, Jeetander Dulani, Washington, D.C., Kenneth W. Taber, Matthew F. Putorti,\\nNicholas M. Buell, PILLSBURY WINTHROP SHAW PITTMAN LLP, New York, New\\nYork, for Appellants. Eric Proshansky, Melanie C.T. Ash, Eric Lee, Claude S. Platton,\\nZachary W. Carter, CORPORATION COUNSEL OF THE CITY OF NEW YORK,\\nNEW YORK CITY LAW DEPARTMENT, New York, New York, for Appellant City of\\nNew York. Dennis J. Herrera, Yvonne R. Mere, Owen J. Clements, SAN FRANCISCO\\nCITY ATTORNEY’S OFFICE, San Francisco, California, for Appellant City and County\\nof San Francisco. Marcel S. Pratt, Eleanor N. Ewing, Benjamin H. Field, CITY OF\\nPHILADELPHIA LAW DEPARTMENT, Philadelphia, Pennsylvania, for Appellant City\\nof Philadelphia. Joseph H. Hunt, Assistant Attorney General, Mark B. Stern, Civil\\nDivision, UNITED STATES DEPARTMENT OF JUSTICE, Washington, D.C.; G.\\nZachary Terwilliger, United States Attorney, OFFICE OF THE UNITED STATES\\nATTORNEY, Alexandria, Virginia; Michael J. Fucci, Associate General Counsel,\\nUNITED STATES DEPARTMENT OF DEFENSE, Washington, D.C., for Appellees.\\n\\n\\n\\n\\n 2\\n\\fWILKINSON, Circuit Judge:\\n\\n Appellants are three municipalities who use the National Instant Criminal\\n\\nBackground Check System to carry out their obligations under state law. This system,\\n\\nknown as the NICS, is managed by the Federal Bureau of Investigation. The Department\\n\\nof Defense (DOD) is required under federal law to provide records to the NICS but has\\n\\npersistently been unable to fully carry out this obligation. The appellants sued DOD and\\n\\nits constituent military departments to compel the department’s more thorough\\n\\ncompliance. The district court dismissed their claim, holding both that the appellants\\n\\nlacked constitutional standing and failed to establish subject matter jurisdiction under the\\n\\nAdministrative Procedure Act. For the following reasons, we affirm.\\n\\n\\n\\n I.\\n\\n A.\\n\\n The responsibility to combat gun violence falls on every level of government. Law\\n\\nenforcement officials, whether local, state, or federal, work to prevent senseless gun\\n\\nviolence and are often the first to risk their lives to protect our communities. Working\\n\\nalongside these officers are many other governmental partners, including agencies of the\\n\\nfederal government. The dispute here grows out of a program that facilitates information\\n\\nsharing between federal agencies and local law enforcement officials: The National\\n\\nInstant Criminal Background Check System.\\n\\n The Brady Handgun Violence Prevention Act, or Brady Act, established the first\\n\\nnationwide system for background checks. Pub. L. No. 103-159, 107 Stat. 1536 (1993).\\n\\n 3\\n\\fUnder the law, enacted in 1993, a background check was required for firearms sales by\\n\\nlicensed dealers. Id. § 102. The Brady Act directed the Attorney General to establish a\\n\\nnational database that would be accessible to the firearms dealers tasked with ensuring\\n\\nthese background checks were performed. Id. § 102(b). To implement the statute, the\\n\\nAttorney General established the National Instant Criminal Background Check System\\n\\n(NICS) and delegated control of the system to the Federal Bureau of Investigation (FBI).\\n\\n The NICS contains records for individuals who are prohibited from possessing a\\n\\nfirearm. The system draws from many distinct federal databases that contain\\n\\ndisqualifying records and relies on information submitted from across the federal\\n\\ngovernment. In the military context, DOD provides information regarding current and\\n\\nformer service members who are disqualified from owning a gun because of a prior\\n\\nconviction. The Brady Act also empowers the Attorney General to request records from\\n\\nother agencies that may possess disqualifying information. Id. § 103(e) (codified at 34\\n\\nU.S.C. § 40901(e) (2018)).\\n\\n As originally designed, state law enforcement agencies were required to\\n\\nadminister the Brady Act’s background checks on a temporary basis while the new\\n\\nnational background check system was established. The division of responsibility\\n\\nenvisioned by Congress was altered by the Supreme Court’s decision in Printz v. United\\n\\nStates, which found that “[t]he Federal Government may [not] command the States’\\n\\nofficers, or those of their political subdivisions, to administer or enforce a federal\\n\\nregulatory program.” 521 U.S. 898, 935 (1997). As the law now stands, states are not\\n\\nrequired to perform any functions associated with the Brady Act, although a state may\\n\\n 4\\n\\fvoluntarily play a role. For states that elect to participate, a “point of contact” is\\n\\ndesignated to “serv[e] as the intermediary between [a dealer] and the federal databases\\n\\nchecked by the NICS.” 28 C.F.R. § 25.2 (2017).\\n\\n This does not mean that state and local governments have no use of the\\n\\ninformation stored in the NICS. To the contrary, many states require law enforcement\\n\\nagencies to carry out a range of functions designed to prevent guns from reaching\\n\\ndangerous hands. Depending on the particulars of state law, a local law enforcement\\n\\nagency may perform checks associated with issuing permits and licenses, or may review\\n\\ndisqualifying information before transferring a gun that is in the state’s possession. For\\n\\nexample, the City of Philadelphia, a party to this case, is required to process applications\\n\\nfor licenses to carry firearms under Pennsylvania law. See 18 Pa. Cons. Stat. § 6109. The\\n\\nother municipal appellants have similar obligations.\\n\\n The Attorney General has long permitted state and local agencies, including the\\n\\nappellants, to access the NICS for these purposes. In 1998, the FBI promulgated a rule\\n\\nallowing state and local law enforcement to use the NICS when “issu[ing] a firearm-\\n\\nrelated or explosives-related permit or license,” including concealed-carry permits. See\\n\\nNational Instant Criminal Background Check System Regulation, 63 Fed. Reg. 58,303,\\n\\n58,309 (Oct. 30, 1998) (codified at 28 C.F.R. § 25.6(j)(1)). In 2014, a new rule further\\n\\nexpanded NICS access, allowing state and local agencies to access the system when\\n\\ndisposing of firearms in their possession. See National Instant Criminal Background\\n\\nCheck System Regulation, 79 Fed. Reg. 69,047, 69,048 (Nov. 20, 2014) (codified at 28\\n\\nC.F.R. § 25.6(j)(3)). The regulations clearly state that these uses of the NICS are\\n\\n 5\\n\\fpermissive, intended as a service, and “unrelated to NICS background checks required by\\n\\nthe Brady Act.” 28 C.F.R. § 25.6(j).\\n\\n At times, local law enforcement officials have pushed for even greater access. For\\n\\ninstance, the FBI’s 1998 rulemaking noted that some local agencies wanted permission to\\n\\naccess the database to determine if a person was in “unlawful possession of a firearm.” 63\\n\\nFed. Reg. at 58,305. The FBI resisted these requests. In the FBI’s view, such expanded\\n\\nuse would potentially run afoul of federal privacy laws. Id. Moreover, the FBI noted that\\n\\nthe Brady Act only required agency reporting for the purpose of carrying out the federal\\n\\nbackground check provisions, rather than for a wider range of law enforcement activities.\\n\\nId. The permissive use regulations therefore account for the requirements of federal law,\\n\\nthe informational needs of local law enforcement, and the privacy concerns of the\\n\\naffected individuals. In arriving at the scheme in place today, the FBI has shown a\\n\\nwillingness to expand NICS access to support local partners, but has apparently not gone\\n\\nas far as some of those partners may desire.\\n\\n The comprehensiveness and accuracy of the NICS has been a subject of frequent\\n\\ndebate and attention. See, e.g., U.S. Gov’t Accountability Office, GAO/T-GGD-00-163,\\n\\nGun Control: Improving the National Instant Criminal Background Check System (June\\n\\n21, 2000). At the federal level, many agencies possess disqualifying information that\\n\\nwould be relevant to a background check. Under the original Brady Act, federal agencies\\n\\nwere required to furnish information to the Attorney General upon request. See Pub. L.\\n\\nNo. 103-159, § 103(e)(1) (1993) (codified as amended at 34 U.S.C. § 40901(e)(1)).\\n\\n\\n\\n 6\\n\\f Following the fatal shooting of 32 students and faculty at Virginia Tech in 2007,\\n\\nCongress enacted new legislation to improve the NICS. See NICS Improvement\\n\\nAmendments Act of 2007 (NIAA), Pub. L. No. 110-180, 121 Stat. 2559 (2008). Finding\\n\\nthat “nearly 21,000,000 criminal records are not accessible by NICS and millions of\\n\\ncriminal records are missing critical data, such as arrest dispositions, due to backlogs,”\\n\\nthe legislation imposed new reporting requirements and authorized new grants to assist\\n\\nstates. Id. §§ 101, 103-104. To improve inter-agency information sharing, the Act\\n\\nimposed an affirmative duty on agencies to report disqualifying information on a\\n\\nquarterly basis. Id. § 101(a) (codified at 34 U.S.C. § 40901(e)(1)(C)-(D)). To incentivize\\n\\ncompliance, the Attorney General is required to provide an annual report to Congress on\\n\\neach agency’s success. Id. (codified at 34 U.S.C. § 40901(e)(1)(E)).\\n\\n The Department of Defense (DOD) has long struggled to comply with the NIAA’s\\n\\naffirmative reporting provision, a deficiency the department readily admits. Response Br.\\n\\nat 1. The DOD Inspector General reviewed the program in 2015 and found that a\\n\\nsubstantial percentage of required records were not being submitted to the FBI. U.S.\\n\\nDep’t of Def. Inspector Gen., Evaluation of Department of Defense Compliance with\\n\\nCriminal History Data Reporting Requirements 9 (Feb. 12, 2015). Similar findings were\\n\\nmade again in 2017. U.S. Dep’t of Def. Inspector Gen., Evaluation of Fingerprint Card\\n\\nand Final Disposition Report Submissions by Military Service Law Enforcement\\n\\nOrganizations (Dec. 4, 2017). On November 5, 2017, a gunman opened fire at a church in\\n\\nSutherland Springs, Texas, killing 26 people and injuring an additional 20. The gunman\\n\\nwas a former member of the military who had been convicted in court-martial\\n\\n 7\\n\\fproceedings. According to the municipal appellants, the gunman would not have been\\n\\nable to obtain a firearm if DOD complied with its reporting obligations under the NIAA.\\n\\n Following the devastating loss of life at Sutherland Springs, Congress again\\n\\namended the statute governing the NICS to improve inter-agency reporting. The Fix\\n\\nNICS Act, Pub. L. No. 115-141, Div. S, Title VI (2018), required federal agencies with\\n\\ndisqualifying records to submit semiannual certification reports to the Attorney General\\n\\nand develop compliance plans to improve their own performance. Id. § 602. Like the\\n\\nearlier amendment, this law also includes measures designed to hold poor performers\\n\\naccountable. First, the law requires that the Attorney General notify Congress of non-\\n\\ncompliant agencies and publish a list of those agencies on the DOJ website. Second, the\\n\\nlaw makes political appointees at non-compliant agencies ineligible for bonus pay until\\n\\nthe agency improves. Id. § 602(1) (codified at 34 U.S.C. § 40901(e)(1)(F)-(I)).\\n\\n In the time since the Sutherland Springs shooting, components of the Department\\n\\nof Defense have taken a wide range of actions to correct their deficiencies. Efforts\\n\\ninclude the creation of new task forces and compliance plans, as well as the development\\n\\nof new technological processes to streamline reporting. See J.A. 302-16. For example,\\n\\nthe Army has, in recent months, provided new records for nearly 33,000 disqualified\\n\\npersons to the NICS.\\n\\n B.\\n\\n The tragic shooting in Sutherland Springs also gave rise to this litigation. The\\n\\nappellants are three municipalities, all of whom use the NICS database to fulfill their\\n\\nrequirements under state law. They brought this suit to compel DOD’s full reporting of\\n\\n 8\\n\\fdisqualifying information to the Attorney General, as required by the NIAA. Since\\n\\nneither the Brady Act nor the NIAA contemplated a separate cause of action to compel\\n\\nperformance with inter-agency reporting obligations, the municipal appellants brought\\n\\ntheir claim under the general provision of the Administrative Procedure Act that allows\\n\\nan aggrieved party to “compel agency action unlawfully withheld or unreasonably\\n\\ndelayed.” 5 U.S.C. § 706(1) (2012).\\n\\n The district court granted the federal defendants’ motion to dismiss this claim,\\n\\nfinding that it lacked jurisdiction to hear the case. The court identified two independent\\n\\njurisdictional defects. First, the district court found that the municipal appellants had\\n\\nfailed “to allege[] a cognizable informational injury sufficient to confer standing.” J.A.\\n\\n341. Second, the court held that the cities did not establish “jurisdiction under the APA\\n\\nsince they have not alleged a discrete agency action.” Id. As a consequence of the\\n\\ndismissal, the court also denied the municipal appellants’ motion for a preliminary\\n\\ninjunction. Id. at 348.\\n\\n This appeal followed. While federal courts must assure themselves that they have\\n\\njurisdiction before proceeding to the merits, see Steel Co. v. Citizens for a Better Env’t,\\n\\n523 U.S. 83, 94-95 (1998), both of the infirmities identified by the district court go to the\\n\\nquestion of jurisdiction. As such, this court can turn to either issue alone to resolve this\\n\\ncase. See Ruhrgas AG v. Marathon Oil Co., 526 U.S. 574, 578 (1999) (“[T]here is no\\n\\nunyielding jurisdictional hierarchy.”). Our review is de novo.\\n\\n\\n\\n\\n 9\\n\\f II.\\n\\n Because this court is not in “the habit of decid[ing] questions of a constitutional\\n\\nnature unless absolutely necessary,” we turn first to the statutory question of whether the\\n\\nmunicipal appellants have established subject matter jurisdiction under the\\n\\nAdministrative Procedure Act (APA). See Flue-Cured Tobacco Coop. Stabilization Corp.\\n\\nv. EPA, 313 F.3d 852, 857 (4th Cir. 2002) (quoting Ashwander v. Tenn. Valley Auth., 297\\n\\nU.S. 288, 347 (1936) (Brandeis, J. concurring)). At the outset, it is important to\\n\\nunderstand the nature of appellants’ claim. Their challenge is not about access to the\\n\\nNICS; it is instead about the quality of the information in that system. By their own\\n\\nsubmission, each of the appellants accesses the NICS frequently to carry out their\\n\\nobligations under state law. This is thus not a case where appellants have asked for access\\n\\nprovided for in the regulations and have been denied. Instead, the municipalities see their\\n\\nexisting access to the NICS as an invitation to compel any federal inter-agency legal\\n\\nrequirement that may affect the quality of the information they receive. On their view, the\\n\\nAPA authorizes a recipient of government information to initiate a private action to\\n\\ncompel governmental conduct that might improve that information’s accuracy or\\n\\ncomprehensiveness. As we explain below, there is simply no basis in the APA’s text for\\n\\nsuch a broad incursion into internal agency management.\\n\\n A.\\n\\n The APA waives the federal government’s sovereign immunity for a limited set of\\n\\nsuits, brought by “a person suffering legal wrong because of agency action” to obtain\\n\\nrelief “other than money damages.” 5 U.S.C. § 702. It is well-established that\\n\\n 10\\n\\f“[s]overeign immunity is jurisdictional in nature” and “absent a waiver . . . shields the\\n\\nFederal Government and its agencies from suit.” FDIC v. Meyer, 510 U.S. 471, 475\\n\\n(1994). Judicial review under the APA, moreover, is limited to “final agency actions.”\\n\\n5 U.S.C. § 704.\\n\\n As these provisions of the APA make plain, subject matter jurisdiction is lacking if\\n\\nthe plaintiff fails to challenge a particular “agency action” that is fit for review. See\\n\\nInvention Submission Corp. v. Rogan, 357 F.3d 452, 460 (4th Cir. 2004). “The term\\n\\n‘action’ as used in the APA is a term of art that does not include all conduct” on the part\\n\\nof the government. Vill. of Bald Head Island v. U.S. Army Corps of Eng’rs, 714 F.3d 186,\\n\\n193 (4th Cir. 2013). See also Hearst Radio v. FCC, 167 F.2d 225, 227 (D.C. Cir. 1948)\\n\\n(“The difficulty with the appellant company’s position is that the Administrative\\n\\nProcedure Act does not provide review for everything done by an agency.”). Instead, the\\n\\nAPA defines “agency action” to include “the whole or a part of an agency rule, order,\\n\\nlicense, sanction, relief, or the equivalent or denial thereof, or failure to act.” 5 U.S.C.\\n\\n§ 551(13).\\n\\n This definition limits the scope of judicial review in two important respects. First,\\n\\neach of the terms that comprise the definition of “agency action” is limited to those acts\\n\\nthat are “circumscribed” and “discrete.” Norton v. Southern Utah Wilderness Alliance\\n\\n(SUWA), 542 U.S. 55, 62 (2004). When challenging agency action―whether it be a\\n\\nparticular action or a failure to act altogether―the plaintiff must therefore identify\\n\\nspecific and discrete governmental conduct, rather than launch a “broad programmatic\\n\\nattack” on the government’s operations. Id. at 64. This distinction between discrete acts,\\n\\n 11\\n\\fwhich are reviewable, and programmatic challenges, which are not, is vital to the APA’s\\n\\nconception of the separation of powers. Courts are well-suited to reviewing specific\\n\\nagency decisions, such as rulemakings, orders, or denials. We are woefully ill-suited,\\n\\nhowever, to adjudicate generalized grievances asking us to improve an agency’s\\n\\nperformance or operations. In such a case, courts would be forced either to enter a\\n\\ndisfavored “obey the law” injunction, see Int’l Longshoremen’s Ass’n, Local 1291 v.\\n\\nPhil. Mar. Trade Ass’n, 389 U.S. 64, 76 (1967), or to engage in day-to-day oversight of\\n\\nthe executive’s administrative practices. Both alternatives are foreclosed by the APA, and\\n\\nrightly so. The Supreme Court’s guidance on this point is worth considering in full:\\n\\n If courts were empowered to enter general orders compelling compliance\\n with broad statutory mandates, they would necessarily be empowered, as\\n well, to determine whether compliance was achieved-which would mean\\n that it would ultimately become the task of the supervising court, rather\\n than the agency, to work out compliance with the broad statutory mandate,\\n injecting the judge into day-to-day agency management.\\n\\nSUWA, 542 U.S. at 66-67. The requirement that the challenger identify a discrete act\\n\\nkeeps us from entering such a quagmire.\\n\\n Second, the definition of “agency action” is limited to those governmental acts\\n\\nthat “determin[e] rights and obligations.” Clear Sky Car Wash LLC v. City of\\n\\nChesapeake, Va., 743 F.3d 438, 445 (4th Cir. 2014). This limitation ensures that judicial\\n\\nreview does not reach into the internal workings of the government, and is instead\\n\\nproperly directed at the effect that agency conduct has on private parties. To meet this\\n\\nrequirement, a party must demonstrate that the challenged act had “an immediate and\\n\\npractical impact,” see Golden & Zimmerman LLC v. Domenech, 599 F.3d 426, 433 (4th\\n\\n\\n 12\\n\\fCir. 2010), or “alter[ed] the legal regime” in which it operates. See Bennett v. Spear, 520\\n\\nU.S. 154, 178 (1997). It is not enough for plaintiffs to simply identify a governmental\\n\\naction that ultimately affected them through the “independent responses and choices of\\n\\nthird parties,” or mere “coercive pressures.” Flue-Cured Tobacco, 313 F.3d at 859, 861.\\n\\nThis requirement applies fully to claims that an agency has failed to act, which is\\n\\n“properly understood as a failure to take an agency action.” See Norton, 542 U.S. at 62.\\n\\nSince “agency actions” must determine rights and obligations, claims to compel an\\n\\nagency to take an action must seek such a determination as well.\\n\\n These two requirements, which flow directly from the APA’s text, apply to all\\n\\nchallenges to agency action and accordingly limit judicial review generally. When a\\n\\nplaintiff brings a claim to compel agency action, like the municipal appellants have here,\\n\\na further limit applies. Under the APA, actions that can be compelled are only those that\\n\\nhave been “unlawfully withheld or unreasonably delayed.” 5 U.S.C. § 706(1). As the\\n\\nSupreme Court has explained, the text of § 706(1) requires that the plaintiff identify\\n\\naction that is “legally required.” SUWA, 542 U.S. at 63. Just like the traditional\\n\\nmandamus remedy from which this provision is derived, claims to compel agency action\\n\\nare “limited to enforcement of ‘a specific, unequivocal command,’” over which an\\n\\nofficial has no discretion. Id. (quoting ICC v. New York, N.H. & H.R. Co., 287 U.S. 178,\\n\\n204 (1932)).\\n\\n Taken together, the limitations imposed on claims to compel agency action under\\n\\nthe APA strike a balance between meaningful judicial review and the needs of effective\\n\\nadministration. Review is available only when acts are discrete in character, required by\\n\\n 13\\n\\flaw, and bear on a party’s rights and obligations. The result is a scheme allowing courts\\n\\nto review only those acts that are specific enough to avoid entangling the judiciary in\\n\\nprogrammatic oversight, clear enough to avoid substituting judicial judgments for those\\n\\nof the executive branch, and substantial enough to prevent an incursion into internal\\n\\nagency management. See SUWA, 542 U.S. at 64-65.\\n\\n These principles guide our consideration of all claims to compel agency action,\\n\\nregardless of the context. Claims involving government information are no exception.\\n\\nOur court, just like our sister circuits, has had many occasions to consider how the\\n\\nrequirements of agency action apply to claims that the government has wrongfully\\n\\nhandled the information in its possession. In some cases, the claim is that the\\n\\ngovernment’s decision to disseminate information, such as an unfavorable report, was\\n\\nunlawful. See Invention Submission Corp., 357 F.3d at 460; see also Flue-Cured\\n\\nTobacco, 313 F.3d at 859; Indus. Safety Equip. Ass’n, Inc. v. EPA, 837 F.2d 1115, 1118\\n\\n(D.C. Cir. 1988). At other times, the claim was that the government improperly withheld\\n\\nor mishandled personal information. See, e.g., Fanin v. U.S. Dep’t of Veterans Affairs,\\n\\n572 F.3d 868, 871 (11th Cir. 2009). Informational harms may involve novel facts, but\\n\\nthey do not disrupt the legal principles set forth in the APA. See Golden & Zimmerman,\\n\\nLLC, 599 F.3d at 431-32 (finding that an agency’s “reference guide” was not agency\\n\\naction because it did not “impose new legal requirements”). As these cases aptly\\n\\ndemonstrate, a plaintiff’s burden remains constant and subject to the above requirements\\n\\nthroughout.\\n\\n\\n\\n 14\\n\\f B.\\n\\n Applying these well-established principles to the facts here, it is clear that the\\n\\nmunicipal appellants have failed to establish subject matter jurisdiction under the APA.\\n\\nOnce again, the claim at issue arises from the appellants’ permissive use of the NICS,\\n\\nafforded to them by regulation, for purposes explicitly “unrelated to the NICS\\n\\nbackground checks required by the Brady Act.” 28 C.F.R. § 25.6(j). The regulation\\n\\naffords the municipalities only “access to the NICS Index.” Id. On the view of the\\n\\nmunicipal appellants, this access, which is not expressly contemplated either by the\\n\\nBrady Act or subsequent legislation, allows a NICS user to reach into the federal\\n\\ngovernment and compel any legal obligations associated with developing the information\\n\\nin the system. Such a broad theory of agency action is untethered from the APA’s text\\n\\nand contravenes important limits that Congress has placed on judicial review.\\n\\n First, the municipal appellants’ claim does not challenge a discrete agency action.\\n\\nInstead appellants ask that we “supervise an agency’s compliance with [the] broad\\n\\nstatutory mandate” of the NIAA. Murray Energy Corp. v. EPA, 861 F.3d 529, 537 n.4\\n\\n(4th Cir. 2017). By appellants’ own account, the DOD’s failure to provide disqualifying\\n\\nconviction records for former service members is widespread and systemic. The\\n\\ndepartment has admitted as much and is engaged in extensive efforts to increase its\\n\\ncompliance. As all parties seem to agree, the road ahead is an arduous one, as DOD\\n\\nattempts to improve on its partial and inconsistent reporting. This is the sort of public\\n\\npolicy problem that often requires reallocating resources, developing new administrative\\n\\n 15\\n\\fsystems, and working closely with partners across government. Solving it will likely\\n\\nrequire expertise in information technology and deep knowledge of how military needs\\n\\nintersect with data collection. In other words, it is exactly the sort of “broad\\n\\nprogrammatic” undertaking for which the APA has foreclosed judicial review. See\\n\\nSUWA, 542 U.S. at 64.\\n\\n Congress seems to be of the same view. Since the passage of the Brady Act,\\n\\nCongress has on multiple occasions turned its attention to the severe challenge of\\n\\nrampant gun violence. Twice, the legislative responses have been directed squarely at\\n\\nagency compliance with NICS reporting obligations. Congress has included\\n\\naccountability measures, designed to identify delinquent agencies and push them into\\n\\nimproving their performance. The most recent effort in this regard singles out executive\\n\\ncompensation at these agencies, limiting bonus pay for those who do not improve their\\n\\noutcomes. See 34 U.S.C. § 40901(e)(1)(I) (providing that certain “political\\n\\nappointee[s] . . . shall not be eligible for the receipt of bonus pay” until their department\\n\\nimproves its compliance). These measures signal that Congress sees this problem as one\\n\\nripe for legislative oversight and in need of attention by experts in the executive branch.\\n\\nAt no point, however, has Congress invited the federal courts into the process. Perhaps\\n\\ncognizant of the judiciary’s inability to oversee and manage a complex scheme of inter-\\n\\nagency collaboration, we have appropriately been left on the sideline.\\n\\n The municipal appellants try to nonetheless force us onto the field by\\n\\ncharacterizing their broad claim as simply an aggregation of many small claims, each one\\n\\nseeking to compel the individual reports required by the NIAA. On this view, what the\\n\\n 16\\n\\fcities seek is not programmatic because each specific act that DOD has failed to perform\\n\\nis discrete when considered on its own. But any limit on programmatic assessment would\\n\\nbe rendered meaningless if such an argument prevailed. All governmental programs are\\n\\nthe aggregation of individual decisions, many of which are required by law. The APA\\n\\nensures that it is the individual decisions that are assessed as agency action, rather than\\n\\nthe whole administrative apparatus.\\n\\n The municipal appellants are surely correct that ongoing failures to carry out\\n\\ndiscrete obligations can be subject to review. Government deficiencies do not become\\n\\nnon-reviewable simply because they are pervasive. This, however, does nothing to\\n\\nobviate the fact that a discrete action is wholly lacking here. By the appellants’ own\\n\\nestimate, full compliance with the NIAA may require DOD to obtain and transmit tens of\\n\\nthousands of records. There is simply no way to achieve such a result without wholesale\\n\\nimprovements in the DOD’s reporting requirements, which take time and require the\\n\\nexpertise of senior civilian and military leaders.\\n\\n If there were any doubt about the nature of the cities’ claim, the requested remedy\\n\\ntells the real story. Their complaint “seeks immediate injunctive relief to compel\\n\\nDefendants to repair this broken system and to cure once and for all the potentially\\n\\ndeadly gaps in the NCIC database.” J.A. 17. In their prayer for relief, the appellants ask\\n\\nthat the DOD, on “a schedule to be set by the Court,” “identify all records” in its\\n\\npossession, provide the information contained in those records to the Attorney General,\\n\\n“conduct a thorough review of [its] records and procedures,” “submit to the Court for\\n\\napproval a compliance plan,” and provide “a monthly report to the Court detailing [its]\\n\\n 17\\n\\fprogress.” Id. at 35-36. The requested relief would continue “until such time as the Court\\n\\nis satisfied that Defendants have brought themselves into full compliance with 34 U.S.C.\\n\\n§ 40901.” Id. at 36 (emphasis added). The APA’s discreteness requirement exists to avoid\\n\\nplacing the courts in this exact position. As we previously explained, “[t]he obvious\\n\\ninability for a court to function in such a day-to-day managerial role over agency\\n\\noperations is precisely the reason why the APA limits judicial review to discrete agency\\n\\nactions.” Vill. of Bald Head Island, 714 F.3d at 194.\\n\\n Moreover, the municipal appellants have failed to demonstrate that the DOD’s\\n\\nreporting requirements in any way determine their rights and obligations. Accordingly,\\n\\nthey have not identified an act that can be compelled by this court under § 706(1). See\\n\\nSUWA, 542 U.S. at 62 (finding that a failure to act under § 706(1) means “failure to take\\n\\nan agency action”). The action challenged in this case is DOD’s obligation to provide\\n\\ninformation only to another agency of the federal government: The Department of\\n\\nJustice. See 34 U.S.C. § 40901(e)(1)(C). The regulation permitting local law enforcement\\n\\nagencies to use the NICS refers only to access to the system, not to the particular\\n\\ninformation provided to the FBI by other federal agencies. The transfer of information\\n\\nbetween agencies does not, without more, alter the rights and obligations of any party.\\n\\nThat is especially true, as here, where outside access to the information is entirely\\n\\npermissive and implicates none of the complaining party’s obligations under federal law.\\n\\n We need not say here that information sharing can never constitute agency action.\\n\\nWe simply note that claims to compel an agency to provide information are held to the\\n\\nsame standard as any other. In arguing otherwise, the municipal appellants point to a\\n\\n 18\\n\\fstring of cases, all from outside this circuit, holding that the government’s alleged misuse\\n\\nof information was reviewable “agency action.” Our holding here, however, raises no\\n\\nconflict with these decisions. The cases relied on by the appellants involve claims wholly\\n\\nunlike the one that they have brought. For example, one case involves the government’s\\n\\nlegal obligations with respect to the plaintiffs’ personal medical information, see Vietnam\\n\\nVeterans of Am. v. CIA, 811 F.3d 1068, 1078 (9th Cir. 2015) (finding that “the Army\\n\\n[has] a duty to provide notice to prior test subjects of information regarding their well-\\n\\nbeing”), while another examines the rights of federal employees under the civil service\\n\\nsystem, see Hondros v. U.S. Civil Service Comm., 720 F.2d 278, 280 (3d Cir. 1983). Each\\n\\nof these cases involved plaintiffs seeking information that was particular to them and\\n\\ntheir own rights under federal law. As such, they tell us little about how to handle a case,\\n\\nlike this one, where the plaintiff seeks wholesale compliance with an entire\\n\\nadministrative scheme, based solely on the fact that the government has granted them\\n\\naccess to an information system.\\n\\n\\n\\n C.\\n\\n What the municipal appellants are ultimately asking for is a judicial decree making\\n\\nthe assistance of the federal government more useful to them than it is now. While their\\n\\nmotives for wanting to see improvement to the NICS are laudable, they point to no case\\n\\nsuggesting that the APA countenances such an action. And for good reason. If a party\\n\\ncould seek review any time the federal government’s alleged non-compliance made a\\n\\ngovernment program less useful than it might otherwise be, the possibilities for litigation\\n\\n 19\\n\\fwould be endless. Followed to its logical conclusion, a recipient of the mail could sue the\\n\\nPostal Service for improper employment practices, alleging that it caused inefficient\\n\\npackage deliveries. A disgruntled grant applicant could sue the National Institutes of\\n\\nHealth for violations of financial management laws, arguing that with more money in its\\n\\ncoffers more grants could be issued. The APA, however, is a creature of Congress; the\\n\\nlegislative branch has not put it to this sort of use, and we can discern no workable limits\\n\\nin the appellants’ theory.\\n\\n The implications of the appellants’ position are particularly troubling in the\\n\\ncontext of voluntary information sharing. The federal government has access to a vast\\n\\namount of data that is of great use both to intergovernmental partners and to those in the\\n\\nprivate sector. Information stored with the federal government is critical to many areas of\\n\\npublic policy, including, for example, homeland security and healthcare. See, e.g., Nat’l\\n\\nInfrastructure Advisory Council, Intelligence Information Sharing: Final Report and\\n\\nRecommendations ES-1 (Jan. 10, 2012) (“Information sharing is perhaps the most\\n\\nimportant factor in the protection and resilience of critical infrastructure.”). The federal\\n\\ngovernment has recently taken steps to make more of its own information accessible to\\n\\nthe general public, aware of the innovative potential that such information can unleash.\\n\\nSee Exec. Order No. 13,642, 78 Fed. Reg. 28,111 (May 9, 2013); see generally Data.gov\\n\\n(“The home of the U.S. Government’s open data.”). If we adopted the all-encompassing\\n\\ndefinition of “agency action” asserted by the municipal appellants here, each of these\\n\\nefforts to enhance public access would be checked by a fear that greater openness would\\n\\ninvite judicial scrutiny of any act that went into developing or disseminating the data.\\n\\n 20\\n\\fWith an agency’s eye peeled towards these consequences, it is easy to imagine the federal\\n\\ngovernment pulling back from these salutary efforts, and instead choosing to silo its\\n\\ninformation.\\n\\n The adverse consequences of appellants’ theory would not just fall on the\\n\\ngovernment’s attempt to share information with the public; they would also compromise\\n\\nthe dissemination of information within the government itself. A rule that made inter-\\n\\nagency information sharing justiciable by federal courts would undermine the whole\\n\\ngamut of federal activities that require collaboration between agencies, of which military\\n\\npreparedness and anti-terrorism efforts are only a part. Agencies dealing with public\\n\\nhealth, environment conservation, and disaster response draw on entire bodies of\\n\\nscientific work, and not all of the needed expertise will be located within a single agency\\n\\nor department. To have internal information sharing haunted by the specter of judicial\\n\\noversight would weaken government operations in innumerable areas, both foreign and\\n\\ndomestic, and allow the prospect of litigation to erect barriers when other nations, both\\n\\nour allies and our competitors, proceed unburdened by similar obstacles.\\n\\n\\n\\n III.\\n\\n The municipal appellants, like localities all over the country, are tasked with\\n\\nkeeping the public safe from horrific acts of violence, which far too often are committed\\n\\nby those with firearms they had no lawful right to possess. The municipalities’ efforts to\\n\\ncombat these threats are commendable. The APA, however, does not permit their efforts\\n\\nto include judicial supervision of the myriad programmatic workings of the federal\\n\\n 21\\n\\fgovernment. No matter the asserted virtues of the intended intervention, we are simply\\n\\nnot equipped to perform such tasks and have no legal basis for doing so.\\n\\n For the foregoing reasons, the judgment of the district court is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 22\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4359325/\", \"author_raw\": \"WILKINSON, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"WILKINSON"},"judge2":{"kind":"string","value":"AGEE"},"judge3":{"kind":"string","value":"THACKER"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4582072/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: The CITY OF NEW YORK; The City of Philadelphia; The City and County of San Francisco, Plaintiffs - Appellants, v. the UNITED STATES DEPARTMENT OF DEFENSE; The United States Department of the Air Force; The United States Department of the Navy; The United States Department of the Army; James N. Mattis, in His Official Capacity as United States Secretary of Defense; Heather A. Wilson, in Her Official Capacity as United States Secretary of the Air Force; Richard v. Spencer, in His Official Capacity as United States Secretary of the Navy; Dr. Mark T. Esper, in His Official Capacity as United States Secretary of the Army; Dermot F. O'Reilly, in His Official Capacity as Director of the Defense Criminal Investigative Service; Colonel Kirk B. Stabler, in His Official Capacity as Commander of the Air Force Office of Special Investigations; Andrew L. Traver, in His Official Capacity as Director of the Naval Criminal Investigative Service; Major General David P. Glaser, in His Official Capacity as Commanding General of the United States Army Criminal Investigation Command; Rear Admiral John B. Nowell, in His Official Capacity as Commander of the Navy Personnel Command and Deputy Chief of Naval Personnel, Defendants - Appellees.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-16\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1699\n\n\nTHE CITY OF NEW YORK; THE CITY OF PHILADELPHIA; THE CITY AND\nCOUNTY OF SAN FRANCISCO,\n\n Plaintiffs – Appellants,\n\n v.\n\nTHE UNITED STATES DEPARTMENT OF DEFENSE; THE UNITED STATES\nDEPARTMENT OF THE AIR FORCE; THE UNITED STATES DEPARTMENT\nOF THE NAVY; THE UNITED STATES DEPARTMENT OF THE ARMY;\nJAMES N. MATTIS, in his official capacity as United States Secretary of Defense;\nHEATHER A. WILSON, in her official capacity as United States Secretary of the\nAir Force; RICHARD V. SPENCER, in his official capacity as United States\nSecretary of the Navy; DR. MARK T. ESPER, in his official capacity as United\nStates Secretary of the Army; DERMOT F. O'REILLY, in his official capacity as\nDirector of the Defense Criminal Investigative Service; COLONEL KIRK B.\nSTABLER, in his official capacity as Commander of the Air Force Office of\nSpecial Investigations; ANDREW L. TRAVER, in his official capacity as Director\nof the Naval Criminal Investigative Service; MAJOR GENERAL DAVID P.\nGLASER, in his official capacity as Commanding General of the United States\nArmy Criminal Investigation Command; REAR ADMIRAL JOHN B. NOWELL,\nin his official capacity as Commander of the Navy Personnel Command and\nDeputy Chief of Naval Personnel,\n\n Defendants - Appellees.\n\n\n\nAppeal from the United States District Court for the Eastern District of Virginia, at\nAlexandria. Claude M. Hilton, Senior District Judge. (1:17-cv-01464-CMH-MSN)\n\n\nArgued: December 11, 2018 Decided: January 16, 2019\n\fBefore WILKINSON, AGEE, and THACKER, Circuit Judges.\n\n\nAffirmed by published opinion. Judge Wilkinson wrote the opinion, in which Judge Agee\nand Judge Thacker joined.\n\n\nARGUED: Matthew Jeffrey MacLean, PILLSBURY WINTHROP SHAW PITTMAN\nLLP, Washington, D.C., for Appellants. Tyce R. Walters, UNITED STATES\nDEPARTMENT OF JUSTICE, Washington, D.C., for Appellees. ON BRIEF: Laura B.\nLoBue, Jeetander Dulani, Washington, D.C., Kenneth W. Taber, Matthew F. Putorti,\nNicholas M. Buell, PILLSBURY WINTHROP SHAW PITTMAN LLP, New York, New\nYork, for Appellants. Eric Proshansky, Melanie C.T. Ash, Eric Lee, Claude S. Platton,\nZachary W. Carter, CORPORATION COUNSEL OF THE CITY OF NEW YORK,\nNEW YORK CITY LAW DEPARTMENT, New York, New York, for Appellant City of\nNew York. Dennis J. Herrera, Yvonne R. Mere, Owen J. Clements, SAN FRANCISCO\nCITY ATTORNEY’S OFFICE, San Francisco, California, for Appellant City and County\nof San Francisco. Marcel S. Pratt, Eleanor N. Ewing, Benjamin H. Field, CITY OF\nPHILADELPHIA LAW DEPARTMENT, Philadelphia, Pennsylvania, for Appellant City\nof Philadelphia. Joseph H. Hunt, Assistant Attorney General, Mark B. Stern, Civil\nDivision, UNITED STATES DEPARTMENT OF JUSTICE, Washington, D.C.; G.\nZachary Terwilliger, United States Attorney, OFFICE OF THE UNITED STATES\nATTORNEY, Alexandria, Virginia; Michael J. Fucci, Associate General Counsel,\nUNITED STATES DEPARTMENT OF DEFENSE, Washington, D.C., for Appellees.\n\n\n\n\n 2\n\fWILKINSON, Circuit Judge:\n\n Appellants are three municipalities who use the National Instant Criminal\n\nBackground Check System to carry out their obligations under state law. This system,\n\nknown as the NICS, is managed by the Federal Bureau of Investigation. The Department\n\nof Defense (DOD) is required under federal law to provide records to the NICS but has\n\npersistently been unable to fully carry out this obligation. The appellants sued DOD and\n\nits constituent military departments to compel the department’s more thorough\n\ncompliance. The district court dismissed their claim, holding both that the appellants\n\nlacked constitutional standing and failed to establish subject matter jurisdiction under the\n\nAdministrative Procedure Act. For the following reasons, we affirm.\n\n\n\n I.\n\n A.\n\n The responsibility to combat gun violence falls on every level of government. Law\n\nenforcement officials, whether local, state, or federal, work to prevent senseless gun\n\nviolence and are often the first to risk their lives to protect our communities. Working\n\nalongside these officers are many other governmental partners, including agencies of the\n\nfederal government. The dispute here grows out of a program that facilitates information\n\nsharing between federal agencies and local law enforcement officials: The National\n\nInstant Criminal Background Check System.\n\n The Brady Handgun Violence Prevention Act, or Brady Act, established the first\n\nnationwide system for background checks. Pub. L. No. 103-159, 107 Stat. 1536 (1993).\n\n 3\n\fUnder the law, enacted in 1993, a background check was required for firearms sales by\n\nlicensed dealers. Id. § 102. The Brady Act directed the Attorney General to establish a\n\nnational database that would be accessible to the firearms dealers tasked with ensuring\n\nthese background checks were performed. Id. § 102(b). To implement the statute, the\n\nAttorney General established the National Instant Criminal Background Check System\n\n(NICS) and delegated control of the system to the Federal Bureau of Investigation (FBI).\n\n The NICS contains records for individuals who are prohibited from possessing a\n\nfirearm. The system draws from many distinct federal databases that contain\n\ndisqualifying records and relies on information submitted from across the federal\n\ngovernment. In the military context, DOD provides information regarding current and\n\nformer service members who are disqualified from owning a gun because of a prior\n\nconviction. The Brady Act also empowers the Attorney General to request records from\n\nother agencies that may possess disqualifying information. Id. § 103(e) (codified at 34\n\nU.S.C. § 40901(e) (2018)).\n\n As originally designed, state law enforcement agencies were required to\n\nadminister the Brady Act’s background checks on a temporary basis while the new\n\nnational background check system was established. The division of responsibility\n\nenvisioned by Congress was altered by the Supreme Court’s decision in Printz v. United\n\nStates, which found that “[t]he Federal Government may [not] command the States’\n\nofficers, or those of their political subdivisions, to administer or enforce a federal\n\nregulatory program.” 521 U.S. 898, 935 (1997). As the law now stands, states are not\n\nrequired to perform any functions associated with the Brady Act, although a state may\n\n 4\n\fvoluntarily play a role. For states that elect to participate, a “point of contact” is\n\ndesignated to “serv[e] as the intermediary between [a dealer] and the federal databases\n\nchecked by the NICS.” 28 C.F.R. § 25.2 (2017).\n\n This does not mean that state and local governments have no use of the\n\ninformation stored in the NICS. To the contrary, many states require law enforcement\n\nagencies to carry out a range of functions designed to prevent guns from reaching\n\ndangerous hands. Depending on the particulars of state law, a local law enforcement\n\nagency may perform checks associated with issuing permits and licenses, or may review\n\ndisqualifying information before transferring a gun that is in the state’s possession. For\n\nexample, the City of Philadelphia, a party to this case, is required to process applications\n\nfor licenses to carry firearms under Pennsylvania law. See 18 Pa. Cons. Stat. § 6109. The\n\nother municipal appellants have similar obligations.\n\n The Attorney General has long permitted state and local agencies, including the\n\nappellants, to access the NICS for these purposes. In 1998, the FBI promulgated a rule\n\nallowing state and local law enforcement to use the NICS when “issu[ing] a firearm-\n\nrelated or explosives-related permit or license,” including concealed-carry permits. See\n\nNational Instant Criminal Background Check System Regulation, 63 Fed. Reg. 58,303,\n\n58,309 (Oct. 30, 1998) (codified at 28 C.F.R. § 25.6(j)(1)). In 2014, a new rule further\n\nexpanded NICS access, allowing state and local agencies to access the system when\n\ndisposing of firearms in their possession. See National Instant Criminal Background\n\nCheck System Regulation, 79 Fed. Reg. 69,047, 69,048 (Nov. 20, 2014) (codified at 28\n\nC.F.R. § 25.6(j)(3)). The regulations clearly state that these uses of the NICS are\n\n 5\n\fpermissive, intended as a service, and “unrelated to NICS background checks required by\n\nthe Brady Act.” 28 C.F.R. § 25.6(j).\n\n At times, local law enforcement officials have pushed for even greater access. For\n\ninstance, the FBI’s 1998 rulemaking noted that some local agencies wanted permission to\n\naccess the database to determine if a person was in “unlawful possession of a firearm.” 63\n\nFed. Reg. at 58,305. The FBI resisted these requests. In the FBI’s view, such expanded\n\nuse would potentially run afoul of federal privacy laws. Id. Moreover, the FBI noted that\n\nthe Brady Act only required agency reporting for the purpose of carrying out the federal\n\nbackground check provisions, rather than for a wider range of law enforcement activities.\n\nId. The permissive use regulations therefore account for the requirements of federal law,\n\nthe informational needs of local law enforcement, and the privacy concerns of the\n\naffected individuals. In arriving at the scheme in place today, the FBI has shown a\n\nwillingness to expand NICS access to support local partners, but has apparently not gone\n\nas far as some of those partners may desire.\n\n The comprehensiveness and accuracy of the NICS has been a subject of frequent\n\ndebate and attention. See, e.g., U.S. Gov’t Accountability Office, GAO/T-GGD-00-163,\n\nGun Control: Improving the National Instant Criminal Background Check System (June\n\n21, 2000). At the federal level, many agencies possess disqualifying information that\n\nwould be relevant to a background check. Under the original Brady Act, federal agencies\n\nwere required to furnish information to the Attorney General upon request. See Pub. L.\n\nNo. 103-159, § 103(e)(1) (1993) (codified as amended at 34 U.S.C. § 40901(e)(1)).\n\n\n\n 6\n\f Following the fatal shooting of 32 students and faculty at Virginia Tech in 2007,\n\nCongress enacted new legislation to improve the NICS. See NICS Improvement\n\nAmendments Act of 2007 (NIAA), Pub. L. No. 110-180, 121 Stat. 2559 (2008). Finding\n\nthat “nearly 21,000,000 criminal records are not accessible by NICS and millions of\n\ncriminal records are missing critical data, such as arrest dispositions, due to backlogs,”\n\nthe legislation imposed new reporting requirements and authorized new grants to assist\n\nstates. Id. §§ 101, 103-104. To improve inter-agency information sharing, the Act\n\nimposed an affirmative duty on agencies to report disqualifying information on a\n\nquarterly basis. Id. § 101(a) (codified at 34 U.S.C. § 40901(e)(1)(C)-(D)). To incentivize\n\ncompliance, the Attorney General is required to provide an annual report to Congress on\n\neach agency’s success. Id. (codified at 34 U.S.C. § 40901(e)(1)(E)).\n\n The Department of Defense (DOD) has long struggled to comply with the NIAA’s\n\naffirmative reporting provision, a deficiency the department readily admits. Response Br.\n\nat 1. The DOD Inspector General reviewed the program in 2015 and found that a\n\nsubstantial percentage of required records were not being submitted to the FBI. U.S.\n\nDep’t of Def. Inspector Gen., Evaluation of Department of Defense Compliance with\n\nCriminal History Data Reporting Requirements 9 (Feb. 12, 2015). Similar findings were\n\nmade again in 2017. U.S. Dep’t of Def. Inspector Gen., Evaluation of Fingerprint Card\n\nand Final Disposition Report Submissions by Military Service Law Enforcement\n\nOrganizations (Dec. 4, 2017). On November 5, 2017, a gunman opened fire at a church in\n\nSutherland Springs, Texas, killing 26 people and injuring an additional 20. The gunman\n\nwas a former member of the military who had been convicted in court-martial\n\n 7\n\fproceedings. According to the municipal appellants, the gunman would not have been\n\nable to obtain a firearm if DOD complied with its reporting obligations under the NIAA.\n\n Following the devastating loss of life at Sutherland Springs, Congress again\n\namended the statute governing the NICS to improve inter-agency reporting. The Fix\n\nNICS Act, Pub. L. No. 115-141, Div. S, Title VI (2018), required federal agencies with\n\ndisqualifying records to submit semiannual certification reports to the Attorney General\n\nand develop compliance plans to improve their own performance. Id. § 602. Like the\n\nearlier amendment, this law also includes measures designed to hold poor performers\n\naccountable. First, the law requires that the Attorney General notify Congress of non-\n\ncompliant agencies and publish a list of those agencies on the DOJ website. Second, the\n\nlaw makes political appointees at non-compliant agencies ineligible for bonus pay until\n\nthe agency improves. Id. § 602(1) (codified at 34 U.S.C. § 40901(e)(1)(F)-(I)).\n\n In the time since the Sutherland Springs shooting, components of the Department\n\nof Defense have taken a wide range of actions to correct their deficiencies. Efforts\n\ninclude the creation of new task forces and compliance plans, as well as the development\n\nof new technological processes to streamline reporting. See J.A. 302-16. For example,\n\nthe Army has, in recent months, provided new records for nearly 33,000 disqualified\n\npersons to the NICS.\n\n B.\n\n The tragic shooting in Sutherland Springs also gave rise to this litigation. The\n\nappellants are three municipalities, all of whom use the NICS database to fulfill their\n\nrequirements under state law. They brought this suit to compel DOD’s full reporting of\n\n 8\n\fdisqualifying information to the Attorney General, as required by the NIAA. Since\n\nneither the Brady Act nor the NIAA contemplated a separate cause of action to compel\n\nperformance with inter-agency reporting obligations, the municipal appellants brought\n\ntheir claim under the general provision of the Administrative Procedure Act that allows\n\nan aggrieved party to “compel agency action unlawfully withheld or unreasonably\n\ndelayed.” 5 U.S.C. § 706(1) (2012).\n\n The district court granted the federal defendants’ motion to dismiss this claim,\n\nfinding that it lacked jurisdiction to hear the case. The court identified two independent\n\njurisdictional defects. First, the district court found that the municipal appellants had\n\nfailed “to allege[] a cognizable informational injury sufficient to confer standing.” J.A.\n\n341. Second, the court held that the cities did not establish “jurisdiction under the APA\n\nsince they have not alleged a discrete agency action.” Id. As a consequence of the\n\ndismissal, the court also denied the municipal appellants’ motion for a preliminary\n\ninjunction. Id. at 348.\n\n This appeal followed. While federal courts must assure themselves that they have\n\njurisdiction before proceeding to the merits, see Steel Co. v. Citizens for a Better Env’t,\n\n523 U.S. 83, 94-95 (1998), both of the infirmities identified by the district court go to the\n\nquestion of jurisdiction. As such, this court can turn to either issue alone to resolve this\n\ncase. See Ruhrgas AG v. Marathon Oil Co., 526 U.S. 574, 578 (1999) (“[T]here is no\n\nunyielding jurisdictional hierarchy.”). Our review is de novo.\n\n\n\n\n 9\n\f II.\n\n Because this court is not in “the habit of decid[ing] questions of a constitutional\n\nnature unless absolutely necessary,” we turn first to the statutory question of whether the\n\nmunicipal appellants have established subject matter jurisdiction under the\n\nAdministrative Procedure Act (APA). See Flue-Cured Tobacco Coop. Stabilization Corp.\n\nv. EPA, 313 F.3d 852, 857 (4th Cir. 2002) (quoting Ashwander v. Tenn. Valley Auth., 297\n\nU.S. 288, 347 (1936) (Brandeis, J. concurring)). At the outset, it is important to\n\nunderstand the nature of appellants’ claim. Their challenge is not about access to the\n\nNICS; it is instead about the quality of the information in that system. By their own\n\nsubmission, each of the appellants accesses the NICS frequently to carry out their\n\nobligations under state law. This is thus not a case where appellants have asked for access\n\nprovided for in the regulations and have been denied. Instead, the municipalities see their\n\nexisting access to the NICS as an invitation to compel any federal inter-agency legal\n\nrequirement that may affect the quality of the information they receive. On their view, the\n\nAPA authorizes a recipient of government information to initiate a private action to\n\ncompel governmental conduct that might improve that information’s accuracy or\n\ncomprehensiveness. As we explain below, there is simply no basis in the APA’s text for\n\nsuch a broad incursion into internal agency management.\n\n A.\n\n The APA waives the federal government’s sovereign immunity for a limited set of\n\nsuits, brought by “a person suffering legal wrong because of agency action” to obtain\n\nrelief “other than money damages.” 5 U.S.C. § 702. It is well-established that\n\n 10\n\f“[s]overeign immunity is jurisdictional in nature” and “absent a waiver . . . shields the\n\nFederal Government and its agencies from suit.” FDIC v. Meyer, 510 U.S. 471, 475\n\n(1994). Judicial review under the APA, moreover, is limited to “final agency actions.”\n\n5 U.S.C. § 704.\n\n As these provisions of the APA make plain, subject matter jurisdiction is lacking if\n\nthe plaintiff fails to challenge a particular “agency action” that is fit for review. See\n\nInvention Submission Corp. v. Rogan, 357 F.3d 452, 460 (4th Cir. 2004). “The term\n\n‘action’ as used in the APA is a term of art that does not include all conduct” on the part\n\nof the government. Vill. of Bald Head Island v. U.S. Army Corps of Eng’rs, 714 F.3d 186,\n\n193 (4th Cir. 2013). See also Hearst Radio v. FCC, 167 F.2d 225, 227 (D.C. Cir. 1948)\n\n(“The difficulty with the appellant company’s position is that the Administrative\n\nProcedure Act does not provide review for everything done by an agency.”). Instead, the\n\nAPA defines “agency action” to include “the whole or a part of an agency rule, order,\n\nlicense, sanction, relief, or the equivalent or denial thereof, or failure to act.” 5 U.S.C.\n\n§ 551(13).\n\n This definition limits the scope of judicial review in two important respects. First,\n\neach of the terms that comprise the definition of “agency action” is limited to those acts\n\nthat are “circumscribed” and “discrete.” Norton v. Southern Utah Wilderness Alliance\n\n(SUWA), 542 U.S. 55, 62 (2004). When challenging agency action―whether it be a\n\nparticular action or a failure to act altogether―the plaintiff must therefore identify\n\nspecific and discrete governmental conduct, rather than launch a “broad programmatic\n\nattack” on the government’s operations. Id. at 64. This distinction between discrete acts,\n\n 11\n\fwhich are reviewable, and programmatic challenges, which are not, is vital to the APA’s\n\nconception of the separation of powers. Courts are well-suited to reviewing specific\n\nagency decisions, such as rulemakings, orders, or denials. We are woefully ill-suited,\n\nhowever, to adjudicate generalized grievances asking us to improve an agency’s\n\nperformance or operations. In such a case, courts would be forced either to enter a\n\ndisfavored “obey the law” injunction, see Int’l Longshoremen’s Ass’n, Local 1291 v.\n\nPhil. Mar. Trade Ass’n, 389 U.S. 64, 76 (1967), or to engage in day-to-day oversight of\n\nthe executive’s administrative practices. Both alternatives are foreclosed by the APA, and\n\nrightly so. The Supreme Court’s guidance on this point is worth considering in full:\n\n If courts were empowered to enter general orders compelling compliance\n with broad statutory mandates, they would necessarily be empowered, as\n well, to determine whether compliance was achieved-which would mean\n that it would ultimately become the task of the supervising court, rather\n than the agency, to work out compliance with the broad statutory mandate,\n injecting the judge into day-to-day agency management.\n\nSUWA, 542 U.S. at 66-67. The requirement that the challenger identify a discrete act\n\nkeeps us from entering such a quagmire.\n\n Second, the definition of “agency action” is limited to those governmental acts\n\nthat “determin[e] rights and obligations.” Clear Sky Car Wash LLC v. City of\n\nChesapeake, Va., 743 F.3d 438, 445 (4th Cir. 2014). This limitation ensures that judicial\n\nreview does not reach into the internal workings of the government, and is instead\n\nproperly directed at the effect that agency conduct has on private parties. To meet this\n\nrequirement, a party must demonstrate that the challenged act had “an immediate and\n\npractical impact,” see Golden & Zimmerman LLC v. Domenech, 599 F.3d 426, 433 (4th\n\n\n 12\n\fCir. 2010), or “alter[ed] the legal regime” in which it operates. See Bennett v. Spear, 520\n\nU.S. 154, 178 (1997). It is not enough for plaintiffs to simply identify a governmental\n\naction that ultimately affected them through the “independent responses and choices of\n\nthird parties,” or mere “coercive pressures.” Flue-Cured Tobacco, 313 F.3d at 859, 861.\n\nThis requirement applies fully to claims that an agency has failed to act, which is\n\n“properly understood as a failure to take an agency action.” See Norton, 542 U.S. at 62.\n\nSince “agency actions” must determine rights and obligations, claims to compel an\n\nagency to take an action must seek such a determination as well.\n\n These two requirements, which flow directly from the APA’s text, apply to all\n\nchallenges to agency action and accordingly limit judicial review generally. When a\n\nplaintiff brings a claim to compel agency action, like the municipal appellants have here,\n\na further limit applies. Under the APA, actions that can be compelled are only those that\n\nhave been “unlawfully withheld or unreasonably delayed.” 5 U.S.C. § 706(1). As the\n\nSupreme Court has explained, the text of § 706(1) requires that the plaintiff identify\n\naction that is “legally required.” SUWA, 542 U.S. at 63. Just like the traditional\n\nmandamus remedy from which this provision is derived, claims to compel agency action\n\nare “limited to enforcement of ‘a specific, unequivocal command,’” over which an\n\nofficial has no discretion. Id. (quoting ICC v. New York, N.H. & H.R. Co., 287 U.S. 178,\n\n204 (1932)).\n\n Taken together, the limitations imposed on claims to compel agency action under\n\nthe APA strike a balance between meaningful judicial review and the needs of effective\n\nadministration. Review is available only when acts are discrete in character, required by\n\n 13\n\flaw, and bear on a party’s rights and obligations. The result is a scheme allowing courts\n\nto review only those acts that are specific enough to avoid entangling the judiciary in\n\nprogrammatic oversight, clear enough to avoid substituting judicial judgments for those\n\nof the executive branch, and substantial enough to prevent an incursion into internal\n\nagency management. See SUWA, 542 U.S. at 64-65.\n\n These principles guide our consideration of all claims to compel agency action,\n\nregardless of the context. Claims involving government information are no exception.\n\nOur court, just like our sister circuits, has had many occasions to consider how the\n\nrequirements of agency action apply to claims that the government has wrongfully\n\nhandled the information in its possession. In some cases, the claim is that the\n\ngovernment’s decision to disseminate information, such as an unfavorable report, was\n\nunlawful. See Invention Submission Corp., 357 F.3d at 460; see also Flue-Cured\n\nTobacco, 313 F.3d at 859; Indus. Safety Equip. Ass’n, Inc. v. EPA, 837 F.2d 1115, 1118\n\n(D.C. Cir. 1988). At other times, the claim was that the government improperly withheld\n\nor mishandled personal information. See, e.g., Fanin v. U.S. Dep’t of Veterans Affairs,\n\n572 F.3d 868, 871 (11th Cir. 2009). Informational harms may involve novel facts, but\n\nthey do not disrupt the legal principles set forth in the APA. See Golden & Zimmerman,\n\nLLC, 599 F.3d at 431-32 (finding that an agency’s “reference guide” was not agency\n\naction because it did not “impose new legal requirements”). As these cases aptly\n\ndemonstrate, a plaintiff’s burden remains constant and subject to the above requirements\n\nthroughout.\n\n\n\n 14\n\f B.\n\n Applying these well-established principles to the facts here, it is clear that the\n\nmunicipal appellants have failed to establish subject matter jurisdiction under the APA.\n\nOnce again, the claim at issue arises from the appellants’ permissive use of the NICS,\n\nafforded to them by regulation, for purposes explicitly “unrelated to the NICS\n\nbackground checks required by the Brady Act.” 28 C.F.R. § 25.6(j). The regulation\n\naffords the municipalities only “access to the NICS Index.” Id. On the view of the\n\nmunicipal appellants, this access, which is not expressly contemplated either by the\n\nBrady Act or subsequent legislation, allows a NICS user to reach into the federal\n\ngovernment and compel any legal obligations associated with developing the information\n\nin the system. Such a broad theory of agency action is untethered from the APA’s text\n\nand contravenes important limits that Congress has placed on judicial review.\n\n First, the municipal appellants’ claim does not challenge a discrete agency action.\n\nInstead appellants ask that we “supervise an agency’s compliance with [the] broad\n\nstatutory mandate” of the NIAA. Murray Energy Corp. v. EPA, 861 F.3d 529, 537 n.4\n\n(4th Cir. 2017). By appellants’ own account, the DOD’s failure to provide disqualifying\n\nconviction records for former service members is widespread and systemic. The\n\ndepartment has admitted as much and is engaged in extensive efforts to increase its\n\ncompliance. As all parties seem to agree, the road ahead is an arduous one, as DOD\n\nattempts to improve on its partial and inconsistent reporting. This is the sort of public\n\npolicy problem that often requires reallocating resources, developing new administrative\n\n 15\n\fsystems, and working closely with partners across government. Solving it will likely\n\nrequire expertise in information technology and deep knowledge of how military needs\n\nintersect with data collection. In other words, it is exactly the sort of “broad\n\nprogrammatic” undertaking for which the APA has foreclosed judicial review. See\n\nSUWA, 542 U.S. at 64.\n\n Congress seems to be of the same view. Since the passage of the Brady Act,\n\nCongress has on multiple occasions turned its attention to the severe challenge of\n\nrampant gun violence. Twice, the legislative responses have been directed squarely at\n\nagency compliance with NICS reporting obligations. Congress has included\n\naccountability measures, designed to identify delinquent agencies and push them into\n\nimproving their performance. The most recent effort in this regard singles out executive\n\ncompensation at these agencies, limiting bonus pay for those who do not improve their\n\noutcomes. See 34 U.S.C. § 40901(e)(1)(I) (providing that certain “political\n\nappointee[s] . . . shall not be eligible for the receipt of bonus pay” until their department\n\nimproves its compliance). These measures signal that Congress sees this problem as one\n\nripe for legislative oversight and in need of attention by experts in the executive branch.\n\nAt no point, however, has Congress invited the federal courts into the process. Perhaps\n\ncognizant of the judiciary’s inability to oversee and manage a complex scheme of inter-\n\nagency collaboration, we have appropriately been left on the sideline.\n\n The municipal appellants try to nonetheless force us onto the field by\n\ncharacterizing their broad claim as simply an aggregation of many small claims, each one\n\nseeking to compel the individual reports required by the NIAA. On this view, what the\n\n 16\n\fcities seek is not programmatic because each specific act that DOD has failed to perform\n\nis discrete when considered on its own. But any limit on programmatic assessment would\n\nbe rendered meaningless if such an argument prevailed. All governmental programs are\n\nthe aggregation of individual decisions, many of which are required by law. The APA\n\nensures that it is the individual decisions that are assessed as agency action, rather than\n\nthe whole administrative apparatus.\n\n The municipal appellants are surely correct that ongoing failures to carry out\n\ndiscrete obligations can be subject to review. Government deficiencies do not become\n\nnon-reviewable simply because they are pervasive. This, however, does nothing to\n\nobviate the fact that a discrete action is wholly lacking here. By the appellants’ own\n\nestimate, full compliance with the NIAA may require DOD to obtain and transmit tens of\n\nthousands of records. There is simply no way to achieve such a result without wholesale\n\nimprovements in the DOD’s reporting requirements, which take time and require the\n\nexpertise of senior civilian and military leaders.\n\n If there were any doubt about the nature of the cities’ claim, the requested remedy\n\ntells the real story. Their complaint “seeks immediate injunctive relief to compel\n\nDefendants to repair this broken system and to cure once and for all the potentially\n\ndeadly gaps in the NCIC database.” J.A. 17. In their prayer for relief, the appellants ask\n\nthat the DOD, on “a schedule to be set by the Court,” “identify all records” in its\n\npossession, provide the information contained in those records to the Attorney General,\n\n“conduct a thorough review of [its] records and procedures,” “submit to the Court for\n\napproval a compliance plan,” and provide “a monthly report to the Court detailing [its]\n\n 17\n\fprogress.” Id. at 35-36. The requested relief would continue “until such time as the Court\n\nis satisfied that Defendants have brought themselves into full compliance with 34 U.S.C.\n\n§ 40901.” Id. at 36 (emphasis added). The APA’s discreteness requirement exists to avoid\n\nplacing the courts in this exact position. As we previously explained, “[t]he obvious\n\ninability for a court to function in such a day-to-day managerial role over agency\n\noperations is precisely the reason why the APA limits judicial review to discrete agency\n\nactions.” Vill. of Bald Head Island, 714 F.3d at 194.\n\n Moreover, the municipal appellants have failed to demonstrate that the DOD’s\n\nreporting requirements in any way determine their rights and obligations. Accordingly,\n\nthey have not identified an act that can be compelled by this court under § 706(1). See\n\nSUWA, 542 U.S. at 62 (finding that a failure to act under § 706(1) means “failure to take\n\nan agency action”). The action challenged in this case is DOD’s obligation to provide\n\ninformation only to another agency of the federal government: The Department of\n\nJustice. See 34 U.S.C. § 40901(e)(1)(C). The regulation permitting local law enforcement\n\nagencies to use the NICS refers only to access to the system, not to the particular\n\ninformation provided to the FBI by other federal agencies. The transfer of information\n\nbetween agencies does not, without more, alter the rights and obligations of any party.\n\nThat is especially true, as here, where outside access to the information is entirely\n\npermissive and implicates none of the complaining party’s obligations under federal law.\n\n We need not say here that information sharing can never constitute agency action.\n\nWe simply note that claims to compel an agency to provide information are held to the\n\nsame standard as any other. In arguing otherwise, the municipal appellants point to a\n\n 18\n\fstring of cases, all from outside this circuit, holding that the government’s alleged misuse\n\nof information was reviewable “agency action.” Our holding here, however, raises no\n\nconflict with these decisions. The cases relied on by the appellants involve claims wholly\n\nunlike the one that they have brought. For example, one case involves the government’s\n\nlegal obligations with respect to the plaintiffs’ personal medical information, see Vietnam\n\nVeterans of Am. v. CIA, 811 F.3d 1068, 1078 (9th Cir. 2015) (finding that “the Army\n\n[has] a duty to provide notice to prior test subjects of information regarding their well-\n\nbeing”), while another examines the rights of federal employees under the civil service\n\nsystem, see Hondros v. U.S. Civil Service Comm., 720 F.2d 278, 280 (3d Cir. 1983). Each\n\nof these cases involved plaintiffs seeking information that was particular to them and\n\ntheir own rights under federal law. As such, they tell us little about how to handle a case,\n\nlike this one, where the plaintiff seeks wholesale compliance with an entire\n\nadministrative scheme, based solely on the fact that the government has granted them\n\naccess to an information system.\n\n\n\n C.\n\n What the municipal appellants are ultimately asking for is a judicial decree making\n\nthe assistance of the federal government more useful to them than it is now. While their\n\nmotives for wanting to see improvement to the NICS are laudable, they point to no case\n\nsuggesting that the APA countenances such an action. And for good reason. If a party\n\ncould seek review any time the federal government’s alleged non-compliance made a\n\ngovernment program less useful than it might otherwise be, the possibilities for litigation\n\n 19\n\fwould be endless. Followed to its logical conclusion, a recipient of the mail could sue the\n\nPostal Service for improper employment practices, alleging that it caused inefficient\n\npackage deliveries. A disgruntled grant applicant could sue the National Institutes of\n\nHealth for violations of financial management laws, arguing that with more money in its\n\ncoffers more grants could be issued. The APA, however, is a creature of Congress; the\n\nlegislative branch has not put it to this sort of use, and we can discern no workable limits\n\nin the appellants’ theory.\n\n The implications of the appellants’ position are particularly troubling in the\n\ncontext of voluntary information sharing. The federal government has access to a vast\n\namount of data that is of great use both to intergovernmental partners and to those in the\n\nprivate sector. Information stored with the federal government is critical to many areas of\n\npublic policy, including, for example, homeland security and healthcare. See, e.g., Nat’l\n\nInfrastructure Advisory Council, Intelligence Information Sharing: Final Report and\n\nRecommendations ES-1 (Jan. 10, 2012) (“Information sharing is perhaps the most\n\nimportant factor in the protection and resilience of critical infrastructure.”). The federal\n\ngovernment has recently taken steps to make more of its own information accessible to\n\nthe general public, aware of the innovative potential that such information can unleash.\n\nSee Exec. Order No. 13,642, 78 Fed. Reg. 28,111 (May 9, 2013); see generally Data.gov\n\n(“The home of the U.S. Government’s open data.”). If we adopted the all-encompassing\n\ndefinition of “agency action” asserted by the municipal appellants here, each of these\n\nefforts to enhance public access would be checked by a fear that greater openness would\n\ninvite judicial scrutiny of any act that went into developing or disseminating the data.\n\n 20\n\fWith an agency’s eye peeled towards these consequences, it is easy to imagine the federal\n\ngovernment pulling back from these salutary efforts, and instead choosing to silo its\n\ninformation.\n\n The adverse consequences of appellants’ theory would not just fall on the\n\ngovernment’s attempt to share information with the public; they would also compromise\n\nthe dissemination of information within the government itself. A rule that made inter-\n\nagency information sharing justiciable by federal courts would undermine the whole\n\ngamut of federal activities that require collaboration between agencies, of which military\n\npreparedness and anti-terrorism efforts are only a part. Agencies dealing with public\n\nhealth, environment conservation, and disaster response draw on entire bodies of\n\nscientific work, and not all of the needed expertise will be located within a single agency\n\nor department. To have internal information sharing haunted by the specter of judicial\n\noversight would weaken government operations in innumerable areas, both foreign and\n\ndomestic, and allow the prospect of litigation to erect barriers when other nations, both\n\nour allies and our competitors, proceed unburdened by similar obstacles.\n\n\n\n III.\n\n The municipal appellants, like localities all over the country, are tasked with\n\nkeeping the public safe from horrific acts of violence, which far too often are committed\n\nby those with firearms they had no lawful right to possess. The municipalities’ efforts to\n\ncombat these threats are commendable. The APA, however, does not permit their efforts\n\nto include judicial supervision of the myriad programmatic workings of the federal\n\n 21\n\fgovernment. No matter the asserted virtues of the intended intervention, we are simply\n\nnot equipped to perform such tasks and have no legal basis for doing so.\n\n For the foregoing reasons, the judgment of the district court is\n\n AFFIRMED.\n\n\n\n\n 22\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: The CITY OF NEW YORK; The City of Philadelphia; The City and County of San Francisco, Plaintiffs - Appellants, v. the UNITED STATES DEPARTMENT OF DEFENSE; The United States Department of the Air Force; The United States Department of the Navy; The United States Department of the Army; James N. Mattis, in His Official Capacity as United States Secretary of Defense; Heather A. Wilson, in Her Official Capacity as United States Secretary of the Air Force; Richard v. Spencer, in His Official Capacity as United States Secretary of the Navy; Dr. Mark T. Esper, in His Official Capacity as United States Secretary of the Army; Dermot F. O'Reilly, in His Official Capacity as Director of the Defense Criminal Investigative Service; Colonel Kirk B. Stabler, in His Official Capacity as Commander of the Air Force Office of Special Investigations; Andrew L. Traver, in His Official Capacity as Director of the Naval Criminal Investigative Service; Major General David P. Glaser, in His Official Capacity as Commanding General of the United States Army Criminal Investigation Command; Rear Admiral John B. Nowell, in His Official Capacity as Commander of the Navy Personnel Command and Deputy Chief of Naval Personnel, Defendants - Appellees.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-16\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1699\\n\\n\\nTHE CITY OF NEW YORK; THE CITY OF PHILADELPHIA; THE CITY AND\\nCOUNTY OF SAN FRANCISCO,\\n\\n Plaintiffs – Appellants,\\n\\n v.\\n\\nTHE UNITED STATES DEPARTMENT OF DEFENSE; THE UNITED STATES\\nDEPARTMENT OF THE AIR FORCE; THE UNITED STATES DEPARTMENT\\nOF THE NAVY; THE UNITED STATES DEPARTMENT OF THE ARMY;\\nJAMES N. MATTIS, in his official capacity as United States Secretary of Defense;\\nHEATHER A. WILSON, in her official capacity as United States Secretary of the\\nAir Force; RICHARD V. SPENCER, in his official capacity as United States\\nSecretary of the Navy; DR. MARK T. ESPER, in his official capacity as United\\nStates Secretary of the Army; DERMOT F. O'REILLY, in his official capacity as\\nDirector of the Defense Criminal Investigative Service; COLONEL KIRK B.\\nSTABLER, in his official capacity as Commander of the Air Force Office of\\nSpecial Investigations; ANDREW L. TRAVER, in his official capacity as Director\\nof the Naval Criminal Investigative Service; MAJOR GENERAL DAVID P.\\nGLASER, in his official capacity as Commanding General of the United States\\nArmy Criminal Investigation Command; REAR ADMIRAL JOHN B. NOWELL,\\nin his official capacity as Commander of the Navy Personnel Command and\\nDeputy Chief of Naval Personnel,\\n\\n Defendants - Appellees.\\n\\n\\n\\nAppeal from the United States District Court for the Eastern District of Virginia, at\\nAlexandria. Claude M. Hilton, Senior District Judge. (1:17-cv-01464-CMH-MSN)\\n\\n\\nArgued: December 11, 2018 Decided: January 16, 2019\\n\\fBefore WILKINSON, AGEE, and THACKER, Circuit Judges.\\n\\n\\nAffirmed by published opinion. Judge Wilkinson wrote the opinion, in which Judge Agee\\nand Judge Thacker joined.\\n\\n\\nARGUED: Matthew Jeffrey MacLean, PILLSBURY WINTHROP SHAW PITTMAN\\nLLP, Washington, D.C., for Appellants. Tyce R. Walters, UNITED STATES\\nDEPARTMENT OF JUSTICE, Washington, D.C., for Appellees. ON BRIEF: Laura B.\\nLoBue, Jeetander Dulani, Washington, D.C., Kenneth W. Taber, Matthew F. Putorti,\\nNicholas M. Buell, PILLSBURY WINTHROP SHAW PITTMAN LLP, New York, New\\nYork, for Appellants. Eric Proshansky, Melanie C.T. Ash, Eric Lee, Claude S. Platton,\\nZachary W. Carter, CORPORATION COUNSEL OF THE CITY OF NEW YORK,\\nNEW YORK CITY LAW DEPARTMENT, New York, New York, for Appellant City of\\nNew York. Dennis J. Herrera, Yvonne R. Mere, Owen J. Clements, SAN FRANCISCO\\nCITY ATTORNEY’S OFFICE, San Francisco, California, for Appellant City and County\\nof San Francisco. Marcel S. Pratt, Eleanor N. Ewing, Benjamin H. Field, CITY OF\\nPHILADELPHIA LAW DEPARTMENT, Philadelphia, Pennsylvania, for Appellant City\\nof Philadelphia. Joseph H. Hunt, Assistant Attorney General, Mark B. Stern, Civil\\nDivision, UNITED STATES DEPARTMENT OF JUSTICE, Washington, D.C.; G.\\nZachary Terwilliger, United States Attorney, OFFICE OF THE UNITED STATES\\nATTORNEY, Alexandria, Virginia; Michael J. Fucci, Associate General Counsel,\\nUNITED STATES DEPARTMENT OF DEFENSE, Washington, D.C., for Appellees.\\n\\n\\n\\n\\n 2\\n\\fWILKINSON, Circuit Judge:\\n\\n Appellants are three municipalities who use the National Instant Criminal\\n\\nBackground Check System to carry out their obligations under state law. This system,\\n\\nknown as the NICS, is managed by the Federal Bureau of Investigation. The Department\\n\\nof Defense (DOD) is required under federal law to provide records to the NICS but has\\n\\npersistently been unable to fully carry out this obligation. The appellants sued DOD and\\n\\nits constituent military departments to compel the department’s more thorough\\n\\ncompliance. The district court dismissed their claim, holding both that the appellants\\n\\nlacked constitutional standing and failed to establish subject matter jurisdiction under the\\n\\nAdministrative Procedure Act. For the following reasons, we affirm.\\n\\n\\n\\n I.\\n\\n A.\\n\\n The responsibility to combat gun violence falls on every level of government. Law\\n\\nenforcement officials, whether local, state, or federal, work to prevent senseless gun\\n\\nviolence and are often the first to risk their lives to protect our communities. Working\\n\\nalongside these officers are many other governmental partners, including agencies of the\\n\\nfederal government. The dispute here grows out of a program that facilitates information\\n\\nsharing between federal agencies and local law enforcement officials: The National\\n\\nInstant Criminal Background Check System.\\n\\n The Brady Handgun Violence Prevention Act, or Brady Act, established the first\\n\\nnationwide system for background checks. Pub. L. No. 103-159, 107 Stat. 1536 (1993).\\n\\n 3\\n\\fUnder the law, enacted in 1993, a background check was required for firearms sales by\\n\\nlicensed dealers. Id. § 102. The Brady Act directed the Attorney General to establish a\\n\\nnational database that would be accessible to the firearms dealers tasked with ensuring\\n\\nthese background checks were performed. Id. § 102(b). To implement the statute, the\\n\\nAttorney General established the National Instant Criminal Background Check System\\n\\n(NICS) and delegated control of the system to the Federal Bureau of Investigation (FBI).\\n\\n The NICS contains records for individuals who are prohibited from possessing a\\n\\nfirearm. The system draws from many distinct federal databases that contain\\n\\ndisqualifying records and relies on information submitted from across the federal\\n\\ngovernment. In the military context, DOD provides information regarding current and\\n\\nformer service members who are disqualified from owning a gun because of a prior\\n\\nconviction. The Brady Act also empowers the Attorney General to request records from\\n\\nother agencies that may possess disqualifying information. Id. § 103(e) (codified at 34\\n\\nU.S.C. § 40901(e) (2018)).\\n\\n As originally designed, state law enforcement agencies were required to\\n\\nadminister the Brady Act’s background checks on a temporary basis while the new\\n\\nnational background check system was established. The division of responsibility\\n\\nenvisioned by Congress was altered by the Supreme Court’s decision in Printz v. United\\n\\nStates, which found that “[t]he Federal Government may [not] command the States’\\n\\nofficers, or those of their political subdivisions, to administer or enforce a federal\\n\\nregulatory program.” 521 U.S. 898, 935 (1997). As the law now stands, states are not\\n\\nrequired to perform any functions associated with the Brady Act, although a state may\\n\\n 4\\n\\fvoluntarily play a role. For states that elect to participate, a “point of contact” is\\n\\ndesignated to “serv[e] as the intermediary between [a dealer] and the federal databases\\n\\nchecked by the NICS.” 28 C.F.R. § 25.2 (2017).\\n\\n This does not mean that state and local governments have no use of the\\n\\ninformation stored in the NICS. To the contrary, many states require law enforcement\\n\\nagencies to carry out a range of functions designed to prevent guns from reaching\\n\\ndangerous hands. Depending on the particulars of state law, a local law enforcement\\n\\nagency may perform checks associated with issuing permits and licenses, or may review\\n\\ndisqualifying information before transferring a gun that is in the state’s possession. For\\n\\nexample, the City of Philadelphia, a party to this case, is required to process applications\\n\\nfor licenses to carry firearms under Pennsylvania law. See 18 Pa. Cons. Stat. § 6109. The\\n\\nother municipal appellants have similar obligations.\\n\\n The Attorney General has long permitted state and local agencies, including the\\n\\nappellants, to access the NICS for these purposes. In 1998, the FBI promulgated a rule\\n\\nallowing state and local law enforcement to use the NICS when “issu[ing] a firearm-\\n\\nrelated or explosives-related permit or license,” including concealed-carry permits. See\\n\\nNational Instant Criminal Background Check System Regulation, 63 Fed. Reg. 58,303,\\n\\n58,309 (Oct. 30, 1998) (codified at 28 C.F.R. § 25.6(j)(1)). In 2014, a new rule further\\n\\nexpanded NICS access, allowing state and local agencies to access the system when\\n\\ndisposing of firearms in their possession. See National Instant Criminal Background\\n\\nCheck System Regulation, 79 Fed. Reg. 69,047, 69,048 (Nov. 20, 2014) (codified at 28\\n\\nC.F.R. § 25.6(j)(3)). The regulations clearly state that these uses of the NICS are\\n\\n 5\\n\\fpermissive, intended as a service, and “unrelated to NICS background checks required by\\n\\nthe Brady Act.” 28 C.F.R. § 25.6(j).\\n\\n At times, local law enforcement officials have pushed for even greater access. For\\n\\ninstance, the FBI’s 1998 rulemaking noted that some local agencies wanted permission to\\n\\naccess the database to determine if a person was in “unlawful possession of a firearm.” 63\\n\\nFed. Reg. at 58,305. The FBI resisted these requests. In the FBI’s view, such expanded\\n\\nuse would potentially run afoul of federal privacy laws. Id. Moreover, the FBI noted that\\n\\nthe Brady Act only required agency reporting for the purpose of carrying out the federal\\n\\nbackground check provisions, rather than for a wider range of law enforcement activities.\\n\\nId. The permissive use regulations therefore account for the requirements of federal law,\\n\\nthe informational needs of local law enforcement, and the privacy concerns of the\\n\\naffected individuals. In arriving at the scheme in place today, the FBI has shown a\\n\\nwillingness to expand NICS access to support local partners, but has apparently not gone\\n\\nas far as some of those partners may desire.\\n\\n The comprehensiveness and accuracy of the NICS has been a subject of frequent\\n\\ndebate and attention. See, e.g., U.S. Gov’t Accountability Office, GAO/T-GGD-00-163,\\n\\nGun Control: Improving the National Instant Criminal Background Check System (June\\n\\n21, 2000). At the federal level, many agencies possess disqualifying information that\\n\\nwould be relevant to a background check. Under the original Brady Act, federal agencies\\n\\nwere required to furnish information to the Attorney General upon request. See Pub. L.\\n\\nNo. 103-159, § 103(e)(1) (1993) (codified as amended at 34 U.S.C. § 40901(e)(1)).\\n\\n\\n\\n 6\\n\\f Following the fatal shooting of 32 students and faculty at Virginia Tech in 2007,\\n\\nCongress enacted new legislation to improve the NICS. See NICS Improvement\\n\\nAmendments Act of 2007 (NIAA), Pub. L. No. 110-180, 121 Stat. 2559 (2008). Finding\\n\\nthat “nearly 21,000,000 criminal records are not accessible by NICS and millions of\\n\\ncriminal records are missing critical data, such as arrest dispositions, due to backlogs,”\\n\\nthe legislation imposed new reporting requirements and authorized new grants to assist\\n\\nstates. Id. §§ 101, 103-104. To improve inter-agency information sharing, the Act\\n\\nimposed an affirmative duty on agencies to report disqualifying information on a\\n\\nquarterly basis. Id. § 101(a) (codified at 34 U.S.C. § 40901(e)(1)(C)-(D)). To incentivize\\n\\ncompliance, the Attorney General is required to provide an annual report to Congress on\\n\\neach agency’s success. Id. (codified at 34 U.S.C. § 40901(e)(1)(E)).\\n\\n The Department of Defense (DOD) has long struggled to comply with the NIAA’s\\n\\naffirmative reporting provision, a deficiency the department readily admits. Response Br.\\n\\nat 1. The DOD Inspector General reviewed the program in 2015 and found that a\\n\\nsubstantial percentage of required records were not being submitted to the FBI. U.S.\\n\\nDep’t of Def. Inspector Gen., Evaluation of Department of Defense Compliance with\\n\\nCriminal History Data Reporting Requirements 9 (Feb. 12, 2015). Similar findings were\\n\\nmade again in 2017. U.S. Dep’t of Def. Inspector Gen., Evaluation of Fingerprint Card\\n\\nand Final Disposition Report Submissions by Military Service Law Enforcement\\n\\nOrganizations (Dec. 4, 2017). On November 5, 2017, a gunman opened fire at a church in\\n\\nSutherland Springs, Texas, killing 26 people and injuring an additional 20. The gunman\\n\\nwas a former member of the military who had been convicted in court-martial\\n\\n 7\\n\\fproceedings. According to the municipal appellants, the gunman would not have been\\n\\nable to obtain a firearm if DOD complied with its reporting obligations under the NIAA.\\n\\n Following the devastating loss of life at Sutherland Springs, Congress again\\n\\namended the statute governing the NICS to improve inter-agency reporting. The Fix\\n\\nNICS Act, Pub. L. No. 115-141, Div. S, Title VI (2018), required federal agencies with\\n\\ndisqualifying records to submit semiannual certification reports to the Attorney General\\n\\nand develop compliance plans to improve their own performance. Id. § 602. Like the\\n\\nearlier amendment, this law also includes measures designed to hold poor performers\\n\\naccountable. First, the law requires that the Attorney General notify Congress of non-\\n\\ncompliant agencies and publish a list of those agencies on the DOJ website. Second, the\\n\\nlaw makes political appointees at non-compliant agencies ineligible for bonus pay until\\n\\nthe agency improves. Id. § 602(1) (codified at 34 U.S.C. § 40901(e)(1)(F)-(I)).\\n\\n In the time since the Sutherland Springs shooting, components of the Department\\n\\nof Defense have taken a wide range of actions to correct their deficiencies. Efforts\\n\\ninclude the creation of new task forces and compliance plans, as well as the development\\n\\nof new technological processes to streamline reporting. See J.A. 302-16. For example,\\n\\nthe Army has, in recent months, provided new records for nearly 33,000 disqualified\\n\\npersons to the NICS.\\n\\n B.\\n\\n The tragic shooting in Sutherland Springs also gave rise to this litigation. The\\n\\nappellants are three municipalities, all of whom use the NICS database to fulfill their\\n\\nrequirements under state law. They brought this suit to compel DOD’s full reporting of\\n\\n 8\\n\\fdisqualifying information to the Attorney General, as required by the NIAA. Since\\n\\nneither the Brady Act nor the NIAA contemplated a separate cause of action to compel\\n\\nperformance with inter-agency reporting obligations, the municipal appellants brought\\n\\ntheir claim under the general provision of the Administrative Procedure Act that allows\\n\\nan aggrieved party to “compel agency action unlawfully withheld or unreasonably\\n\\ndelayed.” 5 U.S.C. § 706(1) (2012).\\n\\n The district court granted the federal defendants’ motion to dismiss this claim,\\n\\nfinding that it lacked jurisdiction to hear the case. The court identified two independent\\n\\njurisdictional defects. First, the district court found that the municipal appellants had\\n\\nfailed “to allege[] a cognizable informational injury sufficient to confer standing.” J.A.\\n\\n341. Second, the court held that the cities did not establish “jurisdiction under the APA\\n\\nsince they have not alleged a discrete agency action.” Id. As a consequence of the\\n\\ndismissal, the court also denied the municipal appellants’ motion for a preliminary\\n\\ninjunction. Id. at 348.\\n\\n This appeal followed. While federal courts must assure themselves that they have\\n\\njurisdiction before proceeding to the merits, see Steel Co. v. Citizens for a Better Env’t,\\n\\n523 U.S. 83, 94-95 (1998), both of the infirmities identified by the district court go to the\\n\\nquestion of jurisdiction. As such, this court can turn to either issue alone to resolve this\\n\\ncase. See Ruhrgas AG v. Marathon Oil Co., 526 U.S. 574, 578 (1999) (“[T]here is no\\n\\nunyielding jurisdictional hierarchy.”). Our review is de novo.\\n\\n\\n\\n\\n 9\\n\\f II.\\n\\n Because this court is not in “the habit of decid[ing] questions of a constitutional\\n\\nnature unless absolutely necessary,” we turn first to the statutory question of whether the\\n\\nmunicipal appellants have established subject matter jurisdiction under the\\n\\nAdministrative Procedure Act (APA). See Flue-Cured Tobacco Coop. Stabilization Corp.\\n\\nv. EPA, 313 F.3d 852, 857 (4th Cir. 2002) (quoting Ashwander v. Tenn. Valley Auth., 297\\n\\nU.S. 288, 347 (1936) (Brandeis, J. concurring)). At the outset, it is important to\\n\\nunderstand the nature of appellants’ claim. Their challenge is not about access to the\\n\\nNICS; it is instead about the quality of the information in that system. By their own\\n\\nsubmission, each of the appellants accesses the NICS frequently to carry out their\\n\\nobligations under state law. This is thus not a case where appellants have asked for access\\n\\nprovided for in the regulations and have been denied. Instead, the municipalities see their\\n\\nexisting access to the NICS as an invitation to compel any federal inter-agency legal\\n\\nrequirement that may affect the quality of the information they receive. On their view, the\\n\\nAPA authorizes a recipient of government information to initiate a private action to\\n\\ncompel governmental conduct that might improve that information’s accuracy or\\n\\ncomprehensiveness. As we explain below, there is simply no basis in the APA’s text for\\n\\nsuch a broad incursion into internal agency management.\\n\\n A.\\n\\n The APA waives the federal government’s sovereign immunity for a limited set of\\n\\nsuits, brought by “a person suffering legal wrong because of agency action” to obtain\\n\\nrelief “other than money damages.” 5 U.S.C. § 702. It is well-established that\\n\\n 10\\n\\f“[s]overeign immunity is jurisdictional in nature” and “absent a waiver . . . shields the\\n\\nFederal Government and its agencies from suit.” FDIC v. Meyer, 510 U.S. 471, 475\\n\\n(1994). Judicial review under the APA, moreover, is limited to “final agency actions.”\\n\\n5 U.S.C. § 704.\\n\\n As these provisions of the APA make plain, subject matter jurisdiction is lacking if\\n\\nthe plaintiff fails to challenge a particular “agency action” that is fit for review. See\\n\\nInvention Submission Corp. v. Rogan, 357 F.3d 452, 460 (4th Cir. 2004). “The term\\n\\n‘action’ as used in the APA is a term of art that does not include all conduct” on the part\\n\\nof the government. Vill. of Bald Head Island v. U.S. Army Corps of Eng’rs, 714 F.3d 186,\\n\\n193 (4th Cir. 2013). See also Hearst Radio v. FCC, 167 F.2d 225, 227 (D.C. Cir. 1948)\\n\\n(“The difficulty with the appellant company’s position is that the Administrative\\n\\nProcedure Act does not provide review for everything done by an agency.”). Instead, the\\n\\nAPA defines “agency action” to include “the whole or a part of an agency rule, order,\\n\\nlicense, sanction, relief, or the equivalent or denial thereof, or failure to act.” 5 U.S.C.\\n\\n§ 551(13).\\n\\n This definition limits the scope of judicial review in two important respects. First,\\n\\neach of the terms that comprise the definition of “agency action” is limited to those acts\\n\\nthat are “circumscribed” and “discrete.” Norton v. Southern Utah Wilderness Alliance\\n\\n(SUWA), 542 U.S. 55, 62 (2004). When challenging agency action―whether it be a\\n\\nparticular action or a failure to act altogether―the plaintiff must therefore identify\\n\\nspecific and discrete governmental conduct, rather than launch a “broad programmatic\\n\\nattack” on the government’s operations. Id. at 64. This distinction between discrete acts,\\n\\n 11\\n\\fwhich are reviewable, and programmatic challenges, which are not, is vital to the APA’s\\n\\nconception of the separation of powers. Courts are well-suited to reviewing specific\\n\\nagency decisions, such as rulemakings, orders, or denials. We are woefully ill-suited,\\n\\nhowever, to adjudicate generalized grievances asking us to improve an agency’s\\n\\nperformance or operations. In such a case, courts would be forced either to enter a\\n\\ndisfavored “obey the law” injunction, see Int’l Longshoremen’s Ass’n, Local 1291 v.\\n\\nPhil. Mar. Trade Ass’n, 389 U.S. 64, 76 (1967), or to engage in day-to-day oversight of\\n\\nthe executive’s administrative practices. Both alternatives are foreclosed by the APA, and\\n\\nrightly so. The Supreme Court’s guidance on this point is worth considering in full:\\n\\n If courts were empowered to enter general orders compelling compliance\\n with broad statutory mandates, they would necessarily be empowered, as\\n well, to determine whether compliance was achieved-which would mean\\n that it would ultimately become the task of the supervising court, rather\\n than the agency, to work out compliance with the broad statutory mandate,\\n injecting the judge into day-to-day agency management.\\n\\nSUWA, 542 U.S. at 66-67. The requirement that the challenger identify a discrete act\\n\\nkeeps us from entering such a quagmire.\\n\\n Second, the definition of “agency action” is limited to those governmental acts\\n\\nthat “determin[e] rights and obligations.” Clear Sky Car Wash LLC v. City of\\n\\nChesapeake, Va., 743 F.3d 438, 445 (4th Cir. 2014). This limitation ensures that judicial\\n\\nreview does not reach into the internal workings of the government, and is instead\\n\\nproperly directed at the effect that agency conduct has on private parties. To meet this\\n\\nrequirement, a party must demonstrate that the challenged act had “an immediate and\\n\\npractical impact,” see Golden & Zimmerman LLC v. Domenech, 599 F.3d 426, 433 (4th\\n\\n\\n 12\\n\\fCir. 2010), or “alter[ed] the legal regime” in which it operates. See Bennett v. Spear, 520\\n\\nU.S. 154, 178 (1997). It is not enough for plaintiffs to simply identify a governmental\\n\\naction that ultimately affected them through the “independent responses and choices of\\n\\nthird parties,” or mere “coercive pressures.” Flue-Cured Tobacco, 313 F.3d at 859, 861.\\n\\nThis requirement applies fully to claims that an agency has failed to act, which is\\n\\n“properly understood as a failure to take an agency action.” See Norton, 542 U.S. at 62.\\n\\nSince “agency actions” must determine rights and obligations, claims to compel an\\n\\nagency to take an action must seek such a determination as well.\\n\\n These two requirements, which flow directly from the APA’s text, apply to all\\n\\nchallenges to agency action and accordingly limit judicial review generally. When a\\n\\nplaintiff brings a claim to compel agency action, like the municipal appellants have here,\\n\\na further limit applies. Under the APA, actions that can be compelled are only those that\\n\\nhave been “unlawfully withheld or unreasonably delayed.” 5 U.S.C. § 706(1). As the\\n\\nSupreme Court has explained, the text of § 706(1) requires that the plaintiff identify\\n\\naction that is “legally required.” SUWA, 542 U.S. at 63. Just like the traditional\\n\\nmandamus remedy from which this provision is derived, claims to compel agency action\\n\\nare “limited to enforcement of ‘a specific, unequivocal command,’” over which an\\n\\nofficial has no discretion. Id. (quoting ICC v. New York, N.H. & H.R. Co., 287 U.S. 178,\\n\\n204 (1932)).\\n\\n Taken together, the limitations imposed on claims to compel agency action under\\n\\nthe APA strike a balance between meaningful judicial review and the needs of effective\\n\\nadministration. Review is available only when acts are discrete in character, required by\\n\\n 13\\n\\flaw, and bear on a party’s rights and obligations. The result is a scheme allowing courts\\n\\nto review only those acts that are specific enough to avoid entangling the judiciary in\\n\\nprogrammatic oversight, clear enough to avoid substituting judicial judgments for those\\n\\nof the executive branch, and substantial enough to prevent an incursion into internal\\n\\nagency management. See SUWA, 542 U.S. at 64-65.\\n\\n These principles guide our consideration of all claims to compel agency action,\\n\\nregardless of the context. Claims involving government information are no exception.\\n\\nOur court, just like our sister circuits, has had many occasions to consider how the\\n\\nrequirements of agency action apply to claims that the government has wrongfully\\n\\nhandled the information in its possession. In some cases, the claim is that the\\n\\ngovernment’s decision to disseminate information, such as an unfavorable report, was\\n\\nunlawful. See Invention Submission Corp., 357 F.3d at 460; see also Flue-Cured\\n\\nTobacco, 313 F.3d at 859; Indus. Safety Equip. Ass’n, Inc. v. EPA, 837 F.2d 1115, 1118\\n\\n(D.C. Cir. 1988). At other times, the claim was that the government improperly withheld\\n\\nor mishandled personal information. See, e.g., Fanin v. U.S. Dep’t of Veterans Affairs,\\n\\n572 F.3d 868, 871 (11th Cir. 2009). Informational harms may involve novel facts, but\\n\\nthey do not disrupt the legal principles set forth in the APA. See Golden & Zimmerman,\\n\\nLLC, 599 F.3d at 431-32 (finding that an agency’s “reference guide” was not agency\\n\\naction because it did not “impose new legal requirements”). As these cases aptly\\n\\ndemonstrate, a plaintiff’s burden remains constant and subject to the above requirements\\n\\nthroughout.\\n\\n\\n\\n 14\\n\\f B.\\n\\n Applying these well-established principles to the facts here, it is clear that the\\n\\nmunicipal appellants have failed to establish subject matter jurisdiction under the APA.\\n\\nOnce again, the claim at issue arises from the appellants’ permissive use of the NICS,\\n\\nafforded to them by regulation, for purposes explicitly “unrelated to the NICS\\n\\nbackground checks required by the Brady Act.” 28 C.F.R. § 25.6(j). The regulation\\n\\naffords the municipalities only “access to the NICS Index.” Id. On the view of the\\n\\nmunicipal appellants, this access, which is not expressly contemplated either by the\\n\\nBrady Act or subsequent legislation, allows a NICS user to reach into the federal\\n\\ngovernment and compel any legal obligations associated with developing the information\\n\\nin the system. Such a broad theory of agency action is untethered from the APA’s text\\n\\nand contravenes important limits that Congress has placed on judicial review.\\n\\n First, the municipal appellants’ claim does not challenge a discrete agency action.\\n\\nInstead appellants ask that we “supervise an agency’s compliance with [the] broad\\n\\nstatutory mandate” of the NIAA. Murray Energy Corp. v. EPA, 861 F.3d 529, 537 n.4\\n\\n(4th Cir. 2017). By appellants’ own account, the DOD’s failure to provide disqualifying\\n\\nconviction records for former service members is widespread and systemic. The\\n\\ndepartment has admitted as much and is engaged in extensive efforts to increase its\\n\\ncompliance. As all parties seem to agree, the road ahead is an arduous one, as DOD\\n\\nattempts to improve on its partial and inconsistent reporting. This is the sort of public\\n\\npolicy problem that often requires reallocating resources, developing new administrative\\n\\n 15\\n\\fsystems, and working closely with partners across government. Solving it will likely\\n\\nrequire expertise in information technology and deep knowledge of how military needs\\n\\nintersect with data collection. In other words, it is exactly the sort of “broad\\n\\nprogrammatic” undertaking for which the APA has foreclosed judicial review. See\\n\\nSUWA, 542 U.S. at 64.\\n\\n Congress seems to be of the same view. Since the passage of the Brady Act,\\n\\nCongress has on multiple occasions turned its attention to the severe challenge of\\n\\nrampant gun violence. Twice, the legislative responses have been directed squarely at\\n\\nagency compliance with NICS reporting obligations. Congress has included\\n\\naccountability measures, designed to identify delinquent agencies and push them into\\n\\nimproving their performance. The most recent effort in this regard singles out executive\\n\\ncompensation at these agencies, limiting bonus pay for those who do not improve their\\n\\noutcomes. See 34 U.S.C. § 40901(e)(1)(I) (providing that certain “political\\n\\nappointee[s] . . . shall not be eligible for the receipt of bonus pay” until their department\\n\\nimproves its compliance). These measures signal that Congress sees this problem as one\\n\\nripe for legislative oversight and in need of attention by experts in the executive branch.\\n\\nAt no point, however, has Congress invited the federal courts into the process. Perhaps\\n\\ncognizant of the judiciary’s inability to oversee and manage a complex scheme of inter-\\n\\nagency collaboration, we have appropriately been left on the sideline.\\n\\n The municipal appellants try to nonetheless force us onto the field by\\n\\ncharacterizing their broad claim as simply an aggregation of many small claims, each one\\n\\nseeking to compel the individual reports required by the NIAA. On this view, what the\\n\\n 16\\n\\fcities seek is not programmatic because each specific act that DOD has failed to perform\\n\\nis discrete when considered on its own. But any limit on programmatic assessment would\\n\\nbe rendered meaningless if such an argument prevailed. All governmental programs are\\n\\nthe aggregation of individual decisions, many of which are required by law. The APA\\n\\nensures that it is the individual decisions that are assessed as agency action, rather than\\n\\nthe whole administrative apparatus.\\n\\n The municipal appellants are surely correct that ongoing failures to carry out\\n\\ndiscrete obligations can be subject to review. Government deficiencies do not become\\n\\nnon-reviewable simply because they are pervasive. This, however, does nothing to\\n\\nobviate the fact that a discrete action is wholly lacking here. By the appellants’ own\\n\\nestimate, full compliance with the NIAA may require DOD to obtain and transmit tens of\\n\\nthousands of records. There is simply no way to achieve such a result without wholesale\\n\\nimprovements in the DOD’s reporting requirements, which take time and require the\\n\\nexpertise of senior civilian and military leaders.\\n\\n If there were any doubt about the nature of the cities’ claim, the requested remedy\\n\\ntells the real story. Their complaint “seeks immediate injunctive relief to compel\\n\\nDefendants to repair this broken system and to cure once and for all the potentially\\n\\ndeadly gaps in the NCIC database.” J.A. 17. In their prayer for relief, the appellants ask\\n\\nthat the DOD, on “a schedule to be set by the Court,” “identify all records” in its\\n\\npossession, provide the information contained in those records to the Attorney General,\\n\\n“conduct a thorough review of [its] records and procedures,” “submit to the Court for\\n\\napproval a compliance plan,” and provide “a monthly report to the Court detailing [its]\\n\\n 17\\n\\fprogress.” Id. at 35-36. The requested relief would continue “until such time as the Court\\n\\nis satisfied that Defendants have brought themselves into full compliance with 34 U.S.C.\\n\\n§ 40901.” Id. at 36 (emphasis added). The APA’s discreteness requirement exists to avoid\\n\\nplacing the courts in this exact position. As we previously explained, “[t]he obvious\\n\\ninability for a court to function in such a day-to-day managerial role over agency\\n\\noperations is precisely the reason why the APA limits judicial review to discrete agency\\n\\nactions.” Vill. of Bald Head Island, 714 F.3d at 194.\\n\\n Moreover, the municipal appellants have failed to demonstrate that the DOD’s\\n\\nreporting requirements in any way determine their rights and obligations. Accordingly,\\n\\nthey have not identified an act that can be compelled by this court under § 706(1). See\\n\\nSUWA, 542 U.S. at 62 (finding that a failure to act under § 706(1) means “failure to take\\n\\nan agency action”). The action challenged in this case is DOD’s obligation to provide\\n\\ninformation only to another agency of the federal government: The Department of\\n\\nJustice. See 34 U.S.C. § 40901(e)(1)(C). The regulation permitting local law enforcement\\n\\nagencies to use the NICS refers only to access to the system, not to the particular\\n\\ninformation provided to the FBI by other federal agencies. The transfer of information\\n\\nbetween agencies does not, without more, alter the rights and obligations of any party.\\n\\nThat is especially true, as here, where outside access to the information is entirely\\n\\npermissive and implicates none of the complaining party’s obligations under federal law.\\n\\n We need not say here that information sharing can never constitute agency action.\\n\\nWe simply note that claims to compel an agency to provide information are held to the\\n\\nsame standard as any other. In arguing otherwise, the municipal appellants point to a\\n\\n 18\\n\\fstring of cases, all from outside this circuit, holding that the government’s alleged misuse\\n\\nof information was reviewable “agency action.” Our holding here, however, raises no\\n\\nconflict with these decisions. The cases relied on by the appellants involve claims wholly\\n\\nunlike the one that they have brought. For example, one case involves the government’s\\n\\nlegal obligations with respect to the plaintiffs’ personal medical information, see Vietnam\\n\\nVeterans of Am. v. CIA, 811 F.3d 1068, 1078 (9th Cir. 2015) (finding that “the Army\\n\\n[has] a duty to provide notice to prior test subjects of information regarding their well-\\n\\nbeing”), while another examines the rights of federal employees under the civil service\\n\\nsystem, see Hondros v. U.S. Civil Service Comm., 720 F.2d 278, 280 (3d Cir. 1983). Each\\n\\nof these cases involved plaintiffs seeking information that was particular to them and\\n\\ntheir own rights under federal law. As such, they tell us little about how to handle a case,\\n\\nlike this one, where the plaintiff seeks wholesale compliance with an entire\\n\\nadministrative scheme, based solely on the fact that the government has granted them\\n\\naccess to an information system.\\n\\n\\n\\n C.\\n\\n What the municipal appellants are ultimately asking for is a judicial decree making\\n\\nthe assistance of the federal government more useful to them than it is now. While their\\n\\nmotives for wanting to see improvement to the NICS are laudable, they point to no case\\n\\nsuggesting that the APA countenances such an action. And for good reason. If a party\\n\\ncould seek review any time the federal government’s alleged non-compliance made a\\n\\ngovernment program less useful than it might otherwise be, the possibilities for litigation\\n\\n 19\\n\\fwould be endless. Followed to its logical conclusion, a recipient of the mail could sue the\\n\\nPostal Service for improper employment practices, alleging that it caused inefficient\\n\\npackage deliveries. A disgruntled grant applicant could sue the National Institutes of\\n\\nHealth for violations of financial management laws, arguing that with more money in its\\n\\ncoffers more grants could be issued. The APA, however, is a creature of Congress; the\\n\\nlegislative branch has not put it to this sort of use, and we can discern no workable limits\\n\\nin the appellants’ theory.\\n\\n The implications of the appellants’ position are particularly troubling in the\\n\\ncontext of voluntary information sharing. The federal government has access to a vast\\n\\namount of data that is of great use both to intergovernmental partners and to those in the\\n\\nprivate sector. Information stored with the federal government is critical to many areas of\\n\\npublic policy, including, for example, homeland security and healthcare. See, e.g., Nat’l\\n\\nInfrastructure Advisory Council, Intelligence Information Sharing: Final Report and\\n\\nRecommendations ES-1 (Jan. 10, 2012) (“Information sharing is perhaps the most\\n\\nimportant factor in the protection and resilience of critical infrastructure.”). The federal\\n\\ngovernment has recently taken steps to make more of its own information accessible to\\n\\nthe general public, aware of the innovative potential that such information can unleash.\\n\\nSee Exec. Order No. 13,642, 78 Fed. Reg. 28,111 (May 9, 2013); see generally Data.gov\\n\\n(“The home of the U.S. Government’s open data.”). If we adopted the all-encompassing\\n\\ndefinition of “agency action” asserted by the municipal appellants here, each of these\\n\\nefforts to enhance public access would be checked by a fear that greater openness would\\n\\ninvite judicial scrutiny of any act that went into developing or disseminating the data.\\n\\n 20\\n\\fWith an agency’s eye peeled towards these consequences, it is easy to imagine the federal\\n\\ngovernment pulling back from these salutary efforts, and instead choosing to silo its\\n\\ninformation.\\n\\n The adverse consequences of appellants’ theory would not just fall on the\\n\\ngovernment’s attempt to share information with the public; they would also compromise\\n\\nthe dissemination of information within the government itself. A rule that made inter-\\n\\nagency information sharing justiciable by federal courts would undermine the whole\\n\\ngamut of federal activities that require collaboration between agencies, of which military\\n\\npreparedness and anti-terrorism efforts are only a part. Agencies dealing with public\\n\\nhealth, environment conservation, and disaster response draw on entire bodies of\\n\\nscientific work, and not all of the needed expertise will be located within a single agency\\n\\nor department. To have internal information sharing haunted by the specter of judicial\\n\\noversight would weaken government operations in innumerable areas, both foreign and\\n\\ndomestic, and allow the prospect of litigation to erect barriers when other nations, both\\n\\nour allies and our competitors, proceed unburdened by similar obstacles.\\n\\n\\n\\n III.\\n\\n The municipal appellants, like localities all over the country, are tasked with\\n\\nkeeping the public safe from horrific acts of violence, which far too often are committed\\n\\nby those with firearms they had no lawful right to possess. The municipalities’ efforts to\\n\\ncombat these threats are commendable. The APA, however, does not permit their efforts\\n\\nto include judicial supervision of the myriad programmatic workings of the federal\\n\\n 21\\n\\fgovernment. No matter the asserted virtues of the intended intervention, we are simply\\n\\nnot equipped to perform such tasks and have no legal basis for doing so.\\n\\n For the foregoing reasons, the judgment of the district court is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 22\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":97,"cells":{"id":{"kind":"number","value":4583961,"string":"4,583,961"},"name":{"kind":"string","value":"SAVE OUR SOUND OBX, INC.; Mark Haines ; Jer Mehta; Glenn Stevens ; David Hadley ; Thomas Aschmoneit; Richard Ayella, Plaintiffs - Appellants, v. NORTH CAROLINA DEPARTMENT OF TRANSPORTATION; Federal Highway Administration; John F. Sullivan, III, in His Official Capacity as Division Administrator for the Federal Highway Administration; James H. Trogdon, III, in His Official Capacity as Secretary of the North Carolina Department of Transportation, Defendants - Appellees, and Defenders of Wildlife; National Wildlife Refuge Association, Intervenors/Defendants - Appellees."},"name_abbreviation":{"kind":"string","value":"Save Our Sound OBX, Inc. v. NC Dept of Transportation"},"decision_date":{"kind":"string","value":"2019-01-23"},"docket_number":{"kind":"string","value":"18-1649"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Niemeyer, Duncan, Quattlebaum\", \"parties\": \"\", \"opinions\": [{\"author\": \"DUNCAN, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1649\\n\\n\\nSAVE OUR SOUND OBX, INC.; MARK HAINES; JER MEHTA; GLENN\\nSTEVENS; DAVID HADLEY; THOMAS ASCHMONEIT; RICHARD\\nAYELLA,\\n\\n Plaintiffs – Appellants,\\n\\nv.\\n\\nNORTH CAROLINA DEPARTMENT OF TRANSPORTATION; FEDERAL\\nHIGHWAY ADMINISTRATION; JOHN F. SULLIVAN, III, in his official\\ncapacity as Division Administrator for the Federal Highway Administration;\\nJAMES H. TROGDON, III, in his official capacity as Secretary of the North\\nCarolina Department of Transportation,\\n\\n Defendants – Appellees,\\n\\nand\\n\\nDEFENDERS OF WILDLIFE; NATIONAL WILDLIFE REFUGE\\nASSOCIATION,\\n\\n Intervenors/Defendants – Appellees.\\n\\n\\nAppeal from the United States District Court for the Eastern District of North Carolina, at\\nElizabeth City. Louise W. Flanagan, District Judge. (2:17-cv-00004-FL)\\n\\n\\nArgued: December 11, 2018 Decided: January 23, 2019\\n\\n\\nBefore NIEMEYER, DUNCAN, and QUATTLEBAUM, Circuit Judges.\\n\\fAffirmed by published opinion. Judge Duncan wrote the opinion, in which Judge\\nNiemeyer and Judge Quattlebaum joined.\\n\\n\\nARGUED: David Ari Schnitzer, GIBSON, DUNN & CRUTCHER LLP, Washington,\\nD.C., for Appellants. Thekla Hansen-Young, UNITED STATES DEPARTMENT OF\\nJUSTICE, Washington, D.C.; Colin Justice, NORTH CAROLINA DEPARTMENT OF\\nJUSTICE, Raleigh, North Carolina, for Appellees. ON BRIEF: Michael K. Murphy,\\nKyle N. Guest, GIBSON, DUNN & CRUTCHER LLP, Washington, D.C., for\\nAppellants. Jeffrey H. Wood, Acting Assistant Attorney General, Eric Grant, Deputy\\nAssistant Attorney General, Andrew C. Mergen, Robert J. Lundman, Carter F. Thurman,\\nAppellate Section, Environment and Natural Resources Division, UNITED STATES\\nDEPARTMENT OF JUSTICE, Washington, D.C.; Josh Stein, Attorney General,\\nOFFICE OF THE ATTORNEY GENERAL OF NORTH CAROLINA, Raleigh, North\\nCarolina; Scott T. Slusser, Special Deputy Attorney General, Mollie Cozart, Assistant\\nAttorney General, NORTH CAROLINA DEPARTMENT OF JUSTICE, Raleigh, North\\nCarolina, for Appellees North Carolina Department of Transportation, Federal Highway\\nAdministration, John F. Sullivan, III, and James H. Trogdon, III. Kimberley Hunter,\\nNicholas S. Torrey, SOUTHERN ENVIRONMENTAL LAW CENTER, Chapel Hill,\\nNorth Carolina, for Appellees Defenders of Wildlife and National Wildlife Refuge\\nAssociation.\\n\\n\\n\\n\\n 2\\n\\fDUNCAN, Circuit Judge:\\n\\n Appellants Save Our Sound OBX, Inc. and its members, residents and vacationers\\n\\nfrom North Carolina’s Outer Banks, (collectively “SOS”) challenge the decision of the\\n\\nNorth Carolina Department of Transportation (the “NCDOT”), the Federal Highway\\n\\nAdministration (the “FHWA”), and their administrators (collectively “the Agencies”) to\\n\\nreplace a segment of North Carolina Highway 12 (“NC-12”) with a bridge across the\\n\\nPamlico Sound (the “Jug-Handle Bridge”). The district court granted the Agencies’\\n\\nmotion for summary judgment, finding that they did not violate the National\\n\\nEnvironmental Policy Act (the “NEPA”), 42 U.S.C. § 4321 et seq., or the Department of\\n\\nTransportation Act (the “DTA”), 49 U.S.C. § 301 et seq., when they approved the bridge.\\n\\nSOS challenges that ruling on appeal. For the reasons that follow, we affirm.\\n\\n\\n\\n I.\\n\\n This case involves a segment of NC-12, which is the main roadway passing\\n\\nthrough the Outer Banks of North Carolina. State and federal agencies have been\\n\\nworking for several years to update and improve NC-12 because of its susceptibility to\\n\\nweather damage and erosion.\\n\\n Like many highway construction projects, the NC-12 project required cooperation\\n\\namong state and federal agencies. For instance, in North Carolina, NCDOT has authority\\n\\nover highway construction, while FWHA supplies federal funds for highway projects.\\n\\nThe agencies tasked with improving NC-12, including NCDOT and FHWA, formed a\\n\\nMerger Team to coordinate decisionmaking and regulatory compliance for the NC-12\\n\\n 3\\n\\fproject. 1 The Merger Team was responsible for ensuring that the NC-12 project\\n\\ncomplied with the requirements of NEPA and the DTA, among other regulations.\\n\\n SOS challenges certain agency decisions in the NC-12 project under NEPA and\\n\\nthe DTA. Accordingly, we first provide a brief overview of the requirements of those\\n\\nstatutes before turning to the specific facts and procedural history of this appeal.\\n\\n\\n\\n A.\\n\\n The first statute at issue in this appeal is NEPA. Pursuant to NEPA, 42 U.S.C.\\n\\n§ 4321 et seq., and its implementing regulations, government agencies considering\\n\\ncertain projects must evaluate whether the project would have a significant impact on the\\n\\nenvironment by preparing an Environmental Assessment (an “EA”). Id. § 4332(C); 40\\n\\nC.F.R. § 1508.9; see id. § 1508.18 (defining the types of federal actions to which NEPA\\n\\napplies). If the project would have a significant impact, the agency must prepare an\\n\\nEnvironmental Impact Statement (an “EIS”). 42 U.S.C. § 4332(C). The agency is\\n\\nresponsible for ensuring that the EIS complies with various regulatory requirements. See\\n\\n40 C.F.R. § 1502.1 et seq. For instance, the EIS must “provide full and fair discussion”\\n\\nof any significant environmental impacts of a proposed action. 40 C.F.R. § 1502.1.\\n\\n 1\\n The Merger Team was comprised of representatives from NCDOT, FHWA, the\\nU.S. Fish and Wildlife Service, the U.S. Army Corps of Engineers, the U.S.\\nEnvironmental Protection Agency, the National Marine Fisheries Service, the National\\nPark Service, the North Carolina Department of Cultural Resources, the North Carolina\\nWildlife Resources Commission, and three divisions of the North Carolina Department of\\nEnvironmental and Natural Resources (the “NCDENR”) (now named the North Carolina\\nDepartment of Environmental Quality)--the Division of Water Resources, the Division of\\nCoastal Management, and the Division of Marine Fisheries.\\n\\n 4\\n\\fAdditionally, the agency must “[r]igorously explore and objectively evaluate all\\n\\nreasonable alternatives” that could “avoid or minimize adverse impacts.” Id.\\n\\n§§ 1502.1, 1502.14. The agency is permitted, however, to identify a preference among\\n\\nalternatives based on non-environmental considerations, such as economic factors or the\\n\\nagency’s statutory mission. Id. § 1505.2(b). If the agency has a preferred alternative,\\n\\nNEPA requires the agency to identify that preference in the EIS. Id. § 1502.14. NEPA\\n\\nalso requires the agency to prepare a supplemental EIS (an “SEIS”) if significant new\\n\\ninformation or environmental changes come to light after the agency prepares an EIS. Id.\\n\\n§ 1502.9(c). After the agency makes its final decision about which alternative to pursue,\\n\\nit publishes a record of decision (an “ROD”) explaining its choice. Id. § 1505.2.\\n\\n We now turn to the second statute at issue: the DTA. The DTA contains\\n\\nsubstantive requirements for government transportation projects. 49 U.S.C. § 301 et seq.\\n\\nRelevant here, the so-called “§ 4(f)” requirements 2 concern transportation projects that\\n\\nrequire the use of publicly owned land of a wildlife refuge or a significant historic site.\\n\\nId. § 303(c). Historic sites include structures “included in, or eligible for inclusion in,”\\n\\nthe National Register of Historic Places. 23 C.F.R. § 774.17. The Secretary of\\n\\nTransportation may only approve such projects if there is no “feasible and prudent”\\n\\nalternative to using that land and the “project includes all possible planning to minimize\\n\\nharm . . . resulting from the use.” Id. § 303(c). If there is no feasible and prudent\\n\\n\\n 2\\n The DTA explains that “[t]he requirements of [49 U.S.C. § 303] are commonly\\nreferred to as section 4(f) requirements” in reference to a previous version of the statute.\\n49 U.S.C. § 303(f)(1).\\n\\n 5\\n\\falternative, the Secretary may only approve the alternative that “[c]auses the least overall\\n\\nharm in light of the [DTA’s] preservation purpose.” 23 C.F.R. § 774.3(c). Relevant\\n\\nconsiderations in selecting the least harmful alternative include whether harm to the land\\n\\ncan be mitigated, whether harm to the land affects the attributes qualifying that land for\\n\\nprotection, and whether the alternative meets the needs of the project. Id.\\n\\n\\n\\n B.\\n\\n Having established the relevant framework, we consider the facts of this case.\\n\\nSOS’s claims in this litigation concern the Agencies’ environmental analysis under\\n\\nNEPA and the DTA with respect to a segment of NC-12 that passes from the southern\\n\\nedge of Bodie Island to the village of Rodanthe. For this segment, the Merger Team was\\n\\nresponsible for preparing EAs and EISs pursuant to NEPA and for determining which\\n\\nproposed plan for the project was the least environmentally-damaging practicable\\n\\nalternative (the “LEDPA”) pursuant to section 404 of the Clean Water Act, 33 U.S.C.\\n\\n§ 1344, among other requirements. 3 See 40 C.F.R. § 230.10 (setting out the LEDPA\\n\\nrequirement).\\n\\n In 2008, the Merger Team issued an EIS and § 4(f) evaluation (the “2008 EIS”)\\n\\nfor improving NC-12. For the segment at issue here, the 2008 EIS included discussion of\\n\\nseveral alternatives, including a proposed bridge in the Pamlico Sound near Rodanthe\\n\\n\\n\\n 3\\n Section 404 of the Clean Water Act regulates activities involving “the discharge\\nof dredged or fill material” into navigable waters. Id.\\n\\n 6\\n\\f(the “Bridge South alternative”) and proposals involving beach nourishment. An EA in\\n\\n2010 (the “2010 EA”) further developed these alternatives.\\n\\n The Merger Team released an updated EA in 2013 (the “2013 EA”) to account for\\n\\nenvironmental changes after the 2010 EA, including the effects of Hurricane Irene in\\n\\n2011. The 2013 EA identified four alternatives for the segment at issue: (1) the so-called\\n\\nJug-Handle Bridge, a bridge extending out into the Pamlico Sound (also referred to in the\\n\\nenvironmental analyses as the “Bridge on New Location”); 4 (2) an easement bridge on\\n\\nthe existing NC-12 location; (3) beach nourishment; and (4) an easement bridge\\n\\ncombined with beach nourishment. The Merger Team did not study the beach\\n\\nnourishment alternatives in depth in the 2013 EA because, at a 2011 meeting, it had\\n\\nalready determined not to pursue them after experts reported on a “high erosion rate and a\\n\\nlack of sand supply.” J.A. 843. In the 2013 EA, the Merger Team identified the\\n\\neasement bridge as its preferred alternative under NEPA. However, certain members of\\n\\nthe Merger Team objected to finding that the easement bridge was the LEDPA under the\\n\\nClean Water Act, citing concerns about its location within the surf zone, additional\\n\\npermits associated with erosion setback requirements, and its impact on a nearby wildlife\\n\\nrefuge. See J.A. 1745–47.\\n\\n In the meantime, environmental groups Defenders of Wildlife and the National\\n\\nWildlife Refuge Association (intervenors here, collectively the “Environmental Groups”)\\n\\nbrought suit in federal court to challenge the Agencies’ NEPA and § 4(f) determinations\\n\\n 4\\n The Jug-Handle Bridge was a modified version of the Bridge South alternative\\nthat was introduced in the 2008 EIS and further developed in the 2010 EA.\\n\\n 7\\n\\fwith respect to a different segment of NC-12 in the Outer Banks--the Bonner Bridge,\\n\\nwhich connects Bodie Island and Hatteras Island to the north of Rodanthe. See Defs. of\\n\\nWildlife v. N.C. Dep’t of Transp., 762 F.3d 374 (4th Cir. 2014). The Environmental\\n\\nGroups and the Agencies eventually reached an agreement in 2015 (the “Settlement”). 5\\n\\nThe Settlement required NCDOT to identify the Jug-Handle Bridge as its preferred\\n\\nalternative for the segment of NC-12 at issue in this case. It also required NCDOT to\\n\\nseek Merger Team concurrence that the Jug-Handle Bridge was the LEDPA. In doing so,\\n\\nit stated that nothing in the Settlement “requires or should be interpreted to predetermine\\n\\nthe choice” of the Jug-Handle Bridge as the final selected alternative. J.A. 1090. In\\n\\nexchange, the Environmental Groups dismissed the Bonner Bridge suit and agreed not to\\n\\nchallenge the Agencies in court if the Jug-Handle Bridge was determined to be the\\n\\nLEDPA and was ultimately selected in the ROD for this project.\\n\\n After a 2015 meeting, the Agencies identified the Jug-Handle Bridge as their\\n\\npreferred alternative. Following public comment and detailed studies, the Merger Team\\n\\ndetermined that the Jug-Handle Bridge was the LEDPA. In 2016, the Merger Team\\n\\nreleased a revised EA (the “2016 EA”) to evaluate the environmental impacts of the Jug-\\n\\nHandle Bridge and its associated construction activities. Later that year, the Merger\\n\\nTeam issued an ROD (the “2016 ROD”) formally approving the Jug-Handle Bridge.\\n\\n In addition to authorizing construction of the Jug-Handle Bridge, the 2016 ROD\\n\\nalso addressed concerns relating to a shipwreck in the proposed bridge’s path known as\\n\\n 5\\n NCDENR was also a party to the Settlement and is represented on the Merger\\nTeam, though it is not a defendant here.\\n\\n 8\\n\\fthe Pappy’s Lane Wreck. The shipwreck is eligible for listing on the National Register of\\n\\nHistoric Places. Because of the shipwreck’s historical significance, the 2016 ROD\\n\\nordered a data recovery project on the shipwreck, which later uncovered evidence that the\\n\\nshipwreck was a World War II assault vessel. The Merger Team has not yet determined\\n\\nhow it will respond to this new information.\\n\\n\\n\\n C.\\n\\n We now turn to the procedural history of this litigation, which began when SOS\\n\\nsued the Agencies on February 2, 2017. A month later, the Environmental Groups\\n\\nintervened in the suit in support of the Agencies. In its complaint, SOS alleged, as\\n\\nrelevant here, that the Agencies’ approval of the Jug-Handle Bridge violated NEPA\\n\\nbecause that decision was predetermined by the Settlement. To show evidence of\\n\\npredetermination, SOS moved to supplement the administrative record before the district\\n\\ncourt to include documents related to the negotiation of the Settlement on the grounds\\n\\nthat those documents were before the Agencies when they made their decision to select\\n\\nthe Jug-Handle Bridge. The district court denied this motion.\\n\\n Later, SOS moved to amend its complaint to add claims related to construction\\n\\nimpacts in Rodanthe and to the Pappy’s Lane Wreck. Specifically, SOS contended that\\n\\nthe Agencies’ environmental analyses did not adequately consider the effects of\\n\\nconstruction or the historic significance of the Pappy’s Lane Wreck. The district court\\n\\ngranted the motion as to construction impacts but denied it as to the shipwreck.\\n\\n\\n\\n 9\\n\\f SOS, the Agencies, and the Environmental Groups each filed cross-motions for\\n\\nsummary judgment on the issue of whether the Agencies’ environmental analyses\\n\\nviolated NEPA or the DTA. The district court granted the Agencies’ and Environmental\\n\\nGroups’ motions for summary judgment and denied SOS’s motion.\\n\\n SOS appeals the district court’s grant of the Agencies’ motion for summary\\n\\njudgment and its denial of SOS’s motion to amend its complaint. SOS contends that the\\n\\nAgencies were not entitled to summary judgment because the Agencies’ environmental\\n\\nanalyses violated NEPA. It also contends that the district court erred in denying SOS’s\\n\\nmotion to amend its complaint with claims related to the Pappy’s Lane Wreck. We\\n\\ndiscuss SOS’s NEPA claims and its motion to amend its complaint, in that order.\\n\\n\\n\\n II.\\n\\n SOS contends that the Agencies violated NEPA when they selected the Jug-\\n\\nHandle Bridge for the NC-12 project. “We review a grant of summary judgment de\\n\\nnovo,” Defs. of Wildlife, 762 F.3d at 392, and, accordingly, review the Agencies’ actions\\n\\ndirectly, pursuant to the Administrative Procedure Act (the “APA”). The APA directs us\\n\\nto overturn agency actions if they are “arbitrary, capricious, an abuse of discretion, or\\n\\notherwise not in accordance with law.” 5 U.S.C. § 706(2)(A). Our precedent also guides\\n\\nthe scope of our review of the sufficiency of an agency’s NEPA analysis. Nat’l Audubon\\n\\nSoc’y v. Dep’t of Navy, 422 F.3d 174, 185, 199 (4th Cir. 2005). In conducting this\\n\\nreview, “we must make a searching and careful inquiry into the facts” and examine\\n\\nwhether the decision was based on consideration of the relevant factors. Id. at 185\\n\\n 10\\n\\f(citation and internal quotation marks omitted). However, we do not “second-guess\\n\\nagency decisions, so long as the agency has given a hard look at the environmental\\n\\nimpacts of its proposed action.” Id. at 199.\\n\\n Under this standard of review, we affirm because the Agencies did not violate\\n\\nNEPA in approving the Jug-Handle Bridge. We consider SOS’s arguments that the\\n\\nAgencies’ environmental analyses violated NEPA because (1) the Agencies failed to\\n\\nprepare an SEIS with regards to the Jug-Handle Bridge and beach nourishment\\n\\nalternatives before issuing the 2016 ROD, (2) the Agencies failed to adequately consider\\n\\nthe impacts of construction, and (3) the Settlement impermissibly predetermined the\\n\\nAgencies’ choice of the Jug-Handle Bridge.\\n\\n\\n\\n A.\\n\\n First, SOS contends that the Agencies’ NEPA analysis was deficient because the\\n\\nAgencies should have prepared an SEIS before approving the Jug-Handle Bridge in the\\n\\n2016 ROD. NEPA requires an agency to prepare an SEIS if “[t]he agency makes\\n\\nsubstantial changes” to a proposed action that implicate environmental concerns or if\\n\\n“[t]here are significant new circumstances or information” that would affect the\\n\\nenvironmental impacts of the proposed action. 40 C.F.R. § 1502.9(c). To merit an SEIS,\\n\\nthe changes “must present a seriously different picture of the environmental impact of the\\n\\nproposed project.” Hughes River Watershed Conservancy v. Glickman, 81 F.3d 437, 443\\n\\n(4th Cir. 1996) (citation and alterations omitted).\\n\\n\\n\\n 11\\n\\f We review an agency’s decision not to prepare an SEIS in two steps, consistent\\n\\nwith our standard of review under NEPA. Id. At step one, we “determine whether the\\n\\nagency took a hard look at the proffered new information.” Id. If the agency concludes\\n\\nafter a preliminary inquiry that the “environmental effect of the change is clearly\\n\\ninsignificant,” its decision not to prepare an SEIS satisfies the hard look requirement.\\n\\nHodges v. Abraham, 300 F.3d 432, 446 (4th Cir. 2002). For instance, in Hodges, we held\\n\\nthat an agency took a hard look at the environmental consequences of its change in plans\\n\\nwhen it explicitly evaluated those consequences and determined that they were not\\n\\nsignificantly different from those discussed in a prior EIS. Id. at 447. We also noted that\\n\\nthe plaintiff in that case “failed to identify any particular risk arising from” the change\\n\\nthat had not already been addressed in the agency’s environmental analyses. Id. Next, at\\n\\nstep two of the SEIS inquiry, we review whether the agency’s decision not to prepare an\\n\\nSEIS after taking a hard look was arbitrary or capricious. Hughes River, 81 F.3d at 443.\\n\\n SOS contends that an SEIS was necessary (1) to evaluate the environmental\\n\\neffects of the Jug-Handle Bridge alternative because it was different from options that\\n\\nhad previously been evaluated and (2) to reconsider alternatives that involved beach\\n\\nnourishment pursuant to new information about sand availability and beach erosion rates.\\n\\nWe address each contention in turn and affirm the district court’s determination that no\\n\\nSEIS was required. Neither of these changes are sufficiently different from the\\n\\ncircumstances initially evaluated in the EIS to merit an SEIS. The Agencies’ decision not\\n\\nto prepare one after taking a hard look at the changes was therefore not arbitrary or\\n\\ncapricious.\\n\\n 12\\n\\f i.\\n\\n Contrary to SOS’s contention, the Agencies were not required to prepare an SEIS\\n\\nwith respect to the Jug-Handle Bridge alternative. SOS argues that the final alignment of\\n\\nthe Jug-Handle Bridge alternative (that is, its path across the Pamlico Sound and its\\n\\nconnection points with the shore) was significantly different from previously evaluated\\n\\nalternatives. Specifically, SOS contends that the bridge’s alignment changed\\n\\nsignificantly because the alternative evaluated in the 2008 EIS was “amorphously\\n\\ndefined” and because the alternative evaluated in the 2010 EA (to which the 2013 EA,\\n\\n2016 EA, and 2016 ROD refer) was “not comparable” to the Jug-Handle Bridge.\\n\\nAppellant’s Br. at 35, 36. It argues that these differences render prior environmental\\n\\nanalyses of those alternatives insufficient to evaluate the environmental effects of the\\n\\nJug-Handle Bridge as approved in the 2016 ROD. We disagree and conclude that the\\n\\nAgencies complied with NEPA when they decided that an SEIS was not warranted by\\n\\nthese changes.\\n\\n At step one, the Agencies took a hard look at changes in the bridge’s alignment in\\n\\nthe 2016 EA. The 2016 EA describes the similarities and differences between the Jug-\\n\\nHandle Bridge as proposed in 2016 and the versions evaluated in the 2013 EA, the 2010\\n\\nEA, and the 2008 EIS. For instance, it explains that the Agencies decided to shift the\\n\\nalignment of the bridge to avoid areas of “dense submerged aquatic vegetation” that fell\\n\\nin the path of previous versions of the bridge. J.A. 1198. The 2016 EA also explains that\\n\\nthe Jug-Handle Bridge’s alignment reduces effects on the community as compared with\\n\\n 13\\n\\fprevious versions because it requires a narrower right-of-way. Because the Agencies\\n\\nwent into detail in their comparison between the Jug-Handle Bridge and previous\\n\\nversions of the bridge, their coverage satisfies the hard look requirement. See Hodges,\\n\\n300 F.3d at 446–47.\\n\\n And, at step two, because the Agencies took the requisite hard look and neither\\n\\ntheir environmental analyses nor SOS identify any particular differences that would merit\\n\\nan SEIS, their decision not to prepare an SEIS was not arbitrary or capricious. See\\n\\nHughes River, 81 F.3d at 443. An SEIS is only required when changes to a project\\n\\npresent a “seriously different picture of the environmental impact.” Id. (alterations and\\n\\ncitation omitted). Based on the discussion presented in the 2016 EA, which compared the\\n\\ndifferent versions of the bridge, it was not arbitrary or capricious for the Agencies to\\n\\ndetermine that the Jug-Handle Bridge’s final alignment did not present a “seriously\\n\\ndifferent picture,” id., than the 2008 EIS, the 2010 EA, or the 2013 EA. The Agencies\\n\\nexplained how the Jug-Handle Bridge was different from previous versions of the bridge,\\n\\nand their explanations do not implicate any significant environmental concerns.\\n\\nAccordingly, their decision not to prepare an SEIS was not arbitrary or capricious.\\n\\n\\n\\n ii.\\n\\n Similarly, the Agencies were not required to prepare an SEIS to reevaluate the\\n\\nfeasibility of alternatives that involved beach nourishment. SOS contends that the\\n\\nAgencies failed to adequately reconsider beach nourishment after new erosion projections\\n\\nwere released and after a 2014 emergency beach nourishment project in the area\\n\\n 14\\n\\fsuccessfully repaired damage from Hurricane Sandy. According to SOS, this new\\n\\ninformation showed that coastal conditions had changed such that erosion would no\\n\\nlonger threaten beach nourishment and that adequate sand was in fact available to\\n\\ncomplete the project.\\n\\n However, the Agencies took the requisite hard look at these new circumstances in\\n\\nthe 2016 EA. See Hughes River, 81 F.3d at 443. The 2016 EA notes that while erosion\\n\\nprojections in the Rodanthe area did decrease, erosion rates in Rodanthe remained\\n\\n“amongst the highest rates along the North Carolina coast.” J.A. 1218. It also discusses\\n\\nthe 2014 emergency beach nourishment project in detail and considers updated\\n\\ninformation about coastal conditions in the area. Specifically, it notes that the 2014\\n\\nemergency beach nourishment project was “essentially one round of nourishment in one\\n\\npart of [NC-12].” J.A. 1227. Finally, it concludes that the Agencies thoroughly\\n\\nconsidered the environmental effects of beach nourishment when they originally\\n\\nevaluated those alternatives in the 2008 EIS. This detailed discussion satisfies the hard\\n\\nlook requirement. See Hodges, 300 F.3d at 446–47.\\n\\n And after taking that hard look, the Agencies’ decision not to prepare an SEIS was\\n\\nnot arbitrary or capricious. See Hughes River, 81 F.3d at 443. SOS cites improved\\n\\nerosion rates and an increased supply of sand as new factors that the Agencies should\\n\\nhave considered when deciding whether to prepare an SEIS. However, erosion and sand\\n\\nsupply were not the Agencies’ only reasons for initially rejecting beach nourishment in\\n\\nthe 2008 EIS. The Agencies also cited independent concerns such as inadequate\\n\\nprotection against future breaches, risks of overwash, and incompatibility with the\\n\\n 15\\n\\fmission of a neighboring wildlife refuge. It was not arbitrary or capricious for the\\n\\nAgencies to decline to reconsider beach nourishment alternatives in an SEIS when the\\n\\nnew information proffered by SOS did not implicate all of the Agencies’ independently\\n\\nadequate reasons for initially rejecting beach nourishment.\\n\\n Accordingly, the Agencies were not required to prepare an SEIS to consider the\\n\\nalignment of the Jug-Handle Bridge or to consider beach nourishment alternatives. Their\\n\\nenvironmental analyses therefore do not violate NEPA in this respect.\\n\\n\\n\\n B.\\n\\n SOS also contends that the Agencies’ environmental analyses violate NEPA\\n\\nbecause they do not adequately consider the environmental effects of construction in the\\n\\nRodanthe area. Specifically, SOS argues that the effects of construction traffic and haul\\n\\nroads are not adequately addressed in the 2016 EA and that any discussion of these issues\\n\\nin the 2008 EIS is irrelevant because that document focuses on a larger area.\\n\\n NEPA requires agencies to consider all “significant environmental impacts,” 40\\n\\nC.F.R. § 1502.1, which can include impacts caused by the use of construction roads and\\n\\nincreased traffic. See, e.g., Arlington Coal. on Transp. v. Volpe, 458 F.2d 1323, 1332\\n\\n(4th Cir. 1972) (explaining that NEPA applies to highway construction projects).\\n\\nAccordingly, if construction roads and traffic are expected to affect the environment near\\n\\nan agency project, the agency must provide “full and fair discussion” of those effects and\\n\\nincorporate them into its comparison of alternatives. 40 C.F.R. § 1502.1.\\n\\n\\n\\n 16\\n\\f Here, the Agencies adequately considered the effects of construction traffic as a\\n\\nresult of the Jug-Handle Bridge in the 2016 ROD. Specifically, the Agencies explained\\n\\nthat a temporary construction easement would be necessary to support traffic during\\n\\nconstruction but noted that “[t]he land affected will be restored after construction is\\n\\ncompleted.” J.A. 1559. While the 2016 ROD does not compare the construction traffic\\n\\neffects of the Jug-Handle Bridge with those of other proposed alternatives, the Agencies\\n\\ndid perform that comparison in the 2013 EA and the 2016 EA and still found the bridge\\n\\nto be the LEDPA. The Agencies also specifically considered the environmental effects of\\n\\nhaul roads in the 2008 EIS. 6\\n\\n We therefore cannot say that the Agencies did not provide “full and fair\\n\\ndiscussion” of the effects of construction traffic or haul roads when they selected the Jug-\\n\\nHandle Bridge among alternatives. See 40 C.F.R. § 1502.1. Accordingly, the Agencies\\n\\ndid not violate NEPA here, and we affirm the district court.\\n\\n\\n\\n\\n 6\\n To be sure, that discussion did not explicitly consider haul roads in the Rodanthe\\narea. However, it is unclear from the record whether the Agencies actually plan to use\\nhaul roads for the Jug-Handle Bridge project. See, e.g., J.A. 214 (containing a\\ndeclaration from an NCDOT engineer stating that NCDOT and its contractor decided not\\nto pursue a previously-discussed haul road in connection with a barge because shallow\\nwater depths would make it impracticable). Regardless, NEPA does not compel the\\nAgencies to specifically consider the environmental impacts of haul roads so long as they\\nadequately examine the environmental consequences of the Jug-Handle Bridge project,\\nincluding construction impacts, as a whole. See 40 C.F.R. § 1502.2(b) (“Impacts shall be\\ndiscussed [in the EIS] in proportion to their significance.”).\\n\\n 17\\n\\f C.\\n\\n Finally, SOS contends that the Agencies violated NEPA because their choice of\\n\\nthe Jug-Handle Bridge did not follow from their NEPA analysis but, rather, was a\\n\\npredetermined result of the Settlement. NEPA “prohibits agencies from preparing an EIS\\n\\nsimply to ‘justify [] decisions already made.’” Nat’l Audubon Soc’y, 422 F.3d at 199\\n\\n(quoting 40 C.F.R. § 1502.2(g)) (alteration in original). That is because, under NEPA,\\n\\nagencies that have yet to issue a final decision may not “commit resources prejudicing\\n\\nselection of alternatives,” 40 C.F.R. § 1502.2(f), nor may they take any action that would\\n\\n“[l]imit the choice of reasonable alternatives,” 40 C.F.R. § 1506.1(a). An EIS based upon\\n\\na predetermined choice that a certain alternative will be selected would violate these\\n\\nprinciples because it would not allow the agency to fully consider all alternatives.\\n\\n We conclude that the Agencies’ choice of the Jug-Handle Bridge was not\\n\\nimpermissibly predetermined. We consider, in turn, the Agencies’ objective\\n\\nenvironmental analyses, the language of the Settlement, and the role of documents\\n\\ngenerated during negotiation of the Settlement.\\n\\n\\n\\n i.\\n\\n First, SOS contends that flaws in the Agencies’ environmental analyses reveal that\\n\\ntheir choice of the Jug-Handle Bridge was predetermined by the Settlement. In alleging\\n\\nthat the environmental analyses were inadequate, it primarily relies upon arguments that\\n\\nwe have already discussed--namely, that the Agencies failed to fully consider the new\\n\\nalignment of the bridge, the feasibility of beach nourishment alternatives, and the effects\\n\\n 18\\n\\fof construction traffic and haul roads. SOS contends that these flaws exist because the\\n\\nAgencies prematurely decided to choose the Jug-Handle Bridge after the Settlement.\\n\\n Under our precedent, “the evidence we look to in determining whether\\n\\n[predetermination] has taken place consists of the environmental analysis itself.” 7 Nat’l\\n\\nAudubon Soc’y, 422 F.3d at 199. In National Audubon Society, in reviewing allegations\\n\\nthat an agency had settled on a certain outcome before preparing its EIS, we declined to\\n\\nlook to the agency’s internal documents and emails. Id. Instead, we limited the scope of\\n\\nour inquiry to the agency’s objective environmental analysis, reasoning that “[w]here an\\n\\nagency has merely engaged in post hoc rationalization, there will be evidence of this in its\\n\\nfailure to comprehensively investigate the environmental impact of its actions and\\n\\nacknowledge their consequences.” Id. Accordingly, our analysis focuses on whether an\\n\\nagency’s objective environmental analyses demonstrate evidence of predetermination.\\n\\n Here, when we examine Agencies’ environmental analyses, we cannot say that\\n\\nthey violated NEPA by selecting the Jug-Handle Bridge following the Settlement. To be\\n\\nsure, the Agencies changed their preferred alternative from the easement bridge to the\\n\\nJug-Handle Bridge following the Settlement. But that change alone does not mean that\\n\\nthe Agencies’ choice was predetermined, particularly where members of the Merger\\n\\nTeam had expressed concerns about the easement bridge as far back as 2013. And when\\n\\nwe look to the Agencies’ environmental analyses here, those analyses satisfied NEPA’s\\n\\n\\n 7\\n We note that some circuits look beyond the objective environmental analysis for\\nevidence of predetermination. See, e.g., Forest Guardians v. U.S. Fish & Wildlife Serv.,\\n611 F.3d 692, 716–17 (10th Cir. 2010) (declining to adopt the Fourth Circuit’s rule).\\n\\n 19\\n\\frequirements. See discussion supra Sections II.A., II.B. We do not see, and SOS cannot\\n\\nidentify, any evidence that the Agencies “fail[ed] to comprehensively investigate” and\\n\\nevaluate the environmental impacts of the Jug-Handle Bridge or the other alternatives.\\n\\nNat’l Audubon Soc’y, 422 F.3d at 199. The EAs and EIS prepared by the Agencies do\\n\\nnot, on their faces, show evidence of predetermination.\\n\\n SOS cites to cases from the Ninth and Tenth Circuits to contend that courts have\\n\\nfound predetermination based on contractual commitments made by an agency before the\\n\\nNEPA process was complete. See Davis v. Mineta, 302 F.3d 1104, 1112 (10th Cir. 2002)\\n\\n(holding that a contract requiring a consultant to recommend that a project had no\\n\\nsignificant environmental impact before actually preparing an EA violated NEPA);\\n\\nMetcalf v. Daley, 214 F.3d 1135, 1145 (9th Cir. 2000) (same, regarding a contract\\n\\nrequiring an agency to make a proposal for a specific alternative before preparing an EA).\\n\\nHowever, these cases are distinguishable because they involved contracts that agencies\\n\\nentered into before conducting any environmental analysis at all; in contrast, the\\n\\nSettlement here, which the Agencies and the Environmental Groups entered into in 2015,\\n\\nwas preceded by a number of environmental analyses, including the 2008 EIS, the 2010\\n\\nEA, and the 2013 EA. And when we examine each of these environmental analyses, we\\n\\nfind no evidence of predetermination warranting reversal.\\n\\n\\n\\n ii.\\n\\n Although circuit precedent limits our predetermination inquiry to the\\n\\n“environmental analysis itself,” id., SOS nonetheless urges us to consider the Settlement\\n\\n 20\\n\\fas evidence that the Agencies’ choice was predetermined. But even if we look to the\\n\\nSettlement, that document does not support SOS’s claim. The Settlement only required\\n\\nNCDOT to identify the Jug-Handle Bridge as its preferred alternative and to seek Merger\\n\\nTeam concurrence that the Jug-Handle Bridge was the LEDPA. These conditions do not\\n\\nrequire the Agencies to select the Jug-Handle Bridge as the final approved alternative for\\n\\nthis project. For instance, it remained possible that the Agencies’ environmental analyses\\n\\nwould demonstrate that the Jug-Handle Bridge was not the LEDPA. Additionally, the\\n\\nAgencies’ preferences alone could not bind the entire Merger Team, which was\\n\\nultimately responsible for approving the final alternative, because the parties to the\\n\\nSettlement comprise only three of the ten state and federal agencies represented on the\\n\\nMerger Team. 8 This does not constitute predetermination.\\n\\n\\n\\n iii.\\n\\n SOS also urges us to consider external documents generated during the negotiation\\n\\nof the Settlement as evidence of predetermination and to reverse the district court’s denial\\n\\nof SOS’s motion to include these documents in the record. We decline to do so because\\n\\nthe district court did not abuse its discretion in denying this motion. See Fort Sumter\\n\\nTours, Inc. v. Babbitt, 66 F.3d 1324, 1335–36 (4th Cir. 1995) (explaining that we review\\n\\n 8\\n To be sure, the parties to the Settlement represented three of the four Lead\\nAgencies tasked with decisionmaking if the Merger Team could not reach consensus.\\nBut, as discussed, the Settlement only required those agencies to seek concurrence that\\nthe Jug-Handle Bridge was the LEDPA; it did not require them to go beyond the\\nobjective environmental analysis to choose the Jug-Handle Bridge if it was not, in fact,\\nthe LEDPA.\\n\\n 21\\n\\fa district court’s decision whether to expand the administrative record for abuse of\\n\\ndiscretion).\\n\\n Federal courts base their review of agency decisions on “the ‘whole record’\\n\\ncompiled by the agency.” Citizens to Pres. Overton Park, Inc. v. Volpe, 401 U.S. 402,\\n\\n419 (1971) (quoting 5 U.S.C. § 706), abrogated on other grounds by Califano v. Sanders,\\n\\n430 U.S. 99 (1977). We may supplement the record as presented by the agency if the\\n\\n“bare record” does not reveal the agency’s reasoning or if it appears that the agency acted\\n\\nin bad faith. Id. at 420. Otherwise, “inquiry into the mental processes of administrative\\n\\ndecisionmakers is usually to be avoided.” Id.\\n\\n Here, the record as presented by the Agencies reveals their reasoning, as we have\\n\\ndiscussed, and the district court found no evidence that the Agencies acted in bad faith.\\n\\nThe district court also determined that there was no evidence that the Agencies actually\\n\\nreviewed the documents put forth by SOS as part of their decision to approve the Jug-\\n\\nHandle Bridge. We hold that the district court did not abuse its discretion by denying\\n\\nSOS’s motion to supplement the record, and accordingly, our review is limited to the\\n\\nrecord as compiled by the Agencies.\\n\\n SOS contends that, even if we cannot consider these documents as part of the\\n\\nadministrative record, we should nevertheless consider them as extra-record evidence. It\\n\\nis true that “in the NEPA context, courts generally have been willing to look outside the\\n\\nrecord when assessing the adequacy of an EIS or a determination that no EIS is\\n\\nnecessary.” Ohio Valley Envtl. Coal. v. Aracoma Coal Co., 556 F.3d 177, 201 (4th Cir.\\n\\n2009). However, we have explained that extra-record evidence in that context is\\n\\n 22\\n\\fprimarily useful “to inform the court about environmental factors that the agency may not\\n\\nhave considered.” Id. (emphasis added). Here, the proffered documents would do\\n\\nnothing to aid the court’s understanding of the environmental concerns at issue, as they\\n\\nconcern the legal terms of the Settlement between the Agencies and the Environmental\\n\\nGroups. Therefore, the district court properly excluded them, and we decline to consider\\n\\nthem now.\\n\\n There is superficial appeal in suggesting that the Agencies’ choice was\\n\\npredetermined because the Settlement yielded a preferred alternative. However, that\\n\\nconclusion is not legally or factually supported by the record. Legally, our analysis is\\n\\ncabined to the environmental analysis itself, with which we find no issues meriting\\n\\nreversal. And factually, we see no evidence that the Merger Team was forced to approve\\n\\nthe Jug-Handle Bridge.\\n\\n In sum, the Agencies did not violate NEPA when they approved the Jug-Handle\\n\\nBridge because they were not required to prepare an SEIS, they adequately evaluated the\\n\\neffects of construction traffic, and they did not rely on a predetermined choice among\\n\\nalternatives. We therefore affirm the district court’s grant of summary judgment in favor\\n\\nof the Agencies.\\n\\n\\n\\n III.\\n\\n Finally, SOS contends that the district court erred when it denied SOS’s motion to\\n\\namend its complaint with claims related to the Pappy’s Lane Wreck. Specifically, SOS\\n\\nalleges that the Agencies violated § 4(f) by approving a transportation project that\\n\\n 23\\n\\fthreatens to harm the land of a site of historic significance because the Jug-Handle Bridge\\n\\nwill pass above the wreck--the site of a World War II vessel.\\n\\n We review a district court’s denial of a motion to amend the complaint for abuse\\n\\nof discretion. See Laber v. Harvey, 438 F.3d 404, 428 (4th Cir. 2006) (en banc).\\n\\nHowever, if the district court denied such a motion on the grounds that the amendment\\n\\nwould have been futile, we review its legal conclusions de novo. United States ex. rel.\\n\\nAhumada v. NISH, 756 F.3d 268, 274 (4th Cir. 2014).\\n\\n A party “may amend its pleading once as a matter of course” before the opposing\\n\\nparty files a responsive pleading. Fed. R. Civ. P. 15(a)(1). After that time, a party may\\n\\nonly amend its pleading with the consent of the opposing party or with leave of the court,\\n\\nand “[t]he court should freely give leave when justice so requires.” Fed. R. Civ. P.\\n\\n15(a)(2). Courts may deny leave to amend a pleading if the amendment would have been\\n\\nfutile. Laber, 438 F.3d at 426. A proposed amendment is futile when it is “clearly\\n\\ninsufficient or frivolous on its face.” Johnson v. Oroweat Foods Co., 785 F.2d 503, 510\\n\\n(4th Cir. 1986). A proposed amendment is also futile if the claim it presents would not\\n\\nsurvive a motion to dismiss. Perkins v. United States, 55 F.3d 910, 917 (4th Cir. 1995).\\n\\n Here, the district court found that SOS’s proposed amendment would be futile for\\n\\ntwo alternative reasons. First, it determined that, to the extent that SOS sought to assert\\n\\nthat the 2016 EA was no longer valid in light of new information about the shipwreck,\\n\\nthat claim would be unripe where the Agencies had not yet made a decision concerning\\n\\nthe significance of the new information. Second, it determined that, to the extent that\\n\\nSOS sought to assert that the 2016 EA was inadequate when issued, that claim would fail\\n\\n 24\\n\\fbecause it would ask the Agencies to consider information that was not discovered until\\n\\nafter the 2016 EA was issued. For the reasons that follow, we affirm the district court’s\\n\\ndenial of SOS’s motion to amend its complaint.\\n\\n First, to the extent that SOS’s proposed amendments contend that the Agencies\\n\\nfailed to consider new information about the shipwreck, those amendments would be\\n\\nfutile because they would raise a claim that is not yet ripe for review. 9 Courts may only\\n\\nreview “final agency action,” 5 U.S.C. § 704, and challenges to agency decisions that are\\n\\nyet to be made are not ripe for review. See Pashby v. Delia, 709 F.3d 307, 317 (4th Cir.\\n\\n2013) (holding that a claim is only ripe when it involves a formalized administrative\\n\\ndecision). Here, the Agencies have not yet made a final decision about the significance\\n\\nof new information revealing that the shipwreck was a World War II assault vessel.\\n\\nTherefore, any claim that the Agencies did not properly account for this information\\n\\nwould be unripe, and any amendment seeking to add such a claim would be futile.\\n\\n Second, SOS contends on appeal that it is challenging the adequacy of the 2016\\n\\nROD’s treatment of the Pappy’s Lane Wreck rather than the Agencies’ failure to consider\\n\\nnew information about the shipwreck’s significance. Specifically, SOS contends that,\\n\\nbecause the Agencies knew that the shipwreck was eligible for listing on the National\\n\\n\\n 9\\n SOS appears to have abandoned this argument on appeal. See Appellants’ Br. at\\n53 (contending that the district court “fundamentally misread [SOS’s] motion” when it\\ndenied it on ripeness grounds because “[t]he [new] allegations were about the\\ninadequacies of the [2016] ROD and the process leading up to that document”)\\n(emphasis added). Nevertheless, we discuss it because it implicates concerns related to\\nthe argument that SOS does raise on appeal regarding the adequacy of the 2016 ROD\\nwhen issued.\\n\\n 25\\n\\fRegister of Historic Places, they were not authorized to build a bridge in its path unless\\n\\nthey determined that there was “no prudent and feasible alternative to using that land”\\n\\nand that the “project include[d] all possible planning to minimize harm . . . resulting from\\n\\nthe use.” See 49 U.S.C. § 303(c).\\n\\n However, as the district court explained, SOS cannot contend that it was\\n\\nchallenging the adequacy of the 2016 ROD’s treatment of the shipwreck when its claims\\n\\n“rest[] upon recent discovery that the Pappy[’s] Lane Wreck contains a World War II\\n\\nvessel.” Save Our Sound OBX, Inc. v. N.C. Dep’t of Transp., No. 2:17-CV-4-FL, 2017\\n\\nWL 7048561, at *5 (E.D.N.C. Dec. 5, 2017). Instead, the Agencies satisfied regulatory\\n\\nrequirements when, based on what they knew about the Pappy’s Lane Wreck, they\\n\\nordered data recovery and decided that the shipwreck did not merit preservation in place.\\n\\nArguments that the Agencies should have gone further are grounded in new information\\n\\nand, therefore, not reviewable until the Agencies issue a final decision, as discussed\\n\\nabove. We therefore affirm the district court’s denial of SOS’s motion to amend its\\n\\ncomplaint.\\n\\n\\n\\n IV.\\n\\n We affirm the district court because the Agencies did not violate NEPA or the\\n\\nDTA when they issued the 2016 ROD selecting the Jug-Handle Bridge and because the\\n\\ndistrict court did not abuse its discretion when it denied SOS’s motions to supplement the\\n\\nadministrative record and to amend the complaint.\\n\\n AFFIRMED\\n\\n 26\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4361214/\", \"author_raw\": \"DUNCAN, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"NIEMEYER"},"judge2":{"kind":"string","value":"DUNCAN"},"judge3":{"kind":"string","value":"QUATTLEBAUM"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583961/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: SAVE OUR SOUND OBX, INC.; Mark Haines ; Jer Mehta; Glenn Stevens ; David Hadley ; Thomas Aschmoneit; Richard Ayella, Plaintiffs - Appellants, v. NORTH CAROLINA DEPARTMENT OF TRANSPORTATION; Federal Highway Administration; John F. Sullivan, III, in His Official Capacity as Division Administrator for the Federal Highway Administration; James H. Trogdon, III, in His Official Capacity as Secretary of the North Carolina Department of Transportation, Defendants - Appellees, and Defenders of Wildlife; National Wildlife Refuge Association, Intervenors/Defendants - Appellees.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-23\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1649\n\n\nSAVE OUR SOUND OBX, INC.; MARK HAINES; JER MEHTA; GLENN\nSTEVENS; DAVID HADLEY; THOMAS ASCHMONEIT; RICHARD\nAYELLA,\n\n Plaintiffs – Appellants,\n\nv.\n\nNORTH CAROLINA DEPARTMENT OF TRANSPORTATION; FEDERAL\nHIGHWAY ADMINISTRATION; JOHN F. SULLIVAN, III, in his official\ncapacity as Division Administrator for the Federal Highway Administration;\nJAMES H. TROGDON, III, in his official capacity as Secretary of the North\nCarolina Department of Transportation,\n\n Defendants – Appellees,\n\nand\n\nDEFENDERS OF WILDLIFE; NATIONAL WILDLIFE REFUGE\nASSOCIATION,\n\n Intervenors/Defendants – Appellees.\n\n\nAppeal from the United States District Court for the Eastern District of North Carolina, at\nElizabeth City. Louise W. Flanagan, District Judge. (2:17-cv-00004-FL)\n\n\nArgued: December 11, 2018 Decided: January 23, 2019\n\n\nBefore NIEMEYER, DUNCAN, and QUATTLEBAUM, Circuit Judges.\n\fAffirmed by published opinion. Judge Duncan wrote the opinion, in which Judge\nNiemeyer and Judge Quattlebaum joined.\n\n\nARGUED: David Ari Schnitzer, GIBSON, DUNN & CRUTCHER LLP, Washington,\nD.C., for Appellants. Thekla Hansen-Young, UNITED STATES DEPARTMENT OF\nJUSTICE, Washington, D.C.; Colin Justice, NORTH CAROLINA DEPARTMENT OF\nJUSTICE, Raleigh, North Carolina, for Appellees. ON BRIEF: Michael K. Murphy,\nKyle N. Guest, GIBSON, DUNN & CRUTCHER LLP, Washington, D.C., for\nAppellants. Jeffrey H. Wood, Acting Assistant Attorney General, Eric Grant, Deputy\nAssistant Attorney General, Andrew C. Mergen, Robert J. Lundman, Carter F. Thurman,\nAppellate Section, Environment and Natural Resources Division, UNITED STATES\nDEPARTMENT OF JUSTICE, Washington, D.C.; Josh Stein, Attorney General,\nOFFICE OF THE ATTORNEY GENERAL OF NORTH CAROLINA, Raleigh, North\nCarolina; Scott T. Slusser, Special Deputy Attorney General, Mollie Cozart, Assistant\nAttorney General, NORTH CAROLINA DEPARTMENT OF JUSTICE, Raleigh, North\nCarolina, for Appellees North Carolina Department of Transportation, Federal Highway\nAdministration, John F. Sullivan, III, and James H. Trogdon, III. Kimberley Hunter,\nNicholas S. Torrey, SOUTHERN ENVIRONMENTAL LAW CENTER, Chapel Hill,\nNorth Carolina, for Appellees Defenders of Wildlife and National Wildlife Refuge\nAssociation.\n\n\n\n\n 2\n\fDUNCAN, Circuit Judge:\n\n Appellants Save Our Sound OBX, Inc. and its members, residents and vacationers\n\nfrom North Carolina’s Outer Banks, (collectively “SOS”) challenge the decision of the\n\nNorth Carolina Department of Transportation (the “NCDOT”), the Federal Highway\n\nAdministration (the “FHWA”), and their administrators (collectively “the Agencies”) to\n\nreplace a segment of North Carolina Highway 12 (“NC-12”) with a bridge across the\n\nPamlico Sound (the “Jug-Handle Bridge”). The district court granted the Agencies’\n\nmotion for summary judgment, finding that they did not violate the National\n\nEnvironmental Policy Act (the “NEPA”), 42 U.S.C. § 4321 et seq., or the Department of\n\nTransportation Act (the “DTA”), 49 U.S.C. § 301 et seq., when they approved the bridge.\n\nSOS challenges that ruling on appeal. For the reasons that follow, we affirm.\n\n\n\n I.\n\n This case involves a segment of NC-12, which is the main roadway passing\n\nthrough the Outer Banks of North Carolina. State and federal agencies have been\n\nworking for several years to update and improve NC-12 because of its susceptibility to\n\nweather damage and erosion.\n\n Like many highway construction projects, the NC-12 project required cooperation\n\namong state and federal agencies. For instance, in North Carolina, NCDOT has authority\n\nover highway construction, while FWHA supplies federal funds for highway projects.\n\nThe agencies tasked with improving NC-12, including NCDOT and FHWA, formed a\n\nMerger Team to coordinate decisionmaking and regulatory compliance for the NC-12\n\n 3\n\fproject. 1 The Merger Team was responsible for ensuring that the NC-12 project\n\ncomplied with the requirements of NEPA and the DTA, among other regulations.\n\n SOS challenges certain agency decisions in the NC-12 project under NEPA and\n\nthe DTA. Accordingly, we first provide a brief overview of the requirements of those\n\nstatutes before turning to the specific facts and procedural history of this appeal.\n\n\n\n A.\n\n The first statute at issue in this appeal is NEPA. Pursuant to NEPA, 42 U.S.C.\n\n§ 4321 et seq., and its implementing regulations, government agencies considering\n\ncertain projects must evaluate whether the project would have a significant impact on the\n\nenvironment by preparing an Environmental Assessment (an “EA”). Id. § 4332(C); 40\n\nC.F.R. § 1508.9; see id. § 1508.18 (defining the types of federal actions to which NEPA\n\napplies). If the project would have a significant impact, the agency must prepare an\n\nEnvironmental Impact Statement (an “EIS”). 42 U.S.C. § 4332(C). The agency is\n\nresponsible for ensuring that the EIS complies with various regulatory requirements. See\n\n40 C.F.R. § 1502.1 et seq. For instance, the EIS must “provide full and fair discussion”\n\nof any significant environmental impacts of a proposed action. 40 C.F.R. § 1502.1.\n\n 1\n The Merger Team was comprised of representatives from NCDOT, FHWA, the\nU.S. Fish and Wildlife Service, the U.S. Army Corps of Engineers, the U.S.\nEnvironmental Protection Agency, the National Marine Fisheries Service, the National\nPark Service, the North Carolina Department of Cultural Resources, the North Carolina\nWildlife Resources Commission, and three divisions of the North Carolina Department of\nEnvironmental and Natural Resources (the “NCDENR”) (now named the North Carolina\nDepartment of Environmental Quality)--the Division of Water Resources, the Division of\nCoastal Management, and the Division of Marine Fisheries.\n\n 4\n\fAdditionally, the agency must “[r]igorously explore and objectively evaluate all\n\nreasonable alternatives” that could “avoid or minimize adverse impacts.” Id.\n\n§§ 1502.1, 1502.14. The agency is permitted, however, to identify a preference among\n\nalternatives based on non-environmental considerations, such as economic factors or the\n\nagency’s statutory mission. Id. § 1505.2(b). If the agency has a preferred alternative,\n\nNEPA requires the agency to identify that preference in the EIS. Id. § 1502.14. NEPA\n\nalso requires the agency to prepare a supplemental EIS (an “SEIS”) if significant new\n\ninformation or environmental changes come to light after the agency prepares an EIS. Id.\n\n§ 1502.9(c). After the agency makes its final decision about which alternative to pursue,\n\nit publishes a record of decision (an “ROD”) explaining its choice. Id. § 1505.2.\n\n We now turn to the second statute at issue: the DTA. The DTA contains\n\nsubstantive requirements for government transportation projects. 49 U.S.C. § 301 et seq.\n\nRelevant here, the so-called “§ 4(f)” requirements 2 concern transportation projects that\n\nrequire the use of publicly owned land of a wildlife refuge or a significant historic site.\n\nId. § 303(c). Historic sites include structures “included in, or eligible for inclusion in,”\n\nthe National Register of Historic Places. 23 C.F.R. § 774.17. The Secretary of\n\nTransportation may only approve such projects if there is no “feasible and prudent”\n\nalternative to using that land and the “project includes all possible planning to minimize\n\nharm . . . resulting from the use.” Id. § 303(c). If there is no feasible and prudent\n\n\n 2\n The DTA explains that “[t]he requirements of [49 U.S.C. § 303] are commonly\nreferred to as section 4(f) requirements” in reference to a previous version of the statute.\n49 U.S.C. § 303(f)(1).\n\n 5\n\falternative, the Secretary may only approve the alternative that “[c]auses the least overall\n\nharm in light of the [DTA’s] preservation purpose.” 23 C.F.R. § 774.3(c). Relevant\n\nconsiderations in selecting the least harmful alternative include whether harm to the land\n\ncan be mitigated, whether harm to the land affects the attributes qualifying that land for\n\nprotection, and whether the alternative meets the needs of the project. Id.\n\n\n\n B.\n\n Having established the relevant framework, we consider the facts of this case.\n\nSOS’s claims in this litigation concern the Agencies’ environmental analysis under\n\nNEPA and the DTA with respect to a segment of NC-12 that passes from the southern\n\nedge of Bodie Island to the village of Rodanthe. For this segment, the Merger Team was\n\nresponsible for preparing EAs and EISs pursuant to NEPA and for determining which\n\nproposed plan for the project was the least environmentally-damaging practicable\n\nalternative (the “LEDPA”) pursuant to section 404 of the Clean Water Act, 33 U.S.C.\n\n§ 1344, among other requirements. 3 See 40 C.F.R. § 230.10 (setting out the LEDPA\n\nrequirement).\n\n In 2008, the Merger Team issued an EIS and § 4(f) evaluation (the “2008 EIS”)\n\nfor improving NC-12. For the segment at issue here, the 2008 EIS included discussion of\n\nseveral alternatives, including a proposed bridge in the Pamlico Sound near Rodanthe\n\n\n\n 3\n Section 404 of the Clean Water Act regulates activities involving “the discharge\nof dredged or fill material” into navigable waters. Id.\n\n 6\n\f(the “Bridge South alternative”) and proposals involving beach nourishment. An EA in\n\n2010 (the “2010 EA”) further developed these alternatives.\n\n The Merger Team released an updated EA in 2013 (the “2013 EA”) to account for\n\nenvironmental changes after the 2010 EA, including the effects of Hurricane Irene in\n\n2011. The 2013 EA identified four alternatives for the segment at issue: (1) the so-called\n\nJug-Handle Bridge, a bridge extending out into the Pamlico Sound (also referred to in the\n\nenvironmental analyses as the “Bridge on New Location”); 4 (2) an easement bridge on\n\nthe existing NC-12 location; (3) beach nourishment; and (4) an easement bridge\n\ncombined with beach nourishment. The Merger Team did not study the beach\n\nnourishment alternatives in depth in the 2013 EA because, at a 2011 meeting, it had\n\nalready determined not to pursue them after experts reported on a “high erosion rate and a\n\nlack of sand supply.” J.A. 843. In the 2013 EA, the Merger Team identified the\n\neasement bridge as its preferred alternative under NEPA. However, certain members of\n\nthe Merger Team objected to finding that the easement bridge was the LEDPA under the\n\nClean Water Act, citing concerns about its location within the surf zone, additional\n\npermits associated with erosion setback requirements, and its impact on a nearby wildlife\n\nrefuge. See J.A. 1745–47.\n\n In the meantime, environmental groups Defenders of Wildlife and the National\n\nWildlife Refuge Association (intervenors here, collectively the “Environmental Groups”)\n\nbrought suit in federal court to challenge the Agencies’ NEPA and § 4(f) determinations\n\n 4\n The Jug-Handle Bridge was a modified version of the Bridge South alternative\nthat was introduced in the 2008 EIS and further developed in the 2010 EA.\n\n 7\n\fwith respect to a different segment of NC-12 in the Outer Banks--the Bonner Bridge,\n\nwhich connects Bodie Island and Hatteras Island to the north of Rodanthe. See Defs. of\n\nWildlife v. N.C. Dep’t of Transp., 762 F.3d 374 (4th Cir. 2014). The Environmental\n\nGroups and the Agencies eventually reached an agreement in 2015 (the “Settlement”). 5\n\nThe Settlement required NCDOT to identify the Jug-Handle Bridge as its preferred\n\nalternative for the segment of NC-12 at issue in this case. It also required NCDOT to\n\nseek Merger Team concurrence that the Jug-Handle Bridge was the LEDPA. In doing so,\n\nit stated that nothing in the Settlement “requires or should be interpreted to predetermine\n\nthe choice” of the Jug-Handle Bridge as the final selected alternative. J.A. 1090. In\n\nexchange, the Environmental Groups dismissed the Bonner Bridge suit and agreed not to\n\nchallenge the Agencies in court if the Jug-Handle Bridge was determined to be the\n\nLEDPA and was ultimately selected in the ROD for this project.\n\n After a 2015 meeting, the Agencies identified the Jug-Handle Bridge as their\n\npreferred alternative. Following public comment and detailed studies, the Merger Team\n\ndetermined that the Jug-Handle Bridge was the LEDPA. In 2016, the Merger Team\n\nreleased a revised EA (the “2016 EA”) to evaluate the environmental impacts of the Jug-\n\nHandle Bridge and its associated construction activities. Later that year, the Merger\n\nTeam issued an ROD (the “2016 ROD”) formally approving the Jug-Handle Bridge.\n\n In addition to authorizing construction of the Jug-Handle Bridge, the 2016 ROD\n\nalso addressed concerns relating to a shipwreck in the proposed bridge’s path known as\n\n 5\n NCDENR was also a party to the Settlement and is represented on the Merger\nTeam, though it is not a defendant here.\n\n 8\n\fthe Pappy’s Lane Wreck. The shipwreck is eligible for listing on the National Register of\n\nHistoric Places. Because of the shipwreck’s historical significance, the 2016 ROD\n\nordered a data recovery project on the shipwreck, which later uncovered evidence that the\n\nshipwreck was a World War II assault vessel. The Merger Team has not yet determined\n\nhow it will respond to this new information.\n\n\n\n C.\n\n We now turn to the procedural history of this litigation, which began when SOS\n\nsued the Agencies on February 2, 2017. A month later, the Environmental Groups\n\nintervened in the suit in support of the Agencies. In its complaint, SOS alleged, as\n\nrelevant here, that the Agencies’ approval of the Jug-Handle Bridge violated NEPA\n\nbecause that decision was predetermined by the Settlement. To show evidence of\n\npredetermination, SOS moved to supplement the administrative record before the district\n\ncourt to include documents related to the negotiation of the Settlement on the grounds\n\nthat those documents were before the Agencies when they made their decision to select\n\nthe Jug-Handle Bridge. The district court denied this motion.\n\n Later, SOS moved to amend its complaint to add claims related to construction\n\nimpacts in Rodanthe and to the Pappy’s Lane Wreck. Specifically, SOS contended that\n\nthe Agencies’ environmental analyses did not adequately consider the effects of\n\nconstruction or the historic significance of the Pappy’s Lane Wreck. The district court\n\ngranted the motion as to construction impacts but denied it as to the shipwreck.\n\n\n\n 9\n\f SOS, the Agencies, and the Environmental Groups each filed cross-motions for\n\nsummary judgment on the issue of whether the Agencies’ environmental analyses\n\nviolated NEPA or the DTA. The district court granted the Agencies’ and Environmental\n\nGroups’ motions for summary judgment and denied SOS’s motion.\n\n SOS appeals the district court’s grant of the Agencies’ motion for summary\n\njudgment and its denial of SOS’s motion to amend its complaint. SOS contends that the\n\nAgencies were not entitled to summary judgment because the Agencies’ environmental\n\nanalyses violated NEPA. It also contends that the district court erred in denying SOS’s\n\nmotion to amend its complaint with claims related to the Pappy’s Lane Wreck. We\n\ndiscuss SOS’s NEPA claims and its motion to amend its complaint, in that order.\n\n\n\n II.\n\n SOS contends that the Agencies violated NEPA when they selected the Jug-\n\nHandle Bridge for the NC-12 project. “We review a grant of summary judgment de\n\nnovo,” Defs. of Wildlife, 762 F.3d at 392, and, accordingly, review the Agencies’ actions\n\ndirectly, pursuant to the Administrative Procedure Act (the “APA”). The APA directs us\n\nto overturn agency actions if they are “arbitrary, capricious, an abuse of discretion, or\n\notherwise not in accordance with law.” 5 U.S.C. § 706(2)(A). Our precedent also guides\n\nthe scope of our review of the sufficiency of an agency’s NEPA analysis. Nat’l Audubon\n\nSoc’y v. Dep’t of Navy, 422 F.3d 174, 185, 199 (4th Cir. 2005). In conducting this\n\nreview, “we must make a searching and careful inquiry into the facts” and examine\n\nwhether the decision was based on consideration of the relevant factors. Id. at 185\n\n 10\n\f(citation and internal quotation marks omitted). However, we do not “second-guess\n\nagency decisions, so long as the agency has given a hard look at the environmental\n\nimpacts of its proposed action.” Id. at 199.\n\n Under this standard of review, we affirm because the Agencies did not violate\n\nNEPA in approving the Jug-Handle Bridge. We consider SOS’s arguments that the\n\nAgencies’ environmental analyses violated NEPA because (1) the Agencies failed to\n\nprepare an SEIS with regards to the Jug-Handle Bridge and beach nourishment\n\nalternatives before issuing the 2016 ROD, (2) the Agencies failed to adequately consider\n\nthe impacts of construction, and (3) the Settlement impermissibly predetermined the\n\nAgencies’ choice of the Jug-Handle Bridge.\n\n\n\n A.\n\n First, SOS contends that the Agencies’ NEPA analysis was deficient because the\n\nAgencies should have prepared an SEIS before approving the Jug-Handle Bridge in the\n\n2016 ROD. NEPA requires an agency to prepare an SEIS if “[t]he agency makes\n\nsubstantial changes” to a proposed action that implicate environmental concerns or if\n\n“[t]here are significant new circumstances or information” that would affect the\n\nenvironmental impacts of the proposed action. 40 C.F.R. § 1502.9(c). To merit an SEIS,\n\nthe changes “must present a seriously different picture of the environmental impact of the\n\nproposed project.” Hughes River Watershed Conservancy v. Glickman, 81 F.3d 437, 443\n\n(4th Cir. 1996) (citation and alterations omitted).\n\n\n\n 11\n\f We review an agency’s decision not to prepare an SEIS in two steps, consistent\n\nwith our standard of review under NEPA. Id. At step one, we “determine whether the\n\nagency took a hard look at the proffered new information.” Id. If the agency concludes\n\nafter a preliminary inquiry that the “environmental effect of the change is clearly\n\ninsignificant,” its decision not to prepare an SEIS satisfies the hard look requirement.\n\nHodges v. Abraham, 300 F.3d 432, 446 (4th Cir. 2002). For instance, in Hodges, we held\n\nthat an agency took a hard look at the environmental consequences of its change in plans\n\nwhen it explicitly evaluated those consequences and determined that they were not\n\nsignificantly different from those discussed in a prior EIS. Id. at 447. We also noted that\n\nthe plaintiff in that case “failed to identify any particular risk arising from” the change\n\nthat had not already been addressed in the agency’s environmental analyses. Id. Next, at\n\nstep two of the SEIS inquiry, we review whether the agency’s decision not to prepare an\n\nSEIS after taking a hard look was arbitrary or capricious. Hughes River, 81 F.3d at 443.\n\n SOS contends that an SEIS was necessary (1) to evaluate the environmental\n\neffects of the Jug-Handle Bridge alternative because it was different from options that\n\nhad previously been evaluated and (2) to reconsider alternatives that involved beach\n\nnourishment pursuant to new information about sand availability and beach erosion rates.\n\nWe address each contention in turn and affirm the district court’s determination that no\n\nSEIS was required. Neither of these changes are sufficiently different from the\n\ncircumstances initially evaluated in the EIS to merit an SEIS. The Agencies’ decision not\n\nto prepare one after taking a hard look at the changes was therefore not arbitrary or\n\ncapricious.\n\n 12\n\f i.\n\n Contrary to SOS’s contention, the Agencies were not required to prepare an SEIS\n\nwith respect to the Jug-Handle Bridge alternative. SOS argues that the final alignment of\n\nthe Jug-Handle Bridge alternative (that is, its path across the Pamlico Sound and its\n\nconnection points with the shore) was significantly different from previously evaluated\n\nalternatives. Specifically, SOS contends that the bridge’s alignment changed\n\nsignificantly because the alternative evaluated in the 2008 EIS was “amorphously\n\ndefined” and because the alternative evaluated in the 2010 EA (to which the 2013 EA,\n\n2016 EA, and 2016 ROD refer) was “not comparable” to the Jug-Handle Bridge.\n\nAppellant’s Br. at 35, 36. It argues that these differences render prior environmental\n\nanalyses of those alternatives insufficient to evaluate the environmental effects of the\n\nJug-Handle Bridge as approved in the 2016 ROD. We disagree and conclude that the\n\nAgencies complied with NEPA when they decided that an SEIS was not warranted by\n\nthese changes.\n\n At step one, the Agencies took a hard look at changes in the bridge’s alignment in\n\nthe 2016 EA. The 2016 EA describes the similarities and differences between the Jug-\n\nHandle Bridge as proposed in 2016 and the versions evaluated in the 2013 EA, the 2010\n\nEA, and the 2008 EIS. For instance, it explains that the Agencies decided to shift the\n\nalignment of the bridge to avoid areas of “dense submerged aquatic vegetation” that fell\n\nin the path of previous versions of the bridge. J.A. 1198. The 2016 EA also explains that\n\nthe Jug-Handle Bridge’s alignment reduces effects on the community as compared with\n\n 13\n\fprevious versions because it requires a narrower right-of-way. Because the Agencies\n\nwent into detail in their comparison between the Jug-Handle Bridge and previous\n\nversions of the bridge, their coverage satisfies the hard look requirement. See Hodges,\n\n300 F.3d at 446–47.\n\n And, at step two, because the Agencies took the requisite hard look and neither\n\ntheir environmental analyses nor SOS identify any particular differences that would merit\n\nan SEIS, their decision not to prepare an SEIS was not arbitrary or capricious. See\n\nHughes River, 81 F.3d at 443. An SEIS is only required when changes to a project\n\npresent a “seriously different picture of the environmental impact.” Id. (alterations and\n\ncitation omitted). Based on the discussion presented in the 2016 EA, which compared the\n\ndifferent versions of the bridge, it was not arbitrary or capricious for the Agencies to\n\ndetermine that the Jug-Handle Bridge’s final alignment did not present a “seriously\n\ndifferent picture,” id., than the 2008 EIS, the 2010 EA, or the 2013 EA. The Agencies\n\nexplained how the Jug-Handle Bridge was different from previous versions of the bridge,\n\nand their explanations do not implicate any significant environmental concerns.\n\nAccordingly, their decision not to prepare an SEIS was not arbitrary or capricious.\n\n\n\n ii.\n\n Similarly, the Agencies were not required to prepare an SEIS to reevaluate the\n\nfeasibility of alternatives that involved beach nourishment. SOS contends that the\n\nAgencies failed to adequately reconsider beach nourishment after new erosion projections\n\nwere released and after a 2014 emergency beach nourishment project in the area\n\n 14\n\fsuccessfully repaired damage from Hurricane Sandy. According to SOS, this new\n\ninformation showed that coastal conditions had changed such that erosion would no\n\nlonger threaten beach nourishment and that adequate sand was in fact available to\n\ncomplete the project.\n\n However, the Agencies took the requisite hard look at these new circumstances in\n\nthe 2016 EA. See Hughes River, 81 F.3d at 443. The 2016 EA notes that while erosion\n\nprojections in the Rodanthe area did decrease, erosion rates in Rodanthe remained\n\n“amongst the highest rates along the North Carolina coast.” J.A. 1218. It also discusses\n\nthe 2014 emergency beach nourishment project in detail and considers updated\n\ninformation about coastal conditions in the area. Specifically, it notes that the 2014\n\nemergency beach nourishment project was “essentially one round of nourishment in one\n\npart of [NC-12].” J.A. 1227. Finally, it concludes that the Agencies thoroughly\n\nconsidered the environmental effects of beach nourishment when they originally\n\nevaluated those alternatives in the 2008 EIS. This detailed discussion satisfies the hard\n\nlook requirement. See Hodges, 300 F.3d at 446–47.\n\n And after taking that hard look, the Agencies’ decision not to prepare an SEIS was\n\nnot arbitrary or capricious. See Hughes River, 81 F.3d at 443. SOS cites improved\n\nerosion rates and an increased supply of sand as new factors that the Agencies should\n\nhave considered when deciding whether to prepare an SEIS. However, erosion and sand\n\nsupply were not the Agencies’ only reasons for initially rejecting beach nourishment in\n\nthe 2008 EIS. The Agencies also cited independent concerns such as inadequate\n\nprotection against future breaches, risks of overwash, and incompatibility with the\n\n 15\n\fmission of a neighboring wildlife refuge. It was not arbitrary or capricious for the\n\nAgencies to decline to reconsider beach nourishment alternatives in an SEIS when the\n\nnew information proffered by SOS did not implicate all of the Agencies’ independently\n\nadequate reasons for initially rejecting beach nourishment.\n\n Accordingly, the Agencies were not required to prepare an SEIS to consider the\n\nalignment of the Jug-Handle Bridge or to consider beach nourishment alternatives. Their\n\nenvironmental analyses therefore do not violate NEPA in this respect.\n\n\n\n B.\n\n SOS also contends that the Agencies’ environmental analyses violate NEPA\n\nbecause they do not adequately consider the environmental effects of construction in the\n\nRodanthe area. Specifically, SOS argues that the effects of construction traffic and haul\n\nroads are not adequately addressed in the 2016 EA and that any discussion of these issues\n\nin the 2008 EIS is irrelevant because that document focuses on a larger area.\n\n NEPA requires agencies to consider all “significant environmental impacts,” 40\n\nC.F.R. § 1502.1, which can include impacts caused by the use of construction roads and\n\nincreased traffic. See, e.g., Arlington Coal. on Transp. v. Volpe, 458 F.2d 1323, 1332\n\n(4th Cir. 1972) (explaining that NEPA applies to highway construction projects).\n\nAccordingly, if construction roads and traffic are expected to affect the environment near\n\nan agency project, the agency must provide “full and fair discussion” of those effects and\n\nincorporate them into its comparison of alternatives. 40 C.F.R. § 1502.1.\n\n\n\n 16\n\f Here, the Agencies adequately considered the effects of construction traffic as a\n\nresult of the Jug-Handle Bridge in the 2016 ROD. Specifically, the Agencies explained\n\nthat a temporary construction easement would be necessary to support traffic during\n\nconstruction but noted that “[t]he land affected will be restored after construction is\n\ncompleted.” J.A. 1559. While the 2016 ROD does not compare the construction traffic\n\neffects of the Jug-Handle Bridge with those of other proposed alternatives, the Agencies\n\ndid perform that comparison in the 2013 EA and the 2016 EA and still found the bridge\n\nto be the LEDPA. The Agencies also specifically considered the environmental effects of\n\nhaul roads in the 2008 EIS. 6\n\n We therefore cannot say that the Agencies did not provide “full and fair\n\ndiscussion” of the effects of construction traffic or haul roads when they selected the Jug-\n\nHandle Bridge among alternatives. See 40 C.F.R. § 1502.1. Accordingly, the Agencies\n\ndid not violate NEPA here, and we affirm the district court.\n\n\n\n\n 6\n To be sure, that discussion did not explicitly consider haul roads in the Rodanthe\narea. However, it is unclear from the record whether the Agencies actually plan to use\nhaul roads for the Jug-Handle Bridge project. See, e.g., J.A. 214 (containing a\ndeclaration from an NCDOT engineer stating that NCDOT and its contractor decided not\nto pursue a previously-discussed haul road in connection with a barge because shallow\nwater depths would make it impracticable). Regardless, NEPA does not compel the\nAgencies to specifically consider the environmental impacts of haul roads so long as they\nadequately examine the environmental consequences of the Jug-Handle Bridge project,\nincluding construction impacts, as a whole. See 40 C.F.R. § 1502.2(b) (“Impacts shall be\ndiscussed [in the EIS] in proportion to their significance.”).\n\n 17\n\f C.\n\n Finally, SOS contends that the Agencies violated NEPA because their choice of\n\nthe Jug-Handle Bridge did not follow from their NEPA analysis but, rather, was a\n\npredetermined result of the Settlement. NEPA “prohibits agencies from preparing an EIS\n\nsimply to ‘justify [] decisions already made.’” Nat’l Audubon Soc’y, 422 F.3d at 199\n\n(quoting 40 C.F.R. § 1502.2(g)) (alteration in original). That is because, under NEPA,\n\nagencies that have yet to issue a final decision may not “commit resources prejudicing\n\nselection of alternatives,” 40 C.F.R. § 1502.2(f), nor may they take any action that would\n\n“[l]imit the choice of reasonable alternatives,” 40 C.F.R. § 1506.1(a). An EIS based upon\n\na predetermined choice that a certain alternative will be selected would violate these\n\nprinciples because it would not allow the agency to fully consider all alternatives.\n\n We conclude that the Agencies’ choice of the Jug-Handle Bridge was not\n\nimpermissibly predetermined. We consider, in turn, the Agencies’ objective\n\nenvironmental analyses, the language of the Settlement, and the role of documents\n\ngenerated during negotiation of the Settlement.\n\n\n\n i.\n\n First, SOS contends that flaws in the Agencies’ environmental analyses reveal that\n\ntheir choice of the Jug-Handle Bridge was predetermined by the Settlement. In alleging\n\nthat the environmental analyses were inadequate, it primarily relies upon arguments that\n\nwe have already discussed--namely, that the Agencies failed to fully consider the new\n\nalignment of the bridge, the feasibility of beach nourishment alternatives, and the effects\n\n 18\n\fof construction traffic and haul roads. SOS contends that these flaws exist because the\n\nAgencies prematurely decided to choose the Jug-Handle Bridge after the Settlement.\n\n Under our precedent, “the evidence we look to in determining whether\n\n[predetermination] has taken place consists of the environmental analysis itself.” 7 Nat’l\n\nAudubon Soc’y, 422 F.3d at 199. In National Audubon Society, in reviewing allegations\n\nthat an agency had settled on a certain outcome before preparing its EIS, we declined to\n\nlook to the agency’s internal documents and emails. Id. Instead, we limited the scope of\n\nour inquiry to the agency’s objective environmental analysis, reasoning that “[w]here an\n\nagency has merely engaged in post hoc rationalization, there will be evidence of this in its\n\nfailure to comprehensively investigate the environmental impact of its actions and\n\nacknowledge their consequences.” Id. Accordingly, our analysis focuses on whether an\n\nagency’s objective environmental analyses demonstrate evidence of predetermination.\n\n Here, when we examine Agencies’ environmental analyses, we cannot say that\n\nthey violated NEPA by selecting the Jug-Handle Bridge following the Settlement. To be\n\nsure, the Agencies changed their preferred alternative from the easement bridge to the\n\nJug-Handle Bridge following the Settlement. But that change alone does not mean that\n\nthe Agencies’ choice was predetermined, particularly where members of the Merger\n\nTeam had expressed concerns about the easement bridge as far back as 2013. And when\n\nwe look to the Agencies’ environmental analyses here, those analyses satisfied NEPA’s\n\n\n 7\n We note that some circuits look beyond the objective environmental analysis for\nevidence of predetermination. See, e.g., Forest Guardians v. U.S. Fish & Wildlife Serv.,\n611 F.3d 692, 716–17 (10th Cir. 2010) (declining to adopt the Fourth Circuit’s rule).\n\n 19\n\frequirements. See discussion supra Sections II.A., II.B. We do not see, and SOS cannot\n\nidentify, any evidence that the Agencies “fail[ed] to comprehensively investigate” and\n\nevaluate the environmental impacts of the Jug-Handle Bridge or the other alternatives.\n\nNat’l Audubon Soc’y, 422 F.3d at 199. The EAs and EIS prepared by the Agencies do\n\nnot, on their faces, show evidence of predetermination.\n\n SOS cites to cases from the Ninth and Tenth Circuits to contend that courts have\n\nfound predetermination based on contractual commitments made by an agency before the\n\nNEPA process was complete. See Davis v. Mineta, 302 F.3d 1104, 1112 (10th Cir. 2002)\n\n(holding that a contract requiring a consultant to recommend that a project had no\n\nsignificant environmental impact before actually preparing an EA violated NEPA);\n\nMetcalf v. Daley, 214 F.3d 1135, 1145 (9th Cir. 2000) (same, regarding a contract\n\nrequiring an agency to make a proposal for a specific alternative before preparing an EA).\n\nHowever, these cases are distinguishable because they involved contracts that agencies\n\nentered into before conducting any environmental analysis at all; in contrast, the\n\nSettlement here, which the Agencies and the Environmental Groups entered into in 2015,\n\nwas preceded by a number of environmental analyses, including the 2008 EIS, the 2010\n\nEA, and the 2013 EA. And when we examine each of these environmental analyses, we\n\nfind no evidence of predetermination warranting reversal.\n\n\n\n ii.\n\n Although circuit precedent limits our predetermination inquiry to the\n\n“environmental analysis itself,” id., SOS nonetheless urges us to consider the Settlement\n\n 20\n\fas evidence that the Agencies’ choice was predetermined. But even if we look to the\n\nSettlement, that document does not support SOS’s claim. The Settlement only required\n\nNCDOT to identify the Jug-Handle Bridge as its preferred alternative and to seek Merger\n\nTeam concurrence that the Jug-Handle Bridge was the LEDPA. These conditions do not\n\nrequire the Agencies to select the Jug-Handle Bridge as the final approved alternative for\n\nthis project. For instance, it remained possible that the Agencies’ environmental analyses\n\nwould demonstrate that the Jug-Handle Bridge was not the LEDPA. Additionally, the\n\nAgencies’ preferences alone could not bind the entire Merger Team, which was\n\nultimately responsible for approving the final alternative, because the parties to the\n\nSettlement comprise only three of the ten state and federal agencies represented on the\n\nMerger Team. 8 This does not constitute predetermination.\n\n\n\n iii.\n\n SOS also urges us to consider external documents generated during the negotiation\n\nof the Settlement as evidence of predetermination and to reverse the district court’s denial\n\nof SOS’s motion to include these documents in the record. We decline to do so because\n\nthe district court did not abuse its discretion in denying this motion. See Fort Sumter\n\nTours, Inc. v. Babbitt, 66 F.3d 1324, 1335–36 (4th Cir. 1995) (explaining that we review\n\n 8\n To be sure, the parties to the Settlement represented three of the four Lead\nAgencies tasked with decisionmaking if the Merger Team could not reach consensus.\nBut, as discussed, the Settlement only required those agencies to seek concurrence that\nthe Jug-Handle Bridge was the LEDPA; it did not require them to go beyond the\nobjective environmental analysis to choose the Jug-Handle Bridge if it was not, in fact,\nthe LEDPA.\n\n 21\n\fa district court’s decision whether to expand the administrative record for abuse of\n\ndiscretion).\n\n Federal courts base their review of agency decisions on “the ‘whole record’\n\ncompiled by the agency.” Citizens to Pres. Overton Park, Inc. v. Volpe, 401 U.S. 402,\n\n419 (1971) (quoting 5 U.S.C. § 706), abrogated on other grounds by Califano v. Sanders,\n\n430 U.S. 99 (1977). We may supplement the record as presented by the agency if the\n\n“bare record” does not reveal the agency’s reasoning or if it appears that the agency acted\n\nin bad faith. Id. at 420. Otherwise, “inquiry into the mental processes of administrative\n\ndecisionmakers is usually to be avoided.” Id.\n\n Here, the record as presented by the Agencies reveals their reasoning, as we have\n\ndiscussed, and the district court found no evidence that the Agencies acted in bad faith.\n\nThe district court also determined that there was no evidence that the Agencies actually\n\nreviewed the documents put forth by SOS as part of their decision to approve the Jug-\n\nHandle Bridge. We hold that the district court did not abuse its discretion by denying\n\nSOS’s motion to supplement the record, and accordingly, our review is limited to the\n\nrecord as compiled by the Agencies.\n\n SOS contends that, even if we cannot consider these documents as part of the\n\nadministrative record, we should nevertheless consider them as extra-record evidence. It\n\nis true that “in the NEPA context, courts generally have been willing to look outside the\n\nrecord when assessing the adequacy of an EIS or a determination that no EIS is\n\nnecessary.” Ohio Valley Envtl. Coal. v. Aracoma Coal Co., 556 F.3d 177, 201 (4th Cir.\n\n2009). However, we have explained that extra-record evidence in that context is\n\n 22\n\fprimarily useful “to inform the court about environmental factors that the agency may not\n\nhave considered.” Id. (emphasis added). Here, the proffered documents would do\n\nnothing to aid the court’s understanding of the environmental concerns at issue, as they\n\nconcern the legal terms of the Settlement between the Agencies and the Environmental\n\nGroups. Therefore, the district court properly excluded them, and we decline to consider\n\nthem now.\n\n There is superficial appeal in suggesting that the Agencies’ choice was\n\npredetermined because the Settlement yielded a preferred alternative. However, that\n\nconclusion is not legally or factually supported by the record. Legally, our analysis is\n\ncabined to the environmental analysis itself, with which we find no issues meriting\n\nreversal. And factually, we see no evidence that the Merger Team was forced to approve\n\nthe Jug-Handle Bridge.\n\n In sum, the Agencies did not violate NEPA when they approved the Jug-Handle\n\nBridge because they were not required to prepare an SEIS, they adequately evaluated the\n\neffects of construction traffic, and they did not rely on a predetermined choice among\n\nalternatives. We therefore affirm the district court’s grant of summary judgment in favor\n\nof the Agencies.\n\n\n\n III.\n\n Finally, SOS contends that the district court erred when it denied SOS’s motion to\n\namend its complaint with claims related to the Pappy’s Lane Wreck. Specifically, SOS\n\nalleges that the Agencies violated § 4(f) by approving a transportation project that\n\n 23\n\fthreatens to harm the land of a site of historic significance because the Jug-Handle Bridge\n\nwill pass above the wreck--the site of a World War II vessel.\n\n We review a district court’s denial of a motion to amend the complaint for abuse\n\nof discretion. See Laber v. Harvey, 438 F.3d 404, 428 (4th Cir. 2006) (en banc).\n\nHowever, if the district court denied such a motion on the grounds that the amendment\n\nwould have been futile, we review its legal conclusions de novo. United States ex. rel.\n\nAhumada v. NISH, 756 F.3d 268, 274 (4th Cir. 2014).\n\n A party “may amend its pleading once as a matter of course” before the opposing\n\nparty files a responsive pleading. Fed. R. Civ. P. 15(a)(1). After that time, a party may\n\nonly amend its pleading with the consent of the opposing party or with leave of the court,\n\nand “[t]he court should freely give leave when justice so requires.” Fed. R. Civ. P.\n\n15(a)(2). Courts may deny leave to amend a pleading if the amendment would have been\n\nfutile. Laber, 438 F.3d at 426. A proposed amendment is futile when it is “clearly\n\ninsufficient or frivolous on its face.” Johnson v. Oroweat Foods Co., 785 F.2d 503, 510\n\n(4th Cir. 1986). A proposed amendment is also futile if the claim it presents would not\n\nsurvive a motion to dismiss. Perkins v. United States, 55 F.3d 910, 917 (4th Cir. 1995).\n\n Here, the district court found that SOS’s proposed amendment would be futile for\n\ntwo alternative reasons. First, it determined that, to the extent that SOS sought to assert\n\nthat the 2016 EA was no longer valid in light of new information about the shipwreck,\n\nthat claim would be unripe where the Agencies had not yet made a decision concerning\n\nthe significance of the new information. Second, it determined that, to the extent that\n\nSOS sought to assert that the 2016 EA was inadequate when issued, that claim would fail\n\n 24\n\fbecause it would ask the Agencies to consider information that was not discovered until\n\nafter the 2016 EA was issued. For the reasons that follow, we affirm the district court’s\n\ndenial of SOS’s motion to amend its complaint.\n\n First, to the extent that SOS’s proposed amendments contend that the Agencies\n\nfailed to consider new information about the shipwreck, those amendments would be\n\nfutile because they would raise a claim that is not yet ripe for review. 9 Courts may only\n\nreview “final agency action,” 5 U.S.C. § 704, and challenges to agency decisions that are\n\nyet to be made are not ripe for review. See Pashby v. Delia, 709 F.3d 307, 317 (4th Cir.\n\n2013) (holding that a claim is only ripe when it involves a formalized administrative\n\ndecision). Here, the Agencies have not yet made a final decision about the significance\n\nof new information revealing that the shipwreck was a World War II assault vessel.\n\nTherefore, any claim that the Agencies did not properly account for this information\n\nwould be unripe, and any amendment seeking to add such a claim would be futile.\n\n Second, SOS contends on appeal that it is challenging the adequacy of the 2016\n\nROD’s treatment of the Pappy’s Lane Wreck rather than the Agencies’ failure to consider\n\nnew information about the shipwreck’s significance. Specifically, SOS contends that,\n\nbecause the Agencies knew that the shipwreck was eligible for listing on the National\n\n\n 9\n SOS appears to have abandoned this argument on appeal. See Appellants’ Br. at\n53 (contending that the district court “fundamentally misread [SOS’s] motion” when it\ndenied it on ripeness grounds because “[t]he [new] allegations were about the\ninadequacies of the [2016] ROD and the process leading up to that document”)\n(emphasis added). Nevertheless, we discuss it because it implicates concerns related to\nthe argument that SOS does raise on appeal regarding the adequacy of the 2016 ROD\nwhen issued.\n\n 25\n\fRegister of Historic Places, they were not authorized to build a bridge in its path unless\n\nthey determined that there was “no prudent and feasible alternative to using that land”\n\nand that the “project include[d] all possible planning to minimize harm . . . resulting from\n\nthe use.” See 49 U.S.C. § 303(c).\n\n However, as the district court explained, SOS cannot contend that it was\n\nchallenging the adequacy of the 2016 ROD’s treatment of the shipwreck when its claims\n\n“rest[] upon recent discovery that the Pappy[’s] Lane Wreck contains a World War II\n\nvessel.” Save Our Sound OBX, Inc. v. N.C. Dep’t of Transp., No. 2:17-CV-4-FL, 2017\n\nWL 7048561, at *5 (E.D.N.C. Dec. 5, 2017). Instead, the Agencies satisfied regulatory\n\nrequirements when, based on what they knew about the Pappy’s Lane Wreck, they\n\nordered data recovery and decided that the shipwreck did not merit preservation in place.\n\nArguments that the Agencies should have gone further are grounded in new information\n\nand, therefore, not reviewable until the Agencies issue a final decision, as discussed\n\nabove. We therefore affirm the district court’s denial of SOS’s motion to amend its\n\ncomplaint.\n\n\n\n IV.\n\n We affirm the district court because the Agencies did not violate NEPA or the\n\nDTA when they issued the 2016 ROD selecting the Jug-Handle Bridge and because the\n\ndistrict court did not abuse its discretion when it denied SOS’s motions to supplement the\n\nadministrative record and to amend the complaint.\n\n AFFIRMED\n\n 26\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: SAVE OUR SOUND OBX, INC.; Mark Haines ; Jer Mehta; Glenn Stevens ; David Hadley ; Thomas Aschmoneit; Richard Ayella, Plaintiffs - Appellants, v. NORTH CAROLINA DEPARTMENT OF TRANSPORTATION; Federal Highway Administration; John F. Sullivan, III, in His Official Capacity as Division Administrator for the Federal Highway Administration; James H. Trogdon, III, in His Official Capacity as Secretary of the North Carolina Department of Transportation, Defendants - Appellees, and Defenders of Wildlife; National Wildlife Refuge Association, Intervenors/Defendants - Appellees.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-23\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 18-1649\\n\\n\\nSAVE OUR SOUND OBX, INC.; MARK HAINES; JER MEHTA; GLENN\\nSTEVENS; DAVID HADLEY; THOMAS ASCHMONEIT; RICHARD\\nAYELLA,\\n\\n Plaintiffs – Appellants,\\n\\nv.\\n\\nNORTH CAROLINA DEPARTMENT OF TRANSPORTATION; FEDERAL\\nHIGHWAY ADMINISTRATION; JOHN F. SULLIVAN, III, in his official\\ncapacity as Division Administrator for the Federal Highway Administration;\\nJAMES H. TROGDON, III, in his official capacity as Secretary of the North\\nCarolina Department of Transportation,\\n\\n Defendants – Appellees,\\n\\nand\\n\\nDEFENDERS OF WILDLIFE; NATIONAL WILDLIFE REFUGE\\nASSOCIATION,\\n\\n Intervenors/Defendants – Appellees.\\n\\n\\nAppeal from the United States District Court for the Eastern District of North Carolina, at\\nElizabeth City. Louise W. Flanagan, District Judge. (2:17-cv-00004-FL)\\n\\n\\nArgued: December 11, 2018 Decided: January 23, 2019\\n\\n\\nBefore NIEMEYER, DUNCAN, and QUATTLEBAUM, Circuit Judges.\\n\\fAffirmed by published opinion. Judge Duncan wrote the opinion, in which Judge\\nNiemeyer and Judge Quattlebaum joined.\\n\\n\\nARGUED: David Ari Schnitzer, GIBSON, DUNN & CRUTCHER LLP, Washington,\\nD.C., for Appellants. Thekla Hansen-Young, UNITED STATES DEPARTMENT OF\\nJUSTICE, Washington, D.C.; Colin Justice, NORTH CAROLINA DEPARTMENT OF\\nJUSTICE, Raleigh, North Carolina, for Appellees. ON BRIEF: Michael K. Murphy,\\nKyle N. Guest, GIBSON, DUNN & CRUTCHER LLP, Washington, D.C., for\\nAppellants. Jeffrey H. Wood, Acting Assistant Attorney General, Eric Grant, Deputy\\nAssistant Attorney General, Andrew C. Mergen, Robert J. Lundman, Carter F. Thurman,\\nAppellate Section, Environment and Natural Resources Division, UNITED STATES\\nDEPARTMENT OF JUSTICE, Washington, D.C.; Josh Stein, Attorney General,\\nOFFICE OF THE ATTORNEY GENERAL OF NORTH CAROLINA, Raleigh, North\\nCarolina; Scott T. Slusser, Special Deputy Attorney General, Mollie Cozart, Assistant\\nAttorney General, NORTH CAROLINA DEPARTMENT OF JUSTICE, Raleigh, North\\nCarolina, for Appellees North Carolina Department of Transportation, Federal Highway\\nAdministration, John F. Sullivan, III, and James H. Trogdon, III. Kimberley Hunter,\\nNicholas S. Torrey, SOUTHERN ENVIRONMENTAL LAW CENTER, Chapel Hill,\\nNorth Carolina, for Appellees Defenders of Wildlife and National Wildlife Refuge\\nAssociation.\\n\\n\\n\\n\\n 2\\n\\fDUNCAN, Circuit Judge:\\n\\n Appellants Save Our Sound OBX, Inc. and its members, residents and vacationers\\n\\nfrom North Carolina’s Outer Banks, (collectively “SOS”) challenge the decision of the\\n\\nNorth Carolina Department of Transportation (the “NCDOT”), the Federal Highway\\n\\nAdministration (the “FHWA”), and their administrators (collectively “the Agencies”) to\\n\\nreplace a segment of North Carolina Highway 12 (“NC-12”) with a bridge across the\\n\\nPamlico Sound (the “Jug-Handle Bridge”). The district court granted the Agencies’\\n\\nmotion for summary judgment, finding that they did not violate the National\\n\\nEnvironmental Policy Act (the “NEPA”), 42 U.S.C. § 4321 et seq., or the Department of\\n\\nTransportation Act (the “DTA”), 49 U.S.C. § 301 et seq., when they approved the bridge.\\n\\nSOS challenges that ruling on appeal. For the reasons that follow, we affirm.\\n\\n\\n\\n I.\\n\\n This case involves a segment of NC-12, which is the main roadway passing\\n\\nthrough the Outer Banks of North Carolina. State and federal agencies have been\\n\\nworking for several years to update and improve NC-12 because of its susceptibility to\\n\\nweather damage and erosion.\\n\\n Like many highway construction projects, the NC-12 project required cooperation\\n\\namong state and federal agencies. For instance, in North Carolina, NCDOT has authority\\n\\nover highway construction, while FWHA supplies federal funds for highway projects.\\n\\nThe agencies tasked with improving NC-12, including NCDOT and FHWA, formed a\\n\\nMerger Team to coordinate decisionmaking and regulatory compliance for the NC-12\\n\\n 3\\n\\fproject. 1 The Merger Team was responsible for ensuring that the NC-12 project\\n\\ncomplied with the requirements of NEPA and the DTA, among other regulations.\\n\\n SOS challenges certain agency decisions in the NC-12 project under NEPA and\\n\\nthe DTA. Accordingly, we first provide a brief overview of the requirements of those\\n\\nstatutes before turning to the specific facts and procedural history of this appeal.\\n\\n\\n\\n A.\\n\\n The first statute at issue in this appeal is NEPA. Pursuant to NEPA, 42 U.S.C.\\n\\n§ 4321 et seq., and its implementing regulations, government agencies considering\\n\\ncertain projects must evaluate whether the project would have a significant impact on the\\n\\nenvironment by preparing an Environmental Assessment (an “EA”). Id. § 4332(C); 40\\n\\nC.F.R. § 1508.9; see id. § 1508.18 (defining the types of federal actions to which NEPA\\n\\napplies). If the project would have a significant impact, the agency must prepare an\\n\\nEnvironmental Impact Statement (an “EIS”). 42 U.S.C. § 4332(C). The agency is\\n\\nresponsible for ensuring that the EIS complies with various regulatory requirements. See\\n\\n40 C.F.R. § 1502.1 et seq. For instance, the EIS must “provide full and fair discussion”\\n\\nof any significant environmental impacts of a proposed action. 40 C.F.R. § 1502.1.\\n\\n 1\\n The Merger Team was comprised of representatives from NCDOT, FHWA, the\\nU.S. Fish and Wildlife Service, the U.S. Army Corps of Engineers, the U.S.\\nEnvironmental Protection Agency, the National Marine Fisheries Service, the National\\nPark Service, the North Carolina Department of Cultural Resources, the North Carolina\\nWildlife Resources Commission, and three divisions of the North Carolina Department of\\nEnvironmental and Natural Resources (the “NCDENR”) (now named the North Carolina\\nDepartment of Environmental Quality)--the Division of Water Resources, the Division of\\nCoastal Management, and the Division of Marine Fisheries.\\n\\n 4\\n\\fAdditionally, the agency must “[r]igorously explore and objectively evaluate all\\n\\nreasonable alternatives” that could “avoid or minimize adverse impacts.” Id.\\n\\n§§ 1502.1, 1502.14. The agency is permitted, however, to identify a preference among\\n\\nalternatives based on non-environmental considerations, such as economic factors or the\\n\\nagency’s statutory mission. Id. § 1505.2(b). If the agency has a preferred alternative,\\n\\nNEPA requires the agency to identify that preference in the EIS. Id. § 1502.14. NEPA\\n\\nalso requires the agency to prepare a supplemental EIS (an “SEIS”) if significant new\\n\\ninformation or environmental changes come to light after the agency prepares an EIS. Id.\\n\\n§ 1502.9(c). After the agency makes its final decision about which alternative to pursue,\\n\\nit publishes a record of decision (an “ROD”) explaining its choice. Id. § 1505.2.\\n\\n We now turn to the second statute at issue: the DTA. The DTA contains\\n\\nsubstantive requirements for government transportation projects. 49 U.S.C. § 301 et seq.\\n\\nRelevant here, the so-called “§ 4(f)” requirements 2 concern transportation projects that\\n\\nrequire the use of publicly owned land of a wildlife refuge or a significant historic site.\\n\\nId. § 303(c). Historic sites include structures “included in, or eligible for inclusion in,”\\n\\nthe National Register of Historic Places. 23 C.F.R. § 774.17. The Secretary of\\n\\nTransportation may only approve such projects if there is no “feasible and prudent”\\n\\nalternative to using that land and the “project includes all possible planning to minimize\\n\\nharm . . . resulting from the use.” Id. § 303(c). If there is no feasible and prudent\\n\\n\\n 2\\n The DTA explains that “[t]he requirements of [49 U.S.C. § 303] are commonly\\nreferred to as section 4(f) requirements” in reference to a previous version of the statute.\\n49 U.S.C. § 303(f)(1).\\n\\n 5\\n\\falternative, the Secretary may only approve the alternative that “[c]auses the least overall\\n\\nharm in light of the [DTA’s] preservation purpose.” 23 C.F.R. § 774.3(c). Relevant\\n\\nconsiderations in selecting the least harmful alternative include whether harm to the land\\n\\ncan be mitigated, whether harm to the land affects the attributes qualifying that land for\\n\\nprotection, and whether the alternative meets the needs of the project. Id.\\n\\n\\n\\n B.\\n\\n Having established the relevant framework, we consider the facts of this case.\\n\\nSOS’s claims in this litigation concern the Agencies’ environmental analysis under\\n\\nNEPA and the DTA with respect to a segment of NC-12 that passes from the southern\\n\\nedge of Bodie Island to the village of Rodanthe. For this segment, the Merger Team was\\n\\nresponsible for preparing EAs and EISs pursuant to NEPA and for determining which\\n\\nproposed plan for the project was the least environmentally-damaging practicable\\n\\nalternative (the “LEDPA”) pursuant to section 404 of the Clean Water Act, 33 U.S.C.\\n\\n§ 1344, among other requirements. 3 See 40 C.F.R. § 230.10 (setting out the LEDPA\\n\\nrequirement).\\n\\n In 2008, the Merger Team issued an EIS and § 4(f) evaluation (the “2008 EIS”)\\n\\nfor improving NC-12. For the segment at issue here, the 2008 EIS included discussion of\\n\\nseveral alternatives, including a proposed bridge in the Pamlico Sound near Rodanthe\\n\\n\\n\\n 3\\n Section 404 of the Clean Water Act regulates activities involving “the discharge\\nof dredged or fill material” into navigable waters. Id.\\n\\n 6\\n\\f(the “Bridge South alternative”) and proposals involving beach nourishment. An EA in\\n\\n2010 (the “2010 EA”) further developed these alternatives.\\n\\n The Merger Team released an updated EA in 2013 (the “2013 EA”) to account for\\n\\nenvironmental changes after the 2010 EA, including the effects of Hurricane Irene in\\n\\n2011. The 2013 EA identified four alternatives for the segment at issue: (1) the so-called\\n\\nJug-Handle Bridge, a bridge extending out into the Pamlico Sound (also referred to in the\\n\\nenvironmental analyses as the “Bridge on New Location”); 4 (2) an easement bridge on\\n\\nthe existing NC-12 location; (3) beach nourishment; and (4) an easement bridge\\n\\ncombined with beach nourishment. The Merger Team did not study the beach\\n\\nnourishment alternatives in depth in the 2013 EA because, at a 2011 meeting, it had\\n\\nalready determined not to pursue them after experts reported on a “high erosion rate and a\\n\\nlack of sand supply.” J.A. 843. In the 2013 EA, the Merger Team identified the\\n\\neasement bridge as its preferred alternative under NEPA. However, certain members of\\n\\nthe Merger Team objected to finding that the easement bridge was the LEDPA under the\\n\\nClean Water Act, citing concerns about its location within the surf zone, additional\\n\\npermits associated with erosion setback requirements, and its impact on a nearby wildlife\\n\\nrefuge. See J.A. 1745–47.\\n\\n In the meantime, environmental groups Defenders of Wildlife and the National\\n\\nWildlife Refuge Association (intervenors here, collectively the “Environmental Groups”)\\n\\nbrought suit in federal court to challenge the Agencies’ NEPA and § 4(f) determinations\\n\\n 4\\n The Jug-Handle Bridge was a modified version of the Bridge South alternative\\nthat was introduced in the 2008 EIS and further developed in the 2010 EA.\\n\\n 7\\n\\fwith respect to a different segment of NC-12 in the Outer Banks--the Bonner Bridge,\\n\\nwhich connects Bodie Island and Hatteras Island to the north of Rodanthe. See Defs. of\\n\\nWildlife v. N.C. Dep’t of Transp., 762 F.3d 374 (4th Cir. 2014). The Environmental\\n\\nGroups and the Agencies eventually reached an agreement in 2015 (the “Settlement”). 5\\n\\nThe Settlement required NCDOT to identify the Jug-Handle Bridge as its preferred\\n\\nalternative for the segment of NC-12 at issue in this case. It also required NCDOT to\\n\\nseek Merger Team concurrence that the Jug-Handle Bridge was the LEDPA. In doing so,\\n\\nit stated that nothing in the Settlement “requires or should be interpreted to predetermine\\n\\nthe choice” of the Jug-Handle Bridge as the final selected alternative. J.A. 1090. In\\n\\nexchange, the Environmental Groups dismissed the Bonner Bridge suit and agreed not to\\n\\nchallenge the Agencies in court if the Jug-Handle Bridge was determined to be the\\n\\nLEDPA and was ultimately selected in the ROD for this project.\\n\\n After a 2015 meeting, the Agencies identified the Jug-Handle Bridge as their\\n\\npreferred alternative. Following public comment and detailed studies, the Merger Team\\n\\ndetermined that the Jug-Handle Bridge was the LEDPA. In 2016, the Merger Team\\n\\nreleased a revised EA (the “2016 EA”) to evaluate the environmental impacts of the Jug-\\n\\nHandle Bridge and its associated construction activities. Later that year, the Merger\\n\\nTeam issued an ROD (the “2016 ROD”) formally approving the Jug-Handle Bridge.\\n\\n In addition to authorizing construction of the Jug-Handle Bridge, the 2016 ROD\\n\\nalso addressed concerns relating to a shipwreck in the proposed bridge’s path known as\\n\\n 5\\n NCDENR was also a party to the Settlement and is represented on the Merger\\nTeam, though it is not a defendant here.\\n\\n 8\\n\\fthe Pappy’s Lane Wreck. The shipwreck is eligible for listing on the National Register of\\n\\nHistoric Places. Because of the shipwreck’s historical significance, the 2016 ROD\\n\\nordered a data recovery project on the shipwreck, which later uncovered evidence that the\\n\\nshipwreck was a World War II assault vessel. The Merger Team has not yet determined\\n\\nhow it will respond to this new information.\\n\\n\\n\\n C.\\n\\n We now turn to the procedural history of this litigation, which began when SOS\\n\\nsued the Agencies on February 2, 2017. A month later, the Environmental Groups\\n\\nintervened in the suit in support of the Agencies. In its complaint, SOS alleged, as\\n\\nrelevant here, that the Agencies’ approval of the Jug-Handle Bridge violated NEPA\\n\\nbecause that decision was predetermined by the Settlement. To show evidence of\\n\\npredetermination, SOS moved to supplement the administrative record before the district\\n\\ncourt to include documents related to the negotiation of the Settlement on the grounds\\n\\nthat those documents were before the Agencies when they made their decision to select\\n\\nthe Jug-Handle Bridge. The district court denied this motion.\\n\\n Later, SOS moved to amend its complaint to add claims related to construction\\n\\nimpacts in Rodanthe and to the Pappy’s Lane Wreck. Specifically, SOS contended that\\n\\nthe Agencies’ environmental analyses did not adequately consider the effects of\\n\\nconstruction or the historic significance of the Pappy’s Lane Wreck. The district court\\n\\ngranted the motion as to construction impacts but denied it as to the shipwreck.\\n\\n\\n\\n 9\\n\\f SOS, the Agencies, and the Environmental Groups each filed cross-motions for\\n\\nsummary judgment on the issue of whether the Agencies’ environmental analyses\\n\\nviolated NEPA or the DTA. The district court granted the Agencies’ and Environmental\\n\\nGroups’ motions for summary judgment and denied SOS’s motion.\\n\\n SOS appeals the district court’s grant of the Agencies’ motion for summary\\n\\njudgment and its denial of SOS’s motion to amend its complaint. SOS contends that the\\n\\nAgencies were not entitled to summary judgment because the Agencies’ environmental\\n\\nanalyses violated NEPA. It also contends that the district court erred in denying SOS’s\\n\\nmotion to amend its complaint with claims related to the Pappy’s Lane Wreck. We\\n\\ndiscuss SOS’s NEPA claims and its motion to amend its complaint, in that order.\\n\\n\\n\\n II.\\n\\n SOS contends that the Agencies violated NEPA when they selected the Jug-\\n\\nHandle Bridge for the NC-12 project. “We review a grant of summary judgment de\\n\\nnovo,” Defs. of Wildlife, 762 F.3d at 392, and, accordingly, review the Agencies’ actions\\n\\ndirectly, pursuant to the Administrative Procedure Act (the “APA”). The APA directs us\\n\\nto overturn agency actions if they are “arbitrary, capricious, an abuse of discretion, or\\n\\notherwise not in accordance with law.” 5 U.S.C. § 706(2)(A). Our precedent also guides\\n\\nthe scope of our review of the sufficiency of an agency’s NEPA analysis. Nat’l Audubon\\n\\nSoc’y v. Dep’t of Navy, 422 F.3d 174, 185, 199 (4th Cir. 2005). In conducting this\\n\\nreview, “we must make a searching and careful inquiry into the facts” and examine\\n\\nwhether the decision was based on consideration of the relevant factors. Id. at 185\\n\\n 10\\n\\f(citation and internal quotation marks omitted). However, we do not “second-guess\\n\\nagency decisions, so long as the agency has given a hard look at the environmental\\n\\nimpacts of its proposed action.” Id. at 199.\\n\\n Under this standard of review, we affirm because the Agencies did not violate\\n\\nNEPA in approving the Jug-Handle Bridge. We consider SOS’s arguments that the\\n\\nAgencies’ environmental analyses violated NEPA because (1) the Agencies failed to\\n\\nprepare an SEIS with regards to the Jug-Handle Bridge and beach nourishment\\n\\nalternatives before issuing the 2016 ROD, (2) the Agencies failed to adequately consider\\n\\nthe impacts of construction, and (3) the Settlement impermissibly predetermined the\\n\\nAgencies’ choice of the Jug-Handle Bridge.\\n\\n\\n\\n A.\\n\\n First, SOS contends that the Agencies’ NEPA analysis was deficient because the\\n\\nAgencies should have prepared an SEIS before approving the Jug-Handle Bridge in the\\n\\n2016 ROD. NEPA requires an agency to prepare an SEIS if “[t]he agency makes\\n\\nsubstantial changes” to a proposed action that implicate environmental concerns or if\\n\\n“[t]here are significant new circumstances or information” that would affect the\\n\\nenvironmental impacts of the proposed action. 40 C.F.R. § 1502.9(c). To merit an SEIS,\\n\\nthe changes “must present a seriously different picture of the environmental impact of the\\n\\nproposed project.” Hughes River Watershed Conservancy v. Glickman, 81 F.3d 437, 443\\n\\n(4th Cir. 1996) (citation and alterations omitted).\\n\\n\\n\\n 11\\n\\f We review an agency’s decision not to prepare an SEIS in two steps, consistent\\n\\nwith our standard of review under NEPA. Id. At step one, we “determine whether the\\n\\nagency took a hard look at the proffered new information.” Id. If the agency concludes\\n\\nafter a preliminary inquiry that the “environmental effect of the change is clearly\\n\\ninsignificant,” its decision not to prepare an SEIS satisfies the hard look requirement.\\n\\nHodges v. Abraham, 300 F.3d 432, 446 (4th Cir. 2002). For instance, in Hodges, we held\\n\\nthat an agency took a hard look at the environmental consequences of its change in plans\\n\\nwhen it explicitly evaluated those consequences and determined that they were not\\n\\nsignificantly different from those discussed in a prior EIS. Id. at 447. We also noted that\\n\\nthe plaintiff in that case “failed to identify any particular risk arising from” the change\\n\\nthat had not already been addressed in the agency’s environmental analyses. Id. Next, at\\n\\nstep two of the SEIS inquiry, we review whether the agency’s decision not to prepare an\\n\\nSEIS after taking a hard look was arbitrary or capricious. Hughes River, 81 F.3d at 443.\\n\\n SOS contends that an SEIS was necessary (1) to evaluate the environmental\\n\\neffects of the Jug-Handle Bridge alternative because it was different from options that\\n\\nhad previously been evaluated and (2) to reconsider alternatives that involved beach\\n\\nnourishment pursuant to new information about sand availability and beach erosion rates.\\n\\nWe address each contention in turn and affirm the district court’s determination that no\\n\\nSEIS was required. Neither of these changes are sufficiently different from the\\n\\ncircumstances initially evaluated in the EIS to merit an SEIS. The Agencies’ decision not\\n\\nto prepare one after taking a hard look at the changes was therefore not arbitrary or\\n\\ncapricious.\\n\\n 12\\n\\f i.\\n\\n Contrary to SOS’s contention, the Agencies were not required to prepare an SEIS\\n\\nwith respect to the Jug-Handle Bridge alternative. SOS argues that the final alignment of\\n\\nthe Jug-Handle Bridge alternative (that is, its path across the Pamlico Sound and its\\n\\nconnection points with the shore) was significantly different from previously evaluated\\n\\nalternatives. Specifically, SOS contends that the bridge’s alignment changed\\n\\nsignificantly because the alternative evaluated in the 2008 EIS was “amorphously\\n\\ndefined” and because the alternative evaluated in the 2010 EA (to which the 2013 EA,\\n\\n2016 EA, and 2016 ROD refer) was “not comparable” to the Jug-Handle Bridge.\\n\\nAppellant’s Br. at 35, 36. It argues that these differences render prior environmental\\n\\nanalyses of those alternatives insufficient to evaluate the environmental effects of the\\n\\nJug-Handle Bridge as approved in the 2016 ROD. We disagree and conclude that the\\n\\nAgencies complied with NEPA when they decided that an SEIS was not warranted by\\n\\nthese changes.\\n\\n At step one, the Agencies took a hard look at changes in the bridge’s alignment in\\n\\nthe 2016 EA. The 2016 EA describes the similarities and differences between the Jug-\\n\\nHandle Bridge as proposed in 2016 and the versions evaluated in the 2013 EA, the 2010\\n\\nEA, and the 2008 EIS. For instance, it explains that the Agencies decided to shift the\\n\\nalignment of the bridge to avoid areas of “dense submerged aquatic vegetation” that fell\\n\\nin the path of previous versions of the bridge. J.A. 1198. The 2016 EA also explains that\\n\\nthe Jug-Handle Bridge’s alignment reduces effects on the community as compared with\\n\\n 13\\n\\fprevious versions because it requires a narrower right-of-way. Because the Agencies\\n\\nwent into detail in their comparison between the Jug-Handle Bridge and previous\\n\\nversions of the bridge, their coverage satisfies the hard look requirement. See Hodges,\\n\\n300 F.3d at 446–47.\\n\\n And, at step two, because the Agencies took the requisite hard look and neither\\n\\ntheir environmental analyses nor SOS identify any particular differences that would merit\\n\\nan SEIS, their decision not to prepare an SEIS was not arbitrary or capricious. See\\n\\nHughes River, 81 F.3d at 443. An SEIS is only required when changes to a project\\n\\npresent a “seriously different picture of the environmental impact.” Id. (alterations and\\n\\ncitation omitted). Based on the discussion presented in the 2016 EA, which compared the\\n\\ndifferent versions of the bridge, it was not arbitrary or capricious for the Agencies to\\n\\ndetermine that the Jug-Handle Bridge’s final alignment did not present a “seriously\\n\\ndifferent picture,” id., than the 2008 EIS, the 2010 EA, or the 2013 EA. The Agencies\\n\\nexplained how the Jug-Handle Bridge was different from previous versions of the bridge,\\n\\nand their explanations do not implicate any significant environmental concerns.\\n\\nAccordingly, their decision not to prepare an SEIS was not arbitrary or capricious.\\n\\n\\n\\n ii.\\n\\n Similarly, the Agencies were not required to prepare an SEIS to reevaluate the\\n\\nfeasibility of alternatives that involved beach nourishment. SOS contends that the\\n\\nAgencies failed to adequately reconsider beach nourishment after new erosion projections\\n\\nwere released and after a 2014 emergency beach nourishment project in the area\\n\\n 14\\n\\fsuccessfully repaired damage from Hurricane Sandy. According to SOS, this new\\n\\ninformation showed that coastal conditions had changed such that erosion would no\\n\\nlonger threaten beach nourishment and that adequate sand was in fact available to\\n\\ncomplete the project.\\n\\n However, the Agencies took the requisite hard look at these new circumstances in\\n\\nthe 2016 EA. See Hughes River, 81 F.3d at 443. The 2016 EA notes that while erosion\\n\\nprojections in the Rodanthe area did decrease, erosion rates in Rodanthe remained\\n\\n“amongst the highest rates along the North Carolina coast.” J.A. 1218. It also discusses\\n\\nthe 2014 emergency beach nourishment project in detail and considers updated\\n\\ninformation about coastal conditions in the area. Specifically, it notes that the 2014\\n\\nemergency beach nourishment project was “essentially one round of nourishment in one\\n\\npart of [NC-12].” J.A. 1227. Finally, it concludes that the Agencies thoroughly\\n\\nconsidered the environmental effects of beach nourishment when they originally\\n\\nevaluated those alternatives in the 2008 EIS. This detailed discussion satisfies the hard\\n\\nlook requirement. See Hodges, 300 F.3d at 446–47.\\n\\n And after taking that hard look, the Agencies’ decision not to prepare an SEIS was\\n\\nnot arbitrary or capricious. See Hughes River, 81 F.3d at 443. SOS cites improved\\n\\nerosion rates and an increased supply of sand as new factors that the Agencies should\\n\\nhave considered when deciding whether to prepare an SEIS. However, erosion and sand\\n\\nsupply were not the Agencies’ only reasons for initially rejecting beach nourishment in\\n\\nthe 2008 EIS. The Agencies also cited independent concerns such as inadequate\\n\\nprotection against future breaches, risks of overwash, and incompatibility with the\\n\\n 15\\n\\fmission of a neighboring wildlife refuge. It was not arbitrary or capricious for the\\n\\nAgencies to decline to reconsider beach nourishment alternatives in an SEIS when the\\n\\nnew information proffered by SOS did not implicate all of the Agencies’ independently\\n\\nadequate reasons for initially rejecting beach nourishment.\\n\\n Accordingly, the Agencies were not required to prepare an SEIS to consider the\\n\\nalignment of the Jug-Handle Bridge or to consider beach nourishment alternatives. Their\\n\\nenvironmental analyses therefore do not violate NEPA in this respect.\\n\\n\\n\\n B.\\n\\n SOS also contends that the Agencies’ environmental analyses violate NEPA\\n\\nbecause they do not adequately consider the environmental effects of construction in the\\n\\nRodanthe area. Specifically, SOS argues that the effects of construction traffic and haul\\n\\nroads are not adequately addressed in the 2016 EA and that any discussion of these issues\\n\\nin the 2008 EIS is irrelevant because that document focuses on a larger area.\\n\\n NEPA requires agencies to consider all “significant environmental impacts,” 40\\n\\nC.F.R. § 1502.1, which can include impacts caused by the use of construction roads and\\n\\nincreased traffic. See, e.g., Arlington Coal. on Transp. v. Volpe, 458 F.2d 1323, 1332\\n\\n(4th Cir. 1972) (explaining that NEPA applies to highway construction projects).\\n\\nAccordingly, if construction roads and traffic are expected to affect the environment near\\n\\nan agency project, the agency must provide “full and fair discussion” of those effects and\\n\\nincorporate them into its comparison of alternatives. 40 C.F.R. § 1502.1.\\n\\n\\n\\n 16\\n\\f Here, the Agencies adequately considered the effects of construction traffic as a\\n\\nresult of the Jug-Handle Bridge in the 2016 ROD. Specifically, the Agencies explained\\n\\nthat a temporary construction easement would be necessary to support traffic during\\n\\nconstruction but noted that “[t]he land affected will be restored after construction is\\n\\ncompleted.” J.A. 1559. While the 2016 ROD does not compare the construction traffic\\n\\neffects of the Jug-Handle Bridge with those of other proposed alternatives, the Agencies\\n\\ndid perform that comparison in the 2013 EA and the 2016 EA and still found the bridge\\n\\nto be the LEDPA. The Agencies also specifically considered the environmental effects of\\n\\nhaul roads in the 2008 EIS. 6\\n\\n We therefore cannot say that the Agencies did not provide “full and fair\\n\\ndiscussion” of the effects of construction traffic or haul roads when they selected the Jug-\\n\\nHandle Bridge among alternatives. See 40 C.F.R. § 1502.1. Accordingly, the Agencies\\n\\ndid not violate NEPA here, and we affirm the district court.\\n\\n\\n\\n\\n 6\\n To be sure, that discussion did not explicitly consider haul roads in the Rodanthe\\narea. However, it is unclear from the record whether the Agencies actually plan to use\\nhaul roads for the Jug-Handle Bridge project. See, e.g., J.A. 214 (containing a\\ndeclaration from an NCDOT engineer stating that NCDOT and its contractor decided not\\nto pursue a previously-discussed haul road in connection with a barge because shallow\\nwater depths would make it impracticable). Regardless, NEPA does not compel the\\nAgencies to specifically consider the environmental impacts of haul roads so long as they\\nadequately examine the environmental consequences of the Jug-Handle Bridge project,\\nincluding construction impacts, as a whole. See 40 C.F.R. § 1502.2(b) (“Impacts shall be\\ndiscussed [in the EIS] in proportion to their significance.”).\\n\\n 17\\n\\f C.\\n\\n Finally, SOS contends that the Agencies violated NEPA because their choice of\\n\\nthe Jug-Handle Bridge did not follow from their NEPA analysis but, rather, was a\\n\\npredetermined result of the Settlement. NEPA “prohibits agencies from preparing an EIS\\n\\nsimply to ‘justify [] decisions already made.’” Nat’l Audubon Soc’y, 422 F.3d at 199\\n\\n(quoting 40 C.F.R. § 1502.2(g)) (alteration in original). That is because, under NEPA,\\n\\nagencies that have yet to issue a final decision may not “commit resources prejudicing\\n\\nselection of alternatives,” 40 C.F.R. § 1502.2(f), nor may they take any action that would\\n\\n“[l]imit the choice of reasonable alternatives,” 40 C.F.R. § 1506.1(a). An EIS based upon\\n\\na predetermined choice that a certain alternative will be selected would violate these\\n\\nprinciples because it would not allow the agency to fully consider all alternatives.\\n\\n We conclude that the Agencies’ choice of the Jug-Handle Bridge was not\\n\\nimpermissibly predetermined. We consider, in turn, the Agencies’ objective\\n\\nenvironmental analyses, the language of the Settlement, and the role of documents\\n\\ngenerated during negotiation of the Settlement.\\n\\n\\n\\n i.\\n\\n First, SOS contends that flaws in the Agencies’ environmental analyses reveal that\\n\\ntheir choice of the Jug-Handle Bridge was predetermined by the Settlement. In alleging\\n\\nthat the environmental analyses were inadequate, it primarily relies upon arguments that\\n\\nwe have already discussed--namely, that the Agencies failed to fully consider the new\\n\\nalignment of the bridge, the feasibility of beach nourishment alternatives, and the effects\\n\\n 18\\n\\fof construction traffic and haul roads. SOS contends that these flaws exist because the\\n\\nAgencies prematurely decided to choose the Jug-Handle Bridge after the Settlement.\\n\\n Under our precedent, “the evidence we look to in determining whether\\n\\n[predetermination] has taken place consists of the environmental analysis itself.” 7 Nat’l\\n\\nAudubon Soc’y, 422 F.3d at 199. In National Audubon Society, in reviewing allegations\\n\\nthat an agency had settled on a certain outcome before preparing its EIS, we declined to\\n\\nlook to the agency’s internal documents and emails. Id. Instead, we limited the scope of\\n\\nour inquiry to the agency’s objective environmental analysis, reasoning that “[w]here an\\n\\nagency has merely engaged in post hoc rationalization, there will be evidence of this in its\\n\\nfailure to comprehensively investigate the environmental impact of its actions and\\n\\nacknowledge their consequences.” Id. Accordingly, our analysis focuses on whether an\\n\\nagency’s objective environmental analyses demonstrate evidence of predetermination.\\n\\n Here, when we examine Agencies’ environmental analyses, we cannot say that\\n\\nthey violated NEPA by selecting the Jug-Handle Bridge following the Settlement. To be\\n\\nsure, the Agencies changed their preferred alternative from the easement bridge to the\\n\\nJug-Handle Bridge following the Settlement. But that change alone does not mean that\\n\\nthe Agencies’ choice was predetermined, particularly where members of the Merger\\n\\nTeam had expressed concerns about the easement bridge as far back as 2013. And when\\n\\nwe look to the Agencies’ environmental analyses here, those analyses satisfied NEPA’s\\n\\n\\n 7\\n We note that some circuits look beyond the objective environmental analysis for\\nevidence of predetermination. See, e.g., Forest Guardians v. U.S. Fish & Wildlife Serv.,\\n611 F.3d 692, 716–17 (10th Cir. 2010) (declining to adopt the Fourth Circuit’s rule).\\n\\n 19\\n\\frequirements. See discussion supra Sections II.A., II.B. We do not see, and SOS cannot\\n\\nidentify, any evidence that the Agencies “fail[ed] to comprehensively investigate” and\\n\\nevaluate the environmental impacts of the Jug-Handle Bridge or the other alternatives.\\n\\nNat’l Audubon Soc’y, 422 F.3d at 199. The EAs and EIS prepared by the Agencies do\\n\\nnot, on their faces, show evidence of predetermination.\\n\\n SOS cites to cases from the Ninth and Tenth Circuits to contend that courts have\\n\\nfound predetermination based on contractual commitments made by an agency before the\\n\\nNEPA process was complete. See Davis v. Mineta, 302 F.3d 1104, 1112 (10th Cir. 2002)\\n\\n(holding that a contract requiring a consultant to recommend that a project had no\\n\\nsignificant environmental impact before actually preparing an EA violated NEPA);\\n\\nMetcalf v. Daley, 214 F.3d 1135, 1145 (9th Cir. 2000) (same, regarding a contract\\n\\nrequiring an agency to make a proposal for a specific alternative before preparing an EA).\\n\\nHowever, these cases are distinguishable because they involved contracts that agencies\\n\\nentered into before conducting any environmental analysis at all; in contrast, the\\n\\nSettlement here, which the Agencies and the Environmental Groups entered into in 2015,\\n\\nwas preceded by a number of environmental analyses, including the 2008 EIS, the 2010\\n\\nEA, and the 2013 EA. And when we examine each of these environmental analyses, we\\n\\nfind no evidence of predetermination warranting reversal.\\n\\n\\n\\n ii.\\n\\n Although circuit precedent limits our predetermination inquiry to the\\n\\n“environmental analysis itself,” id., SOS nonetheless urges us to consider the Settlement\\n\\n 20\\n\\fas evidence that the Agencies’ choice was predetermined. But even if we look to the\\n\\nSettlement, that document does not support SOS’s claim. The Settlement only required\\n\\nNCDOT to identify the Jug-Handle Bridge as its preferred alternative and to seek Merger\\n\\nTeam concurrence that the Jug-Handle Bridge was the LEDPA. These conditions do not\\n\\nrequire the Agencies to select the Jug-Handle Bridge as the final approved alternative for\\n\\nthis project. For instance, it remained possible that the Agencies’ environmental analyses\\n\\nwould demonstrate that the Jug-Handle Bridge was not the LEDPA. Additionally, the\\n\\nAgencies’ preferences alone could not bind the entire Merger Team, which was\\n\\nultimately responsible for approving the final alternative, because the parties to the\\n\\nSettlement comprise only three of the ten state and federal agencies represented on the\\n\\nMerger Team. 8 This does not constitute predetermination.\\n\\n\\n\\n iii.\\n\\n SOS also urges us to consider external documents generated during the negotiation\\n\\nof the Settlement as evidence of predetermination and to reverse the district court’s denial\\n\\nof SOS’s motion to include these documents in the record. We decline to do so because\\n\\nthe district court did not abuse its discretion in denying this motion. See Fort Sumter\\n\\nTours, Inc. v. Babbitt, 66 F.3d 1324, 1335–36 (4th Cir. 1995) (explaining that we review\\n\\n 8\\n To be sure, the parties to the Settlement represented three of the four Lead\\nAgencies tasked with decisionmaking if the Merger Team could not reach consensus.\\nBut, as discussed, the Settlement only required those agencies to seek concurrence that\\nthe Jug-Handle Bridge was the LEDPA; it did not require them to go beyond the\\nobjective environmental analysis to choose the Jug-Handle Bridge if it was not, in fact,\\nthe LEDPA.\\n\\n 21\\n\\fa district court’s decision whether to expand the administrative record for abuse of\\n\\ndiscretion).\\n\\n Federal courts base their review of agency decisions on “the ‘whole record’\\n\\ncompiled by the agency.” Citizens to Pres. Overton Park, Inc. v. Volpe, 401 U.S. 402,\\n\\n419 (1971) (quoting 5 U.S.C. § 706), abrogated on other grounds by Califano v. Sanders,\\n\\n430 U.S. 99 (1977). We may supplement the record as presented by the agency if the\\n\\n“bare record” does not reveal the agency’s reasoning or if it appears that the agency acted\\n\\nin bad faith. Id. at 420. Otherwise, “inquiry into the mental processes of administrative\\n\\ndecisionmakers is usually to be avoided.” Id.\\n\\n Here, the record as presented by the Agencies reveals their reasoning, as we have\\n\\ndiscussed, and the district court found no evidence that the Agencies acted in bad faith.\\n\\nThe district court also determined that there was no evidence that the Agencies actually\\n\\nreviewed the documents put forth by SOS as part of their decision to approve the Jug-\\n\\nHandle Bridge. We hold that the district court did not abuse its discretion by denying\\n\\nSOS’s motion to supplement the record, and accordingly, our review is limited to the\\n\\nrecord as compiled by the Agencies.\\n\\n SOS contends that, even if we cannot consider these documents as part of the\\n\\nadministrative record, we should nevertheless consider them as extra-record evidence. It\\n\\nis true that “in the NEPA context, courts generally have been willing to look outside the\\n\\nrecord when assessing the adequacy of an EIS or a determination that no EIS is\\n\\nnecessary.” Ohio Valley Envtl. Coal. v. Aracoma Coal Co., 556 F.3d 177, 201 (4th Cir.\\n\\n2009). However, we have explained that extra-record evidence in that context is\\n\\n 22\\n\\fprimarily useful “to inform the court about environmental factors that the agency may not\\n\\nhave considered.” Id. (emphasis added). Here, the proffered documents would do\\n\\nnothing to aid the court’s understanding of the environmental concerns at issue, as they\\n\\nconcern the legal terms of the Settlement between the Agencies and the Environmental\\n\\nGroups. Therefore, the district court properly excluded them, and we decline to consider\\n\\nthem now.\\n\\n There is superficial appeal in suggesting that the Agencies’ choice was\\n\\npredetermined because the Settlement yielded a preferred alternative. However, that\\n\\nconclusion is not legally or factually supported by the record. Legally, our analysis is\\n\\ncabined to the environmental analysis itself, with which we find no issues meriting\\n\\nreversal. And factually, we see no evidence that the Merger Team was forced to approve\\n\\nthe Jug-Handle Bridge.\\n\\n In sum, the Agencies did not violate NEPA when they approved the Jug-Handle\\n\\nBridge because they were not required to prepare an SEIS, they adequately evaluated the\\n\\neffects of construction traffic, and they did not rely on a predetermined choice among\\n\\nalternatives. We therefore affirm the district court’s grant of summary judgment in favor\\n\\nof the Agencies.\\n\\n\\n\\n III.\\n\\n Finally, SOS contends that the district court erred when it denied SOS’s motion to\\n\\namend its complaint with claims related to the Pappy’s Lane Wreck. Specifically, SOS\\n\\nalleges that the Agencies violated § 4(f) by approving a transportation project that\\n\\n 23\\n\\fthreatens to harm the land of a site of historic significance because the Jug-Handle Bridge\\n\\nwill pass above the wreck--the site of a World War II vessel.\\n\\n We review a district court’s denial of a motion to amend the complaint for abuse\\n\\nof discretion. See Laber v. Harvey, 438 F.3d 404, 428 (4th Cir. 2006) (en banc).\\n\\nHowever, if the district court denied such a motion on the grounds that the amendment\\n\\nwould have been futile, we review its legal conclusions de novo. United States ex. rel.\\n\\nAhumada v. NISH, 756 F.3d 268, 274 (4th Cir. 2014).\\n\\n A party “may amend its pleading once as a matter of course” before the opposing\\n\\nparty files a responsive pleading. Fed. R. Civ. P. 15(a)(1). After that time, a party may\\n\\nonly amend its pleading with the consent of the opposing party or with leave of the court,\\n\\nand “[t]he court should freely give leave when justice so requires.” Fed. R. Civ. P.\\n\\n15(a)(2). Courts may deny leave to amend a pleading if the amendment would have been\\n\\nfutile. Laber, 438 F.3d at 426. A proposed amendment is futile when it is “clearly\\n\\ninsufficient or frivolous on its face.” Johnson v. Oroweat Foods Co., 785 F.2d 503, 510\\n\\n(4th Cir. 1986). A proposed amendment is also futile if the claim it presents would not\\n\\nsurvive a motion to dismiss. Perkins v. United States, 55 F.3d 910, 917 (4th Cir. 1995).\\n\\n Here, the district court found that SOS’s proposed amendment would be futile for\\n\\ntwo alternative reasons. First, it determined that, to the extent that SOS sought to assert\\n\\nthat the 2016 EA was no longer valid in light of new information about the shipwreck,\\n\\nthat claim would be unripe where the Agencies had not yet made a decision concerning\\n\\nthe significance of the new information. Second, it determined that, to the extent that\\n\\nSOS sought to assert that the 2016 EA was inadequate when issued, that claim would fail\\n\\n 24\\n\\fbecause it would ask the Agencies to consider information that was not discovered until\\n\\nafter the 2016 EA was issued. For the reasons that follow, we affirm the district court’s\\n\\ndenial of SOS’s motion to amend its complaint.\\n\\n First, to the extent that SOS’s proposed amendments contend that the Agencies\\n\\nfailed to consider new information about the shipwreck, those amendments would be\\n\\nfutile because they would raise a claim that is not yet ripe for review. 9 Courts may only\\n\\nreview “final agency action,” 5 U.S.C. § 704, and challenges to agency decisions that are\\n\\nyet to be made are not ripe for review. See Pashby v. Delia, 709 F.3d 307, 317 (4th Cir.\\n\\n2013) (holding that a claim is only ripe when it involves a formalized administrative\\n\\ndecision). Here, the Agencies have not yet made a final decision about the significance\\n\\nof new information revealing that the shipwreck was a World War II assault vessel.\\n\\nTherefore, any claim that the Agencies did not properly account for this information\\n\\nwould be unripe, and any amendment seeking to add such a claim would be futile.\\n\\n Second, SOS contends on appeal that it is challenging the adequacy of the 2016\\n\\nROD’s treatment of the Pappy’s Lane Wreck rather than the Agencies’ failure to consider\\n\\nnew information about the shipwreck’s significance. Specifically, SOS contends that,\\n\\nbecause the Agencies knew that the shipwreck was eligible for listing on the National\\n\\n\\n 9\\n SOS appears to have abandoned this argument on appeal. See Appellants’ Br. at\\n53 (contending that the district court “fundamentally misread [SOS’s] motion” when it\\ndenied it on ripeness grounds because “[t]he [new] allegations were about the\\ninadequacies of the [2016] ROD and the process leading up to that document”)\\n(emphasis added). Nevertheless, we discuss it because it implicates concerns related to\\nthe argument that SOS does raise on appeal regarding the adequacy of the 2016 ROD\\nwhen issued.\\n\\n 25\\n\\fRegister of Historic Places, they were not authorized to build a bridge in its path unless\\n\\nthey determined that there was “no prudent and feasible alternative to using that land”\\n\\nand that the “project include[d] all possible planning to minimize harm . . . resulting from\\n\\nthe use.” See 49 U.S.C. § 303(c).\\n\\n However, as the district court explained, SOS cannot contend that it was\\n\\nchallenging the adequacy of the 2016 ROD’s treatment of the shipwreck when its claims\\n\\n“rest[] upon recent discovery that the Pappy[’s] Lane Wreck contains a World War II\\n\\nvessel.” Save Our Sound OBX, Inc. v. N.C. Dep’t of Transp., No. 2:17-CV-4-FL, 2017\\n\\nWL 7048561, at *5 (E.D.N.C. Dec. 5, 2017). Instead, the Agencies satisfied regulatory\\n\\nrequirements when, based on what they knew about the Pappy’s Lane Wreck, they\\n\\nordered data recovery and decided that the shipwreck did not merit preservation in place.\\n\\nArguments that the Agencies should have gone further are grounded in new information\\n\\nand, therefore, not reviewable until the Agencies issue a final decision, as discussed\\n\\nabove. We therefore affirm the district court’s denial of SOS’s motion to amend its\\n\\ncomplaint.\\n\\n\\n\\n IV.\\n\\n We affirm the district court because the Agencies did not violate NEPA or the\\n\\nDTA when they issued the 2016 ROD selecting the Jug-Handle Bridge and because the\\n\\ndistrict court did not abuse its discretion when it denied SOS’s motions to supplement the\\n\\nadministrative record and to amend the complaint.\\n\\n AFFIRMED\\n\\n 26\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":98,"cells":{"id":{"kind":"number","value":4584448,"string":"4,584,448"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff-Appellee, v. Joseph Decore SIMMS, Defendant-Appellant. Fourth Circuit Federal Defender Offices, Amicus Supporting Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Joseph Simms"},"decision_date":{"kind":"string","value":"2019-01-24"},"docket_number":{"kind":"string","value":"15-4640"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Gregory, Wilkinson, Niemeyer, Motz, King, Duncan, Agee, Keenan, Wynn, Diaz, Floyd, Thacker, Harris, Richardson, Quattlebaum\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9887914/\", \"author_raw\": \"\"}, {\"author\": \"\", \"type\": \"040dissent\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9887915/\", \"author_raw\": \"\"}, {\"author\": \"DIANA GRIBBON MOTZ, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 15-4640\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nJOSEPH DECORE SIMMS,\\n\\n Defendant - Appellant.\\n\\n------------------------------------------\\n\\nFOURTH CIRCUIT FEDERAL DEFENDER OFFICES,\\n\\n Amicus Supporting Appellant.\\n\\n\\nAppeal from the United States District Court for the Eastern District of North Carolina, at\\nGreenville. Terrence W. Boyle, Chief District Judge. (4:15-cr-00010-BO-1)\\n\\n\\nArgued: September 26, 2018 Decided: January 24, 2019\\n\\n\\nBefore GREGORY, Chief Judge, and WILKINSON, NIEMEYER, MOTZ, KING,\\nDUNCAN, AGEE, KEENAN, WYNN, DIAZ, FLOYD, THACKER, HARRIS,\\nRICHARDSON, and QUATTLEBAUM, Circuit Judges.\\n\\n\\nReversed and remanded by published opinion. Judge Motz wrote the opinion, in which\\nChief Judge Gregory and Judges King, Wynn, Diaz, Floyd, Thacker, and Harris joined.\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4361701/\", \"author_raw\": \"DIANA GRIBBON MOTZ, Circuit Judge:\"}, {\"author\": \"Judge Wynn wrote a concurring\", \"type\": \"concurrence\", \"text\": \"Judge Wynn wrote a concurring opinion, in which Judge Harris joined. Judge Wilkinson\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4361701/\", \"author_raw\": \"Judge Wynn wrote a concurring\"}, {\"author\": \"wrote a dissenting opinion. Judge Niemeyer wrote a dissenting\", \"type\": \"dissent\", \"text\": \"wrote a dissenting opinion. Judge Niemeyer wrote a dissenting opinion, in which Judges\\n\\nWilkinson, Duncan, Agee, Keenan, and Quattlebaum joined. Judge Richardson wrote a\\ndissenting opinion, in which Judge Quattlebaum joined.\\n\\n\\nARGUED: Dhamian Blue, BLUE LLP, Raleigh, North Carolina, for Appellant. Phillip\\nAnthony Rubin, OFFICE OF THE UNITED STATES ATTORNEY, Raleigh, North\\nCarolina, for Appellee. Joshua B. Carpenter, FEDERAL DEFENDERS OF WESTERN\\nNORTH CAROLINA, INC., Asheville, North Carolina, for Amici Curiae. ON BRIEF:\\nBrian A. Benczkowski, Assistant Attorney General, Matthew S. Miner, Deputy Assistant\\nAttorney General, John P. Taddei, Appellate Section, Criminal Division, UNITED\\nSTATES DEPARTMENT OF JUSTICE, Washington, D.C.; John Stuart Bruce, Acting\\nUnited States Attorney, Robert J. Higdon, Jr., United States Attorney, Jennifer P. May-\\nParker, Assistant United States Attorney, OFFICE OF THE UNITED STATES\\nATTORNEY, Raleigh, North Carolina, for Appellee. Anthony Martinez, Federal Public\\nDefender, FEDERAL PUBLIC DEFENDERS OF WESTERN NORTH CAROLINA,\\nINC., Charlotte, North Carolina; Parks N. Small, Federal Public Defender, Columbia,\\nSouth Carolina; Louis C. Allen, Federal Public Defender, Greensboro, North Carolina;\\nFred Heblich, Interim Federal Public Defender, Roanoke, Virginia; Christian M. Capece,\\nFederal Public Defender, Charleston, West Virginia; James Wyda, Federal Public\\nDefender, Baltimore, Maryland; Paresh S. Patel, Assistant Federal Public Defender,\\nGreenbelt, Maryland; G. Alan DuBois, Federal Public Defender, Raleigh, North\\nCarolina; Geremy Kamens, Federal Public Defender, Alexandria, Virginia; Brian J.\\nKornbrath, Federal Public Defender, OFFICE OF THE FEDERAL PUBLIC\\nDEFENDER, Clarksburg, West Virginia, for Amici Curiae.\\n\\n\\n\\n\\n 2\\n\\nDIANA GRIBBON MOTZ, Circuit Judge:\\n\\n Joseph Decore Simms was convicted of brandishing a firearm in connection with a\\n\\n“crime of violence,” as defined in 18 U.S.C. § 924(c)(3)(B). He appeals, contending that\\n\\n§ 924(c)(3)(B), as long understood, is unconstitutionally vague. The Government\\n\\nconcedes this point but urges us to abandon the settled meaning of the statute and employ\\n\\na new definition of “crime of violence.”\\n\\n We cannot do so. Neither the statutory language nor controlling precedent offer\\n\\nany support for the Government’s proposed reinterpretation. Rather, the text and\\n\\nstructure of § 924(c)(3)(B) plainly set forth a definition of “crime of violence” that fails\\n\\nto comport with due process. Accordingly, we reverse and remand for further\\n\\nproceedings consistent with this opinion.\\n\\n\\n\\n I.\\n\\n This case arises from an April 2014 conspiracy to rob a McDonald’s in Goldsboro,\\n\\nNorth Carolina. Shortly after 1:00 a.m., Simms and a co-conspirator crawled into the\\n\\nMcDonald’s through the drive-through window; a third robber served as a lookout.\\n\\nWhen inside, Simms pointed a gun at the manager, attempted to strike another employee,\\n\\nand demanded money. The manager complied and opened the restaurant’s safe. After\\n\\nremoving the contents, Simms struck the manager with the gun, threw a cash drawer at\\n\\nthe other employee, and fled with his two co-conspirators and $1,100.\\n\\n After his arrest and indictment, Simms pleaded guilty to Count I, conspiracy to\\n\\ncommit Hobbs Act robbery in violation of 18 U.S.C. § 1951, and Count II, brandishing a\\n\\n 3\\n\\nfirearm during and in relation to a “crime of violence” — that is, the Hobbs Act\\n\\nconspiracy in Count I — in violation of 18 U.S.C. § 924(c)(1)(A). But at sentencing,\\n\\nSimms argued that his conviction under Count II was unconstitutional in light of Johnson\\n\\nv. United States, 135 S. Ct. 2551 (2015). He contended that Hobbs Act conspiracy was\\n\\nnot a “crime of violence” because the definition of this term in 18 U.S.C. § 924(c)(3)(B)\\n\\nwas unconstitutionally vague, like the similar definition of “violent felony” that the\\n\\nSupreme Court struck down in Johnson. The district court rejected this argument and\\n\\nsentenced Simms to 115 months’ incarceration on Count I and 84 months on Count II, for\\n\\na total consecutive sentence of 199 months’ imprisonment.\\n\\n Simms appealed, again contending that his conviction under Count II could not\\n\\nstand because § 924(c)(3)(B) was unconstitutional. 1 After the parties briefed and argued\\n\\nthe appeal before a panel of this court, the Supreme Court struck down as\\n\\nunconstitutionally vague a statute containing language materially identical to that\\n\\nchallenged by Simms. See Sessions v. Dimaya, 138 S. Ct. 1204, 1223 (2018). Given the\\n\\nexceptional importance and recurring nature of the question presented here, we agreed to\\n\\nrehear the case en banc. For the reasons that follow, we now reverse.\\n\\n\\n\\n\\n 1\\n The Government does not contend that Simms’s plea renders him unable to\\nchallenge his § 924(c) conviction. It has expressly disavowed any reliance on the\\nappellate waiver provision in Simms’s plea agreement. See Gov. Supp. Br. at 4 n.2.\\n\\n 4\\n\\n II.\\n\\n We must determine whether the definition of “crime of violence” in\\n\\n§ 924(c)(3)(B) satisfies the requirements of due process.\\n\\n In resolving this question, we first set forth the statutory framework and examine\\n\\nSupreme Court precedent interpreting text materially identical to that at issue here. We\\n\\nthen address the contours of Simms’s constitutional challenge, drawing on the Supreme\\n\\nCourt’s consideration of identical challenges to similar statutory language. Finally, we\\n\\nexplain why, in light of the plain text and binding Supreme Court precedent, we must\\n\\nhold § 924(c)(3)(B) unconstitutional.\\n\\n A.\\n\\n Federal law, as codified at 18 U.S.C. § 924(c)(1)(A), provides that a person who\\n\\nuses or carries a firearm “during and in relation to any crime of violence” or who\\n\\n“possesses a firearm” “in furtherance of any such crime” may be convicted of both the\\n\\nunderlying crime (here, Hobbs Act conspiracy) and the additional, distinct crime of\\n\\nutilizing a firearm in connection with a “crime of violence,” with the latter punishable by\\n\\nat least five consecutive years of imprisonment.\\n\\n Section 924(c)(3) defines “crime of violence” as “an offense that is a felony” and\\n\\n (A) has as an element the use, attempted use, or threatened use of physical\\n force against the person or property of another, or\\n (B) that by its nature, involves a substantial risk that physical force against\\n the person or property of another may be used in the course of committing\\n the offense.\\n\\n18 U.S.C. § 924(c)(3). Courts commonly refer to § 924(c)(3)(A) as the “force clause”\\n\\nand to § 924(c)(3)(B), the provision at issue here, as the “residual clause.” For Simms’s\\n\\n 5\\n\\n§ 924(c) conviction to stand, his Hobbs Act conspiracy offense must constitute a “crime\\n\\nof violence” under one of these two definitions.\\n\\n Our analysis begins with the force clause, § 924(c)(3)(A). To determine whether\\n\\nan offense is a crime of violence under that clause, courts use an inquiry known as the\\n\\n“categorical” approach. They look to whether the statutory elements of the offense\\n\\nnecessarily require the use, attempted use, or threatened use of physical force. See, e.g.,\\n\\nLeocal v. Ashcroft, 543 U.S. 1, 7–10 (2004) (interpreting materially identical text in 18\\n\\nU.S.C. § 16(a)); United States v. McNeal, 818 F.3d 141, 151–52 (4th Cir. 2016)\\n\\n(interpreting § 924(c)(3)(A)). This approach is “categorical” because courts consider\\n\\nonly the crime as defined, not the particular facts in the case. See, e.g., McNeal, 818 F.3d\\n\\nat 152. To be more precise, we will refer to the force clause inquiry as the elements-\\n\\nbased categorical approach, because it begins and ends with the offense’s elements.\\n\\nWhen a statute defines an offense in a way that allows for both violent and nonviolent\\n\\nmeans of commission, that offense is not “categorically” a crime of violence under the\\n\\nforce clause.\\n\\n Simms’s offense — conspiracy to commit Hobbs Act robbery — does not\\n\\ncategorically qualify as a crime of violence under the elements-based categorical\\n\\napproach, as the United States now concedes. Gov. 28(j) Letter at 1, ECF No. 44 (Oct.\\n\\n19, 2016); Simms Suppl. Br. at 1. This is so because to convict a defendant of this\\n\\noffense, the Government must prove only that the defendant agreed with another to\\n\\ncommit actions that, if realized, would violate the Hobbs Act. Such an agreement does\\n\\nnot invariably require the actual, attempted, or threatened use of physical force.\\n\\n 6\\n\\n Accordingly, the only way we can sustain Simms’s conviction on Count II is if his\\n\\ncommission of Hobbs Act conspiracy constitutes a crime of violence under the residual\\n\\nclause — that is, if we determine that he committed a felony offense “that by its nature[]\\n\\ninvolves a substantial risk that physical force against the person or property of another\\n\\nmay be used in the course of committing the offense.” 18 U.S.C. § 924(c)(3)(B).\\n\\nInterpreting a materially identical clause in another statute, the Supreme Court has\\n\\ndirected courts to employ a categorical approach that — as with the force clause —\\n\\n“look[s] to the elements and the nature of the offense of conviction, rather than to the\\n\\nparticular facts.” Leocal, 543 U.S. at 7 (interpreting 18 U.S.C. § 16(b) to “require[]”\\n\\ncategorical analysis); see also United States v. Aragon, 983 F.2d 1306, 1312–13 (4th Cir.\\n\\n1993) (“conclud[ing] that the plain language of § 16(b) mandates that the court embark\\n\\nupon a categorical approach”). 2\\n\\n Importantly, however, the analysis applicable to the residual clause constitutes a\\n\\n“distinctive form” of the categorical approach. Dimaya, 138 S. Ct. at 1211 (interpreting\\n\\n§ 16(b)). Unlike the elements-based categorical approach of the force clause, the residual\\n\\nclause inquiry “goes beyond deciding whether creation of risk is an element of the\\n\\n\\n 2\\n Because § 16(b) and § 924(c)(3)(B) are materially identical, we and other courts\\nhave treated “precedent respecting one as controlling analysis of the other.” In re\\nHubbard, 825 F.3d 225, 230 n.3 (4th Cir. 2016); see also, e.g., Evans v. Zych, 644 F.3d\\n447, 452 n.2 (6th Cir. 2011) (“recogniz[ing] essentially identical nature of § 924(c) and\\n§ 16” and applying § 16(b) case law to § 924(c)(3)(B) analysis); United States v. Serafin,\\n562 F.3d 1105, 1108 n.4 (10th Cir. 2009) (“cases interpreting [§ 16(b)] inform our\\nanalysis” of § 924(c)(3)(B)). The Government urges us to abandon this approach and\\nreinterpret § 924(c)(3)(B); we address its argument in Parts IV-VI of this opinion.\\n\\n\\n 7\\n\\ncrime.” Johnson, 135 S. Ct. at 2557 (interpreting 18 U.S.C. § 924(e)(2)(B)(ii)). Under\\n\\nthe residual clause, courts must use the statutory definition of an offense to imagine its\\n\\n“ordinary case,” and then consider whether this imagined ordinary case entails a\\n\\n“substantial risk” of force. Dimaya, 138 S. Ct. at 1211 (internal quotation marks\\n\\nomitted); see also 18 U.S.C. § 924(c)(3)(B).\\n\\n We call the analysis applicable to the residual clause the ordinary-case categorical\\n\\napproach. This ordinary-case categorical approach is “broader than” the elements-based\\n\\ncategorical approach applicable to the force clause, “in the sense that force need not\\n\\nactually be applied” in a residual clause offense. Leocal, 543 U.S. at 11.\\n\\n B.\\n\\n Simms contends that conspiracy to commit Hobbs Act robbery does not constitute\\n\\na crime of violence under the residual clause, § 924(c)(3)(B), because that clause — like\\n\\nthe similarly worded residual clauses analyzed in Johnson, 135 S. Ct. 2551, and Dimaya,\\n\\n138 S. Ct. 1204 — is void for vagueness.\\n\\n As Justice Kagan explained in Dimaya, “‘[t]he prohibition of vagueness in\\n\\ncriminal statutes’ . . . is an ‘essential’ of due process, required by both ‘ordinary notions\\n\\nof fair play and the settled rules of law.’” 138 S. Ct. at 1212 (plurality opinion) (quoting\\n\\nJohnson, 135 S. Ct. at 2557). Vague criminal statutes “invite the exercise of arbitrary\\n\\npower . . . by leaving people in the dark about what the law demands and allowing\\n\\nprosecutors and courts to make it up.” Id. at 1223–24 (Gorsuch, J., concurring in part and\\n\\nconcurring in the judgment). The void-for-vagueness doctrine thus ensures citizens have\\n\\nfair notice of prohibited conduct, guards against discriminatory enforcement of\\n\\n 8\\n\\nambiguous laws, and respects the foundational principle that only Congress — not the\\n\\nexecutive or the courts — is empowered to establish the bounds of proscribed conduct.\\n\\nId. at 1212 (plurality opinion).\\n\\n In Johnson, the Supreme Court struck down the residual clause of the Armed\\n\\nCareer Criminal Act (“ACCA”) as void for vagueness. 135 S. Ct. at 2557. ACCA\\n\\nenhances the sentence of those convicted of possessing a firearm in violation of 18\\n\\nU.S.C. § 922(g) if they have three or more prior convictions for a “serious drug offense”\\n\\nor for a “violent felony.” It defines “violent felony” as any felony that:\\n\\n (i) has as an element the use, attempted use, or threatened use of physical\\n force against the person of another; or\\n (ii) is burglary, arson, or extortion, involves use of explosives, or otherwise\\n involves conduct that presents a serious potential risk of physical injury to\\n another . . . .\\n\\n18 U.S.C. § 924(e)(2)(B) (emphasis added). The italicized portion is the ACCA residual\\n\\nclause. Johnson, 135 S. Ct. at 2555–56.\\n\\n The Johnson Court explained that “[t]wo features of the [ACCA] residual clause\\n\\nconspire[d] to make it unconstitutionally vague.” Id. at 2557. The clause left uncertainty\\n\\nabout both (1) “how to estimate the risk posed by a crime,” and (2) “how much risk it\\n\\ntakes for a crime to qualify as a violent felony.” Id. at 2557–58.\\n\\n The first problem arose because the residual clause “tie[d] the judicial assessment\\n\\nof risk to a judicially imagined ‘ordinary case’ of a crime, not to real-world facts or\\n\\nstatutory elements,” but “offer[ed] no reliable way” for judges to ascertain what the\\n\\n“ordinary case” involved. Id. Regarding the second problem, the Court clarified that it\\n\\nwas “one thing to apply an imprecise ‘serious potential risk’ standard to real-world facts,”\\n\\n 9\\n\\nbut “quite another to apply it to a judge-imagined abstraction,” as the ACCA residual\\n\\nclause required. Id. at 2558. The Court held that the combination of these two flaws\\n\\nrendered the ACCA residual clause unconstitutional: “Each of the uncertainties in the\\n\\nresidual clause may be tolerable in isolation, but ‘their sum makes a task for us which at\\n\\nbest could be only guesswork.’” Id. at 2560 (quoting United States v. Evans, 333 U.S.\\n\\n483, 495 (1948)).\\n\\n The Supreme Court reiterated this logic in Dimaya, when it held 18 U.S.C. § 16(b)\\n\\nunconstitutionally vague. 138 S. Ct. at 1215–16. That statute defines “crime of\\n\\nviolence,” a term incorporated into many criminal and immigration statutes, as:\\n\\n (a) an offense that has as an element the use, attempted use, or threatened\\n use of physical force against the person or property of another, or\\n (b) any other offense that is a felony and that, by its nature, involves a\\n substantial risk that physical force against the person or property of another\\n may be used in the course of committing the offense.\\n\\n18 U.S.C. § 16. Section 16(b) is similarly known as the “residual clause.” Dimaya, 138\\n\\nS. Ct. at 1212.\\n\\n In Dimaya, the Court held that a “straightforward application” of Johnson made\\n\\nclear that § 16(b), like the ACCA residual clause, was void for vagueness. Id. at 1213.\\n\\nIn doing so, the Court carefully explained that the proper ordinary-case categorical\\n\\nanalysis did not ask “whether ‘the particular facts’ underlying a conviction posed the\\n\\nsubstantial risk that § 16(b) demands,” nor whether “the statutory elements of a crime\\n\\nrequire (or entail) the creation of such a risk in each case that the crime covers.” Id. at\\n\\n1211 (quoting Leocal, 543 U.S. at 7). Rather, a majority of the Court agreed that\\n\\n“§ 16(b) requires a court to ask whether the ordinary case of an offense poses the\\n\\n 10\\n\\nrequisite risk.” Id. (internal quotation marks omitted); see also id. at 1235 (Roberts, C.J.,\\n\\ndissenting) (identifying ordinary-case categorical approach as the way “courts should\\n\\nassess whether a particular crime ‘by its nature’ involves a risk of the use of physical\\n\\nforce”).\\n\\n As a result, § 16(b) possessed “the same two features that conspired to make\\n\\nACCA’s residual clause unconstitutionally vague.” Id. at 1216 (majority opinion)\\n\\n(alterations and internal quotation marks omitted) (quoting Johnson, 135 S. Ct. at 2557).\\n\\nAs with the ACCA residual clause, § 16(b) required courts to “identify a crime’s\\n\\n‘ordinary case’ in order to measure the crime’s risk.” Id. at 1215. But the statute failed\\n\\nto provide any guidance on how to “divin[e] the conduct entailed in a crime’s ordinary\\n\\ncase.” Id. “And § 16(b) also possesse[d] the second fatal feature of ACCA’s residual\\n\\nclause: uncertainty about the level of risk that ma[de] a crime ‘violent.’” Id. Thus, like\\n\\nthe ACCA residual clause, the Court held that § 16(b) violated due process. Id. at 1223.\\n\\n C.\\n\\n With these precedents in mind, we turn to the question at hand: is the materially\\n\\nidentical statute at issue here also unconstitutionally vague?\\n\\n Like the statutes examined in Johnson and Dimaya, § 924(c)(3)(B) requires a\\n\\ncourt to imagine the idealized ordinary case of a crime while providing no guidance on\\n\\nhow to do so, rendering any judicial account of the ordinary case wholly speculative.\\n\\nDimaya, 138 S. Ct. at 1213–14; Johnson, 135 S. Ct. at 2557–58. After conceiving of this\\n\\njudicial abstraction, a court must then assess its speculation using the same vague\\n\\nstandard of “substantial risk” as § 16(b) required in Dimaya. 138 S. Ct. at 1214. This\\n\\n 11\\n\\nconjectural exercise suffers from the same two fundamental flaws that, in combination,\\n\\nrendered the statutory provisions in Johnson and Dimaya void for vagueness. Dimaya,\\n\\n138 S. Ct. at 1213–16; Johnson, 137 S. Ct. at 2557–58.\\n\\n Section 924(c)(3)(B) is therefore unconstitutional. Three other circuits have\\n\\nreached this conclusion. United States v. Davis, 903 F.3d 483, 485–86 (5th Cir. 2018)\\n\\n(per curiam), cert. granted, 2019 WL 98544 (U.S. Jan. 4, 2019) (No. 18-431); United\\n\\nStates v. Eshetu, 898 F.3d 36, 37 (D.C. Cir. 2018) (per curiam), petition for reh’g en banc\\n\\nfiled, No. 15-3020 (Aug. 31, 2018); United States v. Salas, 889 F.3d 681, 684–86 (10th\\n\\nCir. 2018), petition for cert. filed, No. 18-428 (U.S. Oct. 3, 2018). 3\\n\\n To understand why, consider a situation where a defendant is charged with\\n\\npossessing a gun in conjunction with witness tampering. See 18 U.S.C. § 1512(b);\\n\\nDimaya, 138 S. Ct. at 1232 (Gorsuch, J., concurring in part and concurring in the\\n\\njudgment). As the Supreme Court has explained, § 924(c) “requires the prosecution to\\n\\nmake two showings”: the commission of an underlying crime and the use of a firearm.\\n\\nSmith v. United States, 508 U.S. 223, 227–28 (1993); see also Rosemond v. United States,\\n\\n 3\\n Before Dimaya was decided, a panel of the Eleventh Circuit concluded that the\\n§ 924(c)(3)(B) “determination [is] more precise” than that under the ACCA residual\\nclause, because § 924(c) requires a “‘nexus’ between the . . . firearm offense and the\\npredicate crime of violence.” Ovalles v. United States, 861 F.3d 1257, 1265–66 (11th\\nCir. 2017), reh’g en banc granted, opinion vacated, 889 F.3d 1259 (11th Cir. 2018), and\\non reh’g en banc, 905 F.3d 1231 (11th Cir. 2018), and opinion reinstated in part, 905\\nF.3d 1300 (11th Cir. 2018). But this conclusion is premised on a misunderstanding of\\n§ 924(c)(3)(B). In defining “crime of violence,” the statute directs us to consider what\\nthe underlying offense entails “by its nature,” not what it entails when committed using a\\nfirearm. 18 U.S.C. § 924(c)(3)(B). Therefore, the firearm “nexus” offers no meaningful\\nguidance on what satisfies the distinct crime of violence element. See Salas, 889 F.3d at\\n685–86.\\n\\n 12\\n\\n572 U.S. 65, 75 (2014) (“§ 924(c) . . . punishes the temporal and relational conjunction of\\n\\ntwo separate acts, on the ground that together they pose an extreme risk of harm.”).\\n\\n Thus, to evaluate whether witness tampering satisfies the “crime of violence”\\n\\nelement of a § 924(c) violation, a court must assess whether the ordinary case of witness\\n\\ntampering, with or without a firearm, “involves a substantial risk [of] physical force.” 18\\n\\nU.S.C. § 924(c)(3)(B). And when “divining the conduct entailed in [the] crime’s\\n\\nordinary case,” the court must utilize some as-yet-unspecified method — “Surveys?\\n\\nExperts? Google? Gut instinct?” Dimaya, 138 S. Ct. at 1215 (majority opinion) (citing\\n\\nJohnson, 135 S. Ct. at 2557). The statute provides no guidance for this “abstract\\n\\ninquiry.” See Dimaya, 138 S. Ct. at 1215 (quoting Johnson, 135 S. Ct. at 2561). Instead,\\n\\n§ 924(c)(3)(B) effectively requires judges to define the scope of criminal liability, and it\\n\\ndirects them to do so using an unmoored, subjective abstraction that deprives the public\\n\\nof fair notice.\\n\\n Just as in Dimaya, a “straightforward application” of controlling precedent to the\\n\\nchallenged statute requires us to strike it down. Dimaya, 138 S. Ct. at 1213. The\\n\\nSupreme Court has made clear that where a statute requires courts to assess “both an\\n\\nordinary-case requirement and an ill-defined risk threshold,” it is unconstitutional. Id. at\\n\\n1223; see also Johnson, 135 S. Ct. at 2557–60. That principle controls here. Any\\n\\nconviction involving § 924(c)(3)(B) is subject to the same “guesswork,” “intuition,”\\n\\n“arbitrary enforcement,” and lack of “fair notice” that plagued both § 16(b) and the\\n\\nACCA residual clause. Dimaya, 138 S. Ct. at 1223 (quoting Johnson, 135 S. Ct. at\\n\\n2557–59). Because this “produces more unpredictability and arbitrariness than the Due\\n\\n 13\\n\\nProcess Clause tolerates,” id. (quoting Johnson, 135 S. Ct. at 2558), we must conclude\\n\\nthat § 924(c)(3)(B) is unconstitutionally vague.\\n\\n\\n\\n III.\\n\\n The United States concedes that if we adhere to the ordinary-case categorical\\n\\napproach applied by the Supreme Court in Leocal, Johnson, and Dimaya, we must\\n\\ninvalidate § 924(c)(3)(B). The Government, however, urges us to jettison this established\\n\\ninterpretation and adopt a new reading of the challenged statutory language that employs\\n\\na conduct-specific approach to the crime of violence analysis. This conduct-specific\\n\\napproach would consider the facts of each individual case, rather than the statutory\\n\\ndefinition of the underlying offense.\\n\\n Before addressing the merits of the Government’s claim, we must determine\\n\\nwhether to allow it to raise an argument that it previously abandoned. Although the\\n\\nGovernment initially argued in the alternative that a conduct-specific interpretation of\\n\\n§ 924(c)(3)(B) was tenable, Gov. Br. at 28–31, it later expressly disclaimed this reading\\n\\nof § 924(c)(3)(B). The Government did so by submitting to us a written statement that\\n\\n“the position of the United States [is] that the categorical approach is the proper\\n\\ninterpretation of the statute, and it is wholly unaffected by Johnson.” Gov. 28(j) Letter at\\n\\n2 (Oct. 19, 2016). After the Supreme Court decided Dimaya and we ordered\\n\\nsupplemental briefing, the Government again reversed course, deeming a conduct-\\n\\nspecific reading of § 924(c)(3)(B) freshly controlling. Given these changing stances,\\n\\n\\n\\n 14\\n\\nSimms asserts that the Government has forfeited any argument for a conduct-specific\\n\\napproach. 4\\n\\n The Government offers two reasons why we should excuse its voluntary\\n\\nwithdrawal of a conduct-specific interpretation of § 924(c)(3)(B). First, it argues that\\n\\nDimaya represented “an intervening change in the law recognizing an issue that was not\\n\\npreviously available.” United States v. Chittenden, 896 F.3d 633, 639 (4th Cir. 2018)\\n\\n(internal quotation marks omitted). At oral argument, the Government elaborated that the\\n\\nlongstanding position of the United States that § 924(c)(3)(B) required an ordinary-case\\n\\ncategorical approach came “more by way of assumption” than reason, and that Dimaya\\n\\n“caused a lot of searching in the Department [of Justice] to find the right answer.” Oral\\n\\nArg. at 1:27:41, 1:29:00.\\n\\n This claim does not hold water. Dimaya was not the first case to indicate that the\\n\\nordinary-case categorical approach generated serious constitutional doubts. At the very\\n\\nleast, the Government was on notice as to these vagueness concerns after Johnson was\\n\\ndecided in 2015. Indeed, the Ninth Circuit held § 16(b) unconstitutionally vague four\\n\\nmonths later. See Dimaya v. Lynch, 803 F.3d 1110, 1120 (9th Cir. 2015), aff’d sub nom.\\n\\n\\n 4\\n Simms frames this as “waiver,” which we have defined as “identif[ying] an\\nissue, and then explicitly withdraw[ing] it.” United States v. Robinson, 744 F.3d 293, 298\\n(4th Cir. 2014) (internal quotation marks omitted). But waiver, in a technical sense,\\nconcerns a party’s relinquishment of rights before a district court; where a party raises\\nand then knowingly withdraws a claim before the district court, there is no error for us to\\nreview. United States v. Olano, 507 U.S. 725, 733 (1993). Because the Government did\\nnot raise a conduct-specific argument before the district court, its double-turnabout before\\nus is better treated as abandonment or forfeiture of a claim that we retain discretion to\\nreview. Id. at 733–34.\\n\\n 15\\n\\nSessions v. Dimaya, 138 S. Ct. 1204. But a full year thereafter, the Government asserted\\n\\nto us that “the categorical approach [was] the proper interpretation” of § 924(c)(3)(B) and\\n\\nthat this conclusion was “wholly unaffected by Johnson.” Gov. 28(j) Letter at 2. The\\n\\nUnited States has yet to offer a coherent justification for its shifts in position, and its\\n\\ninvocation of Dimaya offers no answer.\\n\\n The Government next asserts that excusing its abandonment would not prejudice\\n\\nSimms, who has had a full opportunity to respond to the Government’s claims. That is\\n\\ncertainly enough to convince us that we can look past the Government’s change of heart,\\n\\ne.g., United States v. Ramos-Cruz, 667 F.3d 487, 496 n.5 (4th Cir. 2012), but not\\n\\nnecessarily that we should do so. As the Government is aware, we routinely exercise our\\n\\ndiscretion in favor of a strict reading of forfeiture. See, e.g., United States v. Brown, 742\\n\\nF. App’x 742, 745 n.3 (4th Cir. 2018) (“[W]e conclude that Brown waived the argument\\n\\nthat 18 U.S.C. § 924(c)(3)(B) (2012) is unconstitutional by failing to raise it in his\\n\\nopening brief.”); United States v. Khoa Dang Hoang, 737 F. App’x 136, 138 n.* (4th Cir.\\n\\n2018) (deeming forfeited defendant’s challenge to validity of Miranda waiver); see also\\n\\nUnited States v. Cannon, 740 F. App’x 785, 791 n.2 (4th Cir. 2018) (deeming forfeited, at\\n\\nGovernment’s suggestion, defendant’s undeveloped sentencing challenges); United States\\n\\nv. Ballard, 727 F. App’x 757, 760 n.* (4th Cir. 2018) (same regarding defendant’s\\n\\nstatutory speedy trial claim).\\n\\n Nevertheless, in this case, we opt to proceed to the merits in view of the\\n\\nexceptional importance and recurring nature of the question presented. Particularly given\\n\\n\\n\\n 16\\n\\nthe markedly effective presentation by the parties and the amici before the en banc court,\\n\\nwe see no reason to defer adjudication of the Government’s current argument.\\n\\n\\n\\n IV.\\n\\n The Government now contends that we must apply a different mode of analysis to\\n\\n§ 924(c)(3)(B), a mode that the Supreme Court expressly rejected in both Dimaya and\\n\\nJohnson.\\n\\n Specifically, the Government insists that the best reading of the statute — which,\\n\\nrecall, asks whether “an offense that is a felony . . . by its nature[] involves a substantial\\n\\nrisk that physical force . . . may be used in the course of committing the offense” —\\n\\ndirects a court to analyze an offender’s specific conduct by diving into the facts before it\\n\\ninstead of limiting the analysis to the offense’s ordinary case. In support of this\\n\\ncontention, the Government argues that “the Supreme Court has been very clear” that the\\n\\ncategorical approach is “essentially a saving construction” designed only to avoid the risk\\n\\nof unfairness that comes with reviewing conduct that underlies long-past convictions.\\n\\nOral Arg. at 1:19:05. Alternatively, the Government claims that even if a conduct-\\n\\nspecific approach is not the best reading of § 924(c)(3)(B), we still must adopt it to avoid\\n\\nstriking down the statute. Three of our sister circuits have embraced the Government’s\\n\\nsuggestion. 5\\n\\n\\n 5\\n See United States v. Douglas, 907 F.3d 1, 16 (1st Cir. 2018), petition for cert.\\nfiled, No. 18-7331 (U.S. Jan. 7, 2019); Ovalles v. United States, 905 F.3d 1231, 1253\\n(11th Cir. 2018) (en banc); United States v. Barrett, 903 F.3d 166, 184 (2d Cir. 2018),\\n(Continued)\\n 17\\n\\n We cannot do so. The Supreme Court did not invent the categorical approach out\\n\\nof whole cloth, as the Government would have us believe. While some other statutes\\n\\ninvoking categorical analysis have been less than clear, the text and structure of\\n\\n§ 924(c)(3)(B) unambiguously require courts to analyze the attributes of an “offense that\\n\\nis a felony . . . by its nature” — that is, categorically. And the Government’s\\n\\ncomparisons to cases involving very different statutes, rather than bolstering its\\n\\npreference for a new mode of analysis, support adherence to the established ordinary-case\\n\\ncategorical approach.\\n\\n A.\\n\\n As a preliminary matter, the Government presents a flawed historical premise. It\\n\\nclaims that the categorical approach is nothing more than a “saving construction,” Oral\\n\\nArg. at 1:19:05, “purely [a] judge-made doctrine” that was “first endorsed” less than\\n\\nthirty years ago, Gov. Supp. Br. at 17 (internal quotation marks omitted). Further, the\\n\\nGovernment asserts, this doctrine is grounded entirely in external considerations far\\n\\nafield from congressional language or intent.\\n\\n\\n\\n\\npetition for cert. filed, No. 18-6985 (U.S. Dec. 3, 2018). But see Davis, 903 F.3d at 485\\n(finding “a suggestion by a minority of justices in [Dimaya]” insufficient to overrule\\ncircuit precedent requiring ordinary-case categorical approach); Eshetu, 898 F.3d at 37\\n(emphasizing that “Dimaya nowise calls into question” circuit precedent requiring “a\\ncategorical approach”); Salas, 889 F.3d at 685 (holding § 924(c)(3)(B) unconstitutionally\\nvague), reh’g and reh’g en banc denied, No. 16-2170 (May 23, 2018) (denying\\nGovernment’s petition for rehearing on constitutional avoidance grounds).\\n\\n\\n 18\\n\\n This is simply not so. Although categorical analysis may be complicated, the\\n\\nrationale for it is simple and long-established: if Congress has conditioned a statutory\\n\\npenalty on commission of an offense generally — rather than on specific acts — courts\\n\\nmust consider the crime as defined, rather than the offender’s conduct. See, e.g., Shepard\\n\\nv. United States, 544 U.S. 13, 19 (2005) (emphasizing Congress’s “language imposing\\n\\nthe categorical approach” in ACCA); Leocal, 543 U.S. at 7 (highlighting Congress’s\\n\\nusage of “offense . . . by its nature” in § 16(b)). Such analysis became more frequent in\\n\\nthe mid-1980s as Congress added general terms like “violent felony,” “crime of\\n\\nviolence,” and “aggravated felony” to the United States Code, but the underlying\\n\\nprinciple is far from novel. Indeed, it has been an important part of American\\n\\njurisprudence for more than a century. See, e.g., U.S. ex rel. Guarino v. Uhl, 107 F.2d\\n\\n399, 400 (2d Cir. 1939) (L. Hand, J.) (explaining that “deporting officials may not\\n\\nconsider the particular conduct for which the alien has been convicted” in determining\\n\\nwhether a crime involved moral turpitude meriting deportation (citing U.S. ex rel. Mylius\\n\\nv. Uhl, 210 F. 860, 863 (2d Cir. 1914))).\\n\\n Moreover, the Supreme Court has always rooted the categorical approach in the\\n\\nstatutory language chosen by Congress and consistently defended this approach as a\\n\\nmeans of effectuating congressional intent. Thus, when analyzing ACCA four years after\\n\\nits passage, the Court looked first to “the language of” the statute, and only then to\\n\\nlegislative history and practical concerns, to conclude that a categorical approach was\\n\\n“the only plausible interpretation of § 924(e)(2)(B)(ii).” Taylor v. United States, 495\\n\\nU.S. 575, 600–02 (1990). Similarly, when defending application of the ordinary-case\\n\\n 19\\n\\ncategorical approach as it relates to ACCA’s residual clause in 2015, the Court again\\n\\nbegan with the statutory text before considering other arguments. Johnson, 135 S. Ct. at\\n\\n2562.\\n\\n The Supreme Court’s interpretation of ACCA in Taylor and Johnson was, of\\n\\ncourse, secondarily informed by considerations beyond the statutory text. But tellingly,\\n\\nthe Court has deemed the text of § 16(b) — a statute far clearer than the ACCA residual\\n\\nclause and materially identical to the statute at issue here — so plain as to speak for itself.\\n\\nThus, in 2004, when the Court first interpreted § 16(b) to require the ordinary-case\\n\\ncategorical approach, it relied only on the text of the statute, and it did not invoke\\n\\nlegislative history or practical concerns. Leocal, 543 U.S. at 7; accord Dimaya, 138 S.\\n\\nCt. at 1204 (plurality opinion) (noting four-Justice plurality, Chief Justice, and\\n\\nGovernment all “accept[ed] that § 16(b), as long interpreted, demands a categorical\\n\\napproach”). The Government’s attempt to rewrite this history is utterly unpersuasive.\\n\\n B.\\n\\n Setting aside the origins of the categorical approach, we have reviewed\\n\\n§ 924(c)(3)(B) on a clean slate and still find no reasonable construction of its text that\\n\\nsupports the Government’s conduct-specific approach. The statutory structure, as well as\\n\\nCongress’s use of materially identical language to implement an ordinary-case\\n\\ncategorical approach in § 16(b), render our conclusion inescapable. Whatever a judge’s\\n\\npersonal feelings as to what does or does not constitute a crime of violence, we are bound\\n\\nto apply the definition that Congress has prescribed. And Congress could hardly have\\n\\nwritten a clearer call for the ordinary-case categorical approach than § 924(c)(3)(B).\\n\\n 20\\n\\n The text of a statute is a court’s first and foremost guide to its meaning. See, e.g.,\\n\\nEsquivel-Quintana v. Sessions, 137 S. Ct. 1562, 1568 (2017) (noting that when\\n\\ninterpreting a statute, courts “begin, as always, with the text”). Here, the plain text of\\n\\n§ 924(c)(3)(B) requires application of the ordinary-case categorical approach. The\\n\\ncombination in § 924(c)(3)(B) of the phrase “offense that is a felony” with the qualifier\\n\\n“by its nature” makes Congress’s intent apparent.\\n\\n As the Government itself admits, the definition of “nature” is “the basic or\\n\\ninherent features, character, or quality of something.” Oxford Dictionary of English 1183\\n\\n(3d ed. 2010). Thus, § 924(c)(3)(B) directs courts to consider only the basic or inherent\\n\\nfeatures of “an offense that is a felony.” 18 U.S.C. § 924(c)(3)(B); see also Dimaya, 138\\n\\nS. Ct. at 1217–18 (plurality opinion) (explaining that phrase “by its nature” directs courts\\n\\n“to figure out what an offense normally . . . entails, not what happened to occur on one\\n\\noccasion”). Had Congress intended a conduct-specific analysis instead, “it presumably\\n\\nwould have said so; other statutes, in other contexts, speak in just that way.” Descamps\\n\\nv. United States, 570 U.S. 254, 267–68 (2013); see, e.g., 18 U.S.C. § 1031(b)(2)\\n\\n(imposing heightened penalties for fraud offenses that “involve[] a conscious or reckless\\n\\nrisk of serious personal injury”); 18 U.S.C. § 2332b(a)(1)(B) (punishing certain\\n\\n“conduct” that “creates a substantial risk of serious bodily injury”).\\n\\n Moreover, we cannot adopt a reading of § 924(c)(3)(B) that renders part of the\\n\\nstatute superfluous over one that gives effect to its “every clause and word.” United\\n\\nStates v. Menasche, 348 U.S. 528, 538–39 (1955) (quoting Inhabitants of Montclair Twp.\\n\\nv. Ramsdell, 107 U.S. 147, 152 (1883)). This well-established rule against surplusage\\n\\n 21\\n\\nfurther cuts against the Government’s conduct-specific reading, which would empty the\\n\\nphrase “by its nature” of meaning. Indeed, even under the Government’s interpretation,\\n\\ngiving “by its nature” meaning would shift the § 924(c)(3)(B) inquiry away from\\n\\nconduct-specific facts and back towards a subjective consideration of that conduct’s\\n\\n“inherent features” — that is to say, another version of ordinary-case analysis.\\n\\n The Government does not even attempt to address this problem. 6 Instead, it\\n\\nsimply quotes a dissent in Dimaya to contend that in the context of § 924(c)(3)(B), “the\\n\\nphrase ‘by its nature’ is reasonably understood to ‘mean only that an offender who\\n\\nengages in risky conduct cannot benefit from the fortuitous fact that physical force was\\n\\nnot actually used during his offense.’” Gov. Supp. Br. at 14 (quoting Dimaya, 138 S. Ct.\\n\\nat 1254 (Thomas, J., dissenting)). One of the dissenters here similarly insists that “by its\\n\\nnature” “broad[ens]” the scope of § 924(c)(3)(B), while another argues (seemingly to the\\n\\ncontrary) that the phrase actually “limits the residual clause” by excluding conduct that\\n\\nrisks force “merely incidentally or by happenstance.”\\n\\n But the Dimaya Court did not embrace any of these readings of this text. And for\\n\\ngood reason: each would still leave “by its nature” wholly superfluous. If we strike that\\n\\nphrase, § 924(c)(3)(B)’s remaining language would require a finding that an offense\\n\\n“involves a substantial risk that physical force . . . may be used in the course of\\n\\ncommitting the offense.” 18 U.S.C. § 924(c)(3)(B) (emphasis added). This text read on\\n\\n 6\\n Nor do any of the courts of appeals that have embraced a conduct-specific\\napproach. For example, while the First Circuit found it “plausible that ‘by its nature’\\nrefers to the real-world conduct of a particular offense,” it did not consider the surplusage\\nproblem that this interpretation creates. Douglas, 907 F.3d at 8.\\n\\n 22\\n\\nits own would still encompass both actual uses of physical force and otherwise “risky”\\n\\nconduct in which force was not used. And the requirement that any risk be “substantial”\\n\\nwould independently exclude “incidental” uses of force. In other words, under the\\n\\nGovernment’s conduct-specific reinterpretation, § 924(c)(3)(B) would have the same\\n\\nmeaning without the phrase “by its nature” as it would with this phrase. This would drain\\n\\nthe phrase “by its nature” of any effect, violating a cardinal rule of statutory construction.\\n\\n The conclusion that “crime of violence” must be defined categorically is made\\n\\neven plainer when we consider the statutory context, as we must. See Davis v. Mich.\\n\\nDep’t of Treasury, 489 U.S. 803, 809 (1989) (“[W]ords of a statute must be read in their\\n\\ncontext and with a view to their place in the overall statutory scheme.”). The\\n\\nGovernment concedes that § 924(c)(3)(A), which covers one half of the “crime of\\n\\nviolence” definition in § 924(c), mandates a categorical approach. Gov. Supp. Br. at 4. It\\n\\nwould stand to reason that § 924(c)(3)(B), the other half of this definition, also requires a\\n\\ncategorical approach rather than analysis of “the facts of each defendant’s conduct.”\\n\\nTaylor, 495 U.S. at 601.\\n\\n This conclusion is confirmed by the Supreme Court’s refusal to give statutory text\\n\\nvariable meanings “depending on the presence or absence of constitutional concerns in\\n\\neach individual case,” explaining that such a “novel interpretive approach . . . would\\n\\nrender every statute a chameleon.” Clark v. Martinez, 543 U.S. 371, 382 (2005). Under\\n\\nthe longstanding interpretation of § 924(c)(3), the statute’s single reference to an “offense\\n\\nthat is a felony” has a single meaning: it refers to a crime as defined by statute.\\n\\nAccepting the Government’s interpretation would require us instead to give this phrase\\n\\n 23\\n\\ntwo contradictory meanings, depending on whether the force clause or the residual clause\\n\\nis in play. Specifically, the Government would have us read “offense that is a felony” to\\n\\nrefer to an offense as defined by statute in prosecutions under the force clause, but to\\n\\ncase-specific conduct in prosecutions under the residual clause. We refuse to so distort\\n\\nthe statutory text.\\n\\n Furthermore, § 924(c)(1)(A), which outlines the elements of a § 924(c) violation,\\n\\nexpressly refers to “a crime of violence . . . that provides for an enhanced punishment if\\n\\ncommitted by the use of a deadly or dangerous weapon or device.” This phrasing would\\n\\nmake no sense under a conduct-specific definition of “crime of violence,” as only\\n\\nstatutes, not conduct-specific facts, can “provide[] for” an amount of punishment. 7\\n\\n\\n 7\\n The Government responds by citing the phrase “during and in relation to any\\ncrime of violence,” 18 U.S.C. § 924(c)(1)(A) (emphasis added), to argue for a conduct-\\nspecific reading of “crime of violence.” The argument fails. In fact, it is not unusual to\\ndescribe specific conduct or circumstances (like use of a firearm) “in relation to” a\\ncategorically defined generic offense (like a crime of violence). For example, in\\nprosecutions under the force clause, § 924(c)(1)(A) itself refers to specific conduct (use\\nof a firearm) “during and in relation to” a generic offense (a categorically defined crime\\nof violence). In § 924(c) prosecutions where the predicate offense is a “drug trafficking\\ncrime” rather than a “crime of violence,” § 924(c)(1)(A) again refers to specific conduct\\n“during and in relation to” a categorically defined crime. Congress has utilized an\\nanalogous approach in other statutes that incorporate the categorical “crime of violence”\\ndefinition in § 16. See, e.g., 18 U.S.C. § 929(a)(2) (criminalizing use of armor-piercing\\nammunition “during and in relation to the commission of a crime of violence”); 18\\nU.S.C. § 1956(a)(3) (imposing criminal penalties for “conduct[ing] a financial transaction\\ninvolving property . . . used to conduct or facilitate” a crime of violence); 18 U.S.C.\\n§ 25(b) (multiplying maximum sentence for adult who “intentionally uses a minor to\\ncommit a [federal] crime of violence”). And the Supreme Court has similarly interpreted\\na misdemeanor domestic violence statute to require a circumstance-specific analysis of\\nwhether a crime was “committed by” an offender with a “specified domestic\\nrelationship” to the victim, and a categorical analysis as to whether the crime requires\\nforce as an element. United States v. Hayes, 555 U.S. 415, 426 (2009).\\n\\n\\n 24\\n\\n Finally, the Government would have us interpret the materially identical 34-word\\n\\nphrase in § 924(c)(3)(B) and § 16(b) in entirely different ways. 8 This argument flies in\\n\\nthe face of the traditional rule that “a legislative body generally uses a particular word\\n\\nwith a consistent meaning in a given context.” Erlenbaugh v. United States, 409 U.S.\\n\\n239, 243 (1972). Whatever force this interpretive presumption may have as to one\\n\\n“particular word,” it must carry more as applied to the 34-word phrase replicated in\\n\\n§ 924(c)(3)(B) and § 16(b). See supra n.8. The presumption has more force still because\\n\\nCongress initially added “crime of violence” to § 924(c) and created § 16(b) in the same\\n\\nlegislative enactment. 9 See Gustafson v. Alloyd Co., Inc., 513 U.S. 561, 570 (1995)\\n\\n(“[T]he normal rule of statutory construction” is that “identical words used in different\\n\\nparts of the same act are intended to have the same meaning.” (internal quotation marks\\n\\nomitted)); Erlenbaugh, 409 U.S. at 244 (noting that presumption of consistent meaning\\n\\n“certainly makes the most sense when the statutes were enacted by the same legislative\\n\\nbody at the same time”). Thus, it is unsurprising that the Government has been unable to\\n\\n\\n 8\\n Compare 18 U.S.C. § 924(c)(3) (“offense that is a felony and[] . . . that by its\\nnature, involves a substantial risk that physical force against the person or property of\\nanother may be used in the course of committing the offense”), with 18 U.S.C. § 16(b)\\n(“offense that is a felony and that, by its nature, involves a substantial risk that physical\\nforce against the person or property of another may be used in the course of committing\\nthe offense”).\\n 9\\n Comprehensive Crime Control Act, Pub. L. No. 98–473, tit. II, § 1005(a), 98\\nStat. 1976, 2138–39 (1984) (amending § 924(c) to reference “crime[s] of violence,” as\\ndefined in new § 16); id. § 1001, 98 Stat. at 2136 (enacting § 16); see also id. §§ 1801–\\n03, 98 Stat. at 2185 (enacting ACCA). Congress enacted § 924(c)(3)(B) two years later,\\nadopting wording materially identical to § 16(b). Firearm Owners’ Protection Act, Pub.\\nL. No. 99–308, § 104, 100 Stat. 449, 456–59 (1986).\\n\\n 25\\n\\ncite even one case in which the Supreme Court or this court have interpreted two\\n\\nmaterially identical statutes differently, as it urges us to do with § 924(c)(3)(B) and\\n\\n§ 16(b).\\n\\n In sum, our de novo application of ordinary textual analysis yields a mountain of\\n\\n“textual evidence” that § 924(c)(3)’s residual clause — “like ACCA’s, except still more\\n\\nplainly” — “has no ‘plausible’ fact-based reading.” Dimaya, 138 S. Ct. at 1218 (plurality\\n\\nopinion) (quoting Johnson, 135 S. Ct. at 2562); see also id. at 1235 (Roberts, C.J.,\\n\\ndissenting) (explaining that the ordinary-case categorical approach outlined in Leocal\\n\\n“provides a model for how courts should assess whether a particular crime ‘by its nature’\\n\\ninvolves a risk of the use of physical force” (quoting § 16(b))). 10\\n\\n C.\\n\\n Resisting this conclusion, the Government contends that the phrases “offense,”\\n\\n“felony,” “by its nature,” “involves,” and “committing the offense” in § 924(c)(3)(B)\\n\\n“compel” a conduct-specific approach. Gov. Supp. Br. at 10.\\n\\n Each of these terms can be susceptible to a conduct-specific analysis in isolation.\\n\\nSee Nijhawan v. Holder, 557 U.S. 29, 33–34 (2009) (construing statute containing the\\n\\nwords “offense” and “felony”); Hayes, 555 U.S. at 420–29 (construing statute containing\\n\\nthe word “offense”); Taylor, 495 U.S. at 600–01 (construing statute containing the word\\n\\n 10\\n Despite the foregoing analysis, Judge Richardson maintains that we “rewrite[]\\nhistory” to “claim[] that the Supreme Court has already resolved this issue.” Of course,\\nwe claim no such thing. Perhaps our colleague only means to assert that our conclusions\\naccord with the reasoning of four Justices interpreting materially identical text mere\\nmonths ago, as well as the indication of the Chief Justice; to that assertion, we readily\\nagree.\\n\\n 26\\n\\n“involves”); United States v. Price, 777 F.3d 700, 708–09 (4th Cir. 2015) (construing\\n\\nstatute containing the terms “by its nature” and “involves”). But that hardly establishes\\n\\nthat these five terms are susceptible to such a reading when appearing together in a single\\n\\nshort statute. Rather, each of the cases on which the Government relies involves only\\n\\nfragments of the language in § 924(c)(3). Just as importantly, in none of these cases did\\n\\nthe court actually rely on these fragments in reaching its holding. In fact, the reasoning\\n\\nthat underlies each of the Government’s cases buttresses our conclusion that the text of\\n\\n§ 924(c)(3)(B) requires an ordinary-case categorical approach.\\n\\n Consider Nijhawan and Hayes. In both opinions, the Supreme Court interpreted\\n\\nstatutes that paired a reference to “offense” with detailed qualifiers far too specific to\\n\\nrefer to generic crimes. Nijhawan concerned an immigration statute that included only\\n\\noffenses “involv[ing] fraud or deceit in which the loss to the victim or victims exceed[ed]\\n\\n$10,000.” 8 U.S.C. § 1101(a)(43)(M)(i). In Hayes, the qualifier was even more specific:\\n\\nthe relevant criminal statute only covered offenses “committed by a current or former\\n\\nspouse, parent, or guardian of the victim, by a person with whom the victim shares a\\n\\nchild in common, by a person who is cohabiting with or has cohabited with the victim as\\n\\na spouse, parent, or guardian, or by a person similarly situated to a spouse, parent, or\\n\\nguardian of the victim.” 18 U.S.C § 921(a)(33)(A)(ii).\\n\\n Faced with these precise qualifiers, the Supreme Court concluded that Congress\\n\\nmust have intended a conduct-specific approach for these statutes to have any force. See\\n\\nNijhawan, 557 U.S. at 37–38 (holding that “to have any meaning at all,” qualifier “must\\n\\nrefer to the particular circumstances in which an offender committed the crime”); Hayes,\\n\\n 27\\n\\n555 U.S. at 427 (explaining that categorical reading of qualifier would render statute “a\\n\\ndead letter in some two-thirds of the States from the very moment of its enactment”\\n\\n(internal quotation marks omitted)). The specificity of each statute — not any talismanic\\n\\nuse of “offense” or “involves” — was the crux of both rulings.\\n\\n The “substantial risk of physical force” proviso in § 924(c)(3)(B) is a far cry from\\n\\nthe specific qualifiers in Nijhawan and Hayes. Rather, the proviso in § 924(c)(3)(B) is\\n\\nmaterially identical to that in § 16(b), and it is similar to the force requirement in statutes\\n\\nthat employ the elements-based categorical approach, like § 924(c)(3)(A) and § 16(a).\\n\\nNijhawan and Hayes thus highlight the relative “absence of terms alluding to a crime’s\\n\\ncircumstances” in § 924(c)(3)(B) beyond those also present in § 16(b). Dimaya, 138 S.\\n\\nCt. at 1218 (plurality opinion); see also id. at 1217 (“Simple references to a ‘conviction,’\\n\\n‘felony,’ or ‘offense,’ we have stated, are ‘read naturally’ to denote the ‘crime as\\n\\ngenerally committed.’” (quoting Nijhawan, 557 U.S. at 34)). The differences between\\n\\nthese statutes and § 924(c)(3)(B) reinforce rather than defeat a categorical reading here.\\n\\n Moreover, despite seeking to rely on Nijhawan, the Government overlooks one of\\n\\nNijhawan’s key teachings. For there, the Court expressly recognized that where\\n\\nCongress “uses similar statutory language and similar statutory structure in two adjoining\\n\\nprovisions, it normally intends similar interpretations.” Nijhawan, 557 U.S. at 39. Here,\\n\\nCongress did not just use “similar” language in the “two adjoining provisions” of\\n\\n§ 924(c)(3)(A) and § 924(c)(3)(B): it tied both definitions to the same use of the\\n\\nintroductory phrase “offense that is a felony.” As we have already explained, the\\n\\n\\n\\n 28\\n\\nGovernment’s reading would give that phrase a conduct-specific interpretation under one\\n\\nprovision and a categorical interpretation under the adjoining provision.\\n\\n As to Taylor, the Government’s reliance is inexplicable. It cites that case alone for\\n\\nthe proposition that “the Supreme Court has previously relied on the absence of the word\\n\\n‘involves’ as indicating that a categorical approach is required.” Gov. Supp. Br. at 13\\n\\n(citing Taylor, 495 U.S. at 600). But Taylor did not rely on the absence of the word\\n\\n“involves” to require use of the categorical approach. The Taylor Court simply\\n\\nrecognized that the ACCA force clause defined a “violent felony” as one that “‘has as an\\n\\nelement’ — not any crime that, in a particular case, involves — the use or threat of\\n\\nforce.” 495 U.S. at 600 (quoting § 924(e)(2)(B)(i)). The Government’s contrary\\n\\nargument is especially unconvincing given that the Supreme Court has held that the\\n\\nACCA residual clause and § 16(b), both of which use the word “involves,” mandate the\\n\\nordinary-case categorical approach. E.g., Johnson, 135 S. Ct. at 2561–62; Leocal, 543\\n\\nU.S. at 7.\\n\\n The Government’s reliance on Taylor, like its reliance on Nijhawan, also ignores a\\n\\ncritical element of the Supreme Court’s analysis. The Taylor Court reasoned that the\\n\\nterm “burglary” as used in ACCA “most likely refer[red] to the elements of the statute of\\n\\nconviction, not to the facts of each defendant’s conduct,” in part because of its proximity\\n\\nto the ACCA force clause. 495 U.S. at 600–01. In this case, the proximity of\\n\\n§ 924(c)(3)(B) to the force clause in § 924(c)(3)(A) warrants a similar inference. Thus,\\n\\nTaylor offers no more support to the Government’s novel argument than Nijhawan or\\n\\nHayes.\\n\\n 29\\n\\n Finally, the Government emphasizes that we have applied a conduct-specific\\n\\nanalysis to a provision of the Sex Offender Registration and Notification Act (“SORNA”)\\n\\nthat uses the phrase “by its nature.” Price, 777 F.3d at 708–09. But in fact, each step of\\n\\nour textual analysis in that case supports a contrary result here.\\n\\n In Price, we followed Nijhawan and Hayes to hold that “where a statute contains\\n\\nlanguage that . . . refers to specific circumstances or conduct,” “Congress meant to allow\\n\\nthe circumstance-specific approach’s more searching factual inquiry.” Id. at 708\\n\\n(alteration in original) (internal quotation marks omitted). Here, Congress’s omission of\\n\\nthis conduct-specific language in § 924(c)(3)(B) warrants the opposite inference. In\\n\\nPrice, we noted that because Congress referenced “elements” in one subsection of\\n\\nSORNA, its contrasting terminology of “a criminal offense” in the next required a\\n\\nbroader reading under the canon of meaningful variation. Id. at 708–09. Here, the\\n\\nordinary-case categorical approach of § 924(c)(3)(B) is already broader than the\\n\\nelements-based approach of § 924(c)(3)(A), and both clauses refer to the same usage of\\n\\nthe phrase “offense that is a felony.” The canon of meaningful variation thus offers the\\n\\nGovernment no support. And in Price, we recognized that because SORNA made\\n\\n“explicit reference to the ‘conduct’ underlying a prior offense, as well as the ‘nature’ of\\n\\nthat conduct,” it “refer[red] to how an offense was committed — not a generic offense.”\\n\\nId. at 709 (quoting Nijhawan, 557 U.S. at 37–39). Here, Congress wrote § 924(c)(3)(B)\\n\\n(unlike SORNA) to refer not to “conduct . . . by its nature” but “an offense that is a\\n\\nfelony . . . by its nature.” 18 U.S.C. § 924(c)(3)(B). Price supports adherence to the\\n\\n\\n\\n 30\\n\\nordinary-case categorical approach, rather than adoption of the Government’s new\\n\\nconstruction.\\n\\n To summarize, the text, structure, and context of § 924(c)(3)(B) clearly mandate\\n\\nuse of the ordinary-case categorical approach, as do all relevant precedents. Given the\\n\\nGovernment’s concession that use of this mode of analysis renders the statute\\n\\nunconstitutionally vague, this dooms the Government’s defense of the statute.\\n\\n\\n\\n V.\\n\\n As the Supreme Court has repeatedly instructed, when statutory language is clear,\\n\\n“judicial inquiry is complete.” Conn. Nat’l Bank v. Germain, 503 U.S. 249, 254 (1992)\\n\\n(internal quotation marks omitted). Refusing to abide by this instruction, the Government\\n\\nheavily relies on considerations unrelated to the unambiguous text to support its new\\n\\nconduct-specific interpretation of § 924(c)(3)(B). We doubt such external considerations\\n\\nare relevant. But to the extent that they are, they confirm our decision to adhere to the\\n\\nordinary-case categorical approach rather than adopting the Government’s new conduct-\\n\\nspecific reinterpretation.\\n\\n A.\\n\\n We begin with practical considerations. The Government contends that\\n\\nnotwithstanding the statutory text, we should apply a conduct-specific approach to\\n\\n§ 924(c)(3)(B) because it, unlike the ACCA residual clause or some applications of\\n\\n§ 16(b), always involves charges prosecuted contemporaneously with any underlying\\n\\ncrimes of violence. According to the Government, this means “the categorical approach\\n\\n 31\\n\\nserves no purpose” in the context of § 924(c)(3)(B). Gov. Supp. Br. at 20. Even setting\\n\\naside the plain text of the statute, the argument fails for two fundamental reasons.\\n\\n First, § 924(c)(3)(B)’s failure to require a court to assess past conduct hardly\\n\\ncompels rejection of the categorical approach. Rather, the categorical approach applies to\\n\\na number of statutes that require no assessment of past conduct. Most notably, the\\n\\nGovernment itself concedes that Congress has “require[d] a categorical approach” in\\n\\ndefining a “crime of violence” under the force clause, § 924(c)(3)(A), the only other\\n\\nsubsection of § 924(c)(3). Gov. Supp. Br. at 4. And the force clause, like the\\n\\nneighboring residual clause challenged here, applies only to contemporaneous offenses,\\n\\nnot prior convictions.\\n\\n Congress, through § 16, has also applied the categorical approach to many other\\n\\nstatutes that similarly involve contemporaneous prosecutions. See, e.g., 18 U.S.C.\\n\\n§ 1952(a)(2) (criminalizing travel or use of mail with intent to commit any “crime of\\n\\nviolence”); 18 U.S.C. § 842(p)(2)(A) (prohibiting teaching, demonstration, or\\n\\ndissemination of information intended for use in committing a “crime of violence”); 18\\n\\nU.S.C. § 3663A(c)(1)(A)(i) (mandating restitution to victims of certain “crime[s] of\\n\\nviolence,” citing § 16); 18 U.S.C. § 5032 (permitting federal trials of juveniles in certain\\n\\ncases where “the offense charged is a crime of violence that is a felony”). 11\\n\\n\\n 11\\n The Government also suggests that “Sixth Amendment concerns . . . led to the\\ncategorical approach” in ACCA and § 16(b) because conduct-specific interpretations of\\nthose statutes would require judicial fact-finding at sentencing, an issue that\\n§ 924(c)(3)(B) does not present. Gov. Supp. Br. at 20. In fact, non-sentencing\\napplications of § 16(b) — including its incorporation into the immigration statute\\n(Continued)\\n 32\\n\\n The second reason the Government’s practical argument fails is that, contrary to\\n\\nits suggestion otherwise, use of the categorical approach in § 924(c) does serve important\\n\\npurposes. Congress acted with good reasons in mandating a categorical approach here,\\n\\neven if the real-world benefits differ from those that arise in the context of prior\\n\\nconvictions. Specifically, § 924(c)’s categorical “crime of violence” analysis serves the\\n\\npurpose of limiting the statute’s penalties to specific classes of federal crimes where the\\n\\nuse of a firearm is especially dangerous. See Rosemond, 572 U.S. at 75 (“§ 924(c) . . .\\n\\npunishes the temporal and relational conjunction of two separate acts, on the ground that\\n\\ntogether they pose an extreme risk of harm.”); cf. Solem v. Helm, 463 U.S. 277, 292\\n\\n(1983) (stating relevance of “gravity of the offense” to proportionality of sentence).\\n\\n Congress amended § 924(c) over time to accomplish this very purpose. Before\\n\\n1984, § 924(c) criminalized the use or unlawful carrying of a firearm in conjunction with\\n\\n“any [federal] felony.” 18 U.S.C. § 924(c) (1982). In 1984, Congress narrowed the\\n\\nstatute to “crime[s] of violence,” defined in relevant part as they are today.\\n\\nComprehensive Crime Control Act, § 1005(a), 98 Stat. at 2138–39. Two years later,\\n\\nCongress limited these “crimes of violence” to felonies while adding “drug trafficking\\n\\ncrimes” to the statute’s scope. Firearm Owners’ Protection Act, § 104, 100 Stat. at 456–\\n\\n\\n\\n\\nreviewed in both Leocal and Dimaya — similarly present no Sixth Amendment concerns.\\nMoreover, even more fundamental constitutional values militate against a conduct-\\nspecific approach here. For where Congress has spoken so plainly, judicially revising its\\nwork would threaten the basic structural principle of separation of powers. See, e.g.,\\nLewis v. City of Chicago, 560 U.S. 205, 215 (2010) (“It is not for us to rewrite the statute\\n. . . to achieve what we think Congress really intended.”).\\n\\n 33\\n\\n59. Thus, Congress has amended § 924(c) to make it crystal clear that not every federal\\n\\nfelony involving use of a gun constitutes a “crime of violence.” Rather, the modern\\n\\nstatute requires the prosecution to make two distinct showings: first, that the defendant\\n\\nutilized a firearm, and second, that the defendant did so in conjunction with not just any\\n\\nfelony, but specifically a crime of violence or drug trafficking crime. Smith, 508 U.S. at\\n\\n227–28.\\n\\n The Government’s interpretation of § 924(c)(3)(B) would eliminate Congress’s\\n\\nintentional choice to narrow the application of § 924(c) from “any felon[ies]” to only\\n\\n“crime[s] of violence” and “drug trafficking crime[s].” As the Government\\n\\nacknowledges, its reading of the statute would require juries to consider at trial whether\\n\\nan offender’s specific conduct involved a substantial risk of physical force. But the use,\\n\\ncarrying, or possession of a firearm, standing alone, will always suffice to generate such a\\n\\nrisk in a conduct-specific analysis, regardless of the nature of the underlying offense. If\\n\\nwe were to adopt a conduct-specific approach, we would in effect judicially repeal the\\n\\n1984 and 1986 congressional amendments to § 924(c).\\n\\n Attempting to address this problem, the Government claims that jurors could avoid\\n\\ncollapsing the firearm and crime of violence elements if they were instructed not to find a\\n\\ncrime of violence based solely on the presence of a firearm. See Ovalles, 905 F.3d at\\n\\n1250 n.8 (adopting Government’s proposed instruction). But this solution offers no\\n\\naffirmative principle to guide jury decision-making. How, exactly, are jurors to keep\\n\\nthese two showings apart? Should they cross out facts involving the firearm? Imagine\\n\\nthe firearm wasn’t there? Pretend it was inoperable? Instead of condemning jurors to\\n\\n 34\\n\\nsuch an ill-defined inquiry, categorical analysis limits § 924(c)’s additional sanctions to\\n\\nthe discrete and particularly serious classes of felonies selected by Congress — drug\\n\\ntrafficking crimes and crimes of violence. 12\\n\\n In sum, even if practical considerations could influence our construction of the\\n\\nclear text of § 924(c)(3)(B), they do not offer the Government any refuge.\\n\\n B.\\n\\n Having opened the door to external considerations, it is noteworthy that the\\n\\nGovernment does not ask us to examine the legislative history of § 924(c). Perhaps that\\n\\nis because the legislative history suggests that Congress intended a categorical approach.\\n\\nRecall that before 1984, § 924(c) penalized the use of a firearm in conjunction with any\\n\\nfederal felony. A 1979 Senate bill unsuccessfully proposed amending § 924(c) to narrow\\n\\nits application to crimes of violence, largely as defined today. Criminal Code Reform\\n\\nAct of 1979, S. 1722, 96th Cong. § 1823 (1979). The Senate Judiciary Committee stated\\n\\nit was “doubtful” that “felonies involving the possession of narcotics with intent to\\n\\ndistribute . . . would be considered by their nature to involve a substantial risk of the use\\n\\nof physical force against another.” S. Rep. No. 96–553, at 849 n.43 (1980). If\\n\\n§ 924(c)(3)(B) required a conduct-specific analysis, this statement would make no sense,\\n\\n\\n\\n 12\\n Judge Wilkinson contends that we “derogat[e] the fact-finding function” of trial\\ncourts in a purported “arrogation of authority.” Far from it. We honor the difficult work\\nof our colleagues on the trial courts by eliminating the need to waste time and energy\\ninterpreting an unconstitutional statute. Our holding rests not on a lack of respect for the\\nexcellent hard work of district judges, but on the inability of this court to rewrite an\\nunambiguous congressional directive.\\n\\n 35\\n\\nbecause using a firearm during and in relation to a narcotics felony would almost\\n\\ncertainly generate a substantial risk of force.\\n\\n Congress did not enact this specific bill. But it did subsequently limit § 924(c) to\\n\\ncrimes of violence in 1984, and it defined the term “crime of violence” in § 16 at the\\n\\nsame time. Comprehensive Crime Control Act, §§ 1001, 1005(a), 98 Stat. at 2136, 2138–\\n\\n39. The Senate Judiciary Committee explained that it intended the revised statute to\\n\\ninclude “all persons who commit Federal crimes of violence, including those crimes set\\n\\nforth in statutes which already provide for enhanced sentences for their commission with\\n\\na dangerous weapon.” S. Rep. No. 98–225, at 313 (1983) (emphasis added). The\\n\\nCommittee additionally noted that the “crime of violence” limitation “expand[ed] the\\n\\nscope of predicate offenses . . . by including some violent misdemeanors, but restrict[ed]\\n\\nit by excluding non-violent felonies.” Id. at 313 n.9 (emphasis added). Though not\\n\\ndispositive, the Committee’s language again supports a categorical interpretation.\\n\\n But, like practical considerations, quotes from committee reports cannot and do\\n\\nnot control our reading of § 924(c)(3)(B). We note, however, that the Government has\\n\\nproduced nothing from the legislative record to support its conduct-specific\\n\\ninterpretation. And if Congress truly intended the materially identical text in § 16(b) and\\n\\n§ 924(c)(3)(B) to embody such divergent approaches, we would expect to find some\\n\\nexplanation of that divergence. Instead, the legislative history of § 924(c)(3)(B) offers\\n\\nthe Government no assistance.\\n\\n\\n\\n\\n 36\\n\\n C.\\n\\n The bedrock doctrine of stare decisis further weakens the Government’s position.\\n\\nAdherence to precedent is the preferred course for courts “because it promotes the\\n\\nevenhanded, predictable, and consistent development of legal principles, fosters reliance\\n\\non judicial decisions, and contributes to the actual and perceived integrity of the judicial\\n\\nprocess.” Payne v. Tennessee, 501 U.S. 808, 827 (1991).\\n\\n Of course, stare decisis “is not an inexorable command.” Id. at 828. But\\n\\nprecedent exerts a particularly “powerful” pull in the context of “settled statutory\\n\\nmeaning” because “Congress remains free to alter what [the courts] have done.”\\n\\nShepard, 544 U.S. at 23 (internal quotation marks omitted).\\n\\n Here, the considered circuit consensus, pre-Dimaya, that § 924(c)(3)(B) requires\\n\\nan ordinary-case categorical approach strongly favors adherence to such an\\n\\ninterpretation. 13 “In this case, time has enhanced even the usual precedential force,”\\n\\n\\n 13\\n See, e.g., United States v. Taylor, 814 F.3d 340, 377 (6th Cir. 2016) (“Section\\n924(c)(3)(B) . . . does not allow a court to consider risk-related conduct beyond that\\nwhich is an element of the predicate crime,” because “[t]he phrase ‘by its nature’\\nindicates that a court’s analysis . . . is confined to the offense itself.”); United States v.\\nFuertes, 805 F.3d 485, 498–99 (4th Cir. 2015) (applying categorical approach under\\n§ 924(c)(3)(B)); United States v. McGuire, 706 F.3d 1333, 1336–37 (11th Cir. 2013)\\n(“We employ this categorical approach because of the statute’s terms: It asks whether\\n[the defendant] committed ‘an offense’ that . . . ‘by its nature, involves a substantial risk\\nthat physical force against the person or property of another may be used.’”), overruled in\\nOvalles, 905 F.3d at 1253; United States v. Acosta, 470 F.3d 132, 134–37 (2d Cir. 2006)\\n(applying categorical approach under § 924(c)(3)(B)), overruled in Barrett, 903 F.3d at\\n178; United States v. Munro, 394 F.3d 865, 870–71 (10th Cir. 2005) (explaining that\\n§ 924(c)(3)(B) determination is a “legal conclusion” and applying categorical analysis);\\nUnited States v. Jennings, 195 F.3d 795, 797–98 (5th Cir. 1999) (stating that use of “by\\nits nature” in § 924(c)(3)(B) “requires courts to determine whether an offense constitutes\\n(Continued)\\n 37\\n\\nShepard, 544 U.S. at 23, because the federal courts of appeals have interpreted\\n\\n§ 924(c)(3)(B) to preclude conduct-specific analysis for decades. And although Congress\\n\\namended § 924(c) repeatedly as this consensus built, it never materially changed the\\n\\ndefinition of “crime of violence” after 1986. See, e.g., Pub. L. No. 105–386, § 1, 112\\n\\nStat. 3469, 3469 (1998) (adding “possess[ing] a firearm” “in furtherance of” specified\\n\\ncrimes to § 924(c)); Pub. L. No. 109–92, § 6, 119 Stat. 2095, 2102 (2005) (creating\\n\\n§ 924(c)(5) to impose additional penalties for armor-piercing ammunition).\\n\\n Circuit case law (even if unanimous, as here) carries less weight than Supreme\\n\\nCourt jurisprudence, and we are hesitant to over-analyze congressional inaction. But we\\n\\nwould be remiss to discount the fact that between at least 1994 and April 2018, every\\n\\n§ 924(c) conviction of which we are aware relied on precedents treating crime of violence\\n\\ndeterminations under § 924(c)(3)(B) (not to mention those under § 16(b)) 14 as questions\\n\\n\\n\\n\\na crime of violence without examining the underlying facts surrounding the conviction”\\n(internal quotation marks omitted)); United States v. Kennedy, 133 F.3d 53, 56–57 (D.C\\nCir. 1998) (under § 924(c)(3)(B), “the question is whether the crime with which\\n[appellant] was charged constituted a . . . crime of violence” under a “categorical\\napproach” (internal quotation marks omitted)); United States v. Amparo, 68 F.3d 1222,\\n1225–26 (9th Cir. 1995) (“[A]pplication of a categorical approach to section 924(c)(3)(B)\\nis required by our cases.”); United States v. Moore, 38 F.3d 977, 979 (8th Cir. 1994)\\n(emphasizing reference to “by its nature” in § 924(c)(3)(B) and holding that “[t]o\\ndetermine the nature of a crime requires an examination of the elements which compose\\nit, . . . not . . . an exploration of the underlying facts”), abrogation on other grounds\\nrecognized, United States v. Torres-Villalobos, 487 F.3d 607, 616 (8th Cir. 2007).\\n 14\\n See, e.g., Jobson v. Ashcroft, 326 F.3d 367, 372 (2d Cir. 2003) (deeming the\\ncategorical approach “not only consistent with precedent and sound policy,” but “also\\nnecessary in view of the language of” § 16(b) (internal quotation marks omitted));\\nAragon, 983 F.2d at 1313 (“[T]he plain language of § 16(b) mandates that the court\\n(Continued)\\n 38\\n\\nof law requiring categorical analysis. Stability, consistency, and coherence therefore\\n\\ncounsel against the Government’s rejection of this approach.\\n\\n D.\\n\\n Finally, a trio of remaining considerations further confirm our adherence to the\\n\\nordinary-case categorical approach or otherwise offer no support to the Government.\\n\\n Although we have chosen not to treat the Government’s withdrawal of its conduct-\\n\\nspecific interpretation as abandonment, it remains notable that the United States\\n\\nembraced an ordinary-case categorical reading of this language for years, and even\\n\\ndisclaimed a conduct-specific reading after Johnson. In Dimaya, for example, the\\n\\nGovernment “accept[ed]” that materially identical text in § 16(b), as incorporated into the\\n\\nImmigration and Nationality Act, “demand[ed] a categorical approach.” Dimaya, 138 S.\\n\\nCt. at 1216. It did so even though a conduct-specific inquiry in that case, which involved\\n\\na deportation determination, raised none of the Sixth Amendment concerns implicated in\\n\\nthe context of criminal sentencing. The Government was right to take this position: a\\n\\nmajority of Justices in both Johnson and Dimaya accepted this reading and declined to\\n\\nreinterpret the ACCA residual clause and § 16(b) to employ a conduct-specific approach.\\n\\nDimaya, 138 S. Ct. at 1216–18 (plurality opinion); id. at 1235 (Roberts, C.J., dissenting)\\n\\n(citing Leocal, 543 U.S. at 10–11); Johnson, 135 S. Ct. at 2561–62. Regardless of the\\n\\n\\n\\n\\nembark upon a categorical approach to determine whether a particular crime, ‘by its\\nnature,’ qualifies as a ‘crime of violence.’”).\\n\\n\\n 39\\n\\nGovernment’s rationale, its most recent change of position can only be read as a late-\\n\\nbreaking effort to resuscitate a twice-rejected argument.\\n\\n Moreover, if the Government were correct and the text at issue here were truly so\\n\\nambiguous as to lend itself to two very different forms of analysis — an ordinary-case\\n\\ncategorical approach in § 16(b) and a conduct-specific approach in § 924(c)(3)(B) — the\\n\\nrule of lenity might nonetheless yield the same result that we reach now. For in the case\\n\\nat hand, this doctrine would tilt in favor of Simms. See Hayes, 555 U.S. at 436 (Roberts,\\n\\nC.J., dissenting) (describing statute that was ambiguous about categorical approach as\\n\\n“textbook case for application of the rule of lenity”).\\n\\n Further, we are not persuaded by the Government’s contention that “the strong\\n\\nsocietal interest in finality,” particularly as it pertains to guilty pleas, favors saving\\n\\n§ 924(c)(3)(B) rather than striking it down. Lee v. United States, 137 S. Ct. 1958, 1967\\n\\n(2017). Under the unusual circumstances presented here, finality cuts both ways. The\\n\\nparties agree that the longstanding interpretation of § 924(c)(3)(B) is unconstitutional.\\n\\nAccordingly, past convictions employing the ordinary-case categorical approach will be\\n\\ncalled into question regardless of whether we invalidate the statute or adopt a new\\n\\nconduct-specific reading that all rejected before Dimaya. If concerns about opening the\\n\\nfloodgates are relevant to our interpretation of § 924(c)(3)(B) — and we doubt that they\\n\\nare — they do not favor either reading.\\n\\n\\n\\n\\n 40\\n\\n VI.\\n\\n Perhaps recognizing that its textual analysis of § 924(c)(3)(B) is untenable and its\\n\\nreliance on external considerations unconvincing, the Government urges us to embrace its\\n\\nnew reading of the statute as a matter of constitutional avoidance. We will not “lightly\\n\\nascribe . . . an unconstitutional intent” to Congress. Ward v. Dixie Nat’l Life Ins. Co.,\\n\\n595 F.3d 164, 177 (4th Cir. 2010). But given the clear language of § 924(c)(3)(B), we\\n\\nlack the power to avoid its constitutional infirmity.\\n\\n We are “obligated to construe [a] statute to avoid [constitutional] problems.” INS\\n\\nv. St. Cyr, 533 U.S. 289, 300 (2001). However, we may do this only if such a reading is\\n\\n“fairly possible,” id. (internal quotation marks omitted), “after the application of ordinary\\n\\ntextual analysis,” Jennings v. Rodriguez, 138 S. Ct. 830, 842 (2018) (internal quotation\\n\\nmarks omitted). Where, as here, there is an “absence of more than one plausible\\n\\nconstruction,” the canon of constitutional avoidance “simply has no application.”\\n\\nJennings, 138 S. Ct. at 842 (internal quotation marks omitted).\\n\\n This limitation is an important one. As the Supreme Court recently explained,\\n\\n“[s]potting a constitutional issue does not give a court the authority to rewrite a statute as\\n\\nit pleases.” Id. at 843. Rather, constitutional avoidance serves the “basic democratic\\n\\nfunction of maintaining a set of statutes that reflect, rather than distort, the policy choices\\n\\nthat elected representatives have made.” Almendarez-Torres v. United States, 523 U.S.\\n\\n224, 238 (1998). The doctrine is thus “a means of giving effect to congressional intent,\\n\\nnot of subverting it.” Clark, 543 U.S. at 382. In the words of the Chief Justice,\\n\\n“rewrit[ing] a law to conform it to constitutional requirements . . . would constitute a\\n\\n 41\\n\\nserious invasion of the legislative domain.” United States v. Stevens, 559 U.S. 460, 481\\n\\n(2010) (alterations and internal quotation marks omitted).\\n\\n In this regard, the seemingly disparate doctrines of vagueness and constitutional\\n\\navoidance unite. Both demand respect for the distinct functions that Congress and the\\n\\njudiciary fulfill in our constitutional republic. Due process requires Congress to speak in\\n\\ndefinite terms, particularly where the consequences for individual liberties are steep, in\\n\\npart because Congress alone — not the executive or the judiciary — is equipped to\\n\\nbalance competing policy priorities and to define the boundaries of criminal law. For\\n\\nsimilar reasons, although courts must interpret statutes under the presumption that\\n\\nlegislators do not intend to violate the Constitution, judges cannot revise invalid statutes.\\n\\nTo the contrary, while the grave remedy of striking down a statute as unconstitutional lies\\n\\nwithin the judicial province, rewriting it is a task solely for the elected legislature.\\n\\n These principles compel us to reject the Government’s constitutional avoidance\\n\\nargument. Given the text and context of § 924(c)(3)(B), accepting the Government’s new\\n\\ninterpretation would amount to judicially rewriting the statute.\\n\\n The United States does not merely seek to narrow an ambiguous statute, as the\\n\\nSupreme Court did in Skilling v. United States, 561 U.S. 358, 404 (2010), and Zadvydas\\n\\nv. Davis, 533 U.S. 678, 682 (2001) — the latter being “a notably generous application of\\n\\nthe constitutional-avoidance canon.” Jennings, 138 S. Ct. at 843. Here, the Government\\n\\nasks us to go “much further,” id., by adopting a conduct-specific reading of\\n\\n§ 924(c)(3)(B) that directly conflicts with how courts and the United States itself have\\n\\nthoughtfully interpreted this statute (and materially identical text in § 16(b)) since its\\n\\n 42\\n\\nenactment three decades ago. Tellingly, the Government has yet to identify any case in\\n\\nwhich the Supreme Court has done anything comparable in the name of constitutional\\n\\navoidance. 15\\n\\n We cannot usurp the legislative role to edit out the constitutional flaw in\\n\\n§ 924(c)(3)(B). The plain text, structure, and context of § 924(c)(3) are more than\\n\\nenough to convince us that its residual clause has no plausible conduct-specific\\n\\ninterpretation. We therefore refuse to rewrite the statute, just as the Supreme Court\\n\\nrefused to rewrite § 16(b) and the ACCA residual clause, even in the face of vigorous\\n\\ndissents urging the employment of constitutional avoidance. See Dimaya, 138 S. Ct. at\\n\\n1216–18 (plurality opinion); id. at 1232–33 (Gorsuch, J., concurring in part and\\n\\nconcurring in the judgment); Johnson, 135 S. Ct. at 2561–62.\\n\\n\\n\\n VII.\\n\\n We are mindful of the consequences of holding § 924(c)(3)(B) unconstitutional.\\n\\nThe provision is part of a widely used criminal statute enacted by Congress, and like\\n\\n§ 16(b), it has been incorporated into other parts of the federal criminal code. See 18\\n\\n 15\\n Judge Richardson’s puzzling invocation of Justice Kavanaugh’s scholarship\\nonly underscores this point. Far from endorsing the unprecedented application of\\nconstitutional avoidance that Judge Richardson champions, then-Judge Kavanaugh\\nwarned against overreliance on this canon and others triggered by a threshold finding of\\nambiguity. Brett Kavanaugh, Fixing Statutory Interpretation, 129 HARV. L. REV. 2118,\\n2144 (2016) (book review). Thus, he proposed “jettison[ing]” constitutional avoidance\\nand instead allowing judges to first “determine the best reading of the statute” and then,\\n“[i]f that reading turn[s] out to be unconstitutional,” “say as much.” Id. at 2148. Of\\ncourse, we lack the power to follow this approach and, in any event, a faithful\\nemployment of the constitutional avoidance canon compels the result we reach.\\n\\n 43\\n\\nU.S.C. §§ 844(o), 1028(b)(3)(B). We do, however, note that our ruling is limited in\\n\\nimportant respects.\\n\\n First, § 924(c)(3)(B) appears to be the last federal statute that directs courts to\\n\\nimpose penalties based on a drifting ordinary-case categorical inquiry and an\\n\\nindeterminate risk threshold. The Government has not pointed to any other statute that\\n\\nour decision places in jeopardy, and there is no colorable argument that the elements-\\n\\nbased categorical approach of § 924(c)(3)(A) suffers from any similar indeterminacy.\\n\\nSection 924(c)(3)(B) is, in other words, the last Johnson domino to fall. In striking it\\n\\ndown, we leave intact the balance of the definition of “crime of violence” and the entirety\\n\\nof the definition of “drug trafficking crime” in § 924(c).\\n\\n Second, nothing in our holding restricts the broad discretion of district judges to\\n\\nmake case-by-case sentencing determinations. Here, for example, the district court was\\n\\nauthorized to sentence Simms to as much as 240 months’ incarceration on his conviction\\n\\nfor Hobbs Act conspiracy alone — that is, more than three years longer than the total\\n\\nsentence it actually imposed on both counts. Although judges must consult the advisory\\n\\nSentencing Guidelines, they may vary from these recommendations in light of the factors\\n\\nlisted in 18 U.S.C. § 3553(a). See, e.g., Peugh v. United States, 569 U.S. 530, 536\\n\\n(2013). Foremost among these is “the nature and circumstances of the offense,” which\\n\\nwill necessarily include whether the offender used a firearm. 18 U.S.C. § 3553(a)(1).\\n\\n Last, Congress is fully equipped to revise the statute here. As Justice Gorsuch\\n\\nnoted in Dimaya:\\n\\n\\n\\n 44\\n\\n Vagueness doctrine represents a procedural, not a substantive, demand. It\\n does not forbid the legislature from acting toward any end it wishes, but\\n only requires it to act with enough clarity that reasonable people can know\\n what it is required of them and judges can apply the law consistent with\\n their limited office.\\n\\nDimaya, 138 S. Ct. at 1233 (Gorsuch, J., concurring in part and concurring in the\\n\\njudgment). These insights apply here. If Congress deems it appropriate to replace\\n\\n§ 924(c)(3)(B) with a statute that achieves similar aims with sufficiently definite terms,\\n\\nthe Due Process Clause poses no obstacle.\\n\\n\\n\\n VIII.\\n\\n For the foregoing reasons, the judgment of the district court is\\n\\n REVERSED AND REMANDED.\\n\\n\\n\\n\\n 45\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4361701/\", \"author_raw\": \"wrote a dissenting opinion. Judge Niemeyer wrote a dissenting\"}, {\"author\": \"WYNN, Circuit Judge, with whom HARRIS, Circuit Judge, joins, concurring\", \"type\": \"concurrence\", \"text\": \"WYNN, Circuit Judge, with whom HARRIS, Circuit Judge, joins, concurring:\\n\\n In this case we must decide whether to jettison the “categorical” approach for\\n\\ndetermining whether an offense is a “crime of violence” for the purpose of 18 U.S.C. §\\n\\n924(c)(3)(B)—an approach that the executive and judicial branches uniformly have\\n\\nembraced for several decades, and which the government advanced to this court as\\n\\nrecently as October 2016 1—and replace it with a “case-specific” approach. The\\n\\ndissenting opinions argue that, in refusing to abandon the categorical approach, the\\n\\nmajority opinion—with which I concur in full—is at odds with the doctrine of\\n\\nconstitutional avoidance. E.g., Post at 85 (Richardson, J.). In particular, my dissenting\\n\\ncolleagues maintain that constitutional avoidance compels adoption of the case-specific\\n\\napproach in order to “reflect, rather than distort, the policy choices that the elected\\n\\nrepresentatives have made.” Post at 84 (Niemeyer, J.) (quoting Almendarez-Torres v.\\n\\nUnited States, 523 U.S. 224, 238 (1998)).\\n\\n Yet it is my dissenting colleagues’ misguided application of the doctrine of\\n\\nconstitutional avoidance—not the majority opinion’s adherence to the long-standing\\n\\nunderstanding of Section 924(c)(3)(B)—that has the potential to “distort” the Framers’\\n\\ncarefully crafted allocation of powers for defining crimes and punishments. Relying on\\n\\n\\n 1\\n Gov. 28(j) letter at 2, ECF No. 44 (Oct. 19, 2016); see also, e.g., United States v.\\nPrickett, 839 F.3d 697 (8th Cir. 2016); United States v. Taylor, 814 F.3d 340, 378, 397\\nn.19 (6th Cir. 2016); United States v. Fuertes, 805 F.3d 485, 498 (4th Cir. 2015); United\\nStates v. McGuire, 706 F.3d 1333, 1336-37 (11th Cir. 2013); United States v. Serafin,\\n562 F.3d 1105, 1107 (10th Cir. 2009); United States v. Jennings, 195 F.3d 795, 797-98\\n(5th Cir. 1999); United States v. Kennedy, 133 F.3d 53, 56-57 (D.C. Cir. 1998); United\\nStates v. Amparo, 68 F.3d 1222, 1224 (9th Cir. 1995).\\n\\n 46\\n\\nconstitutional avoidance as a basis for replacing the categorical approach with a case-\\n\\nspecific approach, as my dissenting colleagues suggest, would broaden the universe of\\n\\ndefendants subject to Section 924(c)(3)(B). But, to date, the Supreme Court has applied\\n\\nthe doctrine only to narrow a criminal statute’s breadth and thereby forestall\\n\\nconstitutional concerns. By relying on constitutional avoidance to expand a criminal\\n\\nstatute’s reach, my dissenting colleagues embrace an unprecedented application of the\\n\\ndoctrine of constitutional avoidance that empowers the judiciary to usurp Congress’s\\n\\nexclusive authority to establish crimes and punishments. I write separately to explain\\n\\nwhy I do not believe the Constitution permits judicial encroachment into such a well-\\n\\ndefined legislative province.\\n\\n I.\\n\\n Section 924(c)(1)(A) provides that a person who “uses or carries a firearm”\\n\\n“during and in relation to any crime of violence” or who “possesses a firearm” “in\\n\\nfurtherance of any such crime” may be convicted of both the underlying crime and the\\n\\nadditional crime of using a firearm in connection with a “crime of violence.” Section\\n\\n924(c)(3)(B) defines “crime of violence” as a felony offense “that by its nature, involves\\n\\na substantial risk that physical force against the person or property of another may be\\n\\nused in the course of committing the offense.” Accordingly, to convict a defendant of\\n\\nviolating Section 924(c), a jury must find both that the defendant possessed or used a\\n\\nfirearm and that the defendant did so in connection with a “crime of violence.”\\n\\n As the majority explains, prior to the Supreme Court’s decision in Sessions v.\\n\\nDimaya, 138 S. Ct. 1204 (2018), federal courts—at the government’s urging and in\\n\\n 47\\n\\naccordance with the Supreme Court’s construction of virtually identical language in other\\n\\nstatutes, see, e.g., Taylor v. United States, 495 U.S. 595, 601 (1990)—universally held\\n\\nthat courts must apply the ordinary-case categorical approach in determining whether a\\n\\npredicate offense constitutes a crime of violence for purposes of Section 924(c)(3)(B).\\n\\nUnder the ordinary-case categorical approach, a court must determine whether the\\n\\nhypothetical “ordinary case” of an offense—i.e., not under the particular facts giving rise\\n\\nto the defendant’s prosecution, Dimaya, 138 S. Ct. at 1211—“involves a substantial risk\\n\\nthat physical force against the person or property of another may be used in the course of\\n\\ncommitting the offense.” By contrast, under the case-specific, or “circumstance-\\n\\nspecific,” approach now advanced by the government, and embraced by my colleagues in\\n\\ndissent, a jury would decide whether the specific conduct giving rise to the defendant’s\\n\\nprosecution involves a “substantial risk that physical force against the person or property\\n\\nof another may be used.” See United States v. Price, 777 F.3d 700, 704 (4th Cir. 2015).\\n\\n If this Court were to replace the ordinary-case categorical approach with the case-\\n\\nspecific approach, then offenses that courts have found do not constitute crimes of\\n\\nviolence under the ordinary-case categorical approach will amount to crimes of violence\\n\\nunder the case-specific approach. The Ninth Circuit has held, for example, that\\n\\ninvoluntary manslaughter, 18 U.S.C. § 1112, is not categorically a crime of violence\\n\\nbecause it “requires a mental state of only gross negligence.” United States v. Benally,\\n\\n843 F.3d 350, 354 (9th Cir. 2016). Yet it takes little effort to imagine specific cases of\\n\\ninvoluntary manslaughter—particularly cases involving guns, which must be present to\\n\\nimplicate Section 924(c)(3)(B)—that a jury would find constitute a “crime of violence”\\n\\n 48\\n\\nunder the case-specific approach. In Benally, for example, the defendant shot and killed\\n\\nthe victim with a rifle. Id. at 352. At trial, the government presented that the “shooting\\n\\nwas accidental and part of a drunken game.” Id. at 352. Accordingly, the Benally\\n\\ndefendant, who was not amenable to prosecution under Section 924(c)(3)(B) under the\\n\\nordinary-case categorical approach, would face a high probability of conviction under the\\n\\ncase-specific approach because a jury would likely find that the defendant’s conduct\\n\\nposed “a substantial risk that physical force against the person . . . of another may be\\n\\nused,” notwithstanding that the crime requires “a mental state of only gross negligence.”\\n\\nId. at 354.\\n\\n Benally demonstrates that if this Court abandons use of the ordinary-case\\n\\ncategorical approach to determine whether an offense constitutes a “crime of violence”\\n\\nfor purposes of Section 924(c)(3)(B) and adopts the case-specific approach the\\n\\ngovernment belatedly advances—and our dissenting colleagues embrace—then the\\n\\nuniverse of defendants subject to prosecution under Section 924(c)(3)(B) will be\\n\\nsubstantially greater. Put differently, the adoption of the case-specific approach would\\n\\nexpand the reach of Section 924(c)(3)(B) to a new class of offenders—namely those\\n\\noffenders who commit offenses that do not “ordinar[ily]” pose a “substantial risk” of\\n\\napplication of physical force against another, but which pose such a risk under the\\n\\n\\n\\n\\n 49\\n\\nspecific factual circumstances of the offender’s case (perhaps because the offender was\\n\\ncarrying a gun when he committed the offense). 2\\n\\n II.\\n\\n Because a shift to the case-specific approach will broaden the class of offenders\\n\\nsubject to prosecution under Section 924(c)(3)(B), I believe constitutional avoidance is an\\n\\nimproper basis for a court to choose the case-specific approach over the ordinary-case\\n\\ncategorical approach. As the majority opinion correctly explains, the canon of\\n\\n\\n\\n 2\\n One of my dissenting colleagues posits in a separate opinion that the ordinary-\\ncase approach “is not inherently ‘narrower’ than the case-specific approach” because “a\\njudicially-imagined ‘ordinary case’ can ensnare a defendant whose actual conduct created\\nno risk of violence, a result barred by the case-specific approach.” Post, at 100–01 n.6\\n(Richardson, J.). Whatever the merits of that contention in other contexts, it makes little\\nsense in the context of Section 924(c)(1)(A).\\n\\n Put simply, my dissenting colleague’s argument rests on the premise that a jury\\nwill find that a defendant did not, as a matter of fact, engage in conduct that posed a\\nsubstantial risk of violence, even though the defendant necessarily (1) committed a crime\\nthat “ordinar[il]y” creates a substantial risk of violence and (2) committed that crime\\nwhile carrying a firearm—“an article that is typically and characteristically dangerous,”\\nMcLaughlin v. United States, 476 U.S. 16, 17 (1986), and therefore “inherently violent,”\\nPelissero v. Thompson, 470 F.3d 442, 447 (4th Cir. 1999). The prospect that a jury\\nwould render such a verdict is, indeed, vanishingly small. Cf. Smith v. United States, 508\\nU.S. 223, 240 (1993) (“We therefore see no reason why Congress would have intended\\ncourts and juries applying § 924(c)(1) to draw a fine metaphysical distinction between a\\ngun’s role in a drug offense as a weapon and its role as an item of barter; it creates a\\ngrave possibility of violence and death in either capacity.”).\\n\\n Rather, it is far more likely that a jury would find that an offense that is not\\n“ordinar[il]y” a crime of violence amounts to a crime of violence when, in a particular\\ncase, the defendant committed the offense while carrying a firearm. In other words, the\\nnumber of additional defendants convicted of violating Section 924(c)(1)(A) under the\\ncase-specific approach would likely substantially exceed the number of defendants—if\\nany—who would be relieved of liability under that approach.\\n\\n\\n 50\\n\\nconstitutional avoidance is a “tool for choosing between competing plausible\\n\\ninterpretations of a statutory text, resting on the reasonable presumption that Congress\\n\\ndid not intend the alternative which raises serious constitutional doubts.” Clark v.\\n\\nMartinez, 543 U.S. 371, 381 (2005); ante at 41–43.\\n\\n In the context of constitutional challenges to criminal statutes, the Supreme Court\\n\\nand lower courts have applied the doctrine of constitutional avoidance to adopt a\\n\\n“narrow[ing] constru[ction]” that avoids constitutional concerns that would arise were\\n\\nthe statute construed more broadly. Skilling v. United States, 561 U.S. 358, 407 n.40, 409\\n\\nn.43 (2010) (emphasis added) (quoting United States v. Lanier, 520 U.S. 259, 257–68 n.6\\n\\n(1997)). For example, in Skilling, the Supreme Court considered a vagueness challenge\\n\\nto the honest-services wire fraud statute. Id. at 402–03. Recognizing that the defendant’s\\n\\n“vagueness challenge ha[d] force,” the Court applied the doctrine of constitutional\\n\\navoidance to “par[e] down” the statute to “only [its] bribe-and-kickback core.” Id. at 409\\n\\n& n.43. In reaching this conclusion, the Supreme Court emphasized that, in view of the\\n\\nstatute’s legislative history, as well as consistent judicial interpretation, there was “no\\n\\ndoubt that Congress intended § 1346 to reach at least bribes and kickbacks.” Id. at 405,\\n\\n408–09 (emphasis in original). Put differently, the Supreme Court applied the doctrine of\\n\\nconstitutional avoidance to narrow the statute’s scope to a range of conduct that Congress\\n\\nunambiguously intended to render unlawful.\\n\\n Skilling recognized that “cases ‘paring down’ federal statutes to avoid\\n\\nconstitutional shoals are legion.” Id. at 406 n.40, 409 n.43 (emphasis added) (collecting\\n\\ncases). By contrast, the government has not identified a single case—nor have I—in\\n\\n 51\\n\\nwhich the Supreme Court has applied the doctrine of constitutional avoidance to expand\\n\\nthe reach of a criminal statute, as my colleagues in dissent suggest we do in construing\\n\\nSection 924(c)(3)(B).\\n\\n That no court appears to have applied constitutional avoidance to construe a\\n\\nstatute to “proscribe a wider range of offensive conduct,” id. at 408 (emphasis added), is\\n\\nunsurprising. The Constitution vests the “power of punishment . . . in the legislative, not\\n\\nin the judicial department.” Dowling v. United States, 473 U.S. 207, 214 (1985) (quoting\\n\\nUnited States v. Wiltberger, 5 Wheat. 76, 95 (1820)). Indeed, it “is the legislature, not\\n\\nthe Court, which is to define a crime, and ordain its punishment.” Id.\\n\\n The Supreme Court has held that applying the doctrine of constitutional avoidance\\n\\nto “par[e] down” the scope of a constitutionally suspect criminal statute does not amount\\n\\nto usurpation of Congress’s singular authority to define crimes and punishments. See\\n\\nSkilling, 561 U.S. at 409 n.43 (explaining that the Court does not usurp Congress’s\\n\\nauthority to define crimes and punishment when it “par[es] down federal statutes to avoid\\n\\nconstitutional shoals” because, in such circumstances, “the Court does not legislate, but\\n\\ninstead respects the legislature, by preserving a statute through a limiting\\n\\ninterpretation”). But see id. at 422 (Scalia, J., dissenting) (“I know of no precedent for\\n\\nsuch ‘paring down,’ and it seems to me clearly beyond judicial power.”). But the\\n\\nSupreme Court has sanctioned the use of constitutional avoidance to narrow a potentially\\n\\nunconstitutional criminal statute’s scope only when there is “no doubt that Congress\\n\\nintended [the statute] to reach” the conduct proscribed by the limiting construction. Id. at\\n\\n408 (majority op.) (emphasis added). In Skilling, for example, the Court’s limiting\\n\\n 52\\n\\nconstruction preserved the honest-services fraud statute’s “solid core.” Id. Put\\n\\ndifferently, a court may apply constitutional avoidance to narrow the scope of a\\n\\nconstitutionally suspect statute without infringing on Congress’s exclusive authority to\\n\\ndefine crimes and punishments because the conduct proscribed by the limiting\\n\\nconstruction necessarily falls within the scope of the conduct Congress intended to\\n\\nproscribe.\\n\\n The same cannot be said when a court applies the doctrine of constitutional\\n\\navoidance to expand a criminal statute’s reach. That is because the doctrine of\\n\\nconstitutional avoidance presupposes that there is at least some doubt as to the scope of\\n\\nconduct a statute proscribes—to apply the doctrine there must be at least two “competing\\n\\nplausible interpretations of a statutory text.” See Clark, 543 U.S. at 381. Accordingly,\\n\\napplying the doctrine of constitutional avoidance to adopt the more expansive of\\n\\n“competing plausible interpretations” of a criminal statute’s reach—as my colleagues in\\n\\ndissent would have us do here—entails the judiciary holding unlawful conduct for which\\n\\nthere necessarily is some doubt as to whether Congress intended to make the conduct a\\n\\ncrime. The Supreme Court, however, has long recognized that the judiciary lacks “the\\n\\npower to define new federal crimes,” Skilling, 561 U.S.at 415 (Scalia, J., dissenting)\\n\\n(citing United States v. Hudson, 7 Cranch 32, 34 (1812))—precisely what would occur if\\n\\na judicial construction of a criminal statute encompasses conduct Congress did not intend\\n\\nto make unlawful.\\n\\n That certainly is the case here. Given (1) the Supreme Court’s long-settled\\n\\nconstruction of several key terms in Section 924(c)(3)(B) as a compelling application of\\n\\n 53\\n\\nthe ordinary-case categorical approach, (2) the government’s decades-long position that\\n\\nthe language of Section 924(c)(3)(B) demands application of the ordinary-case\\n\\ncategorical approach, and (3) lower federal courts’ unanimous determination, prior to\\n\\nDimaya, that the ordinary-case categorical approach applies, there is, at the very least, a\\n\\nstrong possibility—indeed, likelihood, as the majority opinion persuasively explains—\\n\\nthat Congress did not intend for the case-specific approach to apply. Accordingly, my\\n\\ndissenting colleagues’ novel application of the doctrine of constitutional avoidance to\\n\\nexpand Section 924(c)(3)(B)’s reach by requiring application of the case-specific\\n\\napproach would “arrogat[e],” post at 62 (Wilkinson, J.), to the judiciary the authority “to\\n\\ndefine [a] new federal crime,” Skilling, 561 U.S at 415 (Scalia, J., dissenting).\\n\\n Not only does applying the doctrine of constitutional avoidance to expand the\\n\\nreach of a criminal statute conflict with Congress’s exclusive authority to define crimes\\n\\nand punishments, but it also stands in tension with the rule of lenity, which requires that\\n\\n“any ambiguity over the . . . scope [of a criminal statute] be resolved in [a criminal\\n\\ndefendant’s] favor.” Crandon v. United States, 494 U.S. 152, 168 (1990). When a court\\n\\nresorts to the doctrine of constitutional avoidance to construe a statute—as my dissenting\\n\\ncolleagues would have us do here—it necessarily does so because there is some\\n\\n“ambiguity” as to the statute’s reach. Applying the doctrine of constitutional avoidance\\n\\nto narrow a criminal statute’s scope advances the interests served by the rule of lenity\\n\\nbecause it resolves the statutory ambiguity in the criminal defendant’s favor.\\n\\n By contrast, applying constitutional avoidance to widen a statute’s reach fails to\\n\\nkeep faith with the rule of lenity because it resolves a statutory ambiguity in a manner\\n\\n 54\\n\\ncontrary to the interests of criminal defendants. Indeed, were the judiciary to rely on\\n\\nconstitutional avoidance to interpret a statute’s breadth in a manner that extends beyond\\n\\nwhat the text “clearly warrants”—as necessarily occurs when a court adopts a broad\\n\\nreading of an ambiguous statute—it would violate the due process principle of “fair\\n\\nwarning” undergirding the rule of lenity. United States v. Hayes, 555 U.S. 415, 436–37\\n\\n(2009) (Roberts, C.J., dissenting) (quoting Crandon, 494 U.S. at 160).\\n\\n III.\\n\\n My good colleague in dissent asserts that it is the majority’s refusal to abandon the\\n\\nordinary-case categorical approach—rather than the dissenting opinions’ unprecedented\\n\\napplication of constitutional avoidance to usurp Congress’s exclusive authority to define\\n\\ncrimes and punishments—that amounts to an “arrogation of authority . . . all too\\n\\nprevalent in appellate ranks throughout the country.” Post at 62 (Wilkinson, J.). As my\\n\\ncolleague sees it, this Court’s decision to continue to construe Section 924(c)(3)(B) as\\n\\nrequiring use of the ordinary-case categorical approach reflects a “troubling trend” of\\n\\n“appellate micro-management”—that by applying the ordinary-case categorical approach\\n\\nthis Court is “displac[ing]” the historical roles of “trial courts, juries, and indeed\\n\\nCongress.” Post at 60, 63-64, 67 (Wilkinson, J.).\\n\\n Whatever the merits of my dissenting colleague’s concern about the “appellate\\n\\nregency” subverting the traditional role of trial judges, juries, and Congress in criminal\\n\\nadjudication, post at 65 (Wilkinson, J.), such concerns have no place in this case. There\\n\\nis no question that this Court’s resolution keeps faith with the Supreme Court’s long-\\n\\nstanding conclusion that when Congress used identical terms in other statutes, it intended\\n\\n 55\\n\\nfor the categorical approach to apply, see Taylor, 495 U.S. at 601, and with this Court’s\\n\\nconclusion that those terms demand application of the categorical approach in present-\\n\\noffense, as well as past-offense, cases, see Fuertes, 805 F.3d at 498; United States v.\\n\\nAragon, 983 F.2d 1306, 1312 (4th Cir. 1993). There also can be no question that this\\n\\nCourt’s resolution of this case adheres to the—until recently unquestioned—decades-long\\n\\njudicial understanding of Section 924(c)(3)(B). See supra note 1. And there is no\\n\\nquestion that this Court’s resolution of this case mirrors the construction of Section\\n\\n924(c)(3)(B) that the government advanced from the statute’s adoption until Dimaya.\\n\\n Accordingly, this Court’s resolution of this case in no way breaks with the\\n\\nhistorical understanding of Section 924(c)(3)(B) and the roles of juries and trial courts in\\n\\napplying that statute. Rather, it is the government’s post-Dimaya about-face as to the\\n\\nproper construction of Section 924(c)(3)(B), and my dissenting colleagues’ embrace of\\n\\nthat construction, that turns away from the historical understanding and application of\\n\\nthat statute. Likewise, my dissenting colleagues’ proposed expansion of the doctrine of\\n\\nconstitutional avoidance in a manner that empowers the judiciary to “trench upon the\\n\\nlegislature’s [exclusive] powers” to define crimes and punishments, Salinas v. United\\n\\nStates, 522 U.S. 52, 60–61 (1997), is the only evidence of a “troubling trend” of\\n\\n“appellate micro-management” that this case provides.\\n\\n My colleagues in dissent rejoin that surely Congress intended to punish\\n\\nindividuals like Defendant—and, possibly, like the defendant in Benally—who\\n\\ncommitted, under the specific facts of their case, what are undisputedly “violent” crimes,\\n\\nas that term is used colloquially. Post at 63-64 (Wilkinson, J.); post at 85 (Richardson,\\n\\n 56\\n\\nJ.). And they are right. That is why Congress has proscribed conspiracy to commit Hobbs\\n\\nAct robbery and involuntary manslaughter, and why Congress has imposed substantial\\n\\ncriminal penalties for individuals who commit those crimes. But that is not the question\\n\\nwe must address. Rather, we are tasked with deciding whether Congress intended to hold\\n\\nDefendant criminally liable for the additional offense of using a firearm in commission\\n\\nof an “offense” that “by its nature, involves a substantial risk that physical force against\\n\\nthe person or property of another may be used.” § 924(c)(3)(B) (emphases added). And\\n\\nby expressly choosing to render unlawful only those “offenses” that “by [their] nature”\\n\\ninvolve application of violent force, Congress sought to limit the universe of defendants\\n\\nprosecutable under Section 924(c)(3)(B) to those defendants who commit crimes the\\n\\nordinary manifestation of which “involve[] a substantial risk that physical force against\\n\\nthe person or property of another may be used.”\\n\\n As the majority opinion ably explains, the Supreme Court long has held that when\\n\\nCongress uses that specific language, it intends for courts to apply the ordinary-case\\n\\ncategorical approach. And in accordance with the Supreme Court’s construction of that\\n\\nlanguage, the government long has argued—including earlier in this case—that Congress\\n\\nintended for courts to apply the ordinary-case categorical approach in determining\\n\\nwhether a defendant is amenable to prosecution under Section 924(c)(3)(B). Put simply,\\n\\nuntil Dimaya, the judiciary and the government agreed that Congress intended for Section\\n\\n924(c)(3)(B) to require application of the ordinary-case categorical approach, and\\n\\ntherefore that Congress did not contemplate prosecuting individuals like Defendant under\\n\\n\\n\\n 57\\n\\nthat provision. Since Congress enacted Section 924(c)(3)(B) in 1986, Congress never has\\n\\ndisturbed that settled understanding.\\n\\n Of course, Congress is free to amend Section 924(c)(3)(B) to permit further\\n\\npunishment of Defendant under that provision. But this Court is not free to expand the\\n\\nstatute’s reach through an unprecedented application of the doctrine of constitutional\\n\\navoidance, 3 see Clark, 543 U.S. at 382 (2005) (“[Constitutional avoidance] is thus a\\n\\nmeans of giving effect to congressional intent, not of subverting it.”), particularly in light\\n\\nof the Supreme Court’s settled construction of the meaning of Section 924(c)(3)(B)’s key\\n\\nterms, see Rodriguez de Quijas v. Shearson/Am. Express, Inc., 490 U.S. 477, 484 (1989)\\n\\n\\n\\n\\n 3\\n Another one of my dissenting colleagues claims in his separate opinion that I\\n“seek[] to replace the doctrine of constitutional avoidance with a search and destroy\\nmission to strike down federal statutes.” Post at 66 (Wilkinson, J.). Not true. My\\nanalysis leaves ample room for courts to rely on constitutional avoidance to adopt\\nnarrowing constructions of criminal statutes some applications of which pose\\nconstitutional concerns—that simply is not how my dissenting colleagues propose to\\napply the doctrine here. My dissenting colleague further asserts that my understanding of\\nconstitutional avoidance “embrace[s] the odd proposition that upholding a statute is\\nsomehow a usurpation of Congress’ authority.” Post at 66. Again, not true. I am not the\\nfirst to recognize that—even when a limiting, as opposed to a widening, construction is\\nproposed to save a potentially unconstitutional statute—courts do not “have the power, in\\norder to uphold an enactment, to rewrite it.” Skilling, 561 U.S. at 423 (Scalia, J.,\\ndissenting). That is particularly true given that, in the decades leading up to Dimaya,\\nneither the government nor any court believed the case-specific approach applied. Cf. id.\\n(explaining that “[i]f it were a ‘fairly possible’ or ‘reasonable’ construction, not ‘contrary\\nto the intent of Congress’”—and therefore amenable to application of the doctrine of\\nconstitutional avoidance—“one would think that some court would have adopted it”). In\\nsuch circumstances, judicial “restraint” demands “resist[ing] the temptation to make all\\nthings right with the stroke of [the judicial] pen”—as my colleagues in dissent would\\nhave this Court do. Id. at 423–24.\\n\\n\\n 58\\n\\n(‘‘[T]he Court of Appeals should . . . leav[e] to th[e Supreme] Court the prerogative of\\n\\noverruling its own decisions.’’).\\n\\n IV.\\n\\n In sum, neither my dissenting colleagues nor the government points to a single\\n\\ncase in which the Supreme Court has sanctioned the use of constitutional avoidance in a\\n\\nmanner that expands the scope of a criminal statute, as it would if we applied the case-\\n\\nspecific approach to Section 924(c)(3)(B). And, for decades, courts—at the\\n\\ngovernment’s express invitation—have applied the ordinary-case categorical approach in\\n\\naccordance with the settled understanding of that statute’s text. Constitutional avoidance\\n\\nis “not a license for the judiciary to rewrite language enacted by the legislature.” Salinas,\\n\\n522 U.S. at 60–61. But that is precisely what would occur if this Court followed my\\n\\ndissenting colleagues’ suggestion and relied on constitutional avoidance to expand\\n\\nSection 924(c)(3)(B)’s reach. Accordingly, any justification for the case-specific\\n\\napproach grounded in constitutional avoidance radically departs from the established\\n\\nscope and application of the doctrine.\\n\\n\\n\\n\\n 59\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4361701/\", \"author_raw\": \"WYNN, Circuit Judge, with whom HARRIS, Circuit Judge, joins, concurring\"}, {\"author\": \"WILKINSON, Circuit Judge, dissenting\", \"type\": \"dissent\", \"text\": \"WILKINSON, Circuit Judge, dissenting:\\n\\n Once upon a time, now seemingly a geologic age ago, the federal judiciary\\n\\nappeared sold on the inherent advantages that trial courts and trial juries bring to fact-\\n\\nfinding in our criminal justice system. No longer. My colleagues in the majority ably\\n\\ndemonstrate that application of the categorical approach to 18 U.S.C. § 924(c)(3)(B)\\n\\nsaddles that statute with a fatal constitutional infirmity. My colleagues in dissent—whom\\n\\nI join—ably demonstrate why that infirmity need not exist; the better reading of the\\n\\nstatute avoids it by applying the case-specific approach in place of the categorical. I write\\n\\nseparately to further explain how application of the categorical approach here is part of a\\n\\ntroubling trend: the gratuitous conversion of issues of fact into questions of law; the\\n\\nusurpation of authority by appellate courts and the resultant atrophy of trial courts’ fact-\\n\\nfinding function.\\n\\n ****\\n\\n Appellate courts have taken the Sentencing Guidelines and the categorical\\n\\napproach to crimes of violence as an invitation to wade deep into sentencing. This despite\\n\\nthe faith that Gall v. United States placed in district judges with respect to the sentencing\\n\\nfunction. 552 U.S. 38 (2007). There is no mistaking Gall’s thrust: district judges are “in a\\n\\nsuperior position to find facts,” and, because of this, appellate judges must give them\\n\\n“due deference.” Id. at 51. The district judge has “greater familiarity with[] the individual\\n\\ncase and the individual defendant before him than the . . . appeals court.” Id. at 51-52.\\n\\nUnlike the appeals court, the district “judge sees and hears the evidence, makes\\n\\ncredibility determinations, has full knowledge of the facts and gains insight not conveyed\\n\\n 60\\n\\nby the record.” Id. at 51. In short, “district courts have an institutional advantage over\\n\\nappellate courts” in setting sentences. Id. at 52.\\n\\n Because of this institutional advantage—that district judges have the eyes and\\n\\nears that appellate judges lack—Gall commanded appeals courts to apply a “deferential\\n\\nabuse-of-discretion” standard to critical sentencing determinations. Id. This standard,\\n\\nwhen combined with the clearly-erroneous standard for findings of fact, should have\\n\\ninstilled in us a proper respect for the trial courts’ basic judgment calls. Id. at 51. The\\n\\nGall Court underscored this point when it wrote that “[t]he fact that the appellate court\\n\\nmight reasonably have concluded that a different sentence was appropriate is insufficient\\n\\nto justify reversal of the district court.” Id. at 51.\\n\\n One would think that Gall fixed principal responsibility for sentencing where it\\n\\nbelonged: with the trial courts. After all, that case simply reflected the basic principle that\\n\\nsentencing is a fact-bound matter which requires the exercise of wide discretion by trial\\n\\njudges. Landmark cases such as Gall and Anderson v. City of Bessemer City, 470 U.S.\\n\\n564 (1985), inhabit that ironic junction where the role of facts becomes the essence of the\\n\\nrule of law. But Gall’s promise was never fulfilled. By adopting, expanding, and rigidly\\n\\napplying the categorical approach to the characterization of crimes of violence by a\\n\\ndefendant, appellate courts have subjected too many discretionary trial-court sentencing\\n\\ndeterminations to de novo review. This appellate approach has not only led courts to\\n\\n“reach counterintuitive results, and ones which are not what Congress intended.” United\\n\\nStates v. Faust, 853 F.3d 39, 61 (1st Cir. 2017) (Lynch J., concurring). It has further\\n\\n\\n\\n 61\\n\\nundermined the authority of district courts as finders of fact, even where the facts are\\n\\nclearly ascertainable and readily discerned.\\n\\n My fine colleague, Judge Motz, has written thoughtfully. And my friends in the\\n\\nmajority are certainly not alone in derogating the fact-finding function, but part of an\\n\\noverreach all too prevalent in appellate ranks throughout the country. The majority cloaks\\n\\nits latest arrogation of authority in dulcet reassurances: “[N]othing in our holding restricts\\n\\nthe broad discretion of district judges to make case-by-case sentencing determinations …\\n\\nAlthough judges must consult the advisory Sentencing Guidelines, they may vary from\\n\\nthese recommendations in light of the factors listed in 18 U.S.C. § 3553(a).” Maj. Op. at\\n\\n44. It is true that district judges retain the ability to vary from the Sentencing Guidelines’\\n\\nrecommendations. But variant sentences can shed their presumption of reasonableness\\n\\nand are more easily slapped down. United States v. Johnson, 242 Fed. Appx. 7, 10 (4th\\n\\nCir. 2007). What is more, the time and effort we are spending on making categorical\\n\\ndeterminations unmistakably sends this message: categorical holdings may, in the context\\n\\nof the Guidelines, be “advisory,” Maj. Op. at 44, but they carry the peremptory bearing of\\n\\ncommands. Finally, despite the majority’s reassurances, it is openly skeptical of the\\n\\nability of triers of fact to make the kind of determinations a case-specific approach here\\n\\nwould require. Maj. Op. at 34. Plainly the majority has far more faith in the ability of\\n\\nappellate judges to make legal determinations than it has in triers-of-fact to make factual\\n\\nones.\\n\\n Now triers of fact have suffered a double whammy. Just as application of the\\n\\ncategorical approach to crime-of-violence sentencing determinations displaces the district\\n\\n 62\\n\\njudge, application of the categorical approach to the residual clause of 18 U.S.C.\\n\\n§ 924(c)(3) displaces both the trial judge and jury. The majority converts the question\\n\\nbefore us—whether Simms committed a crime of violence—from an ordinary one of fact\\n\\ninto a lofty one of constitutional law that has nothing at all to do with Simms as an\\n\\nindividual. It makes the standard of review de novo. It discards the limited sufficiency\\n\\nreview normally reserved for jury verdicts. See Musacchio v. United States, 136 S.Ct.\\n\\n706, 715 (2016). It jettisons the clear error review normally accorded district courts’\\n\\nsentencing findings. In so doing it runs the role of juries and trial judges further into the\\n\\nground.\\n\\n To this, the majority offers only an adjectival denial that begs the question. Ante at\\n\\nn. 12. Its whole exercise is systemically damaging. In certain circumstances, the\\n\\ncategorical approach is useful because it relieves district courts of the institutional burden\\n\\ninvolved in reaching back through time to discover the undiscoverable. Moncrieffe v.\\n\\nHolder, 569 U.S. 184, 200–01 (2013). Those circumstances are not present here. Joseph\\n\\nSimms pleaded guilty, not because of some legal misunderstanding but because he\\n\\nrobbed a McDonald’s at gunpoint. Simms and his conspirator snuck into the occupied\\n\\nrestaurant in the middle of the night through the drive-through window. Once inside,\\n\\nSimms used his gun to menace the employees and demand money. He even tried to strike\\n\\none of them before ordering the workers to gather in the back office. He thereupon forced\\n\\nthe manager at gunpoint to open the safe and hand over the money. With the money in\\n\\nhand, Simms struck the manager on the top of his head with the gun, threw the cash\\n\\ndrawer at another employee, and fled.\\n\\n 63\\n\\n Those are the facts. That is the actuality of it all. The trial court had this entire\\n\\nnarrative at its disposal because, like all cases brought under §924(c), this conduct was\\n\\npart of instant offense. Simms’ actions are amply detailed in the pre-sentencing report\\n\\nwhich was not contested. Thus, there is not even an arguable institutional deficit at work\\n\\nhere; the trier of fact’s unique competence should be more than sufficient to decide\\n\\nwhether Simms committed a crime of violence.\\n\\n Unlike the categorical approach, the case-specific approach would allow the trial\\n\\njudge and jury to look at what is before them and do what they do best. Under this\\n\\napproach—approved by the First Circuit in United States v. Douglas, 907 F.3d 1 (1st Cir.\\n\\n2018), the Eleventh Circuit in Ovalles v. United States, 905 F.3d 1231 (11th Cir. 2018)\\n\\n(en banc), and the Second Circuit in United States v. Barrett, 903 F.3d 166 (2d Cir.\\n\\n2018)—the trier of fact would determine whether robberies like Simms’ “involved a\\n\\nsubstantial risk that physical force against the person or property of another may be\\n\\nused,” resolving the question no differently than it would the application of any other\\n\\nelement to the facts of the offense. 18 U.S.C. §924(c)(3)(B). Our review would be\\n\\nappropriately deferential and strictly limited, stepping in only if no reasonable trier of fact\\n\\ncould have found a crime of violence. See Jackson v. Virginia, 443 U.S. 307, 318-19\\n\\n(1979). Thus would the case-specific approach begin to right the indefensible imbalance\\n\\noccasioned by appellate micro-management.\\n\\n Ah, but in abjuring the case-specific approach, the majority is able to say, as a\\n\\nmatter of law naturally, that the statute is too vague and that Simms, in conspiring to rob\\n\\na fast food restaurant at gunpoint, committed no crime of violence. And as it stands, I am\\n\\n 64\\n\\nleft scratching my head and attempting to find some even remotely plausible explanation\\n\\nfor the appellate assumption of what should be a routine fact-finding role. I suppose it\\n\\ncould be an example of the old Barnum-and-Bailey urge to move our act to center ring.\\n\\nOr perhaps we simply do all this because we can—an exhibition of appellate muscularity\\n\\nprofoundly at odds with the restraint belonging to the rule of law.\\n\\n This appellate regency is not consonant with common sense, and is at cross-\\n\\npurposes with the thrust of humane sentencing reforms. Those reforms have concentrated\\n\\nin major part on reducing mandatory sentences for drug offenses. See, e.g., First Step Act\\n\\nof 2018, S. 756, 115th Cong. §401 (2018) (reducing mandatory minimums for prior drug\\n\\noffenders but expanding them to prior violent felons under the Controlled Substances\\n\\nAct). Here, by contrast, the majority is mounting a transparent attack upon Congress’\\n\\nintent to punish crimes of violence—particularly recidivist crimes of violence—more\\n\\nseverely, an intent grounded in the basic proposition that violent offenders, 18 U.S.C. §\\n\\n924(c), and repeat offenders, 18 U.S.C. § 924(e), pose a greater threat to public\\n\\nwellbeing.\\n\\n To repeat, the majority’s approach is even at odds with the asserted rationale of\\n\\nthe categorical approach itself, which is to spare district courts the burden of relitigating\\n\\ndifficult-to-ascertain facts to determine whether or not past offenses are crimes of\\n\\nviolence. Moncrieffe, 569 U.S. at 200–01. But this is a present-offense case. The trier of\\n\\nfact here has all the tools it needs to do the job. Rather than use these tools, the majority\\n\\nwould have us take yet another gratuitous flight from reality by throwing out the entire\\n\\nresidual clause of §924(c)(3) and potentially releasing a large and untold number of the\\n\\n 65\\n\\nmost violent cohort of criminal offenders prematurely back on to the streets. This\\n\\napproach floats impossibly above the reality that the trier of fact could capably bring to\\n\\nthe task. The hallmarks of the appellate ascendancy are once again painfully apparent,\\n\\nincluding an obliviousness to the fates of future victims, unknown and anonymous to\\n\\njudges, but whom Congress, in its wisdom, sought to shelter.\\n\\n The credo now seems to be to inflict more, not less, damage upon the whole\\n\\nedifice of law. The majority is so wedded to the categorical approach that it would rather\\n\\nstrike down the residual clause of § 924(c)(3) in its entirety than recognize trial courts’\\n\\ninherent capabilities. Constitutional assault now takes precedence over constitutional\\n\\navoidance. *\\n\\n Only by adopting the categorical approach does the majority create constitutional\\n\\nproblems for itself. The vagueness question that plagued the Supreme Court in Sessions\\n\\nv. Dimaya, 138 S. Ct. 1204 (2018), disappears altogether upon the adoption of the case-\\n\\nspecific approach. The text of 18 U.S.C. 924(c)(3)(B) supports it: as Judge Niemeyer\\n\\nindicates, language like “involves conduct” and “in the course of” and “by its nature” can\\n\\neasily and fairly be read to mandate a case-specific approach. The elements clause of 18\\n\\n\\n *\\n My friend Judge Wynn seeks to replace the doctrine of constitutional avoidance\\nwith a search and destroy mission to strike down federal statutes. He then proceeds to\\nembrace the odd proposition that upholding a statute is somehow a usurpation of\\nCongress’ authority, and that interpreting a statute with due respect for the prerogatives\\nof a coordinate branch is somehow an impermissible judicial exercise.\\n It is further odd to suggest that an interpretation of a statute that allows triers of\\nfact to apply its precise language to specific conduct represents a judicial “expansion” of\\nan offense or indeed anything other than the most textually faithful rendering of the\\nlegislature’s command.\\n\\n 66\\n\\nU.S.C. § 924(c)(3)(A) and the residual clause of 18 U.S.C. § 924(c)(3)(B) were written\\n\\nvery differently for a reason. Determinations of “substantial risk” are familiar territory to\\n\\ndistrict judges and juries, Johnson v. United States, 135 S. Ct. 2551, 2561 (2015), and we\\n\\nhave interpreted similar language to require a case-specific approach before, United\\n\\nStates v. Price, 777 F.3d 700 (4th Cir. 2015). What, if anything, the text leaves\\n\\nambiguous, Congress’ purpose makes manifest: this statute was plainly intended to\\n\\npunish people like Joseph Simms who use firearms to inspire fear and visit lawless and\\n\\nunforgettable trauma upon their fellow citizens.\\n\\n This whole enterprise will not end well. Territorial grabs are seldom becoming to\\n\\nthe rule of law, and the ouster of trial courts, juries, and indeed Congress from their\\n\\nrightful place in criminal justice is becoming one of the worst. This case does not even\\n\\nmount a frontal assault upon the categorical approach, only to the most extreme\\n\\nmanifestations of it. Lacking any rational explanation for the present state of affairs, I can\\n\\nonly conclude that the very words “categorical approach” exert some irresistible pull on\\n\\nthe appellate psyche. Like the children of medieval Hamelin, robbed of their reason,\\n\\ncourts are left only to follow the pied piper’s song off the cliff. But that does not mean we\\n\\ncannot wish a fond and affectionate farewell to those tumbling into the seas.\\n\\n\\n\\n\\n 67\\n\\nNIEMEYER, Circuit Judge, with whom Judges WILKINSON, DUNCAN, AGEE,\\n\\nKEENAN, and QUATTLEBAUM join, dissenting:\\n\\n In holding that the definition of “crime of violence” in 18 U.S.C. § 924(c)(3)(B) is\\n\\nunconstitutionally vague and that § 924(c)(1)’s prohibition on using a firearm in\\n\\nconnection with a crime of violence can therefore never be enforced contemporaneously\\n\\nwith a Hobbs Act robbery conspiracy under 18 U.S.C. § 1951, the majority insists that\\n\\nthe “categorical approach” must be applied to assess whether the charged Hobbs Act\\n\\nconspiracy is a crime of violence. But this insistence both (1) distorts the basic reasons\\n\\nfor and limited application of the categorical approach and (2) rejects a sensible reading\\n\\nof § 924(c) that would avoid holding a key part of a major criminal law unconstitutional.\\n\\nConsequently, thousands of § 924(c)(1) convictions will unnecessarily be challenged as\\n\\npremised on what the majority today concludes is an unconstitutionally vague provision,\\n\\neven though the parties in those cases had little difficulty understanding, enforcing, or\\n\\ndefending the § 924(c)(1) charges at issue.\\n\\n In reaching its conclusion, the majority relies on the Supreme Court’s decisions in\\n\\nJohnson v. United States, 135 S. Ct. 2551 (2015), and Sessions v. Dimaya, 138 S. Ct.\\n\\n1204 (2018), where the Court found unconstitutionally vague the “residual clauses”\\n\\ndefining “violent felony” and “crime of violence” in 18 U.S.C. § 924(e) and § 16(b),\\n\\nwhich were used to categorically characterize prior convictions. While § 924(c) employs\\n\\na similar residual clause to define “crime of violence” in describing proscribed conduct,\\n\\nthe definition in § 924(c) does not require one to imagine in the abstract the “ordinary\\n\\ncase” of a particular crime and then to assess its risk of violence, as required by § 924(e)\\n\\n 68\\n\\nand § 16(b) to determine whether prior convictions were for violent crimes. Johnson,\\n\\n135 S. Ct. at 2557–58; Dimaya, 138 S. Ct. at 1215–16. Instead, as relevant here,\\n\\n§ 924(c)(1) requires rather straightforwardly that the government prove that the defendant\\n\\n(1) used, carried, or possessed a firearm (2) in connection with (3) a crime of violence,\\n\\nwhich, in this case, was alleged to be a Hobbs Act conspiracy. In this distinct context,\\n\\n§ 924(c) can readily be read as requiring the government to prove to the jury, as an\\n\\nelement of the offense, that a particular Hobbs Act conspiracy charged in an indictment\\n\\nqualifies as a crime of violence by showing that that offense, “by its nature,” posed “a\\n\\nsubstantial risk” of physical force being used. 18 U.S.C. § 924(c)(3)(B). And in both\\n\\nJohnson and Dimaya, the Supreme Court could not have been clearer that there are no\\n\\nvagueness problems when a crime-of-violence definition like § 924(c)(3)(B)’s is applied\\n\\nto “real-world conduct” in precisely this manner — that is, to assess “the riskiness of\\n\\nconduct in which an individual defendant engage[d] on a particular occasion.” Johnson,\\n\\n135 S. Ct. at 2561; see also Dimaya, 138 S. Ct. at 1215–16.\\n\\n In this case, Joseph Simms pleaded guilty to two counts — Count I charging him\\n\\nwith conspiracy to commit Hobbs Act robbery, in violation of 18 U.S.C. § 1951, and\\n\\nCount II charging him with brandishing a firearm during the commission of a “crime of\\n\\nviolence” — namely, the Hobbs Act conspiracy — in violation of § 924(c)(1)(A). The\\n\\ncrime-of-violence element in the § 924(c)(1) charge, even though defined in the same\\n\\nterms as the crime-of-violence definition in § 16(b), did not refer to a prior conviction in\\n\\nthe abstract but to the real-world conduct alleged in charging the Hobbs Act violation.\\n\\nSpecifically, Count I charged that Simms and others conspired to, and did in fact, rob\\n\\n 69\\n\\nMcDonald’s Restaurant # 31619 in Goldsboro, North Carolina, on April 14, 2014. To\\n\\nprove that Simms committed that crime, the government would have been required to\\n\\nshow that Simms conspired unlawfully to obstruct, delay, or affect commerce by\\n\\n“robbery,” defined to mean:\\n\\n the unlawful taking or obtaining of personal property from the person or in\\n the presence of another, against his will, by means of actual or threatened\\n force, or violence, or fear of injury, immediate or future, to his person or\\n property, or property in his custody or possession, or the person or property\\n of a relative or member of his family or of anyone in his company at the\\n time of the taking or obtaining.\\n\\nId. § 1951(b)(1) (emphasis added). And then to prove further that Simms’s particular\\n\\nHobbs Act conspiracy offense — which, again, was alleged to have culminated in an\\n\\nactual robbery — qualified as a crime of violence for purposes of the § 924(c)(1)(A)\\n\\ncharge, the government would have been required to show that his conspiracy, “by its\\n\\nnature, involve[d] a substantial risk” of physical force being used “against the person or\\n\\nproperty of another.” Id. § 924(c)(3)(B).\\n\\n No one has asserted or can assert that this charge against Simms is\\n\\nunconstitutionally vague, as defined in Kolender v. Lawson, 461 U.S. 352, 357–58 (1983)\\n\\n(stating that the Due Process Clause “requires that a penal statute define the criminal\\n\\noffense with sufficient definiteness that ordinary people can understand what conduct is\\n\\nprohibited and in a manner that . . . establish[es] minimal guidelines to govern law\\n\\nenforcement”). Instead, the majority purports to make it vague by applying a\\n\\n“categorical approach” designed for completely distinct and limited circumstances, even\\n\\nthough nothing in the statute so requires. Simms’s conviction should be affirmed.\\n\\n\\n 70\\n\\n I\\n\\n Simms and two others conspired to rob the McDonald’s Restaurant on April 14,\\n\\n2014. Shortly after 1:00 a.m., Simms and one co-conspirator entered the restaurant by\\n\\ncrawling through the drive-through window while the third person served as a lookout.\\n\\nSimms then pointed a gun at the restaurant’s manager and demanded money. At\\n\\ngunpoint, the manager opened the restaurant’s safe, after which Simms struck the\\n\\nmanager on the top of his head with the gun and threw a cash drawer at another\\n\\nemployee. The robbers fled with $1,100.\\n\\n After Simms was arrested and indicted, he pleaded guilty to Counts I and II of the\\n\\nindictment. Count I charged him with conspiracy to commit Hobbs Act robbery, in\\n\\nviolation of 18 U.S.C. § 1951, and it specifically alleged, as an overt act taken in\\n\\nfurtherance of the conspiracy, that Simms and others committed the agreed-upon robbery.\\n\\nAnd Count II charged that Simms had brandished a firearm during and in relation to a\\n\\ncrime of violence — namely, the Hobbs Act violation alleged in Count I — in violation\\n\\nof 18 U.S.C. § 924(c)(1)(A). In exchange for his guilty plea on these two counts, the\\n\\ngovernment agreed to dismiss a third count charging that Simms had possessed a firearm\\n\\nafter having been convicted of a felony, in violation of 18 U.S.C. §§ 922(g)(1) and\\n\\n924(a)(2).\\n\\n During sentencing, Simms objected to his § 924(c)(1)(A) conviction under\\n\\nCount II in light of the Supreme Court’s decision in Johnson, contending that the\\n\\nrequired element that he use a firearm during and in relation to a “crime of violence” was\\n\\nnot satisfied because the residual clause used to define “crime of violence” in\\n\\n 71\\n\\n§ 924(c)(3)(B) was unconstitutionally vague. The district court overruled Simms’s\\n\\nobjection and sentenced him to 199 months’ imprisonment — 115 months for the Hobbs\\n\\nAct conspiracy and a mandatory consecutive 84 months for the § 924(c)(1)(A) offense.\\n\\n Simms filed this appeal, maintaining that his § 924(c) conviction cannot stand\\n\\nbecause it is premised on a definition of “crime of violence” that is unconstitutionally\\n\\nvague under the reasoning of Johnson and Dimaya, the latter of which was decided after\\n\\nSimms filed his notice of appeal.\\n\\n\\n II\\n\\n Simms contends that because there is “[n]o meaningful difference” between the\\n\\ndefinition of “violent felony” in § 924(e)(2)(B)(ii) that was found unconstitutionally\\n\\nvague in Johnson and the definition of “crime of violence” that was used to support his\\n\\nconviction under § 924(c)(1)(A), we must find the latter definition unconstitutionally\\n\\nvague and invalidate his conviction. And Dimaya, he maintains, confirms this conclusion\\n\\nsince the text of “Section 924(c)’s residual clause [defining crime of violence] is identical\\n\\nto Section 16(b).” According to Simms, § 924(c)(3)(B) compels the use of “the same\\n\\nordinary case approach and risk inquiry” that doomed the provisions in Johnson and\\n\\nDimaya, and the same result must therefore also follow here. The majority adopts the\\n\\nsame basic approach. Such an argument, however, is too formulaic, overlooking the role\\n\\nand context of the definitions, as well as the limited role of the categorical approach.\\n\\n In both Johnson and Dimaya, the Court addressed the question of applying the\\n\\n“categorical approach” to assess whether prior convictions were for violent crimes when\\n\\n\\n 72\\n\\nsuch crimes were defined to include any felony that, in Johnson, “involves conduct that\\n\\npresents a serious potential risk of physical injury,” 18 U.S.C. § 924(e)(2)(B)(ii) or, in\\n\\nDimaya, that “by its nature, involves a substantial risk that physical force against the\\n\\nperson or property of another may be used in the course of committing the offense,” id.\\n\\n§ 16(b). The difficulty the Supreme Court found in making that determination arose not\\n\\nfrom the inability to assess violent conduct as defined by those “residual clauses,” but\\n\\nfrom assessing whether the prior conviction, considered under the categorical approach,\\n\\nwas for a violent crime under those definitions. In short, it was the limitation imposed by\\n\\napplying the categorical approach — where facts and conduct may not be considered —\\n\\nto those residual clauses that created the problem of vagueness for the Court.\\n\\n The “categorical approach” is a specific form of analysis adopted in light of the\\n\\nneed to determine whether prior convictions were for “violent felonies” or “crimes of\\n\\nviolence” under federal provisions — chief among them 18 U.S.C. § 924(e) — that\\n\\nimpose sentencing or other consequences on individuals who have those types of\\n\\nconvictions in their criminal histories. In Taylor v. United States, 495 U.S. 575, 600–02\\n\\n(1990), the Supreme Court recognized that, when applying § 924(e)’s sentencing\\n\\nenhancement, the question of whether a defendant’s prior conviction was for a “violent\\n\\nfelony” must focus exclusively on (1) the elements of the statute under which the\\n\\ndefendant was convicted and (2) the fact of conviction, and exclude any evaluation of the\\n\\nparticular facts or conduct underlying the prior conviction. In reaching this conclusion,\\n\\nthe Court started with the statutory text but hardly found it conclusive. See id. at 600–01\\n\\n(1990) (“First, the language of § 924(e) generally supports the inference that Congress\\n\\n 73\\n\\nintended the sentencing court to look only to the fact that the defendant had been\\n\\nconvicted of crimes falling within certain categories, and not to the facts underlying the\\n\\nprior convictions. . . . Read in . . . context, [the text] most likely refers to the elements of\\n\\nthe statute of conviction, not to the facts of each defendant’s conduct” (emphasis added)).\\n\\nRather, what appeared to seal the deal in favor of the “categorical approach” was the\\n\\nCourt’s serious concern that, in the context of prior convictions, “the practical difficulties\\n\\nand potential unfairness of a factual approach [would be] daunting.” Id. at 601. In this\\n\\nregard, the Court stressed both the impracticality of attempting to relitigate potentially\\n\\nlong-ago events, as well as the Sixth Amendment problem that would be created if\\n\\nsentencing judges were to make factual findings about the nature of the conduct\\n\\nunderlying a defendant’s prior conviction. Id. at 601–02; see also Descamps v. United\\n\\nStates, 570 U.S. 254, 269–70 (2013) (emphasizing “the categorical approach’s Sixth\\n\\nAmendment underpinnings,” as well as the “‘daunting’ difficulties and inequities that\\n\\nfirst encouraged [the Taylor Court] to adopt the categorical approach”).\\n\\n While the precise question resolved by Taylor was whether a defendant who had\\n\\nin fact committed “burglary,” as federal law defines that term, but was convicted under a\\n\\nbroader state statute should be treated as having a “burglary” conviction when applying\\n\\n§ 924(e), the Supreme Court subsequently confirmed that the “categorical approach” also\\n\\napplied to the “residual clause” portion of the “violent felony” definition, see James v.\\n\\nUnited States, 550 U.S. 192, 201–02 (2007). It did so even though it acknowledged that\\n\\nthe residual clause’s text — covering “crime[s]” that “involve[] conduct that presents a\\n\\nserious potential risk of physical injury to another,” § 924(e)(2)(B)(ii) — was “more\\n\\n 74\\n\\nambiguous” and “pose[d] greater interpretive difficulty” as to whether “it too refers to\\n\\ncrimes as generically defined.” Nijhawan v. Holder, 557 U.S. 29, 36 (2009) (emphasis\\n\\nadded).\\n\\n Unique problems arose, however, as courts attempted to apply the “categorical\\n\\napproach” to determine whether the offense of conviction — as defined by its elements,\\n\\nrather than its underlying conduct — was one that “involves conduct that presents a\\n\\nserious potential risk of physical injury.” 18 U.S.C. § 924(e)(2)(B)(ii) (emphasis added).\\n\\nInitially, in attempting to provide clarity, the Court instructed that “the proper inquiry is\\n\\nwhether the conduct encompassed by the elements of the offense, in the ordinary case,\\n\\npresents a serious potential risk of injury to another.” James, 550 U.S. at 208 (emphasis\\n\\nadded); see also Leocal v. Ashcroft, 543 U.S. 1, 7, 10 (2004) (similarly holding that, “[i]n\\n\\ndetermining whether [an individual’s prior] conviction falls within the ambit of § 16[’s\\n\\ndefinition of crime of violence], the statute directs our focus to the ‘offense’ of\\n\\nconviction,” “rather than to the particular facts relating to [the individual’s] crime,” and\\n\\ninterpreting § 16(b) in particular as “cover[ing] offenses that naturally involve a person\\n\\nacting in disregard of the risk that physical force might be used against another in\\n\\ncommitting an offense”). But in both Johnson and Dimaya, the Court ultimately\\n\\nconcluded that this ordinary-case form of the “categorical approach” entailed too much\\n\\nspeculation to be consistent with the Due Process Clause’s prohibition on enforcing\\n\\nvague laws.\\n\\n In particular, the Court in Johnson addressed the residual clause portion of the\\n\\ndefinition of “violent felony” in § 924(e) — a statute that provides a 15-year mandatory\\n\\n 75\\n\\nminimum sentence for certain firearm offenses if the defendant has three prior\\n\\nconvictions for a “violent felony.” Addressing how § 924(e)’s residual clause failed in\\n\\nthe context of the categorical approach, the Court explained:\\n\\n Two features of the residual clause conspire to make it\\n unconstitutionally vague. In the first place, the residual clause leaves\\n grave uncertainty about how to estimate the risk posed by a crime. It ties\\n the judicial assessment of risk to a judicially imagined “ordinary case” of\\n a crime [as required by the categorical approach], not to real-world facts\\n or statutory elements.\\n\\n * * *\\n\\n At the same time, the residual clause leaves uncertainty about how\\n much risk it takes for a crime to qualify as a violent felony. It is one thing\\n to apply an imprecise “serious potential risk” standard to real-world\\n facts; it is quite another to apply it to a judge-imagined abstraction [as\\n required by the categorical approach].\\n\\nJohnson, 135 S. Ct. at 2557–58 (emphases added). The Court noted further that its own\\n\\n“repeated attempts and repeated failures to craft a principled and objective standard out\\n\\nof the residual clause confirm[ed] its hopeless indeterminacy.” Id. at 2558–59 (referring\\n\\nto the Court’s prior decisions in James, 550 U.S. 192; Begay v. United States, 553 U.S.\\n\\n137 (2008); Chambers v. United States, 555 U.S. 122 (2009); and Sykes v. United States,\\n\\n564 U.S. 1 (2011)). The Court concluded that “[i]nvoking so shapeless a provision to\\n\\ncondemn someone to prison for 15 years to life does not comport with the Constitution’s\\n\\nguarantee of due process.” Id. at 2560. In so concluding, however, the Court was quick\\n\\nto note that numerous statutes using terms like “substantial risk” — which the\\n\\ngovernment had warned would be affected by the Court’s holding — were not, in fact, in\\n\\nconstitutional jeopardy. The Court explained:\\n\\n\\n 76\\n\\n [A]lmost all of the cited laws require gauging the riskiness of conduct in\\n which an individual defendant engages on a particular occasion. As a\\n general matter, we do not doubt the constitutionality of laws that call for\\n the application of a qualitative standard such as “substantial risk” to real-\\n world conduct; “the law is full of instances where a man’s fate depends on\\n his estimating rightly . . . some matter of degree.”\\n\\nId. at 2561 (first emphasis in original; second emphasis added) (quoting Nash v. United\\n\\nStates, 229 U.S. 373, 377 (1913)).\\n\\n In Dimaya, the Court followed precisely the Johnson analysis, finding the residual\\n\\nclause used to define “crime of violence” in § 16(b) unconstitutionally vague. At issue in\\n\\nDimaya were provisions of the Immigration and Nationality Act that rendered deportable\\n\\nany alien convicted of an “aggravated felony,” 8 U.S.C. § 1227(a)(2)(A)(iii), which was\\n\\ndefined to include “crime[s] of violence,” as defined in § 16, see id. § 1101(a)(43)(F).\\n\\nSection 16, in turn, defined “crime of violence” in part by a residual clause similar to the\\n\\none used in § 924(e), which was addressed in Johnson. Specifically, the § 16 residual\\n\\nclause defined crime of violence to include any felony offense “that, by its nature,\\n\\ninvolves a substantial risk that physical force against the person or property of another\\n\\nmay be used in the course of committing the offense.” 18 U.S.C. § 16(b).\\n\\n After recalling in extensive detail the holding and reasoning of Johnson, the\\n\\nDimaya Court applied Johnson to find the residual clause in § 16(b) also\\n\\nunconstitutionally vague. It explained:\\n\\n To begin where Johnson did, § 16(b) also calls for a court to identify a\\n crime’s “ordinary case” in order to measure the crime’s risk. . . . Nothing\\n in § 16(b) helps courts to perform that task, just as nothing in [§ 924(e)]\\n did. . . . [T]he “ordinary case” remains, as Johnson described it, an\\n excessively “speculative,” essentially inscrutable thing.\\n\\n\\n 77\\n\\n And § 16(b) also possesses the second fatal feature of [§ 924(e)’s]\\n residual clause: uncertainty about the level of risk that makes a crime\\n “violent.” In [§ 924(e)], that threshold was “serious potential risk”; in\\n § 16(b), it is “substantial risk.” . . . The difficulty comes, in § 16’s residual\\n clause just as in [§ 924(e)’s], from applying such a standard to “a judge-\\n imagined abstraction” — i.e., “an idealized ordinary case of the crime.” It\\n is then that the standard ceases to work in a way consistent with due\\n process.\\n\\n138 S. Ct. at 1215–16 (citations omitted). But again, as in Johnson, the Court repeated\\n\\nthat it did “‘not doubt’ the constitutionality of applying § 16(b)’s ‘substantial risk\\n\\n[standard] to real-world conduct.’” Id. at 1215 (quoting Johnson, 135 S. Ct. at 2561).\\n\\n Thus, in both Johnson and Dimaya, the constitutional vagueness problem arose\\n\\nfrom having to imagine the ordinary case of an offense in the abstract — as required by\\n\\nthe categorical approach — and then to assess that imagined crime’s risk of violence.\\n\\n But the two features identified in Johnson and Dimaya that rendered the residual\\n\\nclauses there unconstitutional — the requirements of (1) imagining the ordinary case of a\\n\\ncrime and (2) applying to it a qualitative risk standard — do not arise when enforcing\\n\\n§ 924(c) because that statute does not require judicial assessment of an imagined ordinary\\n\\ncase. Instead, § 924(c) uses “crime of violence” as an element that is charged in the\\n\\nindictment in the context of real-world conduct on a particular occasion. See United\\n\\nStates v. Rodriguez-Moreno, 526 U.S. 275, 280 (1999) (noting that the commission of a\\n\\ncrime of violence is “an essential conduct element of the § 924(c)(1) offense”). In\\n\\nessence, rather than creating sentencing or immigration consequences for past convictions,\\n\\n§ 924(c)(1) “punishes the temporal and relational conjunction of two separate acts, on the\\n\\n\\n\\n\\n 78\\n\\nground that together they pose an extreme risk of harm.” Rosemond v. United States, 572\\n\\nU.S. 65, 75 (2014).\\n\\n Because real-world conduct was charged in Simms’s indictment, including the\\n\\nHobbs Act violation alleged to be a crime of violence, we are not left to speculate about an\\n\\n“ordinary case” — a “judge-imagined abstraction.” Johnson, 135 S. Ct. at 2557–58.\\n\\nInstead, the indictment informs us of the conduct alleged to constitute a crime of violence,\\n\\nprecluding the need for guesswork. In Count II, Simms was charged with brandishing a\\n\\nfirearm on April 14, 2014, while conspiring to and actually robbing a specified\\n\\nMcDonald’s restaurant and its employees in Goldsboro, with the robbery element being\\n\\ndefined as “taking . . . personal property from [a] person . . . by means of actual or\\n\\nthreatened force, or violence, or fear of injury . . . to his person or property.” 18 U.S.C.\\n\\n§ 1951(b)(1). Simms was thus clearly notified of the government’s allegation that his\\n\\nHobbs Act conspiracy was among the offenses that, “by [their] nature, involve[] a\\n\\nsubstantial risk that physical force against the person or property of another may be used\\n\\nin the course of committing the offense.” Id. § 924(c)(3)(B).\\n\\n This indictment does not invite reliance on some vague, imagined, ordinary\\n\\noffense. Rather, it alleges specific offense conduct, which had to be proved with real-\\n\\nworld facts in order to obtain a conviction. Simms was thus placed on full notice of the\\n\\ncharges and of what had to be proved against him. The problem identified in Johnson and\\n\\nDimaya with courts’ imagining “an ‘idealized ordinary case of the crime,’” such that “no\\n\\none could tell how much risk the offense generally posed,” Dimaya, 138 S. Ct. at 1214\\n\\n(quoting Johnson, 135 S. Ct. at 2557), is simply not a problem in enforcing § 924(c). The\\n\\n 79\\n\\nprosecution of the offense does not involve divining the degree of risk from “a judge-\\n\\nimagined abstraction — i.e., an idealized ordinary case of the crime.” Id. at 1216 (internal\\n\\nquotation marks and citation omitted).\\n\\n In short, in both Johnson and Dimaya, the Supreme Court was presented with the\\n\\nproblem of applying the ordinary-case categorical approach to a prior conviction and\\n\\nthus imagining an abstract offense with a risk that is unknowable due to that very act of\\n\\njudicial imagination. Under § 924(c), however, no prior conviction must be imagined. To\\n\\nthe contrary, the commission of a crime of violence must be alleged as an element of the\\n\\n§ 924(c) offense and must be proved with real-world facts that occurred on a particular\\n\\noccasion. Thus, the definition of crime of violence, as used in § 924(c) as an element of\\n\\nthe offense, does not implicate the unique context identified in both Johnson and Dimaya,\\n\\nwhere the analysis was limited by the severe restrictions imposed by the categorical\\n\\napproach as applied to assess prior convictions.\\n\\n The majority argues that Congress adopted the “categorical approach” by including\\n\\nthe language in § 924(c)(3)(B) that a crime of violence includes a felony “offense . . . that\\n\\nby its nature, involves a substantial risk that physical force against the person or property\\n\\nof another may be used in the course of committing the offense.” It asserts that the phrase\\n\\n“offense . . . that by its nature,” naturally construed, means “categorically” and thus\\n\\nincorporates the “categorical approach.” Ante at 18, 21. Indeed, the majority concludes\\n\\nthat the only “plausible construction” of § 924(c)(3)(B) is that it “requires application of\\n\\nthe ordinary-case categorical approach.” Ante at 21, 41.\\n\\n\\n\\n 80\\n\\n But the majority’s insistence on interpreting § 924(c)(3)(B) as requiring the\\n\\n“categorical approach” represents the judicial equivalent of cramming a square peg into a\\n\\nround hole. Again, the lynchpin of the majority’s textual argument is § 924(c)(3)(B)’s\\n\\nprovision that an offense qualifies as a “violent felony” if “by its nature” it involves the\\n\\nrequisite risk of physical force, and it notes that “nature” is defined as “the basic or\\n\\ninherent features, character, or quality of something.” Ante at 21 (quoting Oxford\\n\\nDictionary of English 1183 (3d ed. 2010)). But while the majority emphasizes that\\n\\n§ 924(c)(3)(B) uses the phrase “by its nature” to modify “offense,” it overlooks that\\n\\n“offense” is a word that, as the Supreme Court has recognized, is sometimes used in\\n\\nordinary speech to “refer to a generic crime, say, the crime of fraud or theft in general”\\n\\nand other times readily used to “refer to the specific acts in which an offender engaged on\\n\\na specific occasion” — e.g., “the fraud that the defendant planned and executed last\\n\\nmonth.” Nijhawan, 557 U.S. at 33–34. And it is just as linguistically reasonable to speak\\n\\nof the “nature” of the defendant’s particular offense, as it is to refer to the “nature” of the\\n\\ngeneral offense as defined by law. See United States v. Barrett, 903 F.3d 166, 182 (2d\\n\\nCir. 2018) (noting that “nothing in the[] definitions [of the word ‘nature’] indicates\\n\\nwhether the offense whose inherent characteristics are to be considered is the generic\\n\\ncrime or the particular one charged”); accord United States v. Douglas, 907 F.3d 1, 11\\n\\n(1st Cir. 2018); Ovalles v. United States, 905 F.3d 1231, 1248 (11th Cir. 2018) (en banc).\\n\\n In addition, the majority’s argument is undermined by another feature of\\n\\n§ 924(c)(3)’s text — namely, the textual difference between subsections (A) and (B).\\n\\nSubsection (A) provides that a “crime of violence” includes any felony offense that has\\n\\n 81\\n\\n“as an element the use, attempted use, or threatened use of physical force,” whereas\\n\\nsubsection (B) provides that a “crime of violence” includes any felony offense that “by its\\n\\nnature[] involves a substantial risk” of physical force being used in the course of its\\n\\ncommission. The phrase “by its nature” in subsection (B) is thus distinct from the use of\\n\\n“elements” in subsection (A), suggesting that the analysis under subsection (B) should\\n\\nfocus not on how an offense is defined by law, but on the nature of the defendant’s offense\\n\\nand the degree of risk posed by it. And this interpretation is only strengthened by\\n\\nsubsection (B)’s focus on the risk that force may be “used in the course of committing the\\n\\noffense.” Moreover, such a distinction between subsections (A) and (B) makes good\\n\\nsense. Subsection (A) thus qualifies a felony as a “crime of violence” if its elements\\n\\nrequire proof that the defendant “use[d], attempt[ed] [to] use, or threaten[ed] [to] use . . .\\n\\nphysical force,” while subsection (B) allows that even if an offense does not have such an\\n\\nelement, it can still qualify as a crime of violence if, as committed on a particular\\n\\noccasion, it actually “involve[d] a substantial risk” of physical force being used. And\\n\\nCongress added further certain phrases to emphasize that this determination is intended to\\n\\nbe relatively broad, covering even those particular violations that, “by [their] nature,\\n\\ninvolve a substantial risk that physical force . . . may be used.”\\n\\n This last statutory feature in particular also precludes the majority’s additional\\n\\nargument that the rule against surplusage compels a categorical interpretation of\\n\\n§ 924(c)(3)(B). See ante at 21–22.\\n\\n To be sure, this reading of § 924(c)(3)(B) differs from the interpretation the\\n\\nSupreme Court in Johnson gave to the similar language defining “violent felony” in\\n\\n 82\\n\\n§ 924(e), as well as from the Dimaya plurality’s interpretation of the materially identical\\n\\ntext in § 16(b). But this difference is readily explained by the fact that § 924(e) and\\n\\n§ 16(b) are applied to characterize prior convictions, and the Court was therefore\\n\\ncompelled to apply the categorical approach. See Johnson, 135 S. Ct. at 2562 (concluding\\n\\nthat “‘[t]he only plausible interpretation’” of § 924(e)’s residual clause is that it “requires\\n\\nuse of the categorical approach” (1) because the text’s “emphasis on convictions indicates\\n\\nthat ‘Congress intended the sentencing court to look only to the fact that the defendant had\\n\\nbeen convicted of crimes falling within certain categories’” and (2) because of “the utter\\n\\nimpracticality of requiring a sentencing court to reconstruct, long after the original\\n\\nconviction, the conduct underlying that conviction” (emphasis added) (quoting Taylor,\\n\\n495 U.S. at 600–02)); see also Dimaya, 138 S. Ct. at 1217–18 (plurality opinion)\\n\\n(emphasizing, among other reasons for concluding that § 16(b) must be read as\\n\\nincorporating the categorical approach, (1) that the “Court adopted the categorical\\n\\napproach in part to avoid the Sixth Amendment concerns that would arise from sentencing\\n\\ncourts’ making findings of fact that properly belong to juries” and (2) that a fact-based\\n\\nreading would create “the daunting difficulties of accurately reconstructing, often many\\n\\nyears later, the conduct underlying a conviction’” (emphasis added) (internal quotation\\n\\nmarks, brackets, and citations omitted)).\\n\\n By contrast, the definition of crime of violence in § 924(c)(3) applies only to\\n\\ncontemporaneously charged conduct that is made an element of the § 924(c)(1) violation\\n\\nand never to prior convictions. And, in that distinct context, the important practical\\n\\nconsiderations and Sixth Amendment concerns that led the Court to develop and adhere to\\n\\n 83\\n\\nthe categorical approach for similar residual clauses simply do not apply. It is therefore\\n\\nnot surprising that § 924(c) has presented little difficulty to courts, prosecutors, and\\n\\ndefense counsel in its enforcement, and the so-called problems with that statute have been\\n\\ncreated only by the effort to force the ordinary-case categorical approach, applicable in\\n\\nother circumstances, onto a statute that punishes the use of a firearm in connection with a\\n\\ncrime of violence, in this case a Hobbs Act conspiracy.\\n\\n But were there any doubt about the proper construction of § 924(c) we would\\n\\nnonetheless have to give the statute the benefit of the doubt when a constitutional reading\\n\\nof it is “fairly possible,” as I surely conclude. I.N.S. v. St. Cyr, 533 U.S. 289, 299–300\\n\\n(2001). This constitutional avoidance doctrine serves the “basic democratic function of\\n\\nmaintaining a set of statutes that reflect, rather than distort, the policy choices that the\\n\\nelected representatives have made.” Almendarez-Torres v. United States, 523 U.S. 224,\\n\\n238 (1998).\\n\\n I thus readily conclude that the residual clause in § 924(c) defining the “crime of\\n\\nviolence” element of the offense is not unconstitutionally vague. Simms received ample\\n\\nnotice of how to conform his conduct to the law, and the statute provides adequate\\n\\nstandards to prevent “arbitrary and discriminatory enforcement.” Kolender, 461 U.S. at\\n\\n357. I would accordingly affirm the district court’s judgment.\\n\\n\\n\\n\\n 84\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4361701/\", \"author_raw\": \"WILKINSON, Circuit Judge, dissenting\"}, {\"author\": \"RICHARDSON, Circuit Judge, with whom Judge QUATTLEBAUM joins, dissenting\", \"type\": \"dissent\", \"text\": \"RICHARDSON, Circuit Judge, with whom Judge QUATTLEBAUM joins, dissenting:\\n\\n While robbing a McDonalds, Simms struck the manager on the head with a gun.\\n\\nBy statute, if the nature of Simms’s offense involved a “substantial risk of physical\\n\\nforce,” then it was a “crime of violence.” 18 U.S.C. § 924(c)(3)(B). And if we look to\\n\\nthe facts here, it seems obvious that Simms’s offense was a crime of violence: of course\\n\\nhitting someone over the head with a gun involves a substantial risk of physical force.\\n\\nAnd Simms agreed when he pleaded guilty.\\n\\n My colleagues in the majority take a different tack. Refusing to read the statute to\\n\\napply to the facts of this case, they insist that the statute must be applied to some\\n\\nhypothetical conduct that would be involved in an “ordinary case” of federal robbery.\\n\\nYet, by the majority’s own account, the hypothetical, “ordinary case” interpretation is not\\n\\nworkable here. In fact, even before adopting it, the majority accepts that its interpretation\\n\\nis unconstitutionally vague under the Fifth Amendment.\\n\\n This is not the right approach. It is our duty as judges, if we can, to give statutes a\\n\\nreasonable interpretation that conforms to the Constitution. Because the statute permits\\n\\nlooking directly to Simms’s conduct in pistol whipping a manager during a robbery, I\\n\\nrespectfully dissent.\\n\\n I. Avoiding an Unconstitutional Construction\\n\\n Any statutory provision must be interpreted, whenever possible, to avoid\\n\\nunconstitutionality. Our duty to adopt saving constructions dates back more than two\\n\\nhundred years. See Mossman v. Higginson, 4 U.S. (4 Dall.) 12 (1800); Society for the\\n\\n\\n\\n 85\\n\\nPropagation of the Gospel v. Wheeler, 22 F. Cas. 756, 769 (C.C.D.N.H. 1814). 1 At base,\\n\\nthe rule reflects respect for the political branches, presuming they intend to comply with\\n\\nour Constitution. 2 So long as it does not require doing violence to unambiguous\\n\\nlanguage, courts must act to save a statute with any plausible constitutional interpretation.\\n\\nGrenada Cty. Supervisors v. Brogden, 112 U.S. 261, 269 (1884).\\n\\n Here, we face a binary choice. On the one hand, if Section 924(c)(3)(B) compels\\n\\nthe “ordinary case” interpretation, then it is unconstitutionally vague and Simms escapes\\n\\nliability. On the other, if the statute permits a case-specific interpretation, then it is\\n\\nconstitutional and Simms’s guilty plea stands.\\n\\n\\n 1\\n Justice Story later explained that if a\\n\\n section admits of two interpretations, one of which brings it within, and the\\n other presses it beyond the constitutional authority of congress, it will\\n become our duty to adopt the former construction; because a presumption\\n never ought to be indulged, that congress meant to exercise or usurp any\\n unconstitutional authority, unless that conclusion is forced upon the Court\\n by language altogether unambiguous.\\n\\nUnited States v. Coombs, 37 U.S. (12 Pet.) 72, 76 (1838); see also Blodgett v. Holden,\\n275 U.S. 142, 148 (1927) (Holmes, J., concurring) (“[A]s between two possible\\ninterpretations of a statute, by one of which it would be unconstitutional and by the other\\nvalid, [a court’s] plain duty is to adopt that which will save the Act.”).\\n 2\\n The requirement that a court adopt a plausible interpretation to avoid striking\\ndown a statute as unconstitutional is sometimes referred to as the presumption of validity\\nor the unconstitutionality canon. It is related to the more recent, and arguably weaker,\\n“doubts” canon, which urges courts to adopt plausible interpretations of statutes to avoid\\nhaving to contemplate difficult constitutional questions. See United States ex rel.\\nAttorney General v. Delaware & Hudson Co., 213 U.S. 366, 408 (1909); see also\\nJennings v. Rodriguez, 138 S. Ct. 830, 836 (2018). For a discussion of these two\\nprinciples, see Adrian Vermeule, Saving Constructions, 85 GEO. L.J. 1945, 1948–50\\n(1997).\\n\\n\\n 86\\n\\n While our choice is binary, statutory interpretation often is not. Typically, judges\\n\\nseek the “best reading of the statute by interpreting the words of the statute, taking\\n\\naccount of the context of the whole statute, and applying the agreed-upon semantic\\n\\ncanons.” Brett Kavanaugh, Fixing Statutory Interpretation, 129 HARV. L. REV. 2118,\\n\\n2121 (2016) (book review). Along the way to the “best” interpretation, we discard other\\n\\npossibilities. Not all the rejects are flat-out wrong (although some are). An interpretation\\n\\nmay have some support in the text, and even from a canon, but still get left on the cutting-\\n\\nroom floor in favor of another, better option. And we keep on discarding until we find\\n\\nthe best one.\\n\\n But in some circumstances, we must abandon the search for the best reading of the\\n\\nstatute. When a statute’s best interpretation would render it unconstitutional, a court\\n\\nmust identify and adopt any fairly possible interpretation that would save it. See Hooper\\n\\nv. California, 155 U.S. 648, 657 (1895) (“The elementary rule is that every reasonable\\n\\nconstruction must be resorted to, in order to save a statute from unconstitutionality.”).\\n\\nThat means looking for a plausible constitutional option for Section 924(c)(3)(B). 3\\n\\n\\n\\n\\n 3\\n I agree with much of Judge Niemeyer’s fine opinion finding that the proper\\nconstruction of the residual clause requires looking to Simms’s actual conduct. In my\\nview, however, the duty to adopt a saving construction obviates the need to identify the\\nbest reading, requiring us to determine only whether a fairly possible reading permits\\nlooking to Simms’s actual conduct. See Ante at 84 (Niemeyer, J., dissenting) (noting in\\nthe alternative that the constitutional avoidance doctrine would apply if there were any\\ndoubt about the proper construction).\\n\\n\\n 87\\n\\n II. The Residual Clause of Section 924(c)(3)\\n\\n Having framed our endeavor, I begin by asking what readings of the statute are\\n\\neven conceivable. Once the conceivable interpretations are identified, I turn to evaluating\\n\\nwhich of those are plausible.\\n\\n Section 924(c)(3) defines the term “crime of violence” to mean\\n\\n an offense that is a felony and—\\n (A) has as an element the use, attempted use, or threatened use of physical\\n force against the person or property of another, or\\n (B) that by its nature, involves a substantial risk that physical force\\n against the person or property of another may be used in the course of\\n committing the offense.\\n\\n(emphasis added). This statute provides two definitions of what constitutes a “crime of\\n\\nviolence.” The first, sometimes called the “elements clause,” focuses on whether the\\n\\n“elements” of an offense include the “use, attempted use, or threatened use of physical\\n\\nforce.” The second, called the “residual clause,” focuses on whether the offense’s\\n\\n“nature” involves “a substantial risk that physical force” may be “used in the course of\\n\\ncommitting the offense.” As its name conveys, the second clause is residual, meaning it\\n\\noperates as a catch-all for those offenders engaged in this type of risky conduct that might\\n\\notherwise fail to meet the elements clause.\\n\\n A. Three Conceivable Interpretations of the Residual Clause\\n\\n The language and context of the residual clause point to three conceivable\\n\\nreadings, each asking us to look at the offense through a different lens. First, an\\n\\nelements-based one: Does the offense legally require proof of a substantial risk of\\n\\nphysical force? Second, a hypothetical one: Does a judicially imagined “ordinary”\\n\\n 88\\n\\nversion of the offense involve conduct that presents a substantial risk of force? Third, a\\n\\nfactual one: Does the specific offense involve actual conduct that presents a substantial\\n\\nrisk of physical force? See generally Johnson v. United States, 135 S. Ct. 2551, 2557\\n\\n(2015) (noting three possibilities for consideration: the statutory “elements,” a “judicially\\n\\nimagined ordinary case,” or “real-world facts”). These readings have been fleshed out in\\n\\nthe context of other, similar statutes, although there is no binding Supreme Court\\n\\nprecedent governing this particular statute.\\n\\n The first and most formalistic reading requires looking at the elements of the\\n\\n“offense.” See Descamps v. United States, 570 U.S. 254, 257 (2013). That is, one would\\n\\nask whether one element of the crime is a substantial risk that physical force may be\\n\\nused.\\n\\n The second reading concentrates not on the legal elements of the crime but on the\\n\\nconduct thought to be ordinarily involved in violating those elements. This approach is\\n\\nsimilar to the first in that it is “categorical”: once the courts decide whether a particular\\n\\ncriminal statute satisfies the residual clause, that holding applies to any conviction under\\n\\nthe statute, without a factfinder looking at what that defendant did. Yet it differs from the\\n\\nfirst in that it looks to conduct: namely “whether the conduct encompassed by the\\n\\nelements of the offense, in the ordinary case, presents a serious potential risk.” James v.\\n\\nUnited States, 550 U.S. 192, 208 (2007) (emphasis added). This approach is an exercise\\n\\nin judicial imagination, requiring “a court to picture the kind of conduct that the crime\\n\\ninvolves in ‘the ordinary case,’ and to judge whether that abstraction presents a serious\\n\\npotential risk.” Johnson, 135 S. Ct. at 2557.\\n\\n 89\\n\\n Real-world facts are the focus of the approach resulting from the third and final\\n\\ninterpretation. This approach is like the second approach, and unlike the first, in that it\\n\\nlooks at conduct. Yet unlike the second approach, it is not categorical and requires no\\n\\njudicial ingenuity: it asks only whether the actual conduct committed by the defendant\\n\\npresents a substantial risk on a case-by-case basis. The third approach has significant\\n\\nappeal, relieving judges of imagining hypotheticals and empowering factfinders\\n\\n(generally juries) to do their job. See Ante at 64 (Wilkinson, J., dissenting).\\n\\n B. The Case-Specific Interpretation of the Residual Clause is Plausible\\n\\n Thus, three conceivable interpretations are available. The first and third readings\\n\\nare constitutional; the second, “ordinary case” reading, would be unconstitutionally\\n\\nvague. We must therefore ask whether the first and third are fairly possible. If either is,\\n\\nthen the “ordinary case” interpretation must be rejected to save the statute.\\n\\n Neither party argues that the first interpretation is plausible, and for good reason.\\n\\nTo be sure, the term “offense” can be read to encompass the formalistic concept of a\\n\\ncrime as defined by its elements. Indeed, “offense” takes that meaning in subsection A’s\\n\\nelements clause. Yet there is little else good to say about this interpretation, and two\\n\\nconsiderations make it untenable. First, Congress knew how to specify an elements-\\n\\nbased approach and did so in subsection A, but not in subsection B. Subsection B\\n\\ncontemplates an understanding of “offense” that is broader than the formalistic\\n\\nsubsection A. See United States v. Price, 777 F.3d 700, 708–09 (4th Cir. 2015). Second,\\n\\nI am aware of no other federal criminal statute with a “substantial risk” that “physical\\n\\n\\n\\n 90\\n\\nforce” “may be used” as an actual element. And we generally avoid interpreting statutes\\n\\nto render them a nullity.\\n\\n The third interpretation is a different story. Consider again the term “offense.”\\n\\nThe term is ambiguous: it is consistent with the elements-based approach (as already\\n\\nnoted), but also with the others. The Supreme Court has found it may refer to (1) “a\\n\\ngeneric crime, say, the crime of fraud or theft in general,” or (2) “the specific acts in\\n\\nwhich an offender engaged on a specific occasion, say, the fraud that the defendant\\n\\nplanned and executed last month.” Nijhawan v. Holder, 557 U.S. 29, 33–34 (2009); see\\n\\nalso United States v. Hayes, 555 U.S. 415, 426 (2009). While definition (1) fits the\\n\\nelements-based and “ordinary case” approaches, definition (2) permits consideration of\\n\\nthe real-world conduct committed by the defendant.\\n\\n To decide which definition is appropriate, courts look to the statutory context. In\\n\\nsome cases, context compels a case-specific approach based on real-world conduct. See\\n\\nNijhawan, 557 U.S. at 40. In others, context compels the “generic” interpretation. See\\n\\nid. at 37. The term may even be used in both senses within the same sentence: to mean a\\n\\ngeneric crime and how the specific crime was committed. See Hayes, 555 U.S. at 421\\n\\n(holding “offense” that “has, as an element, the use or attempted use of physical\\n\\nforce . . . , committed by a current or former spouse,” requires a categorical determination\\n\\nof the elements but a fact-specific evaluation of the person who committed the offense).\\n\\n Our own precedent confirms that “offense” may compel examining real-world\\n\\nconduct. In Price, the statute defined “sex offense” to mean a “criminal offense that is a\\n\\nspecified offense against a minor.” 777 F.3d at 704 (quoting 42 U.S.C.\\n\\n 91\\n\\n§ 16911(5)(A)(ii)). The statute then defined “specified offense[s] against a minor”\\n\\naccording to a list of enumerated offenses and a residual clause encompassing “[a]ny\\n\\nconduct that by its nature is a sex offense against a minor.” Id. (quoting 42 U.S.C.\\n\\n§ 16911(7)(I)). In that context, we concluded, the statute “refers to how an offense was\\n\\ncommitted—not a generic offense.” Id. at 709. 4\\n\\n Here, we need only decide whether the fact-specific approach—which again, the\\n\\nSupreme Court has held is a permissible reading of the word “offense”—is plausible.\\n\\nAnd the context here shows that it is.\\n\\n Consider the phrase “by its nature.” In ordinary use, “nature” means a “normal\\n\\nand characteristic quality” of something. Webster’s Third New International Dictionary\\n\\n1507–08 (1986); see also Oxford Dictionary of English 1183 (3d ed. 2010) (“basic or\\n\\ninherent features, character, or qualities of something”). This definition, however, merely\\n\\nraises the question of what the “something” is? See United States v. Barrett, 903 F.3d\\n\\n166, 182 (2d Cir. 2018). It could be either the hypothetical, “ordinary case” conduct of\\n\\nthe second interpretation or the case-specific, real-world conduct of the third. Compare\\n\\n\\n 4\\n The majority attempts to distinguish Price on the basis that Section\\n924(c)(3)(B)’s residual clause lacks “conduct-specific language.” Majority Op. at 30.\\nYet the majority has found that the residual clause demands adopting the “ordinary case”\\napproach, an interpretation that focuses exclusively on hypothetical conduct.\\n\\n Even were the majority’s distinction convincing, this would miss the point. Cases\\nlike Nijhawan, Hayes, and Price reveal that the phrasing used here does not unavoidably\\nrefer to the “ordinary case” approach. It makes no difference whether the majority can\\nfind some linguistic distinction for each case, because a reading calling for the fact-\\nspecific approach need only be fairly possible.\\n\\n\\n 92\\n\\nDugger v. Adams, 489 U.S. 401, 410 n.6 (1989) (using “by its nature” to refer to general\\n\\ncharacteristics and not individualized circumstances), with H.J. Inc. v. Nw. Bell Tel. Co.,\\n\\n492 U.S. 229, 241–42 (1989) (noting that RICO continuity may be shown by “past\\n\\nconduct that by its nature projects into the future with a threat of repetition,” and that this\\n\\nconduct “depends on the specific facts of each case” (emphasis added)), and Doolan v.\\n\\nCarr, 125 U.S. 618, 625 (1887) (“[E]ven a patent from the government of the United\\n\\nStates, issued with all the forms of law, may be shown to be void by extrinsic evidence if\\n\\nit be such evidence as by its nature is capable of showing a want of authority for its\\n\\nissue.” (emphasis added)). Thus, the phrase “by its nature” does not resolve the meaning\\n\\nof “offense” one way or the other.\\n\\n Nor does the rest of the residual clause: “involves a substantial risk that physical\\n\\nforce against the person or property of another may be used in the course of committing\\n\\nthe offense.” Either hypothetical conduct or actual conduct may “involve substantial\\n\\nrisk.” Similarly, the predictive phrase “may be used” applies equally well to hypothetical\\n\\nor actual conduct. And the same is true of “in the course of committing the offense.”\\n\\n Tellingly, the majority concedes that all the individual terms in the statute are\\n\\nsusceptible to a case-specific interpretation. Somehow, it claims, the combination of\\n\\nwords compels the “ordinary case” approach. See Majority Op. at 26–27. But a handful\\n\\nof maybe’s simply do not add up to a never.\\n\\n III. Precedent Does Not Demand the “Ordinary Case” Approach\\n\\n The majority also claims that the Supreme Court has already resolved this issue by\\n\\nholding that the language used in Section 924(c)(3)(B) permits only one reading: the\\n\\n 93\\n\\nhypothetical conduct of an ordinary case. In so doing, the majority rewrites history. The\\n\\nSupreme Court has never held that the language like that in Section 924(c)(3)(B)\\n\\nnecessarily requires the “ordinary case” analysis.\\n\\n The origins of the modern “ordinary case” approach lie in Supreme Court\\n\\ndecisions interpreting statutory sentencing enhancements based on prior convictions for\\n\\n“violent felonies.” Those decisions adopted a “categorical approach,” requiring courts to\\n\\nlook at the elements of the offense and not the defendant’s conduct. See Shepard v.\\n\\nUnited States, 544 U.S. 13, 19 (2005); Taylor v. United States, 495 U.S. 575, 600–02\\n\\n(1990). In addition to the text and practical considerations, one of the main motivators of\\n\\nthe “categorical approach” was the need to avoid a potential Sixth Amendment problem:\\n\\nif a mandatory sentencing enhancement arose from the facts underlying a prior\\n\\nconviction, as opposed to the fact of conviction itself, then those facts could not be\\n\\ndetermined by a judge (absent a defendant’s wavier). Shepard, 544 U.S. at 24 (plurality\\n\\nopinion). The importance of the Sixth Amendment to the history of the categorical\\n\\napproach is hardly controversial. The Supreme Court itself has directed courts to\\n\\nconsider “the categorical approach’s Sixth Amendment underpinnings” when applying it.\\n\\nDescamps, 570 U.S. at 269. And multiple panel decisions by this Court have\\n\\nacknowledged as much. See, e.g., Price, 777 F.3d at 709–10. 5\\n\\n\\n 5\\n The majority downplays the importance of the Sixth Amendment concern,\\nsuggesting that these cases were only “secondarily informed” by nontextual\\nconsiderations. Majority Op. at 20. That argument is ad hoc, running against uniform\\nSupreme Court and circuit-level precedent to the contrary. Equally unconvincing is the\\nmajority’s suggestion that, because the Court started with the text in these cases, the text\\n(Continued)\\n 94\\n\\n Over time, the categorical approach was extended to new contexts. There are a\\n\\nnumber of statutes that mix and match similar language to define “crimes of violence” or\\n\\n“violent felonies.” The language at issue in Taylor and Shepard, the classic cases,\\n\\nencompasses crimes that correspond to the “generic” definition of certain enumerated\\n\\ncrimes. Other statutes include language resembling the “elements clause” of Section\\n\\n924(c)(3)(A) and the “residual clause” of Section 924(c)(3)(B). Unsurprisingly, the\\n\\nCourt transplanted the categorical approach into these similar contexts. Yet the Court\\n\\ncontinued to note the important Sixth Amendment problems that the categorical approach\\n\\navoided. See James, 550 U.S. at 213–14.\\n\\n The majority identifies only two cases suggesting that statutory text alone—\\n\\nunaccompanied by constitutional and other considerations—was sufficient to support the\\n\\ncategorical approach. Neither is persuasive in interpreting the statute at hand. The first\\n\\ncase, Leocal v. Ashcroft, only superficially supports the majority. After quoting language\\n\\nfrom the residual clause in 18 U.S.C. § 16(b) (textually similar to the residual clause of\\n\\nSection 924(c)(3)(B)), the Court stated: “[t]his language requires us to look to the\\n\\nelements and the nature of the offense of conviction, rather than to the particular facts\\n\\nrelating to petitioner’s crime.” 543 U.S. 1, 7 (2004). Yet it is hardly surprising that the\\n\\nSupreme Court did not analyze the issue in detail: the parties, amici, and the Court\\n\\n\\n\\n\\nalone must have been decisive. Id. at 19. The Supreme Court, like all courts, always\\nstarts from the text in statutory interpretation cases. See, e.g., Sebelius v. Cloer, 569 U.S.\\n369, 376 (2013).\\n\\n\\n 95\\n\\naccepted the application of the categorical approach as an untested premise before\\n\\naddressing the issue presented. Cf. Sessions v. Dimaya, 138 S. Ct. 1204, 1232 (2018)\\n\\n(Gorsuch, J., concurring in part and concurring in judgment) (accepting the “ordinary\\n\\ncase” approach to Section 16(b) as a premise).\\n\\n As everyone accepted the categorical approach, Leocal had no reason to consider\\n\\nany saving constructions to avoid unconstitutionality (or constitutional doubts). So even\\n\\nwere one to read Leocal as finding the “best” interpretation, that does not answer whether\\n\\nthat is the only plausible interpretation. Moreover, Leocal addressed the application of\\n\\nSection 16 to prior convictions. It is in that context that applying a factual approach\\n\\nwould raise the serious practical and Sixth Amendment concerns at issue in Taylor,\\n\\nShepard, and James. Section 924(c)(3) presents none of those problems, as it applies\\n\\nonly to contemporaneous conduct. Nor did Leocal foresee that applying the “ordinary\\n\\ncase” approach would be unconstitutionally vague under the Fifth Amendment. In fact,\\n\\nLeocal did not even use the term “ordinary case.” In sum, Leocal’s acceptance of an\\n\\nundisputed premise while interpreting a different statute in a different context without\\n\\ndiscussing the plausibility of a saving construction does not dictate the interpretation of\\n\\nSection 924(c)(3)(B).\\n\\n The second case, Dimaya, is even less supportive. It is true that Section IV(A) of\\n\\nJustice Kagan’s opinion in Dimaya held that similar language demands the use of the\\n\\ncategorical approach, but that interpretation was only endorsed by a plurality of the\\n\\nSupreme Court. Justice Gorsuch chose not to join that section of the opinion. Under the\\n\\nMarks rule, the binding holding of the Court is the narrowest opinion from those\\n\\n 96\\n\\nconcurring in the judgment. Marks v. United States, 430 U.S. 188, 193 (1977). Thus,\\n\\nJustice Gorsuch’s narrower concurrence controls. He (like the parties) simply assumed\\n\\nthat the “ordinary case” approach applied, and on that basis held that § 16(b) is\\n\\nimpermissibly vague. Dimaya, 138 S. Ct. at 1232–33 (Gorsuch, J., concurring in part and\\n\\nconcurring in judgment).\\n\\n As for the debated language, Justice Gorsuch noted that “[p]lausibly, anyway, the\\n\\nword ‘nature’ might refer to an inevitable characteristic of the offense; one that would\\n\\npresent itself automatically, whenever the statute is violated.” Dimaya, 138 S. Ct. at\\n\\n1233. He continued, “[w]hile I remain open to different arguments about our precedent\\n\\nand the proper reading of language like this, I would address them in another case,\\n\\nwhether involving the INA or a different statute, where the parties have a chance to be\\n\\nheard and we might benefit from their learning.” Id. Thus, Justice Gorsuch\\n\\nunambiguously stated that he is open to other interpretations, even involving the statute at\\n\\nissue in his own opinion. As his concurrence shows, the majority gets Dimaya backward.\\n\\nDimaya makes clear that the interpretation of this language is a live issue before the\\n\\nSupreme Court, not one settled by precedent.\\n\\n If anything, the history of the categorical approach shows that the “ordinary case”\\n\\napproach should be jettisoned wherever possible. In truth, there is not one categorical\\n\\napproach; there are two. When the purely elements-based categorical approach from\\n\\nTaylor and Shepard was applied to residual clauses, it evolved (or perhaps devolved) into\\n\\nthe “ordinary case” approach. See James, 550 U.S. at 208. Those two approaches are\\n\\nonly superficially similar. The elements-based approach looks only at the formal\\n\\n 97\\n\\ndefinition of the offense; the “ordinary case” approach tries to construct a hypothetical\\n\\nmodel of conduct for the offense. In both logic and application, they are as different from\\n\\neach other as they are from the case-specific approach. History has shown that the\\n\\n“ordinary case” approach is unworkable, so much so that its application has been\\n\\ndeclared unconstitutionally vague twice. Johnson, 135 S. Ct. at 2563; Dimaya, 138 S. Ct.\\n\\nat 1232–33 (Gorsuch, J., concurring in part and concurring in judgment).\\n\\n In contexts where the Sixth Amendment applies—in particular, mandatory\\n\\nsentencing enhancements for prior convictions—the “ordinary case” approach is the only\\n\\nway to interpret a residual clause. But in many contexts, those Sixth Amendment\\n\\nconcerns do not apply. This is one of them: The consideration of contemporaneous\\n\\nconduct under Section 924(c)(3)(B) need not create any Sixth Amendment concerns. See\\n\\nAnte at 79 (Niemeyer, J., dissenting). And we have noted the importance of this\\n\\ndistinction when rejecting specific applications of the categorical approach. Price, 777\\n\\nF.3d at 709–10 (noting, in rejecting the categorical approach, that “Sixth Amendment\\n\\nconcerns that compel the judicial use of the categorical approach in other contexts are not\\n\\npresent here”). When Sixth Amendment concerns do not apply, but Fifth Amendment\\n\\nvagueness concerns do, we must adopt the fact-specific interpretation.\\n\\n IV. The Majority’s Remaining Arguments\\n\\n The majority advances a grab-bag of other considerations to support its “ordinary\\n\\ncase” interpretation. Many of these are unpersuasive on their face, but I mention three\\n\\nbriefly.\\n\\n\\n\\n 98\\n\\n First, the majority argues that adopting the factual approach to the residual clause\\n\\nwould lead to a contradiction: “offense that is a felony” would be read to have a\\n\\ncategorical interpretation in the elements clause, but a case-specific interpretation in the\\n\\nresidual clause. Majority Op. at 23–24. This reasoning is hollow because, as I have\\n\\nalready explained, there is not only one categorical approach. The hypothetical conduct\\n\\nof the “ordinary case” approach adopted by the majority differs substantially from the\\n\\nlegal elements of the elements-based approach. Thus, the interpretation the majority\\n\\nadopts is similarly contradictory. And in any event, neither “contradiction” is that\\n\\nconcerning. See Nijhawan, 557 U.S. at 37 (The “statute lists several of its ‘offenses’ in\\n\\nlanguage that must refer to generic crimes . . . [but] it lists certain other ‘offenses’ using\\n\\nlanguage that almost certainly does not refer to generic crimes but refers to specific\\n\\ncircumstances.”).\\n\\n The majority also suggests that reading the residual clause to apply to real-world\\n\\nfactual conduct violates the rule against surplusage by draining the phrase “by its nature”\\n\\nof any meaning. At the outset, the Supreme Court has explained that the rule against\\n\\nsurplusage “is not absolute” and is itself to be avoided when it causes more problems\\n\\nthan it solves. Lamie v. U.S. Trustee, 540 U.S. 526, 536 (2004). In any event, “by its\\n\\nnature” is not superfluous under the case-specific approach for two reasons. First, the\\n\\nphrase distinguishes subsection B’s conduct-based residual clause from subsection A’s\\n\\nelements clause. The latter addresses the legal elements of the offense (“has as an\\n\\nelement”), while the former focuses more broadly on conduct (whether hypothetical or\\n\\nactual conduct). See Price, 777 F.3d at 708–09. Second, “by its nature” limits the\\n\\n 99\\n\\nresidual clause to conduct that involves risk inherently or naturally, not merely\\n\\nincidentally or by happenstance. In this sense, the phrase “by its nature” acts as an\\n\\nintensifier that limits the clause’s application to more dangerous crimes.\\n\\n Finally, the majority makes passing reference to the rule of lenity. Majority Op. at\\n\\n40. The majority cites no authority for the proposition that the rule of lenity, grounded in\\n\\nthe need for fair warning, demands that this Court knowingly adopt an interpretation so\\n\\nunclear that it is unconstitutionally vague. Indeed, this makes no sense. Cf. United States\\n\\nv. Lanier, 520 U.S. 259, 266 (1997) (describing the “rule of lenity” as the “junior version\\n\\nof the vagueness doctrine” that “ensures fair warning by so resolving ambiguity in a\\n\\ncriminal statute as to apply it only to conduct clearly covered”); United States v. Harriss,\\n\\n347 U.S. 612, 617–18 (1954) (noting that while the Constitution “is violated by a\\n\\ncriminal statute that fails to give a person of ordinary intelligence fair notice,” a court is\\n\\nunder a “duty” to give a “reasonable construction of the statute” that makes the “class of\\n\\noffenses . . . constitutionally definite”). It may well be that no ordinary person would be\\n\\nfairly warned that their conduct might be implicated by the hypothetical, “ordinary case”\\n\\nof robbery, but most everyone would understand that pistol whipping someone during an\\n\\narmed robbery is a crime of violence. 6\\n\\n\\n 6\\n Judge Wynn suggests that the avoidance doctrine should allow only those\\ninterpretations that “narrow” a criminal statute. See Ante at 47 (Wynn, J., concurring).\\nEven if one accepts this novel theory, the “ordinary case” approach is not inherently\\n“narrower” than the case-specific approach. Since the “ordinary case” approach focuses\\non judicially-imagined hypothetical conduct in place of a defendant’s own actions, that\\napproach is both over- and under-inclusive. While some defendants would be guilty\\nunder the case-specific approach but not the “ordinary case” approach, other defendants\\n(Continued)\\n 100\\n\\n * * *\\n\\n Occasionally we find ourselves so far down the rabbit hole that logic appears\\n\\nupside down. It is true that the faithful application of the law may lead to odd results.\\n\\nAnd I certainly do not fault the majority for following its analysis to this seemingly\\n\\nnonsensical result. For good judges must be willing to reach results that go against their\\n\\npreferences when those results are dictated by principles or precedent.\\n\\n But judges are also required to exercise restraint. Voiding an act of Congress is an\\n\\nextraordinary exercise of judicial power, and accordingly, such power should only be\\n\\ninvoked when it is incumbent upon us to do so. Here, the statute plausibly permits\\n\\nlooking directly at Simms’s conduct in pistol whipping a manager during a robbery in\\n\\ndetermining whether his conduct qualified as a crime of violence under the residual\\n\\n\\n\\n\\nwould find themselves in the exact reverse position. These latter defendants, whose\\nactual conduct did not create a substantial risk of violence, would be guilty when\\nevaluated under the guise of a hypothetical ordinary case. Assuming it matters, I cannot\\nas an empirical matter reasonably identify whether the former group is larger than the\\nlatter. Cf. Dimaya, 138 S. Ct. at 1232 (Gorsuch, J., concurring in part and concurring in\\njudgment) (rhetorically asking whether “a conviction for witness tampering ordinarily\\ninvolve[s] a threat to the kneecaps or just the promise of a bribe”).\\n Moreover, the concurrence’s characterization of what it means to “expand” a\\nstatute’s reach is perverse. A judicially-imagined “ordinary case” can ensnare a\\ndefendant whose actual conduct created no risk of violence, a result barred by the case-\\nspecific approach. It is the “ordinary case” approach that expands the statute to cover\\nhypothetical conduct imagined by a court. And this is why the “ordinary case” approach\\nis unconstitutionally vague. A far more precise approach is to let juries determine guilt\\nbased on the real actions taken by the defendant. See Harriss, 347 U.S. at 618 (noting the\\nduty to make the “class of offenses . . . constitutionally definite”). It is entirely proper to\\nreplace an unworkable, unconstitutionally vague interpretation with a readily-\\ncomprehensible, textually-supported interpretation, even if that interpretation would\\n“expand” liability by clarifying which conduct falls within the statute and which does not.\\n\\n 101\\n\\nclause. We are therefore required to adopt that reading. For these reasons, I respectfully\\n\\ndissent.\\n\\n\\n\\n\\n 102\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4361701/\", \"author_raw\": \"RICHARDSON, Circuit Judge, with whom Judge QUATTLEBAUM joins, dissenting\"}]}"},"judge1":{"kind":"string","value":"GREGORY"},"judge2":{"kind":"string","value":"WILKINSON"},"judge3":{"kind":"string","value":"NIEMEYER"},"exactly_three_caps":{"kind":"number","value":2,"string":"2"},"extra_judges":{"kind":"string","value":"MOTZ; KING; DUNCAN; AGEE; KEENAN; WYNN; DIAZ; FLOYD; THACKER; HARRIS; RICHARDSON; QUATTLEBAUM"},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":8,"string":"8"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":4,"string":"4"},"concurrence_count":{"kind":"number","value":2,"string":"2"},"other_count":{"kind":"number","value":2,"string":"2"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4584448/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":1,"string":"1"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff-Appellee, v. Joseph Decore SIMMS, Defendant-Appellant. Fourth Circuit Federal Defender Offices, Amicus Supporting Appellant.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-24\nOpinion type: majority\nHas dissenting opinion: Yes\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 15-4640\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff - Appellee,\n\n v.\n\nJOSEPH DECORE SIMMS,\n\n Defendant - Appellant.\n\n------------------------------------------\n\nFOURTH CIRCUIT FEDERAL DEFENDER OFFICES,\n\n Amicus Supporting Appellant.\n\n\nAppeal from the United States District Court for the Eastern District of North Carolina, at\nGreenville. Terrence W. Boyle, Chief District Judge. (4:15-cr-00010-BO-1)\n\n\nArgued: September 26, 2018 Decided: January 24, 2019\n\n\nBefore GREGORY, Chief Judge, and WILKINSON, NIEMEYER, MOTZ, KING,\nDUNCAN, AGEE, KEENAN, WYNN, DIAZ, FLOYD, THACKER, HARRIS,\nRICHARDSON, and QUATTLEBAUM, Circuit Judges.\n\n\nReversed and remanded by published opinion. Judge Motz wrote the opinion, in which\nChief Judge Gregory and Judges King, Wynn, Diaz, Floyd, Thacker, and Harris joined.\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff-Appellee, v. Joseph Decore SIMMS, Defendant-Appellant. Fourth Circuit Federal Defender Offices, Amicus Supporting Appellant.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-24\\nOpinion type: majority\\nHas dissenting opinion: Yes\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 15-4640\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nJOSEPH DECORE SIMMS,\\n\\n Defendant - Appellant.\\n\\n------------------------------------------\\n\\nFOURTH CIRCUIT FEDERAL DEFENDER OFFICES,\\n\\n Amicus Supporting Appellant.\\n\\n\\nAppeal from the United States District Court for the Eastern District of North Carolina, at\\nGreenville. Terrence W. Boyle, Chief District Judge. (4:15-cr-00010-BO-1)\\n\\n\\nArgued: September 26, 2018 Decided: January 24, 2019\\n\\n\\nBefore GREGORY, Chief Judge, and WILKINSON, NIEMEYER, MOTZ, KING,\\nDUNCAN, AGEE, KEENAN, WYNN, DIAZ, FLOYD, THACKER, HARRIS,\\nRICHARDSON, and QUATTLEBAUM, Circuit Judges.\\n\\n\\nReversed and remanded by published opinion. Judge Motz wrote the opinion, in which\\nChief Judge Gregory and Judges King, Wynn, Diaz, Floyd, Thacker, and Harris joined.\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":99,"cells":{"id":{"kind":"number","value":4584957,"string":"4,584,957"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff - Appellee, v. Johnny Sylvester EDGELL, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Johnny Edgell"},"decision_date":{"kind":"string","value":"2019-01-25"},"docket_number":{"kind":"string","value":"17-4432"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Fourth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Gregory, Niemeyer, Harris\", \"parties\": \"\", \"opinions\": [{\"author\": \"PAMELA HARRIS, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"PUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-4432\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nJOHNNY SYLVESTER EDGELL,\\n\\n Defendant - Appellant.\\n\\n\\nAppeal from the United States District Court for Northern District of West Virginia, at\\nClarksburg. Irene M. Keeley, Senior District Judge. (1:16-cr-00045-IMK-MJA-1)\\n\\n\\nArgued: November 1, 2018 Decided: January 25, 2019\\n\\n\\nBefore GREGORY, Chief Judge, NIEMEYER and HARRIS, Circuit Judges.\\n\\n\\nSentence vacated and case remanded by published opinion. Judge Harris wrote the\\nopinion, in which Chief Judge Gregory and Judge Niemeyer joined.\\n\\n\\nARGUED: Linn Richard Walker, OFFICE OF THE FEDERAL PUBLIC DEFENDER,\\nClarksburg, West Virginia, for Appellant. Stephen Donald Warner, OFFICE OF THE\\nUNITED STATES ATTORNEY, Elkins, West Virginia, for Appellee. ON BRIEF:\\nKristen M. Leddy, Research and Writing Specialist, OFFICE OF THE FEDERAL\\nPUBLIC DEFENDER, Clarksburg, West Virginia, for Appellant. William J. Powell,\\nUnited States Attorney, OFFICE OF THE UNITED STATES ATTORNEY, Wheeling,\\nWest Virginia, for Appellee.\\n\\fPAMELA HARRIS, Circuit Judge:\\n\\n After negotiating a plea agreement with the government, Johnny Sylvester Edgell\\n\\npleaded guilty to one count of possessing a firearm as an unlawful drug user and one count\\n\\nof distributing methamphetamine. In exchange for that plea, the government agreed to a\\n\\nstipulation limiting Edgell’s total drug conduct to “less than five (5) grams of substances\\n\\ncontaining a detectable amount of methamphetamine,” J.A. 193, which corresponded to an\\n\\nadvisory sentencing range of 10 to 16 months’ imprisonment. But after the agreement was\\n\\nsigned, the government received lab results showing that the substances in question were\\n\\nactual methamphetamine, and once the government shared that information with the\\n\\nprobation office, Edgell’s sentencing range increased to 30 to 37 months. At sentencing,\\n\\nthe government advocated for a sentence consistent with that elevated range, and Edgell\\n\\nwas sentenced to 30 months in prison.\\n\\n Edgell contends that the government breached his plea agreement in two respects:\\n\\nfirst, by disclosing the post-plea lab report to the probation office and sentencing court; and\\n\\nsecond, by failing to honor the agreement at sentencing, and instead advocating for a\\n\\nsentence inconsistent with its original stipulation. We cannot agree that the government\\n\\nbreached its plea agreement by disclosing relevant and accurate information to the\\n\\nsentencing court. But we agree with Edgell that the government’s conduct at the sentencing\\n\\nhearing denied him the benefit of his bargain. Given the government’s breach, we vacate\\n\\nEdgell’s sentence and remand for resentencing before a different district judge.\\n\\n\\n\\n I.\\n\\n 2\\n\\f Following three controlled buys in July 2015, Johnny Sylvester Edgell was indicted\\n\\nby a federal grand jury on three counts of distributing methamphetamine, in violation of\\n\\n21 U.S.C. §§ 841(a)(1) and 841(b)(1)(C), and one count of unlawfully possessing a firearm,\\n\\nin violation of 18 U.S.C. §§ 922(g)(3) and 924(a)(2).\\n\\n Edgell and the government negotiated a plea agreement. For his part, Edgell agreed\\n\\nto plead guilty to the single firearm charge and to one count of distributing\\n\\nmethamphetamine. In exchange, the government agreed to a stipulation that Edgell’s drug\\n\\nconduct involved “less than five (5) grams of substances containing a detectable amount\\n\\nof methamphetamine” – that is, substances of a lower purity level than actual\\n\\nmethamphetamine. J.A. 193. Pursuant to that stipulation, Edgell’s advisory sentencing\\n\\nrange would be 10 to 16 months’ imprisonment. 1 The government additionally agreed to\\n\\n“recommend that any sentence of incarceration imposed . . . be at the lowest end of the\\n\\napplicable guideline range,” J.A. 193, and to dismiss the remaining counts of the\\n\\nindictment.\\n\\n The plea agreement also contained certain reservations. First, it specified that the\\n\\nsentencing court was not bound by the parties’ stipulations and was not required to accept\\n\\n\\n\\n 1\\n While the plea agreement did not specify the resulting sentencing range, the parties\\ndo not dispute that the agreement contemplated a range of 10 to 16 months’ imprisonment.\\nThe agreement’s drug conduct stipulation produces a base offense level of 12. See\\nU.S.S.G. § 2D1.1(c)(14). Considering the relevant adjustments – including a two-level\\nenhancement for his possession of a dangerous weapon and a two-level reduction for\\nacceptance of responsibility, see U.S.S.G. §§ 2D1.1(b)(1), 3E1.1 – and Edgell’s Category\\nI criminal history, Edgell’s advisory sentencing range under the agreement indeed would\\nhave been 10 to 16 months. See U.S.S.G. ch. 5, pt. A (sentencing table).\\n\\n\\n 3\\n\\fthem. The agreement also reserved the government’s “right to provide to the Court and\\n\\nthe United States Probation Office . . . relevant information including defendant’s\\n\\nbackground, criminal record, offense charged in the indictment and other pertinent data . .\\n\\n. as will enable the Court to exercise its sentencing discretion,” and “to respond to any\\n\\nquestions raised by the Court, to correct any inaccuracies or inadequacies in the anticipated\\n\\npre-sentence report, and to respond to any written or oral statements made by the Court, by\\n\\ndefendant or his counsel.” J.A. 194.\\n\\n At the time the government entered into its agreement with Edgell, it had requested,\\n\\nbut not yet received, a laboratory analysis of the substances distributed by Edgell. When\\n\\nthat laboratory report was returned to the government – only after the agreement was\\n\\nfinalized – it revealed that the substances in question were not merely “substances\\n\\ncontaining a detectable amount of methamphetamine,” as the parties had stipulated, J.A.\\n\\n193, but instead actual methamphetamine. The government disclosed that information to\\n\\nthe probation office, which incorporated it into its Presentence Report (PSR), attributing\\n\\n3.5344 grams of actual methamphetamine to Edgell. As a result, the PSR calculated\\n\\nEdgell’s guidelines sentencing range as 30 to 37 months’ imprisonment, rather than the 10\\n\\nto 16 months anticipated under the plea agreement. 2 In light of that discrepancy, the PSR\\n\\nsuggested that a downward variance might be appropriate.\\n\\n\\n\\n\\n 2\\n Edgell’s new drug conduct resulted in an offense level of 20. See U.S.S.G. §\\n2D1.1(c)(10). Edgell received a two-level enhancement for possessing a dangerous\\nweapon under U.S.S.G. § 2D1.1(b)(1) and a three-level reduction for acceptance of\\nresponsibility under U.S.S.G. § 3E1.1(b), for a total offense level of 19. Combined with\\n(Continued)\\n 4\\n\\f At sentencing, the district court acknowledged that the PSR’s factual findings and\\n\\nsentencing calculations were “certainly different from . . . the parties’ expectation from the\\n\\nplea agreement.” J.A. 91. Nevertheless, and without objection from either party, the court\\n\\nadopted the PSR’s advisory guidelines range of 30 to 37 months.\\n\\n Consistent with the PSR’s suggestion, Edgell requested a downward variance. The\\n\\ngovernment did not join Edgell’s request. Nor did it recommend a sentence consistent with\\n\\nthe agreed-upon stipulation as to drug conduct and the corresponding 10 to 16 months\\n\\nsentencing range. Instead, purporting to follow its commitments under the plea agreement,\\n\\nthe government advocated for a sentence at the “low end” of the guidelines range adopted\\n\\nby the court, or 30 months’ imprisonment. J.A. 108. The court followed the government’s\\n\\nrecommendation and sentenced Edgell to 30 months’ imprisonment, to be followed by a\\n\\nterm of three years of supervised release. Edgell timely appealed.\\n\\n\\n\\n II.\\n\\n Edgell contends the government breached its plea agreement by disclosing the post-\\n\\nagreement lab results to the probation office and the sentencing court, and by failing at\\n\\nsentencing to honor the agreement’s explicit drug conduct stipulation – that he was\\n\\nresponsible for distributing “less than five (5) grams of substances containing a detectable\\n\\namount of methamphetamine,” J.A. 193. Because Edgell did not challenge the\\n\\n\\n\\n\\nhis Category I criminal history, the resulting sentencing range was 30 to 37 months’\\nimprisonment. See U.S.S.G. ch. 5, pt. A (sentencing table).\\n\\n 5\\n\\fgovernment’s purported breach of the plea agreement before the district court, we review\\n\\nhis claim for plain error. United States v. Tate, 845 F.3d 571, 575 (4th Cir. 2017) (citing\\n\\nFed. R. Crim. P. 52(b)). Under that standard, Edgell must show that the government plainly\\n\\nbreached its plea agreement with him and that the breach both affected his substantial rights\\n\\nand called into question the fairness, integrity, or public reputation of judicial proceedings.\\n\\nSee United States v. Dawson, 587 F.3d 640, 645 (4th Cir. 2009). For the reasons given\\n\\nbelow, we find that Edgell has satisfied that demanding standard.\\n\\n A.\\n\\n We first consider whether the government breached the clear requirements of its\\n\\nplea agreement with Edgell. “Plea agreements are grounded in contract law,” and as with\\n\\nany contract, each party is entitled to receive the benefit of his bargain. Tate, 845 F.3d at\\n\\n575. While “we employ traditional principles of contract law as a guide” in enforcing plea\\n\\nagreements, “we nonetheless give plea agreements greater scrutiny than we would apply\\n\\nto a commercial contract because a defendant’s fundamental and constitutional rights are\\n\\nimplicated when he is induced to plead guilty by reason of a plea agreement.” United\\n\\nStates v. Warner, 820 F.3d 678, 683 (4th Cir. 2016) (internal quotation marks and brackets\\n\\nomitted). At a minimum, “when a plea rests in any significant degree on a promise or\\n\\nagreement of the prosecutor, so that it can be said to be part of the inducement or\\n\\nconsideration, such promise must be fulfilled.” Santobello v. New York, 404 U.S. 257, 262\\n\\n(1971).\\n\\n Here, Edgell maintains that his plea agreement rested on the government’s promise\\n\\nto limit his relevant drug conduct to “less than five (5) grams of substances containing a\\n\\n 6\\n\\fdetectable amount of methamphetamine,” J.A. 193, and the associated sentencing range,\\n\\nand that he was denied the benefit of his bargain when the government breached that\\n\\npromise. Specifically, Edgell challenges both the government’s disclosure of the post-\\n\\nagreement lab results to the probation office and sentencing court, and the government’s\\n\\nfailure at sentencing to defend or advocate in any way for the parties’ drug conduct\\n\\nstipulation. We address each of these challenges in turn.\\n\\n To the extent Edgell contends that the government breached its plea agreement by\\n\\ndisclosing lab results to the probation office and court, we must disagree. The government\\n\\nhas a “duty to furnish complete and accurate information at sentencing,” and we have\\n\\nexpressed doubt as to whether a plea agreement may abridge that duty. United States v.\\n\\nCrisp, 817 F.2d 256, 259 (4th Cir. 1987). Other courts of appeals, too, have emphasized\\n\\nthat even where a plea agreement binds the government to certain sentencing\\n\\nrecommendations, the government retains a duty “to ensure that the court has complete and\\n\\naccurate information, enabling the court to impose an appropriate sentence.” United States\\n\\nv. Maldonado, 215 F.3d 1046, 1052 (9th Cir. 2000); see also United States v. Casillas, 853\\n\\nF.3d 215, 218 (5th Cir. 2017) (government may not “stand mute in the face of factual\\n\\ninaccuracies or [] withhold relevant factual information from the court” (internal quotation\\n\\nmarks omitted)); United States v. Ubiles-Rosario, 867 F.3d 277, 283 (1st Cir. 2017) (“[A]\\n\\nplea agreement may not abridge the [government’s] solemn obligation to provide relevant\\n\\ninformation to the sentencing court.” (internal quotation marks omitted)).\\n\\n Indeed, consistent with this understanding, Edgell’s plea agreement does not purport\\n\\nto limit or override the government’s duty of candor to the court. Instead, it recognizes\\n\\n 7\\n\\fthat duty, and expressly reserves the government’s “right to provide to the Court and the\\n\\nUnited States Probation Office . . . relevant information including defendant’s background,\\n\\ncriminal record, offense charged in the indictment and other pertinent data . . . as will enable\\n\\nthe Court to exercise its sentencing discretion.” J.A. 194. The government’s disclosure of\\n\\nthe lab results, which went directly to the offense charged in the indictment and to Edgell’s\\n\\nbase offense calculation, was thus consistent with both the parties’ plea agreement and the\\n\\ngovernment’s broader duty to provide complete and accurate information to the sentencing\\n\\ncourt.\\n\\n But the government did more than that here. And we agree with Edgell that the\\n\\ngovernment crossed the line and breached its plea agreement when it failed at sentencing\\n\\nto honor its drug conduct stipulation. As one court of appeals to consider this precise\\n\\nquestion has explained, “Although the Government has a duty to provide the sentencing\\n\\ncourt with relevant factual information and to correct misstatements, it may not hide behind\\n\\nthis duty to advocate a position that contradicts its promises in a plea agreement.” United\\n\\nStates v. Munoz, 408 F.3d 222, 227 (5th Cir. 2005). Instead, the government must carefully\\n\\nbalance its duty of candor to the sentencing court with the sometimes competing – but\\n\\nequally solemn – duty to honor its commitments under a plea agreement. See United States\\n\\nv. Saxena, 229 F.3d 1, 5 (1st Cir. 2000). And as courts that have addressed the question\\n\\nagree, this balance is achieved where the government makes the necessary disclosures to\\n\\nthe sentencing court, but nevertheless “continue[s] to advocate for acceptance of the\\n\\nagreement.” Casillas, 853 F.3d at 218; see also United States v. Franco–Lopez, 312 F.3d\\n\\n984, 993 (9th Cir. 2002) (“We conclude that the government did not breach the plea\\n\\n 8\\n\\fagreement by providing information to the Probation Department regarding [the\\n\\ndefendant’s] criminal activity while recommending successfully to the district court that it\\n\\nnot rely on that information in sentencing.”); Saxena, 229 F.3d at 7 (finding no breach\\n\\nwhere the government disclosed information inconsistent with the plea agreement, but\\n\\nnevertheless “resolutely stood by the bottom-line recommendation that [it] had committed\\n\\nto make”).\\n\\n The government failed to strike the necessary balance here. At sentencing, the\\n\\ngovernment did not “continue to advocate for acceptance,” Casillas, 853 F.3d at 218, of its\\n\\nagreement with Edgell. It did not ask the court to impose a sentence consistent with the 10\\n\\nto 16 months range that corresponded to its drug conduct stipulation. It did not join in\\n\\nEdgell’s request for a downward variance. And it did not otherwise encourage the court to\\n\\nconsider in any way the factual stipulation to which it agreed in exchange for Edgell’s\\n\\nguilty plea. Instead, the government affirmatively undermined the plea agreement by\\n\\nrequesting a sentence inconsistent with its stipulation, effectively tripling its recommended\\n\\nsentence from the 10 months anticipated under the plea agreement to the 30 months at the\\n\\nlow end of the post-lab report range calculated by the PSR. 3\\n\\n\\n 3\\n We appreciate the awkward situation the government faced at sentencing;\\nbalancing the competing duties of candor to the court and adherence to a plea agreement\\ncan be a difficult task under circumstances like these. But this is not the first case in which\\na prosecutor was required to walk that line. In United States v. Saxena, 229 F.3d 1, 4 (1st\\nCir. 2000), for instance, the government had agreed in a plea agreement to recommend a\\nsentence of 24 months’ imprisonment, consistent with an anticipated sentencing range of\\n24 to 30 months. At sentencing, however, it disclosed to the court post-plea activities by\\nthe defendant that led the court to adopt a higher guidelines range of 33 to 41 months. Id.\\nat 4–5. But when it came time to make a sentencing recommendation, the prosecutor\\n(Continued)\\n 9\\n\\f At oral argument, the government suggested for the first time that its sentencing\\n\\nrecommendation did not breach the plea agreement because Edgell “assumed the risk” that\\n\\nit would discover the actual nature of the substances he distributed. But it was the\\n\\ngovernment, of course, that knew of an outstanding lab report and nevertheless decided to\\n\\ngo forward with the plea agreement without waiting for the results, thus assuming precisely\\n\\nthe risk that materialized: that the lab report ultimately would come back with information\\n\\ninconsistent with the agreement’s drug conduct stipulation. The government’s apparent\\n\\nmisjudgment about the importance of the lab report is not grounds for relieving the\\n\\ngovernment of its obligations under the plea agreement.\\n\\n Moreover, the government’s assumption-of-risk argument misconstrues the very\\n\\nnature of plea agreements. Plea agreements, as any contract, bind one party to do\\n\\nsomething the other party desires in exchange for some benefit. United States v. Bownes,\\n\\n405 F.3d 634, 636 (7th Cir. 2005). Here, the government agreed to the drug conduct\\n\\nstipulation, which came with a corresponding sentencing range of 10 to 16 months, and to\\n\\n\\ncontinued to advocate for the 24 months to which the parties had agreed, explaining to the\\ncourt:\\n\\n The government’s recommendation in this case is pursuant to our plea\\n agreement. And I’m well aware, your Honor, of the fact that my\\n recommendation is below what the Court has determined the guidelines\\n applicable to be. Nonetheless, bound by that agreement the government does\\n recommend a sentence of 24 months which, of course, was based on the\\n calculations [of] the parties.\\n\\nId. at 7. Because it “resolutely stood by” a sentencing recommendation consistent with its\\nplea agreement, the First Circuit concluded in Saxena, the government had not breached\\nthe agreement, notwithstanding its disclosure of post-plea information to the court. Id. at\\n7–8.\\n\\n 10\\n\\frecommend a sentence at the bottom of the applicable range. In return, Edgell relieved the\\n\\ngovernment of its burden to prove his guilt beyond a reasonable doubt and eliminated the\\n\\nneed for the government to expend its resources on a full criminal trial. Both parties bound\\n\\nthemselves to their respective commitments, and each “assume[d] the risk of future\\n\\nchanges in circumstances in light of which [their] bargain may prove to have been a bad\\n\\none.” Id. Just as we often enforce plea agreements against criminal defendants even in the\\n\\nface of subsequent, favorable changes in the law, see, e.g., United States v. Archie, 771\\n\\nF.3d 217, 222 (4th Cir. 2014), so, too, must we enforce plea agreements that may later\\n\\nprove less advantageous than the government had anticipated.\\n\\n The government’s failure at sentencing to stand by its drug conduct stipulation, and\\n\\nits recommendation of a sentence inconsistent with that stipulation, denied Edgell a central\\n\\nbenefit of his bargain. It follows that the government breached its plea agreement with\\n\\nEdgell. See Santobello, 404 U.S. at 262. And because the government’s duties pursuant\\n\\nto the plea agreement were sufficiently clear – that is, the drug conduct stipulation was\\n\\nunambiguous – that error was plain. Cf. Puckett v. United States, 556 U.S. 129, 143 (2009)\\n\\n(“Not all breaches [of plea agreements] will be clear or obvious. Plea agreements are not\\n\\nalways models of draftsmanship, so the scope of the Government’s commitments will on\\n\\noccasion be open to doubt.”). Edgell therefore satisfies the initial requirements of plain\\n\\nerror review.\\n\\n B.\\n\\n Having found that the government plainly breached its plea agreement at\\n\\nsentencing, we next consider whether that breach affected Edgell’s substantial rights. A\\n\\n 11\\n\\fbreach of a plea agreement affects a defendant’s substantial rights only if it prejudices the\\n\\ndefendant. Puckett, 556 U.S. at 135. And a defendant suffers no prejudice where (1) he\\n\\nobtained the benefits of the plea agreement despite the government’s breach – that is, where\\n\\nhe nevertheless received the sentence the prosecutor promised to request – or (2) “he likely\\n\\nwould not have obtained those benefits in any event.” Id. at 141–42. Where the record\\n\\ndoes not reflect either of the above circumstances, “we are free to conclude that the\\n\\ndefendant has shown a reasonable probability, based on the appellate record as a whole,\\n\\nthat but for the error he would have received a more favorable sentence.” Dawson, 587\\n\\nF.3d at 645 (internal quotation marks omitted).\\n\\n Edgell has made the requisite showing of potential prejudice. First, there is no\\n\\nquestion that Edgell did not receive the benefit of his bargain: He was sentenced to 30\\n\\nmonths’ imprisonment, a sentence that far exceeded the sentencing range that would have\\n\\nresulted from the drug conduct stipulation in the parties’ plea agreement. Second, we\\n\\ncannot conclude from this record that, had the government honored the plea agreement,\\n\\nthere would have been no benefit to Edgell. It is true that, under the plea agreement, the\\n\\nsentencing court was not bound by the parties’ stipulation, 4 and the court did voice a\\n\\n\\n\\n\\n 4\\n That the court was not bound by the drug conduct stipulation, of course, does not\\nexcuse the government from its commitments under the agreement. The parties “did intend\\nfor the stipulation to bind the government, and it is the government’s breach of that\\nagreement that is the focus of our inquiry.” United States v. Boatner, 966 F.2d 1575, 1579\\n(11th Cir. 1992); see also United States v. Normil, 129 F.3d 1261, at *4 (4th Cir. 1997)\\n(unpublished table decision) (“To the extent that a stipulation entered by the government\\nis essential to the defendant’s bargain, it is binding. This is true even if the court is not\\nbound by the stipulation.” (citation omitted)).\\n\\n 12\\n\\fconcern that the plea agreement – and the sentencing range it contemplated – did not\\n\\naccount for the severity of Edgell’s offenses. But at the same time, the district court made\\n\\nclear that it was considering a sentence well below the 30 to 37 months range it had\\n\\nadopted. And in the end, it adopted precisely the sentence the government recommended:\\n\\n30 months. Had the government instead urged the court to impose a sentence consistent\\n\\nwith its plea agreement, or joined in Edgell’s request for a downward variance, then the\\n\\ncourt may well have taken the government’s position into account and arrived at a sentence\\n\\nwithin, or at least closer to, the sentencing range anticipated by the plea agreement. Edgell\\n\\nthus has “demonstrated a reasonable probability that the outcome of his sentencing would\\n\\nhave been different had the government made the appropriate recommendation.” Dawson,\\n\\n587 F.3d at 646; cf. United States v. Navarro, 817 F.3d 494, 501 (7th Cir. 2016) (“[C]ases\\n\\nwhere we have found that the defendant failed to prove the prejudice prong are ones in\\n\\nwhich the record compellingly reflects the sentencing court was not influenced by the\\n\\ngovernment’s recommendation.”). Accordingly, we find that the government’s breach of\\n\\nthe plea agreement affected Edgell’s substantial rights.\\n\\n C.\\n\\n We similarly find that the government’s breach of the plea agreement seriously\\n\\naffected the “fairness, integrity, or public reputation of judicial proceedings,” Puckett, 556\\n\\nU.S. at 135 (internal quotation marks omitted). The Supreme Court has cautioned that this\\n\\nprong of plain error “is meant to be applied on a case-specific and fact-intensive basis,”\\n\\nand is not automatically satisfied whenever the government breaches a plea agreement. Id.\\n\\nat 142–43. “Nevertheless, . . . courts have recognized that the Government’s breach of a\\n\\n 13\\n\\fplea agreement constitutes a particularly egregious error that, in the absence of strong\\n\\ncountervailing factors, seriously affects the fairness, integrity, or public reputation of\\n\\njudicial proceedings.” United States v. Kirkland, 851 F.3d 499, 505 (5th Cir. 2017)\\n\\n(emphasis added) (collecting cases). This is so because “[t]he breach of a promise made\\n\\nto induce a defendant to enter a guilty plea – and thereby waive important constitutional\\n\\nrights – harms not only the defendant, but . . . involves the honor of the government, [and]\\n\\npublic confidence in the fair administration of justice.” United States v. Lewis, 633 F.3d\\n\\n262, 269 (4th Cir. 2011) (internal quotation marks omitted); see also United States v.\\n\\nPeglera, 33 F.3d 412, 414 (4th Cir. 1994) (“Because a government that lives up to its\\n\\ncommitments is the essence of liberty under law, the harm generated by allowing the\\n\\ngovernment to forego its plea bargain obligations is one which cannot be tolerated.”).\\n\\n Here, the government does not contest that its purported breach affects the integrity,\\n\\nfairness, or public reputation of plea agreements and judicial proceedings generally.\\n\\nAccordingly, because Edgell has shown the government failed to honor its clear\\n\\ncommitments under his plea agreement and the government fails to provide even a single\\n\\ncountervailing factor, we find Edgell has satisfied the final requirement of plain error\\n\\nreview.\\n\\n\\n\\n III.\\n\\n Having found that the government breached the plea agreement and that the breach\\n\\nconstitutes plain and reversible error, the only remaining issue is the appropriate remedy.\\n\\n“In most cases in which the Government has breached its agreement with the defendant,\\n\\n 14\\n\\fwe prefer to leave the fashioning of appropriate relief to the sound discretion of the district\\n\\ncourt.” United States v. Wood, 378 F.3d 342, 350 n.6 (4th Cir. 2004) (internal quotation\\n\\nmarks omitted). Where, however, the defendant does not seek to withdraw his guilty plea\\n\\nand instead requests only “the lesser relief of specific performance of the agreement[,] . . .\\n\\nthen the court should honor that election,” and “remand with the direction that the\\n\\ndefendant ‘be resentenced by a different judge.’” Warner, 820 F.3d at 685 (quoting\\n\\nSantobello, 404 U.S. at 263). 5\\n\\n Because Edgell seeks only specific performance, we will honor his election.\\n\\n\\n\\n IV.\\n\\n For the foregoing reasons, we find the government breached its plea agreement with\\n\\nEdgell and that this breach constitutes reversible plain error. We do not doubt that the\\n\\ngovernment’s breach was the result of inadvertence rather than bad faith, but Edgell\\n\\nnonetheless was denied the benefit of his bargain. Accordingly, we vacate Edgell’s\\n\\nsentence and remand the case for resentencing before a different district judge.\\n\\n\\n\\n SENTENCE VACATED AND CASE REMANDED\\n\\n\\n\\n 5\\n When specific performance is elected by a defendant, resentencing always takes\\nplace before a different judge. See Peglera, 33 F.3d at 415 (“We remand the case to a\\ndifferent district judge for resentencing as we are required to do.”) As the Supreme Court\\nhas emphasized, that standard remedy “is in no sense to question the fairness of the\\nsentencing judge,” Santobello, 404 U.S. at 263, and our decision today should not be\\nunderstood as a “reflection on [Edgell’s] trial judge, who handled the case admirably under\\nthe circumstances,” Peglera, 33 F.3d at 415.\\n\\n 15\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4362210/\", \"author_raw\": \"PAMELA HARRIS, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"GREGORY"},"judge2":{"kind":"string","value":"NIEMEYER"},"judge3":{"kind":"string","value":"HARRIS"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4584957/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Johnny Sylvester EDGELL, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Fourth Circuit\nDate decided: 2019-01-25\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-4432\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff - Appellee,\n\n v.\n\nJOHNNY SYLVESTER EDGELL,\n\n Defendant - Appellant.\n\n\nAppeal from the United States District Court for Northern District of West Virginia, at\nClarksburg. Irene M. Keeley, Senior District Judge. (1:16-cr-00045-IMK-MJA-1)\n\n\nArgued: November 1, 2018 Decided: January 25, 2019\n\n\nBefore GREGORY, Chief Judge, NIEMEYER and HARRIS, Circuit Judges.\n\n\nSentence vacated and case remanded by published opinion. Judge Harris wrote the\nopinion, in which Chief Judge Gregory and Judge Niemeyer joined.\n\n\nARGUED: Linn Richard Walker, OFFICE OF THE FEDERAL PUBLIC DEFENDER,\nClarksburg, West Virginia, for Appellant. Stephen Donald Warner, OFFICE OF THE\nUNITED STATES ATTORNEY, Elkins, West Virginia, for Appellee. ON BRIEF:\nKristen M. Leddy, Research and Writing Specialist, OFFICE OF THE FEDERAL\nPUBLIC DEFENDER, Clarksburg, West Virginia, for Appellant. William J. Powell,\nUnited States Attorney, OFFICE OF THE UNITED STATES ATTORNEY, Wheeling,\nWest Virginia, for Appellee.\n\fPAMELA HARRIS, Circuit Judge:\n\n After negotiating a plea agreement with the government, Johnny Sylvester Edgell\n\npleaded guilty to one count of possessing a firearm as an unlawful drug user and one count\n\nof distributing methamphetamine. In exchange for that plea, the government agreed to a\n\nstipulation limiting Edgell’s total drug conduct to “less than five (5) grams of substances\n\ncontaining a detectable amount of methamphetamine,” J.A. 193, which corresponded to an\n\nadvisory sentencing range of 10 to 16 months’ imprisonment. But after the agreement was\n\nsigned, the government received lab results showing that the substances in question were\n\nactual methamphetamine, and once the government shared that information with the\n\nprobation office, Edgell’s sentencing range increased to 30 to 37 months. At sentencing,\n\nthe government advocated for a sentence consistent with that elevated range, and Edgell\n\nwas sentenced to 30 months in prison.\n\n Edgell contends that the government breached his plea agreement in two respects:\n\nfirst, by disclosing the post-plea lab report to the probation office and sentencing court; and\n\nsecond, by failing to honor the agreement at sentencing, and instead advocating for a\n\nsentence inconsistent with its original stipulation. We cannot agree that the government\n\nbreached its plea agreement by disclosing relevant and accurate information to the\n\nsentencing court. But we agree with Edgell that the government’s conduct at the sentencing\n\nhearing denied him the benefit of his bargain. Given the government’s breach, we vacate\n\nEdgell’s sentence and remand for resentencing before a different district judge.\n\n\n\n I.\n\n 2\n\f Following three controlled buys in July 2015, Johnny Sylvester Edgell was indicted\n\nby a federal grand jury on three counts of distributing methamphetamine, in violation of\n\n21 U.S.C. §§ 841(a)(1) and 841(b)(1)(C), and one count of unlawfully possessing a firearm,\n\nin violation of 18 U.S.C. §§ 922(g)(3) and 924(a)(2).\n\n Edgell and the government negotiated a plea agreement. For his part, Edgell agreed\n\nto plead guilty to the single firearm charge and to one count of distributing\n\nmethamphetamine. In exchange, the government agreed to a stipulation that Edgell’s drug\n\nconduct involved “less than five (5) grams of substances containing a detectable amount\n\nof methamphetamine” – that is, substances of a lower purity level than actual\n\nmethamphetamine. J.A. 193. Pursuant to that stipulation, Edgell’s advisory sentencing\n\nrange would be 10 to 16 months’ imprisonment. 1 The government additionally agreed to\n\n“recommend that any sentence of incarceration imposed . . . be at the lowest end of the\n\napplicable guideline range,” J.A. 193, and to dismiss the remaining counts of the\n\nindictment.\n\n The plea agreement also contained certain reservations. First, it specified that the\n\nsentencing court was not bound by the parties’ stipulations and was not required to accept\n\n\n\n 1\n While the plea agreement did not specify the resulting sentencing range, the parties\ndo not dispute that the agreement contemplated a range of 10 to 16 months’ imprisonment.\nThe agreement’s drug conduct stipulation produces a base offense level of 12. See\nU.S.S.G. § 2D1.1(c)(14). Considering the relevant adjustments – including a two-level\nenhancement for his possession of a dangerous weapon and a two-level reduction for\nacceptance of responsibility, see U.S.S.G. §§ 2D1.1(b)(1), 3E1.1 – and Edgell’s Category\nI criminal history, Edgell’s advisory sentencing range under the agreement indeed would\nhave been 10 to 16 months. See U.S.S.G. ch. 5, pt. A (sentencing table).\n\n\n 3\n\fthem. The agreement also reserved the government’s “right to provide to the Court and\n\nthe United States Probation Office . . . relevant information including defendant’s\n\nbackground, criminal record, offense charged in the indictment and other pertinent data . .\n\n. as will enable the Court to exercise its sentencing discretion,” and “to respond to any\n\nquestions raised by the Court, to correct any inaccuracies or inadequacies in the anticipated\n\npre-sentence report, and to respond to any written or oral statements made by the Court, by\n\ndefendant or his counsel.” J.A. 194.\n\n At the time the government entered into its agreement with Edgell, it had requested,\n\nbut not yet received, a laboratory analysis of the substances distributed by Edgell. When\n\nthat laboratory report was returned to the government – only after the agreement was\n\nfinalized – it revealed that the substances in question were not merely “substances\n\ncontaining a detectable amount of methamphetamine,” as the parties had stipulated, J.A.\n\n193, but instead actual methamphetamine. The government disclosed that information to\n\nthe probation office, which incorporated it into its Presentence Report (PSR), attributing\n\n3.5344 grams of actual methamphetamine to Edgell. As a result, the PSR calculated\n\nEdgell’s guidelines sentencing range as 30 to 37 months’ imprisonment, rather than the 10\n\nto 16 months anticipated under the plea agreement. 2 In light of that discrepancy, the PSR\n\nsuggested that a downward variance might be appropriate.\n\n\n\n\n 2\n Edgell’s new drug conduct resulted in an offense level of 20. See U.S.S.G. §\n2D1.1(c)(10). Edgell received a two-level enhancement for possessing a dangerous\nweapon under U.S.S.G. § 2D1.1(b)(1) and a three-level reduction for acceptance of\nresponsibility under U.S.S.G. § 3E1.1(b), for a total offense level of 19. Combined with\n(Continued)\n 4\n\f At sentencing, the district court acknowledged that the PSR’s factual findings and\n\nsentencing calculations were “certainly different from . . . the parties’ expectation from the\n\nplea agreement.” J.A. 91. Nevertheless, and without objection from either party, the court\n\nadopted the PSR’s advisory guidelines range of 30 to 37 months.\n\n Consistent with the PSR’s suggestion, Edgell requested a downward variance. The\n\ngovernment did not join Edgell’s request. Nor did it recommend a sentence consistent with\n\nthe agreed-upon stipulation as to drug conduct and the corresponding 10 to 16 months\n\nsentencing range. Instead, purporting to follow its commitments under the plea agreement,\n\nthe government advocated for a sentence at the “low end” of the guidelines range adopted\n\nby the court, or 30 months’ imprisonment. J.A. 108. The court followed the government’s\n\nrecommendation and sentenced Edgell to 30 months’ imprisonment, to be followed by a\n\nterm of three years of supervised release. Edgell timely appealed.\n\n\n\n II.\n\n Edgell contends the government breached its plea agreement by disclosing the post-\n\nagreement lab results to the probation office and the sentencing court, and by failing at\n\nsentencing to honor the agreement’s explicit drug conduct stipulation – that he was\n\nresponsible for distributing “less than five (5) grams of substances containing a detectable\n\namount of methamphetamine,” J.A. 193. Because Edgell did not challenge the\n\n\n\n\nhis Category I criminal history, the resulting sentencing range was 30 to 37 months’\nimprisonment. See U.S.S.G. ch. 5, pt. A (sentencing table).\n\n 5\n\fgovernment’s purported breach of the plea agreement before the district court, we review\n\nhis claim for plain error. United States v. Tate, 845 F.3d 571, 575 (4th Cir. 2017) (citing\n\nFed. R. Crim. P. 52(b)). Under that standard, Edgell must show that the government plainly\n\nbreached its plea agreement with him and that the breach both affected his substantial rights\n\nand called into question the fairness, integrity, or public reputation of judicial proceedings.\n\nSee United States v. Dawson, 587 F.3d 640, 645 (4th Cir. 2009). For the reasons given\n\nbelow, we find that Edgell has satisfied that demanding standard.\n\n A.\n\n We first consider whether the government breached the clear requirements of its\n\nplea agreement with Edgell. “Plea agreements are grounded in contract law,” and as with\n\nany contract, each party is entitled to receive the benefit of his bargain. Tate, 845 F.3d at\n\n575. While “we employ traditional principles of contract law as a guide” in enforcing plea\n\nagreements, “we nonetheless give plea agreements greater scrutiny than we would apply\n\nto a commercial contract because a defendant’s fundamental and constitutional rights are\n\nimplicated when he is induced to plead guilty by reason of a plea agreement.” United\n\nStates v. Warner, 820 F.3d 678, 683 (4th Cir. 2016) (internal quotation marks and brackets\n\nomitted). At a minimum, “when a plea rests in any significant degree on a promise or\n\nagreement of the prosecutor, so that it can be said to be part of the inducement or\n\nconsideration, such promise must be fulfilled.” Santobello v. New York, 404 U.S. 257, 262\n\n(1971).\n\n Here, Edgell maintains that his plea agreement rested on the government’s promise\n\nto limit his relevant drug conduct to “less than five (5) grams of substances containing a\n\n 6\n\fdetectable amount of methamphetamine,” J.A. 193, and the associated sentencing range,\n\nand that he was denied the benefit of his bargain when the government breached that\n\npromise. Specifically, Edgell challenges both the government’s disclosure of the post-\n\nagreement lab results to the probation office and sentencing court, and the government’s\n\nfailure at sentencing to defend or advocate in any way for the parties’ drug conduct\n\nstipulation. We address each of these challenges in turn.\n\n To the extent Edgell contends that the government breached its plea agreement by\n\ndisclosing lab results to the probation office and court, we must disagree. The government\n\nhas a “duty to furnish complete and accurate information at sentencing,” and we have\n\nexpressed doubt as to whether a plea agreement may abridge that duty. United States v.\n\nCrisp, 817 F.2d 256, 259 (4th Cir. 1987). Other courts of appeals, too, have emphasized\n\nthat even where a plea agreement binds the government to certain sentencing\n\nrecommendations, the government retains a duty “to ensure that the court has complete and\n\naccurate information, enabling the court to impose an appropriate sentence.” United States\n\nv. Maldonado, 215 F.3d 1046, 1052 (9th Cir. 2000); see also United States v. Casillas, 853\n\nF.3d 215, 218 (5th Cir. 2017) (government may not “stand mute in the face of factual\n\ninaccuracies or [] withhold relevant factual information from the court” (internal quotation\n\nmarks omitted)); United States v. Ubiles-Rosario, 867 F.3d 277, 283 (1st Cir. 2017) (“[A]\n\nplea agreement may not abridge the [government’s] solemn obligation to provide relevant\n\ninformation to the sentencing court.” (internal quotation marks omitted)).\n\n Indeed, consistent with this understanding, Edgell’s plea agreement does not purport\n\nto limit or override the government’s duty of candor to the court. Instead, it recognizes\n\n 7\n\fthat duty, and expressly reserves the government’s “right to provide to the Court and the\n\nUnited States Probation Office . . . relevant information including defendant’s background,\n\ncriminal record, offense charged in the indictment and other pertinent data . . . as will enable\n\nthe Court to exercise its sentencing discretion.” J.A. 194. The government’s disclosure of\n\nthe lab results, which went directly to the offense charged in the indictment and to Edgell’s\n\nbase offense calculation, was thus consistent with both the parties’ plea agreement and the\n\ngovernment’s broader duty to provide complete and accurate information to the sentencing\n\ncourt.\n\n But the government did more than that here. And we agree with Edgell that the\n\ngovernment crossed the line and breached its plea agreement when it failed at sentencing\n\nto honor its drug conduct stipulation. As one court of appeals to consider this precise\n\nquestion has explained, “Although the Government has a duty to provide the sentencing\n\ncourt with relevant factual information and to correct misstatements, it may not hide behind\n\nthis duty to advocate a position that contradicts its promises in a plea agreement.” United\n\nStates v. Munoz, 408 F.3d 222, 227 (5th Cir. 2005). Instead, the government must carefully\n\nbalance its duty of candor to the sentencing court with the sometimes competing – but\n\nequally solemn – duty to honor its commitments under a plea agreement. See United States\n\nv. Saxena, 229 F.3d 1, 5 (1st Cir. 2000). And as courts that have addressed the question\n\nagree, this balance is achieved where the government makes the necessary disclosures to\n\nthe sentencing court, but nevertheless “continue[s] to advocate for acceptance of the\n\nagreement.” Casillas, 853 F.3d at 218; see also United States v. Franco–Lopez, 312 F.3d\n\n984, 993 (9th Cir. 2002) (“We conclude that the government did not breach the plea\n\n 8\n\fagreement by providing information to the Probation Department regarding [the\n\ndefendant’s] criminal activity while recommending successfully to the district court that it\n\nnot rely on that information in sentencing.”); Saxena, 229 F.3d at 7 (finding no breach\n\nwhere the government disclosed information inconsistent with the plea agreement, but\n\nnevertheless “resolutely stood by the bottom-line recommendation that [it] had committed\n\nto make”).\n\n The government failed to strike the necessary balance here. At sentencing, the\n\ngovernment did not “continue to advocate for acceptance,” Casillas, 853 F.3d at 218, of its\n\nagreement with Edgell. It did not ask the court to impose a sentence consistent with the 10\n\nto 16 months range that corresponded to its drug conduct stipulation. It did not join in\n\nEdgell’s request for a downward variance. And it did not otherwise encourage the court to\n\nconsider in any way the factual stipulation to which it agreed in exchange for Edgell’s\n\nguilty plea. Instead, the government affirmatively undermined the plea agreement by\n\nrequesting a sentence inconsistent with its stipulation, effectively tripling its recommended\n\nsentence from the 10 months anticipated under the plea agreement to the 30 months at the\n\nlow end of the post-lab report range calculated by the PSR. 3\n\n\n 3\n We appreciate the awkward situation the government faced at sentencing;\nbalancing the competing duties of candor to the court and adherence to a plea agreement\ncan be a difficult task under circumstances like these. But this is not the first case in which\na prosecutor was required to walk that line. In United States v. Saxena, 229 F.3d 1, 4 (1st\nCir. 2000), for instance, the government had agreed in a plea agreement to recommend a\nsentence of 24 months’ imprisonment, consistent with an anticipated sentencing range of\n24 to 30 months. At sentencing, however, it disclosed to the court post-plea activities by\nthe defendant that led the court to adopt a higher guidelines range of 33 to 41 months. Id.\nat 4–5. But when it came time to make a sentencing recommendation, the prosecutor\n(Continued)\n 9\n\f At oral argument, the government suggested for the first time that its sentencing\n\nrecommendation did not breach the plea agreement because Edgell “assumed the risk” that\n\nit would discover the actual nature of the substances he distributed. But it was the\n\ngovernment, of course, that knew of an outstanding lab report and nevertheless decided to\n\ngo forward with the plea agreement without waiting for the results, thus assuming precisely\n\nthe risk that materialized: that the lab report ultimately would come back with information\n\ninconsistent with the agreement’s drug conduct stipulation. The government’s apparent\n\nmisjudgment about the importance of the lab report is not grounds for relieving the\n\ngovernment of its obligations under the plea agreement.\n\n Moreover, the government’s assumption-of-risk argument misconstrues the very\n\nnature of plea agreements. Plea agreements, as any contract, bind one party to do\n\nsomething the other party desires in exchange for some benefit. United States v. Bownes,\n\n405 F.3d 634, 636 (7th Cir. 2005). Here, the government agreed to the drug conduct\n\nstipulation, which came with a corresponding sentencing range of 10 to 16 months, and to\n\n\ncontinued to advocate for the 24 months to which the parties had agreed, explaining to the\ncourt:\n\n The government’s recommendation in this case is pursuant to our plea\n agreement. And I’m well aware, your Honor, of the fact that my\n recommendation is below what the Court has determined the guidelines\n applicable to be. Nonetheless, bound by that agreement the government does\n recommend a sentence of 24 months which, of course, was based on the\n calculations [of] the parties.\n\nId. at 7. Because it “resolutely stood by” a sentencing recommendation consistent with its\nplea agreement, the First Circuit concluded in Saxena, the government had not breached\nthe agreement, notwithstanding its disclosure of post-plea information to the court. Id. at\n7–8.\n\n 10\n\frecommend a sentence at the bottom of the applicable range. In return, Edgell relieved the\n\ngovernment of its burden to prove his guilt beyond a reasonable doubt and eliminated the\n\nneed for the government to expend its resources on a full criminal trial. Both parties bound\n\nthemselves to their respective commitments, and each “assume[d] the risk of future\n\nchanges in circumstances in light of which [their] bargain may prove to have been a bad\n\none.” Id. Just as we often enforce plea agreements against criminal defendants even in the\n\nface of subsequent, favorable changes in the law, see, e.g., United States v. Archie, 771\n\nF.3d 217, 222 (4th Cir. 2014), so, too, must we enforce plea agreements that may later\n\nprove less advantageous than the government had anticipated.\n\n The government’s failure at sentencing to stand by its drug conduct stipulation, and\n\nits recommendation of a sentence inconsistent with that stipulation, denied Edgell a central\n\nbenefit of his bargain. It follows that the government breached its plea agreement with\n\nEdgell. See Santobello, 404 U.S. at 262. And because the government’s duties pursuant\n\nto the plea agreement were sufficiently clear – that is, the drug conduct stipulation was\n\nunambiguous – that error was plain. Cf. Puckett v. United States, 556 U.S. 129, 143 (2009)\n\n(“Not all breaches [of plea agreements] will be clear or obvious. Plea agreements are not\n\nalways models of draftsmanship, so the scope of the Government’s commitments will on\n\noccasion be open to doubt.”). Edgell therefore satisfies the initial requirements of plain\n\nerror review.\n\n B.\n\n Having found that the government plainly breached its plea agreement at\n\nsentencing, we next consider whether that breach affected Edgell’s substantial rights. A\n\n 11\n\fbreach of a plea agreement affects a defendant’s substantial rights only if it prejudices the\n\ndefendant. Puckett, 556 U.S. at 135. And a defendant suffers no prejudice where (1) he\n\nobtained the benefits of the plea agreement despite the government’s breach – that is, where\n\nhe nevertheless received the sentence the prosecutor promised to request – or (2) “he likely\n\nwould not have obtained those benefits in any event.” Id. at 141–42. Where the record\n\ndoes not reflect either of the above circumstances, “we are free to conclude that the\n\ndefendant has shown a reasonable probability, based on the appellate record as a whole,\n\nthat but for the error he would have received a more favorable sentence.” Dawson, 587\n\nF.3d at 645 (internal quotation marks omitted).\n\n Edgell has made the requisite showing of potential prejudice. First, there is no\n\nquestion that Edgell did not receive the benefit of his bargain: He was sentenced to 30\n\nmonths’ imprisonment, a sentence that far exceeded the sentencing range that would have\n\nresulted from the drug conduct stipulation in the parties’ plea agreement. Second, we\n\ncannot conclude from this record that, had the government honored the plea agreement,\n\nthere would have been no benefit to Edgell. It is true that, under the plea agreement, the\n\nsentencing court was not bound by the parties’ stipulation, 4 and the court did voice a\n\n\n\n\n 4\n That the court was not bound by the drug conduct stipulation, of course, does not\nexcuse the government from its commitments under the agreement. The parties “did intend\nfor the stipulation to bind the government, and it is the government’s breach of that\nagreement that is the focus of our inquiry.” United States v. Boatner, 966 F.2d 1575, 1579\n(11th Cir. 1992); see also United States v. Normil, 129 F.3d 1261, at *4 (4th Cir. 1997)\n(unpublished table decision) (“To the extent that a stipulation entered by the government\nis essential to the defendant’s bargain, it is binding. This is true even if the court is not\nbound by the stipulation.” (citation omitted)).\n\n 12\n\fconcern that the plea agreement – and the sentencing range it contemplated – did not\n\naccount for the severity of Edgell’s offenses. But at the same time, the district court made\n\nclear that it was considering a sentence well below the 30 to 37 months range it had\n\nadopted. And in the end, it adopted precisely the sentence the government recommended:\n\n30 months. Had the government instead urged the court to impose a sentence consistent\n\nwith its plea agreement, or joined in Edgell’s request for a downward variance, then the\n\ncourt may well have taken the government’s position into account and arrived at a sentence\n\nwithin, or at least closer to, the sentencing range anticipated by the plea agreement. Edgell\n\nthus has “demonstrated a reasonable probability that the outcome of his sentencing would\n\nhave been different had the government made the appropriate recommendation.” Dawson,\n\n587 F.3d at 646; cf. United States v. Navarro, 817 F.3d 494, 501 (7th Cir. 2016) (“[C]ases\n\nwhere we have found that the defendant failed to prove the prejudice prong are ones in\n\nwhich the record compellingly reflects the sentencing court was not influenced by the\n\ngovernment’s recommendation.”). Accordingly, we find that the government’s breach of\n\nthe plea agreement affected Edgell’s substantial rights.\n\n C.\n\n We similarly find that the government’s breach of the plea agreement seriously\n\naffected the “fairness, integrity, or public reputation of judicial proceedings,” Puckett, 556\n\nU.S. at 135 (internal quotation marks omitted). The Supreme Court has cautioned that this\n\nprong of plain error “is meant to be applied on a case-specific and fact-intensive basis,”\n\nand is not automatically satisfied whenever the government breaches a plea agreement. Id.\n\nat 142–43. “Nevertheless, . . . courts have recognized that the Government’s breach of a\n\n 13\n\fplea agreement constitutes a particularly egregious error that, in the absence of strong\n\ncountervailing factors, seriously affects the fairness, integrity, or public reputation of\n\njudicial proceedings.” United States v. Kirkland, 851 F.3d 499, 505 (5th Cir. 2017)\n\n(emphasis added) (collecting cases). This is so because “[t]he breach of a promise made\n\nto induce a defendant to enter a guilty plea – and thereby waive important constitutional\n\nrights – harms not only the defendant, but . . . involves the honor of the government, [and]\n\npublic confidence in the fair administration of justice.” United States v. Lewis, 633 F.3d\n\n262, 269 (4th Cir. 2011) (internal quotation marks omitted); see also United States v.\n\nPeglera, 33 F.3d 412, 414 (4th Cir. 1994) (“Because a government that lives up to its\n\ncommitments is the essence of liberty under law, the harm generated by allowing the\n\ngovernment to forego its plea bargain obligations is one which cannot be tolerated.”).\n\n Here, the government does not contest that its purported breach affects the integrity,\n\nfairness, or public reputation of plea agreements and judicial proceedings generally.\n\nAccordingly, because Edgell has shown the government failed to honor its clear\n\ncommitments under his plea agreement and the government fails to provide even a single\n\ncountervailing factor, we find Edgell has satisfied the final requirement of plain error\n\nreview.\n\n\n\n III.\n\n Having found that the government breached the plea agreement and that the breach\n\nconstitutes plain and reversible error, the only remaining issue is the appropriate remedy.\n\n“In most cases in which the Government has breached its agreement with the defendant,\n\n 14\n\fwe prefer to leave the fashioning of appropriate relief to the sound discretion of the district\n\ncourt.” United States v. Wood, 378 F.3d 342, 350 n.6 (4th Cir. 2004) (internal quotation\n\nmarks omitted). Where, however, the defendant does not seek to withdraw his guilty plea\n\nand instead requests only “the lesser relief of specific performance of the agreement[,] . . .\n\nthen the court should honor that election,” and “remand with the direction that the\n\ndefendant ‘be resentenced by a different judge.’” Warner, 820 F.3d at 685 (quoting\n\nSantobello, 404 U.S. at 263). 5\n\n Because Edgell seeks only specific performance, we will honor his election.\n\n\n\n IV.\n\n For the foregoing reasons, we find the government breached its plea agreement with\n\nEdgell and that this breach constitutes reversible plain error. We do not doubt that the\n\ngovernment’s breach was the result of inadvertence rather than bad faith, but Edgell\n\nnonetheless was denied the benefit of his bargain. Accordingly, we vacate Edgell’s\n\nsentence and remand the case for resentencing before a different district judge.\n\n\n\n SENTENCE VACATED AND CASE REMANDED\n\n\n\n 5\n When specific performance is elected by a defendant, resentencing always takes\nplace before a different judge. See Peglera, 33 F.3d at 415 (“We remand the case to a\ndifferent district judge for resentencing as we are required to do.”) As the Supreme Court\nhas emphasized, that standard remedy “is in no sense to question the fairness of the\nsentencing judge,” Santobello, 404 U.S. at 263, and our decision today should not be\nunderstood as a “reflection on [Edgell’s] trial judge, who handled the case admirably under\nthe circumstances,” Peglera, 33 F.3d at 415.\n\n 15\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Johnny Sylvester EDGELL, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Fourth Circuit\\nDate decided: 2019-01-25\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISHED\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE FOURTH CIRCUIT\\n\\n\\n No. 17-4432\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v.\\n\\nJOHNNY SYLVESTER EDGELL,\\n\\n Defendant - Appellant.\\n\\n\\nAppeal from the United States District Court for Northern District of West Virginia, at\\nClarksburg. Irene M. Keeley, Senior District Judge. (1:16-cr-00045-IMK-MJA-1)\\n\\n\\nArgued: November 1, 2018 Decided: January 25, 2019\\n\\n\\nBefore GREGORY, Chief Judge, NIEMEYER and HARRIS, Circuit Judges.\\n\\n\\nSentence vacated and case remanded by published opinion. Judge Harris wrote the\\nopinion, in which Chief Judge Gregory and Judge Niemeyer joined.\\n\\n\\nARGUED: Linn Richard Walker, OFFICE OF THE FEDERAL PUBLIC DEFENDER,\\nClarksburg, West Virginia, for Appellant. Stephen Donald Warner, OFFICE OF THE\\nUNITED STATES ATTORNEY, Elkins, West Virginia, for Appellee. ON BRIEF:\\nKristen M. Leddy, Research and Writing Specialist, OFFICE OF THE FEDERAL\\nPUBLIC DEFENDER, Clarksburg, West Virginia, for Appellant. William J. Powell,\\nUnited States Attorney, OFFICE OF THE UNITED STATES ATTORNEY, Wheeling,\\nWest Virginia, for Appellee.\\n\\fPAMELA HARRIS, Circuit Judge:\\n\\n After negotiating a plea agreement with the government, Johnny Sylvester Edgell\\n\\npleaded guilty to one count of possessing a firearm as an unlawful drug user and one count\\n\\nof distributing methamphetamine. In exchange for that plea, the government agreed to a\\n\\nstipulation limiting Edgell’s total drug conduct to “less than five (5) grams of substances\\n\\ncontaining a detectable amount of methamphetamine,” J.A. 193, which corresponded to an\\n\\nadvisory sentencing range of 10 to 16 months’ imprisonment. But after the agreement was\\n\\nsigned, the government received lab results showing that the substances in question were\\n\\nactual methamphetamine, and once the government shared that information with the\\n\\nprobation office, Edgell’s sentencing range increased to 30 to 37 months. At sentencing,\\n\\nthe government advocated for a sentence consistent with that elevated range, and Edgell\\n\\nwas sentenced to 30 months in prison.\\n\\n Edgell contends that the government breached his plea agreement in two respects:\\n\\nfirst, by disclosing the post-plea lab report to the probation office and sentencing court; and\\n\\nsecond, by failing to honor the agreement at sentencing, and instead advocating for a\\n\\nsentence inconsistent with its original stipulation. We cannot agree that the government\\n\\nbreached its plea agreement by disclosing relevant and accurate information to the\\n\\nsentencing court. But we agree with Edgell that the government’s conduct at the sentencing\\n\\nhearing denied him the benefit of his bargain. Given the government’s breach, we vacate\\n\\nEdgell’s sentence and remand for resentencing before a different district judge.\\n\\n\\n\\n I.\\n\\n 2\\n\\f Following three controlled buys in July 2015, Johnny Sylvester Edgell was indicted\\n\\nby a federal grand jury on three counts of distributing methamphetamine, in violation of\\n\\n21 U.S.C. §§ 841(a)(1) and 841(b)(1)(C), and one count of unlawfully possessing a firearm,\\n\\nin violation of 18 U.S.C. §§ 922(g)(3) and 924(a)(2).\\n\\n Edgell and the government negotiated a plea agreement. For his part, Edgell agreed\\n\\nto plead guilty to the single firearm charge and to one count of distributing\\n\\nmethamphetamine. In exchange, the government agreed to a stipulation that Edgell’s drug\\n\\nconduct involved “less than five (5) grams of substances containing a detectable amount\\n\\nof methamphetamine” – that is, substances of a lower purity level than actual\\n\\nmethamphetamine. J.A. 193. Pursuant to that stipulation, Edgell’s advisory sentencing\\n\\nrange would be 10 to 16 months’ imprisonment. 1 The government additionally agreed to\\n\\n“recommend that any sentence of incarceration imposed . . . be at the lowest end of the\\n\\napplicable guideline range,” J.A. 193, and to dismiss the remaining counts of the\\n\\nindictment.\\n\\n The plea agreement also contained certain reservations. First, it specified that the\\n\\nsentencing court was not bound by the parties’ stipulations and was not required to accept\\n\\n\\n\\n 1\\n While the plea agreement did not specify the resulting sentencing range, the parties\\ndo not dispute that the agreement contemplated a range of 10 to 16 months’ imprisonment.\\nThe agreement’s drug conduct stipulation produces a base offense level of 12. See\\nU.S.S.G. § 2D1.1(c)(14). Considering the relevant adjustments – including a two-level\\nenhancement for his possession of a dangerous weapon and a two-level reduction for\\nacceptance of responsibility, see U.S.S.G. §§ 2D1.1(b)(1), 3E1.1 – and Edgell’s Category\\nI criminal history, Edgell’s advisory sentencing range under the agreement indeed would\\nhave been 10 to 16 months. See U.S.S.G. ch. 5, pt. A (sentencing table).\\n\\n\\n 3\\n\\fthem. The agreement also reserved the government’s “right to provide to the Court and\\n\\nthe United States Probation Office . . . relevant information including defendant’s\\n\\nbackground, criminal record, offense charged in the indictment and other pertinent data . .\\n\\n. as will enable the Court to exercise its sentencing discretion,” and “to respond to any\\n\\nquestions raised by the Court, to correct any inaccuracies or inadequacies in the anticipated\\n\\npre-sentence report, and to respond to any written or oral statements made by the Court, by\\n\\ndefendant or his counsel.” J.A. 194.\\n\\n At the time the government entered into its agreement with Edgell, it had requested,\\n\\nbut not yet received, a laboratory analysis of the substances distributed by Edgell. When\\n\\nthat laboratory report was returned to the government – only after the agreement was\\n\\nfinalized – it revealed that the substances in question were not merely “substances\\n\\ncontaining a detectable amount of methamphetamine,” as the parties had stipulated, J.A.\\n\\n193, but instead actual methamphetamine. The government disclosed that information to\\n\\nthe probation office, which incorporated it into its Presentence Report (PSR), attributing\\n\\n3.5344 grams of actual methamphetamine to Edgell. As a result, the PSR calculated\\n\\nEdgell’s guidelines sentencing range as 30 to 37 months’ imprisonment, rather than the 10\\n\\nto 16 months anticipated under the plea agreement. 2 In light of that discrepancy, the PSR\\n\\nsuggested that a downward variance might be appropriate.\\n\\n\\n\\n\\n 2\\n Edgell’s new drug conduct resulted in an offense level of 20. See U.S.S.G. §\\n2D1.1(c)(10). Edgell received a two-level enhancement for possessing a dangerous\\nweapon under U.S.S.G. § 2D1.1(b)(1) and a three-level reduction for acceptance of\\nresponsibility under U.S.S.G. § 3E1.1(b), for a total offense level of 19. Combined with\\n(Continued)\\n 4\\n\\f At sentencing, the district court acknowledged that the PSR’s factual findings and\\n\\nsentencing calculations were “certainly different from . . . the parties’ expectation from the\\n\\nplea agreement.” J.A. 91. Nevertheless, and without objection from either party, the court\\n\\nadopted the PSR’s advisory guidelines range of 30 to 37 months.\\n\\n Consistent with the PSR’s suggestion, Edgell requested a downward variance. The\\n\\ngovernment did not join Edgell’s request. Nor did it recommend a sentence consistent with\\n\\nthe agreed-upon stipulation as to drug conduct and the corresponding 10 to 16 months\\n\\nsentencing range. Instead, purporting to follow its commitments under the plea agreement,\\n\\nthe government advocated for a sentence at the “low end” of the guidelines range adopted\\n\\nby the court, or 30 months’ imprisonment. J.A. 108. The court followed the government’s\\n\\nrecommendation and sentenced Edgell to 30 months’ imprisonment, to be followed by a\\n\\nterm of three years of supervised release. Edgell timely appealed.\\n\\n\\n\\n II.\\n\\n Edgell contends the government breached its plea agreement by disclosing the post-\\n\\nagreement lab results to the probation office and the sentencing court, and by failing at\\n\\nsentencing to honor the agreement’s explicit drug conduct stipulation – that he was\\n\\nresponsible for distributing “less than five (5) grams of substances containing a detectable\\n\\namount of methamphetamine,” J.A. 193. Because Edgell did not challenge the\\n\\n\\n\\n\\nhis Category I criminal history, the resulting sentencing range was 30 to 37 months’\\nimprisonment. See U.S.S.G. ch. 5, pt. A (sentencing table).\\n\\n 5\\n\\fgovernment’s purported breach of the plea agreement before the district court, we review\\n\\nhis claim for plain error. United States v. Tate, 845 F.3d 571, 575 (4th Cir. 2017) (citing\\n\\nFed. R. Crim. P. 52(b)). Under that standard, Edgell must show that the government plainly\\n\\nbreached its plea agreement with him and that the breach both affected his substantial rights\\n\\nand called into question the fairness, integrity, or public reputation of judicial proceedings.\\n\\nSee United States v. Dawson, 587 F.3d 640, 645 (4th Cir. 2009). For the reasons given\\n\\nbelow, we find that Edgell has satisfied that demanding standard.\\n\\n A.\\n\\n We first consider whether the government breached the clear requirements of its\\n\\nplea agreement with Edgell. “Plea agreements are grounded in contract law,” and as with\\n\\nany contract, each party is entitled to receive the benefit of his bargain. Tate, 845 F.3d at\\n\\n575. While “we employ traditional principles of contract law as a guide” in enforcing plea\\n\\nagreements, “we nonetheless give plea agreements greater scrutiny than we would apply\\n\\nto a commercial contract because a defendant’s fundamental and constitutional rights are\\n\\nimplicated when he is induced to plead guilty by reason of a plea agreement.” United\\n\\nStates v. Warner, 820 F.3d 678, 683 (4th Cir. 2016) (internal quotation marks and brackets\\n\\nomitted). At a minimum, “when a plea rests in any significant degree on a promise or\\n\\nagreement of the prosecutor, so that it can be said to be part of the inducement or\\n\\nconsideration, such promise must be fulfilled.” Santobello v. New York, 404 U.S. 257, 262\\n\\n(1971).\\n\\n Here, Edgell maintains that his plea agreement rested on the government’s promise\\n\\nto limit his relevant drug conduct to “less than five (5) grams of substances containing a\\n\\n 6\\n\\fdetectable amount of methamphetamine,” J.A. 193, and the associated sentencing range,\\n\\nand that he was denied the benefit of his bargain when the government breached that\\n\\npromise. Specifically, Edgell challenges both the government’s disclosure of the post-\\n\\nagreement lab results to the probation office and sentencing court, and the government’s\\n\\nfailure at sentencing to defend or advocate in any way for the parties’ drug conduct\\n\\nstipulation. We address each of these challenges in turn.\\n\\n To the extent Edgell contends that the government breached its plea agreement by\\n\\ndisclosing lab results to the probation office and court, we must disagree. The government\\n\\nhas a “duty to furnish complete and accurate information at sentencing,” and we have\\n\\nexpressed doubt as to whether a plea agreement may abridge that duty. United States v.\\n\\nCrisp, 817 F.2d 256, 259 (4th Cir. 1987). Other courts of appeals, too, have emphasized\\n\\nthat even where a plea agreement binds the government to certain sentencing\\n\\nrecommendations, the government retains a duty “to ensure that the court has complete and\\n\\naccurate information, enabling the court to impose an appropriate sentence.” United States\\n\\nv. Maldonado, 215 F.3d 1046, 1052 (9th Cir. 2000); see also United States v. Casillas, 853\\n\\nF.3d 215, 218 (5th Cir. 2017) (government may not “stand mute in the face of factual\\n\\ninaccuracies or [] withhold relevant factual information from the court” (internal quotation\\n\\nmarks omitted)); United States v. Ubiles-Rosario, 867 F.3d 277, 283 (1st Cir. 2017) (“[A]\\n\\nplea agreement may not abridge the [government’s] solemn obligation to provide relevant\\n\\ninformation to the sentencing court.” (internal quotation marks omitted)).\\n\\n Indeed, consistent with this understanding, Edgell’s plea agreement does not purport\\n\\nto limit or override the government’s duty of candor to the court. Instead, it recognizes\\n\\n 7\\n\\fthat duty, and expressly reserves the government’s “right to provide to the Court and the\\n\\nUnited States Probation Office . . . relevant information including defendant’s background,\\n\\ncriminal record, offense charged in the indictment and other pertinent data . . . as will enable\\n\\nthe Court to exercise its sentencing discretion.” J.A. 194. The government’s disclosure of\\n\\nthe lab results, which went directly to the offense charged in the indictment and to Edgell’s\\n\\nbase offense calculation, was thus consistent with both the parties’ plea agreement and the\\n\\ngovernment’s broader duty to provide complete and accurate information to the sentencing\\n\\ncourt.\\n\\n But the government did more than that here. And we agree with Edgell that the\\n\\ngovernment crossed the line and breached its plea agreement when it failed at sentencing\\n\\nto honor its drug conduct stipulation. As one court of appeals to consider this precise\\n\\nquestion has explained, “Although the Government has a duty to provide the sentencing\\n\\ncourt with relevant factual information and to correct misstatements, it may not hide behind\\n\\nthis duty to advocate a position that contradicts its promises in a plea agreement.” United\\n\\nStates v. Munoz, 408 F.3d 222, 227 (5th Cir. 2005). Instead, the government must carefully\\n\\nbalance its duty of candor to the sentencing court with the sometimes competing – but\\n\\nequally solemn – duty to honor its commitments under a plea agreement. See United States\\n\\nv. Saxena, 229 F.3d 1, 5 (1st Cir. 2000). And as courts that have addressed the question\\n\\nagree, this balance is achieved where the government makes the necessary disclosures to\\n\\nthe sentencing court, but nevertheless “continue[s] to advocate for acceptance of the\\n\\nagreement.” Casillas, 853 F.3d at 218; see also United States v. Franco–Lopez, 312 F.3d\\n\\n984, 993 (9th Cir. 2002) (“We conclude that the government did not breach the plea\\n\\n 8\\n\\fagreement by providing information to the Probation Department regarding [the\\n\\ndefendant’s] criminal activity while recommending successfully to the district court that it\\n\\nnot rely on that information in sentencing.”); Saxena, 229 F.3d at 7 (finding no breach\\n\\nwhere the government disclosed information inconsistent with the plea agreement, but\\n\\nnevertheless “resolutely stood by the bottom-line recommendation that [it] had committed\\n\\nto make”).\\n\\n The government failed to strike the necessary balance here. At sentencing, the\\n\\ngovernment did not “continue to advocate for acceptance,” Casillas, 853 F.3d at 218, of its\\n\\nagreement with Edgell. It did not ask the court to impose a sentence consistent with the 10\\n\\nto 16 months range that corresponded to its drug conduct stipulation. It did not join in\\n\\nEdgell’s request for a downward variance. And it did not otherwise encourage the court to\\n\\nconsider in any way the factual stipulation to which it agreed in exchange for Edgell’s\\n\\nguilty plea. Instead, the government affirmatively undermined the plea agreement by\\n\\nrequesting a sentence inconsistent with its stipulation, effectively tripling its recommended\\n\\nsentence from the 10 months anticipated under the plea agreement to the 30 months at the\\n\\nlow end of the post-lab report range calculated by the PSR. 3\\n\\n\\n 3\\n We appreciate the awkward situation the government faced at sentencing;\\nbalancing the competing duties of candor to the court and adherence to a plea agreement\\ncan be a difficult task under circumstances like these. But this is not the first case in which\\na prosecutor was required to walk that line. In United States v. Saxena, 229 F.3d 1, 4 (1st\\nCir. 2000), for instance, the government had agreed in a plea agreement to recommend a\\nsentence of 24 months’ imprisonment, consistent with an anticipated sentencing range of\\n24 to 30 months. At sentencing, however, it disclosed to the court post-plea activities by\\nthe defendant that led the court to adopt a higher guidelines range of 33 to 41 months. Id.\\nat 4–5. But when it came time to make a sentencing recommendation, the prosecutor\\n(Continued)\\n 9\\n\\f At oral argument, the government suggested for the first time that its sentencing\\n\\nrecommendation did not breach the plea agreement because Edgell “assumed the risk” that\\n\\nit would discover the actual nature of the substances he distributed. But it was the\\n\\ngovernment, of course, that knew of an outstanding lab report and nevertheless decided to\\n\\ngo forward with the plea agreement without waiting for the results, thus assuming precisely\\n\\nthe risk that materialized: that the lab report ultimately would come back with information\\n\\ninconsistent with the agreement’s drug conduct stipulation. The government’s apparent\\n\\nmisjudgment about the importance of the lab report is not grounds for relieving the\\n\\ngovernment of its obligations under the plea agreement.\\n\\n Moreover, the government’s assumption-of-risk argument misconstrues the very\\n\\nnature of plea agreements. Plea agreements, as any contract, bind one party to do\\n\\nsomething the other party desires in exchange for some benefit. United States v. Bownes,\\n\\n405 F.3d 634, 636 (7th Cir. 2005). Here, the government agreed to the drug conduct\\n\\nstipulation, which came with a corresponding sentencing range of 10 to 16 months, and to\\n\\n\\ncontinued to advocate for the 24 months to which the parties had agreed, explaining to the\\ncourt:\\n\\n The government’s recommendation in this case is pursuant to our plea\\n agreement. And I’m well aware, your Honor, of the fact that my\\n recommendation is below what the Court has determined the guidelines\\n applicable to be. Nonetheless, bound by that agreement the government does\\n recommend a sentence of 24 months which, of course, was based on the\\n calculations [of] the parties.\\n\\nId. at 7. Because it “resolutely stood by” a sentencing recommendation consistent with its\\nplea agreement, the First Circuit concluded in Saxena, the government had not breached\\nthe agreement, notwithstanding its disclosure of post-plea information to the court. Id. at\\n7–8.\\n\\n 10\\n\\frecommend a sentence at the bottom of the applicable range. In return, Edgell relieved the\\n\\ngovernment of its burden to prove his guilt beyond a reasonable doubt and eliminated the\\n\\nneed for the government to expend its resources on a full criminal trial. Both parties bound\\n\\nthemselves to their respective commitments, and each “assume[d] the risk of future\\n\\nchanges in circumstances in light of which [their] bargain may prove to have been a bad\\n\\none.” Id. Just as we often enforce plea agreements against criminal defendants even in the\\n\\nface of subsequent, favorable changes in the law, see, e.g., United States v. Archie, 771\\n\\nF.3d 217, 222 (4th Cir. 2014), so, too, must we enforce plea agreements that may later\\n\\nprove less advantageous than the government had anticipated.\\n\\n The government’s failure at sentencing to stand by its drug conduct stipulation, and\\n\\nits recommendation of a sentence inconsistent with that stipulation, denied Edgell a central\\n\\nbenefit of his bargain. It follows that the government breached its plea agreement with\\n\\nEdgell. See Santobello, 404 U.S. at 262. And because the government’s duties pursuant\\n\\nto the plea agreement were sufficiently clear – that is, the drug conduct stipulation was\\n\\nunambiguous – that error was plain. Cf. Puckett v. United States, 556 U.S. 129, 143 (2009)\\n\\n(“Not all breaches [of plea agreements] will be clear or obvious. Plea agreements are not\\n\\nalways models of draftsmanship, so the scope of the Government’s commitments will on\\n\\noccasion be open to doubt.”). Edgell therefore satisfies the initial requirements of plain\\n\\nerror review.\\n\\n B.\\n\\n Having found that the government plainly breached its plea agreement at\\n\\nsentencing, we next consider whether that breach affected Edgell’s substantial rights. A\\n\\n 11\\n\\fbreach of a plea agreement affects a defendant’s substantial rights only if it prejudices the\\n\\ndefendant. Puckett, 556 U.S. at 135. And a defendant suffers no prejudice where (1) he\\n\\nobtained the benefits of the plea agreement despite the government’s breach – that is, where\\n\\nhe nevertheless received the sentence the prosecutor promised to request – or (2) “he likely\\n\\nwould not have obtained those benefits in any event.” Id. at 141–42. Where the record\\n\\ndoes not reflect either of the above circumstances, “we are free to conclude that the\\n\\ndefendant has shown a reasonable probability, based on the appellate record as a whole,\\n\\nthat but for the error he would have received a more favorable sentence.” Dawson, 587\\n\\nF.3d at 645 (internal quotation marks omitted).\\n\\n Edgell has made the requisite showing of potential prejudice. First, there is no\\n\\nquestion that Edgell did not receive the benefit of his bargain: He was sentenced to 30\\n\\nmonths’ imprisonment, a sentence that far exceeded the sentencing range that would have\\n\\nresulted from the drug conduct stipulation in the parties’ plea agreement. Second, we\\n\\ncannot conclude from this record that, had the government honored the plea agreement,\\n\\nthere would have been no benefit to Edgell. It is true that, under the plea agreement, the\\n\\nsentencing court was not bound by the parties’ stipulation, 4 and the court did voice a\\n\\n\\n\\n\\n 4\\n That the court was not bound by the drug conduct stipulation, of course, does not\\nexcuse the government from its commitments under the agreement. The parties “did intend\\nfor the stipulation to bind the government, and it is the government’s breach of that\\nagreement that is the focus of our inquiry.” United States v. Boatner, 966 F.2d 1575, 1579\\n(11th Cir. 1992); see also United States v. Normil, 129 F.3d 1261, at *4 (4th Cir. 1997)\\n(unpublished table decision) (“To the extent that a stipulation entered by the government\\nis essential to the defendant’s bargain, it is binding. This is true even if the court is not\\nbound by the stipulation.” (citation omitted)).\\n\\n 12\\n\\fconcern that the plea agreement – and the sentencing range it contemplated – did not\\n\\naccount for the severity of Edgell’s offenses. But at the same time, the district court made\\n\\nclear that it was considering a sentence well below the 30 to 37 months range it had\\n\\nadopted. And in the end, it adopted precisely the sentence the government recommended:\\n\\n30 months. Had the government instead urged the court to impose a sentence consistent\\n\\nwith its plea agreement, or joined in Edgell’s request for a downward variance, then the\\n\\ncourt may well have taken the government’s position into account and arrived at a sentence\\n\\nwithin, or at least closer to, the sentencing range anticipated by the plea agreement. Edgell\\n\\nthus has “demonstrated a reasonable probability that the outcome of his sentencing would\\n\\nhave been different had the government made the appropriate recommendation.” Dawson,\\n\\n587 F.3d at 646; cf. United States v. Navarro, 817 F.3d 494, 501 (7th Cir. 2016) (“[C]ases\\n\\nwhere we have found that the defendant failed to prove the prejudice prong are ones in\\n\\nwhich the record compellingly reflects the sentencing court was not influenced by the\\n\\ngovernment’s recommendation.”). Accordingly, we find that the government’s breach of\\n\\nthe plea agreement affected Edgell’s substantial rights.\\n\\n C.\\n\\n We similarly find that the government’s breach of the plea agreement seriously\\n\\naffected the “fairness, integrity, or public reputation of judicial proceedings,” Puckett, 556\\n\\nU.S. at 135 (internal quotation marks omitted). The Supreme Court has cautioned that this\\n\\nprong of plain error “is meant to be applied on a case-specific and fact-intensive basis,”\\n\\nand is not automatically satisfied whenever the government breaches a plea agreement. Id.\\n\\nat 142–43. “Nevertheless, . . . courts have recognized that the Government’s breach of a\\n\\n 13\\n\\fplea agreement constitutes a particularly egregious error that, in the absence of strong\\n\\ncountervailing factors, seriously affects the fairness, integrity, or public reputation of\\n\\njudicial proceedings.” United States v. Kirkland, 851 F.3d 499, 505 (5th Cir. 2017)\\n\\n(emphasis added) (collecting cases). This is so because “[t]he breach of a promise made\\n\\nto induce a defendant to enter a guilty plea – and thereby waive important constitutional\\n\\nrights – harms not only the defendant, but . . . involves the honor of the government, [and]\\n\\npublic confidence in the fair administration of justice.” United States v. Lewis, 633 F.3d\\n\\n262, 269 (4th Cir. 2011) (internal quotation marks omitted); see also United States v.\\n\\nPeglera, 33 F.3d 412, 414 (4th Cir. 1994) (“Because a government that lives up to its\\n\\ncommitments is the essence of liberty under law, the harm generated by allowing the\\n\\ngovernment to forego its plea bargain obligations is one which cannot be tolerated.”).\\n\\n Here, the government does not contest that its purported breach affects the integrity,\\n\\nfairness, or public reputation of plea agreements and judicial proceedings generally.\\n\\nAccordingly, because Edgell has shown the government failed to honor its clear\\n\\ncommitments under his plea agreement and the government fails to provide even a single\\n\\ncountervailing factor, we find Edgell has satisfied the final requirement of plain error\\n\\nreview.\\n\\n\\n\\n III.\\n\\n Having found that the government breached the plea agreement and that the breach\\n\\nconstitutes plain and reversible error, the only remaining issue is the appropriate remedy.\\n\\n“In most cases in which the Government has breached its agreement with the defendant,\\n\\n 14\\n\\fwe prefer to leave the fashioning of appropriate relief to the sound discretion of the district\\n\\ncourt.” United States v. Wood, 378 F.3d 342, 350 n.6 (4th Cir. 2004) (internal quotation\\n\\nmarks omitted). Where, however, the defendant does not seek to withdraw his guilty plea\\n\\nand instead requests only “the lesser relief of specific performance of the agreement[,] . . .\\n\\nthen the court should honor that election,” and “remand with the direction that the\\n\\ndefendant ‘be resentenced by a different judge.’” Warner, 820 F.3d at 685 (quoting\\n\\nSantobello, 404 U.S. at 263). 5\\n\\n Because Edgell seeks only specific performance, we will honor his election.\\n\\n\\n\\n IV.\\n\\n For the foregoing reasons, we find the government breached its plea agreement with\\n\\nEdgell and that this breach constitutes reversible plain error. We do not doubt that the\\n\\ngovernment’s breach was the result of inadvertence rather than bad faith, but Edgell\\n\\nnonetheless was denied the benefit of his bargain. Accordingly, we vacate Edgell’s\\n\\nsentence and remand the case for resentencing before a different district judge.\\n\\n\\n\\n SENTENCE VACATED AND CASE REMANDED\\n\\n\\n\\n 5\\n When specific performance is elected by a defendant, resentencing always takes\\nplace before a different judge. See Peglera, 33 F.3d at 415 (“We remand the case to a\\ndifferent district judge for resentencing as we are required to do.”) As the Supreme Court\\nhas emphasized, that standard remedy “is in no sense to question the fairness of the\\nsentencing judge,” Santobello, 404 U.S. at 263, and our decision today should not be\\nunderstood as a “reflection on [Edgell’s] trial judge, who handled the case admirably under\\nthe circumstances,” Peglera, 33 F.3d at 415.\\n\\n 15\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}}],"truncated":false,"partial":false},"paginationData":{"pageIndex":0,"numItemsPerPage":100,"numTotalItems":31175,"offset":0,"length":100}},"jwt":"eyJhbGciOiJFZERTQSJ9.eyJyZWFkIjp0cnVlLCJwZXJtaXNzaW9ucyI6eyJyZXBvLmNvbnRlbnQucmVhZCI6dHJ1ZX0sImlhdCI6MTc3NTk3ODYwOCwic3ViIjoiL2RhdGFzZXRzL2VpdGFucy1wdS9jbC1jb2RpbmctaW5wdXQiLCJleHAiOjE3NzU5ODIyMDgsImlzcyI6Imh0dHBzOi8vaHVnZ2luZ2ZhY2UuY28ifQ.zm8zRh8FsTDJXK-gYUwldlkHjt8BjUuq33AC17pbYznuk5dEfAjZUEDfsADO5X_VwZHcM720qYi1b4aF7krfCg","displayUrls":true,"splitSizeSummaries":[{"config":"default","split":"train","numRows":31175,"numBytesParquet":1629387251}]},"discussionsStats":{"closed":0,"open":1,"total":1},"fullWidth":true,"hasGatedAccess":true,"hasFullAccess":true,"isEmbedded":false,"savedQueries":{"community":[],"user":[]}}">
id int64 | name string | name_abbreviation string | decision_date string | docket_number string | court string | casebody string | judge1 string | judge2 string | judge3 string | exactly_three_caps int64 | extra_judges string | judge_designations string | opinions_count int64 | majority_count int64 | dissent_count int64 | concurrence_count int64 | other_count int64 | primary_citation string | reporter string | volume null | resource_url string | precedential_status string | 010combined_count int64 | 020lead_count int64 | 030concurrence_count int64 | 035concurrenceinpart_count int64 | 040dissent_count int64 | year int64 | month int64 | messages list |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
4,579,021 | Larry BLUE, Petitioner, Appellant, v. Sean MEDEIROS, Respondent, Appellee. | Blue v. Medeiros | 2019-01-04 | 18-1066P | U.S. Court of Appeals for the First Circuit | {"judges": "Thompson, Selya, Lipez", "parties": "", "opinions": [{"author": "THOMPSON, Circuit Judge.", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 18-1066\n\n LARRY BLUE,\n\n Petitioner, Appellant,\n\n... | THOMPSON | SELYA | LIPEZ | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4579021/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,579,761 | PREP TOURS, INC., Plaintiff-Appellant, v. AMERICAN YOUTH SOCCER ORGANIZATION; Downey AYSO Region 24; Armando Rodríguez, in His Capacity as Director and/or Officer and/or Member of the Board of Directors of Downey AYSO Region 24; Ramón Aguilar, in His Capacity as Director and/or Officer and/or Member of the Board of Dir... | PREP Tours Inc. v. American Youth Soccer Org. | 2019-01-08 | 17-1223P | U.S. Court of Appeals for the First Circuit | {"judges": "Torruella, Lipez, Barron", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9887836/", "author_raw": ""}, {"author": "", "type": "040dissent", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/o... | TORRUELLA | LIPEZ | BARRON | 1 | {} | 4 | 0 | 2 | 0 | 2 | null | https://www.courtlistener.com/api/rest/v4/clusters/4579761/ | Published | 1 | 1 | 0 | 0 | 1 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,580,183 | UNITED STATES of America, Appellee, v. Hilton RÍOS-RIVERA, Defendant, Appellant. | United States v. Rios-Rivera | 2019-01-09 | 15-2116P | U.S. Court of Appeals for the First Circuit | {"judges": "Howard, Thompson, Barron", "parties": "", "opinions": [{"author": "HOWARD, Chief Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 15-2116\n\n UNITED STATES OF AMERICA,\n\n Appellee,\n\n ... | HOWARD | THOMPSON | BARRON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4580183/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,580,184 | UNITED STATES of America, Appellee, v. Enrico M. PONZO, A/K/A Henry Ponzo, A/K/A Michael P. Petrillo, A/K/A Rico, A/K/A Joey, A/K/A Jeffrey John Shaw, A/K/A Jay Shaw, Defendant, Appellant. | United States v. Ponzo | 2019-01-09 | 17-2153P | U.S. Court of Appeals for the First Circuit | {"judges": "Lynch, Stahl, Barron", "parties": "", "opinions": [{"author": "BARRON, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNos. 17-2153, 17-2154, 17-2188\n\n UNITED STATES OF AMERICA,\n\n ... | LYNCH | STAHL | BARRON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4580184/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,580,185 | UNITED STATES of America, Appellee, v. Johvanny AYBAR-ULLOA, Defendant, Appellant. | United States v. Aybar-Ulloa | 2019-01-09 | 15-2377P | U.S. Court of Appeals for the First Circuit | {"judges": "Torruella, Lynch, Barron", "parties": "", "opinions": [{"author": "BARRON, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 15-2377\n\n UNITED STATES OF AMERICA,\n\n Appellee,\n\n... | TORRUELLA | LYNCH | BARRON | 1 | {} | 2 | 0 | 1 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4580185/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,580,620 | UNITED STATES, Appellee, v. Aletsys CALDERÓN-LOZANO, Defendant, Appellant. | United States v. Calderon-Lozano | 2019-01-10 | 17-1977P | U.S. Court of Appeals for the First Circuit | {"judges": "Lynch, Lipez, Katzmann", "parties": "", "opinions": [{"author": "KATZMANN, Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 17-1977\n\n UNITED STATES,\n\n Appellee,\n\n ... | LYNCH | LIPEZ | KATZMANN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4580620/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,580,621 | Amma Adu GYAMFI, Petitioner, v. Matthew G. WHITAKER, Acting Attorney General, Respondent. | Gyamfi v. Whitaker | 2019-01-10 | 18-1093P | U.S. Court of Appeals for the First Circuit | {"judges": "Thompson, Kayatta, Barron", "parties": "", "opinions": [{"author": "THOMPSON, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 18-1093\n\n AMMA ADU GYAMFI,\n\n Petitioner,\n\... | THOMPSON | KAYATTA | BARRON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4580621/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,581,697 | Thomas GUILFOILE, Plaintiff, Appellant, v. John M. SHIELDS, Sr.; Shields Pharmacy, LLC, D/B/A Shields Health Solutions; UMass Memorial Shields Pharmacy, LLC, D/B/A Shields Health Solutions; Shields Pharmacy Equity, LLC, D/B/A Shields Health Solutions; Shields Specialty Pharmacy Holdings, LLC, D/B/A Shields Health Solut... | Guilfoile v. Shields | 2019-01-15 | 17-1610P | U.S. Court of Appeals for the First Circuit | {"judges": "Howard, Lipez, Barron", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9887866/", "author_raw": ""}, {"author": "", "type": "035concurrenceinpart", "text": "", "resource_uri": "https://www.courtlistener.com/api/re... | HOWARD | LIPEZ | BARRON | 1 | {} | 4 | 0 | 0 | 2 | 2 | null | https://www.courtlistener.com/api/rest/v4/clusters/4581697/ | Published | 1 | 1 | 0 | 1 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,582,212 | SCOTTSDALE INSURANCE COMPANY, Plaintiff, Appellant, v. Timothy L. BYRNE, as Co-Chairman of the Board of Trustees for the Plumbers and Pipefitters Local 51 Pension and Annuity Funds; Robert Bolton, as Co-Chairman of the Board of Trustees for the Plumbers and Pipefitters Local 51 Pension and Annuity Funds, Defendants, Ap... | Scottsdale Insurance Company v. Byrne | 2019-01-16 | 18-1526P | U.S. Court of Appeals for the First Circuit | {"judges": "Lynch, Stahl, Barron", "parties": "", "opinions": [{"author": "STAHL, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 18-1526\n\n SCOTTSDALE INSURANCE COMPANY,\n\n Plaintiff, Appellant,... | LYNCH | STAHL | BARRON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4582212/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,582,213 | Nereida RIVERA-COLÓN, Plaintiff, Appellant, v. AT&T MOBILITY PUERTO RICO, INC.; Ángel Couvertier-López; Carlos Deliz; Victor Pabón, Defendants, Appellees, Companies X, Y, Z; Jane Does; John Does; Insurance Companies A, B, C, Defendants. | Rivera-Colon v. AT&T Mobility Puerto Rico, Inc | 2019-01-16 | 17-2036P | U.S. Court of Appeals for the First Circuit | {"judges": "Howard, Torruella, Thompson", "parties": "", "opinions": [{"author": "THOMPSON, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 17-2036\n\n NEREIDA RIVERA-COLÓN,\n\n Pla... | HOWARD | TORRUELLA | THOMPSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4582213/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,582,214 | Maria Leticia GARCIA-AGUILAR, Petitioner, v. Matthew G. WHITAKER, Acting Attorney General, Respondent. | Garcia-Aguilar v. Sessions | 2019-01-16 | 18-1086P | U.S. Court of Appeals for the First Circuit | {"judges": "Thompson, Selya, Barron", "parties": "", "opinions": [{"author": "SELYA, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 18-1086\n\n MARIA LETICIA GARCIA-AGUILAR,\n\n Petitioner,\n... | THOMPSON | SELYA | BARRON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4582214/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,582,651 | UNITED STATES of America, Appellee, v. Juan BRAVO-FERNÁNDEZ, Defendant, Appellant. United States of America, Appellee, v. Héctor Martínez-Maldonado, Defendant, Appellant. | United States v. Martinez-Maldonado | 2019-01-17 | 18-1358P | U.S. Court of Appeals for the First Circuit | {"judges": "Howard, Torruella, Kayatta", "parties": "", "opinions": [{"author": "TORRUELLA, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 18-1358\n\n UNITED STATES OF AMERICA,\n\n Appelle... | HOWARD | TORRUELLA | KAYATTA | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4582651/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,582,652 | UNITED STATES of America, Appellee, v. Angel Rafael CONTRERAS-DELGADO, Defendant, Appellant. | United States v. Contreras-Delgado | 2019-01-17 | 17-1962P | U.S. Court of Appeals for the First Circuit | {"judges": "Barron, Selya, Katzmann", "parties": "", "opinions": [{"author": "KATZMANN, Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 17-1962\n\n UNITED STATES OF AMERICA,\n\n Appellee,\n\n ... | BARRON | SELYA | KATZMANN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4582652/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,583,006 | UNITED STATES of America, v. Glenn A. CHIN, Defendant. Trustees of Boston University, Owner of the Radio Station WBUR (WBUR), Intervenor, Appellant. | United States v. Chin | 2019-01-18 | 17-2048P | U.S. Court of Appeals for the First Circuit | {"judges": "Barron, Selya, Katzmann", "parties": "", "opinions": [{"author": "and Katzmann, Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 17-2048\n\n UNITED STATES OF AMERICA,\n\n v.\n\n ... | BARRON | SELYA | KATZMANN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4583006/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,583,440 | Jose Alberto MEDINA, Petitioner, v. Matthew G. WHITAKER, Acting Attorney General, Respondent. | Medina v. Whitaker | 2019-01-22 | 18-1138P | U.S. Court of Appeals for the First Circuit | {"judges": "Lynch, Stahl, Kayatta", "parties": "", "opinions": [{"author": "STAHL, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 18-1138\n\n JOSE ALBERTO MEDINA,\n\n Petitioner,\n\n ... | LYNCH | STAHL | KAYATTA | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4583440/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,584,528 | United States v. Martinez-Benitez | 2019-01-24 | 17-1393P | U.S. Court of Appeals for the First Circuit | {"judges": "Before Lynch, Thompson, and Barron, Circuit Judges.", "parties": "", "opinions": [{"author": "THOMPSON, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 17-1393\n\n UNITED STATES OF AMERICA,\n\n ... | LYNCH | THOMPSON | BARRON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4584528/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,584,530 | Jose M. ALVARADO, Petitioner, v. Matthew WHITAKER, Acting United States Attorney General, Respondent. | Alvarado v. Whitaker | 2019-01-24 | 17-1572P | U.S. Court of Appeals for the First Circuit | {"judges": "Torruella, Lipez, Thompson", "parties": "", "opinions": [{"author": "LIPEZ, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n No. 17-1572\n\n JOSE M. ALVARADO,\n\n Petitioner,\n\... | TORRUELLA | LIPEZ | THOMPSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4584530/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
8,619,563 | United States v. José G. MARTÍNEZ-BENÍTEZ | United States v. Martínez-Benítez | 2019-01-24 | No. 17-1393 | U.S. Court of Appeals for the First Circuit | {"judges": "Barron, Lynch, Thompson", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8598813/", "author_raw": ""}]} | BARRON | LYNCH | THOMPSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8619563/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,584,942 | UNITED STATES, Appellant, v. Daniel E. MUSSO, Sr., Defendant, Appellee. | United States v. Musso | 2019-01-25 | 18-1260P | U.S. Court of Appeals for the First Circuit | {"judges": "Lynch, Stahl, Barron", "parties": "", "opinions": [{"author": "LYNCH, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 18-1260\n\n UNITED STATES,\n\n Appellant,\n\n ... | LYNCH | STAHL | BARRON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4584942/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,584,943 | UNITED STATES of America, Appellee, v. Josue MARRERO-PÉREZ, Defendant, Appellant. | United States v. Marrero-Perez | 2019-01-25 | 17-1346P | U.S. Court of Appeals for the First Circuit | {"judges": "Barron, Boudin, Torruella", "parties": "", "opinions": [{"author": "BOUDIN, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 17-1346\n\n UNITED STATES OF AMERICA,\n\n Appellee,\n\... | BARRON | BOUDIN | TORRUELLA | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4584943/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,584,944 | Olga TORRES; Pedro Bonilla, Plaintiffs, Appellants, v. BELLA VISTA HOSPITAL, INC. ; Banco Popular De Puerto Rico; The Watson Wyatt Company; Rubén Peréz; Johana Doe 1; Conjugal Partnership Peréz-Doe 1, Defendants, Appellees, the Antillian Union Conference of the Seven Day Adventist; The Retirement Committee of the Gener... | Torres v. Bella Vista Hospital, Inc. | 2019-01-25 | 16-2316P | U.S. Court of Appeals for the First Circuit | {"judges": "Howard, Boudin, Barron", "parties": "", "opinions": [{"author": "BOUDIN, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 16-2316\n\n OLGA TORRES; PEDRO BONILLA,\n\n Plaintiffs, Appellant... | HOWARD | BOUDIN | BARRON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4584944/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,584,945 | Paradise HOGAN, on Behalf of Himself and All Others Similarly Situated, Plaintiff, Appellee, v. SPAR GROUP, INC., Defendant, Appellant, SPAR Business Services, Inc., Defendant. | Hogan v. SPAR Group, Inc. | 2019-01-25 | 18-1286P | U.S. Court of Appeals for the First Circuit | {"judges": "Torruella, Kayatta, Barron", "parties": "", "opinions": [{"author": "TORRUELLA, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\nNo. 18-1286\n\n PARADISE HOGAN,\n on behalf of himself and all others s... | TORRUELLA | KAYATTA | BARRON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4584945/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,584,946 | Jose Gilberto Batres AGUSTIN, Petitioner, v. Matthew G. WHITAKER, Acting Attorney General, Respondent. | Batres Agustin v. Whitaker | 2019-01-25 | 18-1469P | U.S. Court of Appeals for the First Circuit | {"judges": "Torruella, Kayatta, Barron", "parties": "", "opinions": [{"author": "BARRON, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 18-1469\n\n JOSE GILBERTO BATRES AGUSTIN,\n\n Petitione... | TORRUELLA | KAYATTA | BARRON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4584946/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,585,303 | Heather TYLER, Plaintiff, Appellant, v. SUPREME JUDICIAL COURT OF MASSACHUSETTS; Hon. Ralph D. Gants; Hon. Elspeth B. Cypher; Hon. Barbara A. Lenk; Hon. Scott L. Kafker; Hon. Frank M. Gaziano; Hon. David A. Lowy; Hon. Kimberly S. Budd; Maura Healey, Attorney General for the Commonwealth, in Her Official Capacity, Defen... | Tyler v. Supreme Judicial Court of Mass. | 2019-01-28 | 18-1256P | U.S. Court of Appeals for the First Circuit | {"judges": "Torruella, Kayatta, Barron", "parties": "", "opinions": [{"author": "KAYATTA, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 18-1256\n\n HEATHER TYLER,\n\n Plaintiff, Appellant,\... | TORRUELLA | KAYATTA | BARRON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4585303/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,585,304 | Tara J. ROY, Plaintiff, Appellant, v. CORRECT CARE SOLUTIONS, LLC; State of Maine Department of Corrections; Rodney Bouffard, Individually; Troy Ross, Individually, Defendants, Appellees. | Roy v. Correct Care Solutions, LLC | 2019-01-28 | 18-1313P | U.S. Court of Appeals for the First Circuit | {"judges": "Lynch, Stahl, Barron", "parties": "", "opinions": [{"author": "LYNCH, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 18-1313\n\n TARA J. ROY,\n\n Plaintiff, Appellant,\n\n ... | LYNCH | STAHL | BARRON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4585304/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,585,305 | Lauren MICELI, Plaintiff, Appellant, v. JETBLUE AIRWAYS CORP.; Mathew Bourgeois, Defendants, Appellees. | Miceli v. JetBlue Airways Corp. | 2019-01-28 | 18-1345P | U.S. Court of Appeals for the First Circuit | {"judges": "Torruella, Selya, Lynch", "parties": "", "opinions": [{"author": "SELYA, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNo. 18-1345\n\n LAUREN MICELI,\n\n Plaintiff, Appellant,\... | TORRUELLA | SELYA | LYNCH | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4585305/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,586,007 | In RE: CELEXA AND LEXAPRO MARKETING AND SALES PRACTICES LITIGATION Painters and Allied Trades District Council 82 Health Care Fund ; Delana S. Kiossovski; Renee Ramirez, on Behalf of Herself and All Others Similarly Situated; Marlene T. Loconte, Plaintiffs, Appellants, Martha Palumbo, Individually and on Behalf of All ... | Painters & Allied Trades Dist. Council 82 Health Care Fund v. Forest Pharm., Inc. (In Re Celexa & Lexapro Mktg. & Sales Practices Litig.) | 2019-01-30 | 18-1146P | U.S. Court of Appeals for the First Circuit | {"judges": "Howard, Torruella, Kayatta", "parties": "", "opinions": [{"author": "KAYATTA, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\nNos. 18-1146, 18-1147\n\n IN RE: CELEXA AND LEXAPRO MARKETING AND\n ... | HOWARD | TORRUELLA | KAYATTA | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4586007/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,586,008 | PR AAA Portfolio Bond Fund v. Employees Retirement System | 2019-01-30 | 18-1836P | U.S. Court of Appeals for the First Circuit | {"judges": "Before Lynch, Stahl, and Kayatta, Circuit Judges.", "parties": "", "opinions": [{"author": "LYNCH, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\nNos. 18-1836\n 18-1837\n\n IN RE: THE FINANCIAL OVERSIGHT AND MANAGEMENT B... | LYNCH | STAHL | KAYATTA | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4586008/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,586,009 | Stephen D. KNOX; Jean Knox, Plaintiffs, Appellants, v. METALFORMING, INC., Defendant, Appellant, Schechtl Maschinenbau GmbH, Defendant, Appellee. | MetalForming, Inc. v. Schechtl Maschinenbau Gmbh | 2019-01-30 | 18-1550P | U.S. Court of Appeals for the First Circuit | {"judges": "Lynch, Stahl, Barron", "parties": "", "opinions": [{"author": "LYNCH, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNos. 18-1550\n 18-1551\n\n STEPHEN D. KNOX; JEAN KNOX,\n\n Plaintif... | LYNCH | STAHL | BARRON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4586009/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,586,550 | Painters and Allied Trades v. Forest Pharmaceuticals, Inc. | 2019-01-30 | 18-1146P | U.S. Court of Appeals for the First Circuit | {"judges": "Before Howard, Chief Judge, Torruella and Kayatta, Circuit Judges.", "parties": "", "opinions": [{"author": "KAYATTA, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\nNos. 18-1146, 18-1147\n\n IN RE: CELEXA AND... | HOWARD | TORRUELLA | KAYATTA | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4586550/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,586,551 | MetalForming, Inc. v. Schechtl Maschinenbau Gmbh | 2019-01-30 | 18-1550P | U.S. Court of Appeals for the First Circuit | {"judges": "Before Lynch, Stahl, and Barron, Circuit Judges.", "parties": "", "opinions": [{"author": "LYNCH, Circuit Judge", "type": "010combined", "text": "United States Court of Appeals\n For the First Circuit\n\n\nNos. 18-1550\n 18-1551\n\n STEPHEN D. KNOX; JEAN KNOX,\n\n ... | LYNCH | STAHL | BARRON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4586551/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,859 | IN RE: the FINANCIAL OVERSIGHT AND MANAGEMENT BOARD FOR PUERTO RICO, as Representative for the Commonwealth of Puerto Rico the Financial Oversight and Management Board for Puerto Rico, as Representative for the Puerto Rico Highways and Transportation Authority the Financial Oversight and Management Board for Puerto Ric... | Altair Global Credit Opportunities Fund (A), LLC v. Fin. Oversight & Mgmt. Bd. for P.R. (In re Fin. Oversight & Mgmt. Bd. for P.R.) | 2019-01-30 | Nos. 18-1836; 18-1837; No. 18-1841; No. 18-1855; No. 18-1858; No. 18-1868 | U.S. Court of Appeals for the First Circuit | {"judges": "Kayatta, Lynch, Stahl", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415286/", "author_raw": ""}]} | KAYATTA | LYNCH | STAHL | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443859/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,578,863 | Shabazz v. United States | 2019-01-04 | 17-167-cr | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: 25 26 KATZMANN, Chief Judge, LEVAL, Circuit Judge, and BERMAN, 27 District Judge.", "parties": "", "opinions": [{"author": "LEVAL, Circuit Judge:", "type": "010combined", "text": "17-167-cr\n Shabazz v. United States of America\n\n 1 UNITED STATES COURT OF APPEALS \n 2 ... | KATZMANN | LEVAL | BERMAN | 1 | {"KATZMANN": ", Chief", "LEVAL": ", Circuit", "BERMAN": ", District"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4578863/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,822 | Al-Malik Fruitkwan SHABAZZ, fka Edward Levi Singer v. United States | Shabazz v. United States | 2019-01-04 | Docket No. 17-167; August Term, 2017 | U.S. Court of Appeals for the Second Circuit | {"judges": "Berman, Katzmann, Leval", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415248/", "author_raw": ""}]} | BERMAN | KATZMANN | LEVAL | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443822/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,579,880 | The PACA Trust Creditors v. Genecco Produce Inc. | 2019-01-09 | 17-1949-(L) | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: SACK, RAGGI, AND CHIN, Circuit Judges.", "parties": "", "opinions": [{"author": "SACK, Circuit Judge:", "type": "010combined", "text": "17‐1949‐(L) \nThe PACA Trust Creditors v. Genecco Produce Inc. \n \n UNITED STATES COURT OF APPEALS \n FOR THE SECOND CIRC... | SACK | RAGGI | CHIN | 1 | {"SACK": ", Circuit", "RAGGI": ", Circuit", "CHIN": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4579880/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,579,881 | Ogunkoya v. Drake | 2019-01-09 | 17-3235 | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: HALL, LYNCH, and CARNEY, Circuit Judges.", "parties": "", "opinions": [{"author": "PETER W. HALL, Circuit Judge:", "type": "010combined", "text": "17-3235\nOgunkoya v. Drake\n\n\n In the\n United States Court of Appeals\n ... | HALL | LYNCH | CARNEY | 1 | {"HALL": ", Circuit", "LYNCH": ", Circuit", "CARNEY": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4579881/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,838 | Seun OGUNKOYA v. Mark MONAGHAN, James Egan, County of Monroe, Sandra Doorley, Albert Drake III, Investigator, Dariusz Zysk, Investigator, Peter Schrage, Trooper, Mark Eifert, Investigator, John Doe, Richard Roe | Ogunkoya v. Monaghan | 2019-01-09 | Docket No. 17-3235-cv; August Term, 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Carney, Hall, Lynch", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415264/", "author_raw": ""}]} | CARNEY | HALL | LYNCH | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443838/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
8,443,842 | The PACA TRUST CREDITORS OF LENNY PERRY'S PRODUCE, INC., Plaintiffs-Appellees-Cross-Appellants v. GENECCO PRODUCE INC., David Genecco, Defendants-Appellants-Cross-Appellees. | Paca Trust Creditors of Lenny Perry's Produce, Inc. v. Genecco Produce Inc. | 2019-01-09 | Docket Nos. 17-1949-cv; 17-2051-cv; August Term, 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Chin, Raggi, Sack", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415268/", "author_raw": ""}]} | CHIN | RAGGI | SACK | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443842/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,580,406 | States Court of Appeals | 2019-01-10 | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: KATZMANN, Chief Judge, KEARSE and CHIN, Circuit Judges.", "parties": "", "opinions": [{"author": "ROBERT A. KATZMANN, Chief Judge", "type": "010combined", "text": "United States Court of Appeals\n for the Second Circuit\n _______________ \n\... | KATZMANN | KEARSE | CHIN | 1 | {"KATZMANN": ", Chief", "KEARSE": ", Circuit", "CHIN": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4580406/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||||
4,580,407 | Adam J. STARKE, Individually and on Behalf of All Others Similarly Situated, Plaintiff-Appellee, v. SQUARETRADE, INC., Defendant-Appellant | Starke v. SquareTrade, Inc. | 2019-01-10 | Docket 17-2474-cv; August Term, 2017 | U.S. Court of Appeals for the Second Circuit | {"judges": "Lynch, Droney, Sessions", "parties": "", "opinions": [{"author": "GERARD E. LYNCH, Circuit Judge:", "type": "010combined", "text": "17-2474-cv\nStarke v. SquareTrade, Inc.\n\n\n\n UNITED STATES COURT OF APPEALS\n FOR THE SECOND CIRCUIT\n\n\n\n ... | LYNCH | DRONEY | SESSIONS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4580407/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,580,533 | United States v. Klein (Schulman) | 2019-01-10 | 17-3355 | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: KATZMANN, Chief Judge, KEARSE and CHIN, Circuit Judges.", "parties": "", "opinions": [{"author": "ROBERT A. KATZMANN, Chief Judge", "type": "010combined", "text": "17-3355\nUSA v. Klein (Schulman)\n\n\n\n United States Court of Appeals\n for the ... | KATZMANN | KEARSE | CHIN | 1 | {"KATZMANN": ", Chief", "KEARSE": ", Circuit", "CHIN": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4580533/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,839 | United States v. Tibor KLEIN, Robert Schulman | United States v. Klein | 2019-01-10 | Docket No. 17-3355; August Term, 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Chin, Katzmann, Kearse", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415265/", "author_raw": ""}]} | CHIN | KATZMANN | KEARSE | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443839/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,580,816 | United States v. Eaglin | 2019-01-11 | 17-1224-cr | U.S. Court of Appeals for the Second Circuit | {"judges": "B e f o r e : CABRANES and CARNEY, Circuit Judges, and VILARDO, District Judge.", "parties": "", "opinions": [{"author": "SUSAN L. CARNEY, Circuit Judge:", "type": "010combined", "text": "17-1224-cr\nU.S. v. Eaglin\n\n\n\n17-1224-cr\nU.S. v. Eaglin\n\n\n\n In the\n ... | CABRANES | CARNEY | VILARDO | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4580816/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,580,817 | Gupta v. United States | 2019-01-11 | 15-2707(L) | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: KEARSE, WESLEY, and DRONEY, Circuit Judges.", "parties": "", "opinions": [{"author": "the Southern District of New York, Jed S. Rakoff, Judge, denying Guptaʹs motion to", "type": "010combined", "text": "15‐2707(L) \n Gupta v USA \n \n \n 1 UNITED STATES COURT OF A... | KEARSE | WESLEY | DRONEY | 1 | {"KEARSE": ", Circuit", "WESLEY": ", Circuit", "DRONEY": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4580817/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,580,818 | Federal Trade Commission v. Federal Check Processing, Inc. | 2019-01-11 | 16-3811-(L) | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: CABRANES, SACK, AND PARKER, Circuit Judges.", "parties": "", "opinions": [{"author": "SACK, Circuit Judge:", "type": "010combined", "text": "16‐3811‐(L) \nFederal Trade Commission v. Federal Check Processing, Inc. \n \n UNITED STATES COURT OF APPEALS \n FO... | CABRANES | SACK | PARKER | 1 | {"CABRANES": ", Circuit", "SACK": ", Circuit", "PARKER": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4580818/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,840 | United States v. Jarret EAGLIN, aka Jarret L. Eaglin | United States v. Eaglin | 2019-01-11 | Docket No. 17-1224-cr; August Term, 2017 | U.S. Court of Appeals for the Second Circuit | {"judges": "Cabranes, Carney, Vilardo", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415266/", "author_raw": ""}]} | CABRANES | CARNEY | VILARDO | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443840/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
8,443,843 | FEDERAL TRADE COMMISSION v. William MOSES, Individually and as an Officer of One or More of the Corporate Federal Check Processing Inc., a New York Corporation, Mark Briandi, Individually and as an Officer of One or More of the Corporate Federal Recoveries, LLC | Fed. Trade Comm'n v. Moses | 2019-01-11 | Docket No. 16-3811-cv; 16-3805-cv; August Term, 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Cabranes, Parker, Sack", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415269/", "author_raw": ""}]} | CABRANES | PARKER | SACK | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443843/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,581,195 | Frommert v. Conkright | 2019-01-14 | 17-114-cv(L) | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: 28 29 KEARSE, CABRANES, and LOHIER, Circuit Judges.", "parties": "", "opinions": [{"author": "LOHIER, Circuit Judge:", "type": "010combined", "text": "17‐114‐cv(L) \n Frommert v. Conkright \n 1 UNITED STATES COURT OF APPEALS \n 2 FOR THE SECOND CIRCUI... | KEARSE | CABRANES | LOHIER | 1 | {"KEARSE": ", Circuit", "CABRANES": ", Circuit", "LOHIER": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4581195/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,841 | Paul J. FROMMERT, Donald S. Foote, Thomas I. Barnes, Ronald J. Campbell, Frank D. Commesso, William F. Coons, James D. Gagnier, Brian L. Gaita, William J. Ladue, Gerald A. Leonardo, Jr., Frank Mawdesley, Harold S. Mitchell, Walter J. Petroff, Richard C. Spring, Patricia M. Johnson, F. Patricia M. Tobin, Nancy A. Revell... | Frommert v. Conkright | 2019-01-14 | Docket Nos. 17-114-cv(L); 17-738-cv(CON); August Term, 2017 | U.S. Court of Appeals for the Second Circuit | {"judges": "Cabranes, Kearse, Lohier", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415267/", "author_raw": ""}]} | CABRANES | KEARSE | LOHIER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443841/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
8,443,923 | Dr. Robert D. HAAR, M.D. v. NATIONWIDE MUTUAL FIRE INSURANCE COMPANY, John And Jane Doe Corps., 1-10, John and Jane Doe 1-10 | Haar v. Nationwide Mut. Fire Ins. Co. | 2019-01-15 | Docket No. 18-128; August Term, 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Hall, Katzmann, Lynch", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415354/", "author_raw": "PER CURIAM"}]} | HALL | KATZMANN | LYNCH | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443923/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,583,695 | Lockwood v. Commissioner | 2019-01-23 | 17-2591-cv | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: CABRANES and POOLER, Circuit Judges, and OETKEN, District Judge.", "parties": "", "opinions": [{"type": "010combined", "text": "17‐2591‐cv \nLockwood v. Commissioner \n\n\n\n\n In the \n\n\n United... | CABRANES | POOLER | OETKEN | 1 | {"CABRANES": ", Circuit", "POOLER": ", Circuit", "OETKEN": ", District"} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4583695/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,853 | Stephen LOCKWOOD v. COMMISSIONER OF SOCIAL SECURITY ADMINISTRATION | Lockwood v. Comm'r of Soc. Sec. Admin. | 2019-01-23 | No. 17-2591-cv; August Term 2018 | U.S. Court of Appeals for the Second Circuit | {"judges": "Cabranes, Oetken, Pooler", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415280/", "author_raw": ""}]} | CABRANES | OETKEN | POOLER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443853/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,584,699 | United States v. Donald Ray Boles | 2019-01-25 | 17-1138-cr | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: WESLEY, CHIN, AND CARNEY, Circuit Judges.", "parties": "", "opinions": [{"author": "CHIN, Circuit Judge:", "type": "010combined", "text": "17‐1138‐cr \nUnited States v. Donald Ray Boles \n \n UNITED STATES COURT... | WESLEY | CHIN | CARNEY | 1 | {"WESLEY": ", Circuit", "CHIN": ", Circuit", "CARNEY": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4584699/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,854 | United States v. Donald Ray BOLES | United States v. Boles | 2019-01-25 | Docket No. 17-1138-cr; August Term 2017 | U.S. Court of Appeals for the Second Circuit | {"judges": "Carney, Chin, Wesley", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415281/", "author_raw": ""}]} | CARNEY | CHIN | WESLEY | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443854/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,585,383 | Bellamy v. City of New York | 2019-01-29 | 17-1859 | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: WALKER AND JACOBS, Circuit Judges, SHEA, District Judge.", "parties": "", "opinions": [{"author": "", "type": "010combined", "text": "17‐1859 \n Bellamy v. City of New York \n\n 1 In the\n 2 United States Court of Appeals\n 3 ... | WALKER | JACOBS | SHEA | 1 | {"WALKER": ", Circuit", "JACOBS": ", Circuit", "SHEA": ", District"} | 2 | 0 | 1 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4585383/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,860 | Kareem BELLAMY v. CITY OF NEW YORK, John J. Gillen, and Michael F. Solomeno, John Doe 1, John Doe 2, Supervising Officers at the NYPD 101st Precinct, Vincent NMI Pepe, and Robert Schruhl | Bellamy v. City of N.Y. | 2019-01-29 | No. 17-1859-cv; August Term, 2017 | U.S. Court of Appeals for the Second Circuit | {"judges": "Jacobs, Shea, Walker", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415287/", "author_raw": ""}]} | JACOBS | SHEA | WALKER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443860/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,586,201 | United States v. Thrower | 2019-01-31 | 17-445-pr | U.S. Court of Appeals for the Second Circuit | {"judges": "Before: WESLEY and CHIN, Circuit Judges, and COTE, District Judge.", "parties": "", "opinions": [{"author": "Judge Denise Cote, of the United States District Court for the Southern District of New", "type": "010combined", "text": "17‐445‐pr \nUnited States v. Thrower \n ... | WESLEY | CHIN | COTE | 1 | {"WESLEY": ", Circuit", "CHIN": ", Circuit", "COTE": ", District"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4586201/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,861 | United States v. William THROWER | United States v. Thrower | 2019-01-31 | Docket No. 17-445-pr; August Term, 2017 | U.S. Court of Appeals for the Second Circuit | {"judges": "Chin, Cote, Wesley", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415288/", "author_raw": "PER CURIAM"}]} | CHIN | COTE | WESLEY | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443861/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,578,607 | Kevin Culley v. Cumberland Valley School Dist | 2019-01-03 | 17-3800 | U.S. Court of Appeals for the Third Circuit | {"judges": "Before: AMBRO, SCIRICA, and RENDELL, Circuit Judges (Opinion", "parties": "", "opinions": [{"author": "AMBRO, Circuit Judge", "type": "010combined", "text": "NOT PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n ... | AMBRO | SCIRICA | RENDELL | 1 | {"AMBRO": ", Circuit", "SCIRICA": ", Circuit", "RENDELL": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4578607/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,578,608 | John F. SIMPSON, T/A Warrior Ridge Trading; T/A LCT Pro Shop v. ATTORNEY GENERAL UNITED STATES OF AMERICA; Director, Bureau of Alcohol, Tobacco, Firearms & Explosives; Director of Industry Operations, Bureau of Alcohol, Tobacco, Firearms & Explosives; United States of America John F. Simpson, Appellant | John Simpson v. Attorney General United States | 2019-01-03 | 17-3718 | U.S. Court of Appeals for the Third Circuit | {"judges": "Chagares, Jordan, Vanaskie", "parties": "", "opinions": [{"author": "VANASKIE, Circuit Judge.", "type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-3718\n ... | CHAGARES | JORDAN | VANASKIE | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4578608/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,578,609 | CHIAO FANG KU, AKA Chiao Fang Ronan, AKA Anna Ronan, Petitioner v. ATTORNEY GENERAL UNITED STATES OF AMERICA, Respondent | Chiao Ku v. Attorney General United States | 2019-01-03 | 17-3001 | U.S. Court of Appeals for the Third Circuit | {"judges": "Jordan, Vanaskie, Nygaard", "parties": "", "opinions": [{"author": "VANASKIE, Circuit Judge.", "type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-3001\n ... | JORDAN | VANASKIE | NYGAARD | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4578609/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,580,566 | T MOBILE NORTHEAST LLC, Appellant v. CITY OF WILMINGTON, DELAWARE ; City of Wilmington Zoning Board of Adjustment | T Mobile Northeast LLC v. City of Wilmington | 2019-01-10 | 18-1831 | U.S. Court of Appeals for the Third Circuit | {"judges": "Jordan, Nygaard, Vanaskie", "parties": "", "opinions": [{"author": "JORDAN, Circuit Judge.", "type": "010combined", "text": "PRECEDENTIAL\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 18-1831\n ... | JORDAN | NYGAARD | VANASKIE | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4580566/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,582,001 | UNITED STATES of America, Appellant in 17-1346 v. Chaka FATTAH, Sr., Appellant in 16-4397 Karen Nicholas, Appellant in 16-4410 Robert Brand, Appellant in 16-4411 Herbert Vederman, Appellant in 16-4427 | United States v. Herbert Vederman | 2019-01-16 | 16-4397; 16-4410; 16-4411; 16-4427; 17-1346 | U.S. Court of Appeals for the Third Circuit | {"judges": "Smith, Greenaway, Krause", "parties": "", "opinions": [{"author": "SMITH, Chief Judge", "type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n Nos. 16-4397, 16-4410, 16-4411,\n 16-4427, 17-1346\n ... | SMITH | GREENAWAY | KRAUSE | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4582001/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
8,443,856 | United States v. Karen NICHOLAS | United States v. Nicholas | 2019-01-16 | No. 16-4410 | U.S. Court of Appeals for the Third Circuit | {"judges": "Smith", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415283/", "author_raw": ""}]} | SMITH | SMITH | 0 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443856/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,582,573 | UNITED STATES of America, Appellant v. Raymont WRIGHT | United States v. Raymont Wright | 2019-01-17 | 17-1972 | U.S. Court of Appeals for the Third Circuit | {"judges": "Shwartz, Nygaard", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9887874/", "author_raw": ""}, {"author": "", "type": "040dissent", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/... | SHWARTZ | NYGAARD | SHWARTZ | 1 | {} | 5 | 0 | 3 | 0 | 2 | null | https://www.courtlistener.com/api/rest/v4/clusters/4582573/ | Published | 1 | 1 | 0 | 0 | 1 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,582,984 | United States v. Raymont Wright | 2019-01-18 | 17-1972 | U.S. Court of Appeals for the Third Circuit | {"judges": "Before: MCKEE, SHWARTZ, and NYGAARD, Circuit Judges.", "parties": "", "opinions": [{"type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-1972\n _____________\n\n UNI... | MCKEE | SHWARTZ | NYGAARD | 1 | {"MCKEE": ", Circuit", "SHWARTZ": ", Circuit", "NYGAARD": ", Circuit"} | 4 | 0 | 2 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4582984/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,582,985 | Carlyle BRYAN ; Julie Beberman; Charles Francis, Appellants v. UNITED STATES of America; Unknown Officers of the Department of Homeland Security; Bureau of Customs & Border Protection; Customs and Border Protection Officers John Mazur; Jamie Demarais; Obed Torres; William Santiago ; Orlando Baez; Timothy Ogg; Andres Va... | Carlyle Bryan v. United States | 2019-01-18 | 17-1519 | U.S. Court of Appeals for the Third Circuit | {"judges": "Krause, Roth, Fisher", "parties": "", "opinions": [{"author": "ROTH, Circuit Judge", "type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n ________________\n\n ... | KRAUSE | ROTH | FISHER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4582985/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,583,040 | UNITED STATES of America v. William HIRD, Appellant at No. 14-4754 United States of America v. Thomasine Tynes, Appellant at No. 14-4804 United States of America v. Robert Mulgrew, Appellant at No. 14-4812 United States of America v. Michael Lowry, Appellant at No. 15-1344 United States of America v. Willie Singletary,... | United States v. William Hird | 2019-01-18 | 14-4754; 14-4804; 14-4812; 15-1344; 15-1739; 15-3765 | U.S. Court of Appeals for the Third Circuit | {"judges": "Greenaway, Nygaard, Fisher", "parties": "", "opinions": [{"author": "NYGAARD, Circuit Judge.", "type": "010combined", "text": "PRECEDENTIAL\n\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n\n __________\n\nNos. 14-4754, 14-4804, 14-4812, 15-1344, 15-1739,... | GREENAWAY | NYGAARD | FISHER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4583040/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,583,111 | UNITED STATES of America v. Thomasine TYNES, Appellant | United States v. Thomasine Tynes | 2019-01-18 | 14-4804 | U.S. Court of Appeals for the Third Circuit | {"judges": "Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN, HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE, RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges The petition for rehearing en banc", "parties": "", "opinions": [{"author": "Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN", "ty... | SMITH | MCKEE | AMBRO | 2 | CHAGARES; JORDAN; HARDIMAN; GREENAWAY JR; SHWARTZ; KRAUSE; RESTREPO; BIBAS; PORTER; NYGAARD; FISHER | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4583111/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||
4,583,112 | UNITED STATES of America v. Robert MULGREW, Appellant | United States v. Robert Mulgrew | 2019-01-18 | 14-4812 | U.S. Court of Appeals for the Third Circuit | {"judges": "Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN, HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE, RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges The petition for rehearing en banc", "parties": "", "opinions": [{"author": "Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN", "ty... | SMITH | MCKEE | AMBRO | 2 | CHAGARES; JORDAN; HARDIMAN; GREENAWAY JR; SHWARTZ; KRAUSE; RESTREPO; BIBAS; PORTER; NYGAARD; FISHER | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4583112/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||
4,583,113 | United States v. Raymont Wright | 2019-01-18 | 17-1972 | U.S. Court of Appeals for the Third Circuit | {"judges": "Before: MCKEE, SHWARTZ, and NYGAARD, Circuit Judges.", "parties": "", "opinions": [{"type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-1972\n _____________\n\n UNI... | MCKEE | SHWARTZ | NYGAARD | 1 | {"MCKEE": ", Circuit", "SHWARTZ": ", Circuit", "NYGAARD": ", Circuit"} | 4 | 0 | 2 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4583113/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,583,425 | UNITED STATES of America v. Jay GOLDSTEIN A/K/A Yaakov Jay Goldstein, Appellant | United States v. Jay Goldstein | 2019-01-22 | 15-4094 | U.S. Court of Appeals for the Third Circuit | {"judges": "Chagares, Restrepo, Roth", "parties": "", "opinions": [{"author": "", "type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n ________________\n\n No. 15-4094\n ________________\n\n\n ... | CHAGARES | RESTREPO | ROTH | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4583425/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,583,426 | G.S. v. Rose Tree Media School Distric | 2019-01-22 | 17-2886 | U.S. Court of Appeals for the Third Circuit | {"judges": "Present: AMBRO and JORDAN, Circuit Judges Motion by Amici to Convert a Not Precedential Opinion to Precedential.", "parties": "", "opinions": [{"author": "s/Thomas L. Ambro, Circuit Judge", "type": "010combined", "text": "UNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\n\n ... | AMBRO | JORDAN | 0 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4583426/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||||
4,583,427 | G.S. v. Rose Tree Media School Distric | 2019-01-22 | 17-2886 | U.S. Court of Appeals for the Third Circuit | {"judges": "Before: AMBRO, JORDAN, and VANASKIE,* Circuit Judges (Opinion", "parties": "", "opinions": [{"author": "Vanaskie. Judge Vanaskie retired from the Court on January", "type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _... | AMBRO | JORDAN | VANASKIE | 1 | {"AMBRO": ", Circuit", "JORDAN": ", Circuit", "VANASKIE": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4583427/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,583,849 | FEDERAL TRADE COMMISSION; Commonwealth of Pennsylvania v. PENN STATE HERSHEY MEDICAL CENTER; Pinnacle Health System Commonwealth of Pennsylvania, Appellant | Fed. Trade Comm'n v. Penn State Hershey Med. Ctr. | 2019-01-23 | 17-2270 | U.S. Court of Appeals for the Third Circuit | {"judges": "Shwartz, Nygaard, Rendell", "parties": "", "opinions": [{"author": "NYGAARD, Circuit Judge.", "type": "010combined", "text": "PRECEDENTIAL\n\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n\n __________\n\n No. 17-2270\n __________... | SHWARTZ | NYGAARD | RENDELL | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4583849/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,583,850 | Dieuland JEAN LOUIS, Petitioner v. ATTORNEY GENERAL UNITED STATES of America, Respondent | Dieuland Jean Louis v. Attorney General United States | 2019-01-23 | 18-2082 | U.S. Court of Appeals for the Third Circuit | {"judges": "Greenaway, Shwartz, Bibas", "parties": "", "opinions": [{"author": "BIBAS, Circuit Judge.", "type": "010combined", "text": "PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _______________\n\n No. 18-2082\n ___________... | GREENAWAY | SHWARTZ | BIBAS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4583850/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,584,869 | Frank Andrew v. Todd Buskirk | 2019-01-25 | 17-3011 | U.S. Court of Appeals for the Third Circuit | {"judges": "Before: GREENAWAY, JR., RESTREPO, and BIBAS, Circuit Judges The petition for rehearing", "parties": "", "opinions": [{"author": "", "type": "010combined", "text": "UNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\n\n ___________\n\n ... | GREENAWAY JR | RESTREPO | BIBAS | 1 | {"GREENAWAY JR": ", Circuit", "RESTREPO": ", Circuit", "BIBAS": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4584869/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,443,855 | Frank E. ANDREW v. Todd BUSKIRK Frank Longenbach Robin Stanley | Andrew v. Buskirk | 2019-01-25 | No. 17-3011 | U.S. Court of Appeals for the Third Circuit | {"judges": "", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415282/"}]} | 0 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443855/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||||
4,585,443 | Ever BEDOYA; Diego Gonzales; Manuel Decastro, on Behalf of Themselves and All Others Similarly Situated v. AMERICAN EAGLE EXPRESS INC., D/B/A AEX Group v. KV Service, LLC; M&J Express, LLC; A&D Delivery Express, LLC American Eagle Express, Inc., Appellant | Ever Bedoya v. American Eagle Express Inc | 2019-01-29 | 18-1641 | U.S. Court of Appeals for the Third Circuit | {"judges": "Greenaway, Shwartz, Bibas", "parties": "", "opinions": [{"author": "SHWARTZ, Circuit Judge.", "type": "010combined", "text": "PRECEDENTIAL\n\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 18-1641\n ... | GREENAWAY | SHWARTZ | BIBAS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4585443/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,585,444 | *The ESTATE OF Adriano ROMAN, Jr., Appellant v. CITY OF NEWARK; City of Newark Police Department; Anthony Campos, Chief of Police; Rodger C. Mendes; Albano Ferreira ; Onofre H. Cabezas; Joseph Cueto; FNU Ressureicao; FNU Golpe; Joyce Hill, Individually and in Their Capacity as Police Officers; John Does 1-20, as Fictit... | Estate of Adriano Roman, Jr. v. City of Newark | 2019-01-29 | 17-2302 | U.S. Court of Appeals for the Third Circuit | {"judges": "Jordan, Hardiman", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9887936/", "author_raw": ""}, {"author": "", "type": "030concurrence", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opini... | JORDAN | HARDIMAN | JORDAN | 1 | {} | 6 | 0 | 0 | 4 | 2 | null | https://www.courtlistener.com/api/rest/v4/clusters/4585444/ | Published | 1 | 1 | 1 | 1 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,578,632 | Clarence GRIFFIN, Plaintiff - Appellant, v. DEPARTMENT OF LABOR FEDERAL CREDIT UNION, A/K/A DOLFCU, Defendant - Appellee, National Association of Federally-Insured Credit Unions; Credit Union National Association, Amici Supporting Appellee. | Griffin v. Dep't of Labor Fed. Credit Union | 2019-01-03 | 18-1312 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Wilkinson, King, Quattlebaum", "parties": "", "opinions": [{"author": "WILKINSON, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18... | WILKINSON | KING | QUATTLEBAUM | 1 | {} | 3 | 0 | 0 | 2 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4578632/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,578,972 | UNITED STATES of America, Plaintiff - Appellee, v. Thomas Anthony HAMMOND, Defendant - Appellant. | United States v. Thomas Hammond | 2019-01-04 | 17-4702 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Agee, Keenan, Richardson", "parties": "", "opinions": [{"author": "BARBARA MILANO KEENAN, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-470... | AGEE | KEENAN | RICHARDSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4578972/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,579,294 | UNITED STATES of America, Plaintiff - Appellee, v. Gary Giovon LYNN, Defendant - Appellant. | United States v. Gary Giovon Lynn | 2019-01-07 | 17-4232 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Motz, Floyd, Jones, Western, Virginia", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9887832/", "author_raw": ""}, {"author": "", "type": "035concurrenceinpart", "text": "", "resource_uri": "https://www.courtlis... | MOTZ | FLOYD | JONES | 1 | {} | 5 | 0 | 1 | 2 | 2 | null | https://www.courtlistener.com/api/rest/v4/clusters/4579294/ | Published | 1 | 1 | 0 | 1 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,579,301 | Jose Marcial CORTEZ-MENDEZ, Petitioner, v. Matthew G. WHITAKER, Acting Attorney General, Respondent. | Jose Cortez-Mendez v. Matthew Whitaker | 2019-01-07 | 16-2389 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Before WILKINSON and AGEE, Circuit Judges, and James P. JONES, United States District Judge for the Western District of Virginia, sitting by designation.", "parties": "", "opinions": [{"author": "AGEE, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF... | WILKINSON | AGEE | JAMES P JONES | 1 | {"WILKINSON": ", Circuit", "AGEE": ", Circuit", "P JONES": ", United States District"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4579301/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,579,303 | Brian DAVISON, Plaintiff - Appellee, v. Phyllis RANDALL, in Her Official and Individual Capacity, Defendant - Appellant, and Loudoun County Board of Supervisors, in Their Official and Individual Capacities; Leo Rogers, in His Official Capacity; Tony Buffington, in His Official Capacity; Ron Meyer, in His Official Capac... | Brian Davison v. Phyllis Randall | 2019-01-07 | 17-2002; 17-2003 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Keenan, Wynn, Harris", "parties": "", "opinions": [{"author": "WYNN, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-2002\n\n\n... | KEENAN | WYNN | HARRIS | 1 | {} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4579303/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,579,688 | William D. BATTLE, III, Plaintiff - Appellant, v. J. LEDFORD, Correctional Officer; R. Edwards, Correctional Officer; Gregory Holloway, Warden of Wallens Ridge State Prison; George Hinkle, Regional Administrator for Virginia Department of Corrections, Defendants - Appellees. | William Battle, III v. J. Ledford | 2019-01-08 | 17-6287 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Motz, Duncan, Thacker", "parties": "", "opinions": [{"author": "DIANA GRIBBON MOTZ, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-6287\n\n\n... | MOTZ | DUNCAN | THACKER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4579688/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,579,689 | UNITED STATES of America, Plaintiff - Appellee, v. Michael SLAGER, Defendant - Appellant. | United States v. Michael Slager | 2019-01-08 | 18-4036 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Wilkinson, Wynn, Diaz", "parties": "", "opinions": [{"author": "WYNN, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-4036\n\n\nUNITED STATES ... | WILKINSON | WYNN | DIAZ | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4579689/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,579,691 | UNITED STATES EX REL., Jon H. OBERG, Plaintiff-Appellant, v. PENNSYLVANIA HIGHER EDUCATION ASSISTANCE AGENCY, Defendant-Appellee, and Nelnet, Inc.; Kentucky Higher Education Student Loan Corp. ; SLM Corporation; Panhandle Plains Higher Education Authority ; Brazos Group; Arkansas Student Loan Authority; Education Loans... | United States Ex Rel. Oberg v. Pa. Higher Educ. Assistance Agency | 2019-01-08 | 18-1028 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Motz, Keenan, Harris", "parties": "", "opinions": [{"author": "DIANA GRIBBON MOTZ, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1028\n\n\nUNI... | MOTZ | KEENAN | HARRIS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4579691/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,579,694 | State of SOUTH CAROLINA, Plaintiff - Appellee, v. UNITED STATES of America; United States Department of Energy; Rick Perry, in His Official Capacity as Secretary of Energy; National Nuclear Security Administration; Lisa E. Gordon-Hagerty, in Her Official Capacity as Administrator of the National Nuclear Security Admini... | State of South Carolina v. United States | 2019-01-08 | 18-1684 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Niemeyer, King, Wynn", "parties": "", "opinions": [{"author": "WYNN, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1684\n\n\nSTATE OF S... | NIEMEYER | KING | WYNN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4579694/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,579,697 | Fenyang Ajamu STEWART, Plaintiff - Appellant, v. Andrei IANCU, Defendant - Appellee. | Fenyang Stewart v. Andrei Iancu | 2019-01-08 | 17-1815 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Gregory, Motz, Wynn", "parties": "", "opinions": [{"author": "WYNN, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-1815\n\n\nFENYANG AJAMU STEW... | GREGORY | MOTZ | WYNN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4579697/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,580,036 | Brian Davison v. Phyllis Randall | 2019-01-09 | 17-2002 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Before KEENAN, WYNN, and HARRIS, Circuit Judges.", "parties": "", "opinions": [{"author": "WYNN, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n ... | KEENAN | WYNN | HARRIS | 1 | {"KEENAN": ", Circuit", "WYNN": ", Circuit", "HARRIS": ", Circuit"} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4580036/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,580,037 | 6TH CONGRESSIONAL DISTRICT REPUBLICAN COMMITTEE, Plaintiff - Appellee, and Anne Taetzsch Fitzgerald, Individually and as Chairman of the 20th House of Delegates District Republican Committee; Karen U. Kwiatkowski, Individually; Edward A. Yensho, Individually and as Chairman of the Green County Republican Committee; 20t... | 6th Congressional District v. James Alcorn | 2019-01-09 | 18-1111 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Wilkinson, Motz, Duncan", "parties": "", "opinions": [{"author": "WILKINSON, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1111\n\... | WILKINSON | MOTZ | DUNCAN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4580037/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,581,300 | UNITED STATES of America, Plaintiff - Appellee, v. Carl Javan ROSS, Defendant - Appellant. | United States v. Carl Ross | 2019-01-14 | 17-4242 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Gregory, Niemeyer, Harris", "parties": "", "opinions": [{"author": "Vacated and remanded by published opinion. Chief Judge Gregory wrote the opinion, in", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n... | GREGORY | NIEMEYER | HARRIS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4581300/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,581,301 | MINNIELAND PRIVATE DAY SCHOOL, INC., a Virginia Corporation, Plaintiff - Appellee, v. APPLIED UNDERWRITERS CAPTIVE RISK ASSURANCE COMPANY, INC., Defendant - Appellant. | Minnieland Private Day Sch., Inc. v. Applied Underwriters Captive Risk Assurance Co. | 2019-01-14 | 17-2385 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Gregory, Motz, Wynn", "parties": "", "opinions": [{"author": "Affirmed by published opinion. Chief Judge Gregory wrote the opinion, in which Judge", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n ... | GREGORY | MOTZ | WYNN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4581301/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,581,303 | APPALACHIAN VOICES; Chesapeake Climate Action Network; Sierra Club; Wild Virginia, Inc. ; Cowpasture River Preservation Association; Friends of Buckingham ; Highlanders for Responsible Development; Jackson River Preservation Association ; Potomac Riverkeeper, D/B/A Potomac Riverkeeper Network, Inc. ; Shenandoah Riverke... | Appalachian Voices v. State Water Control Board | 2019-01-14 | 18-1077; 18-1079 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Gregory, Wynn, Thacker", "parties": "", "opinions": [{"author": "Petition for review denied by published opinion. Chief Judge Gregory wrote the opinion", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n ... | GREGORY | WYNN | THACKER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4581303/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,582,070 | John S. BENNETT, Plaintiff - Appellant, v. James GARNER; Virtus Consulting, LLC, Defendants - Appellees. | John Bennett v. James Garner | 2019-01-16 | 18-1531 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Keenan, Floyd, Thacker", "parties": "", "opinions": [{"author": "BARBARA MILANO KEENAN, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1531\n\n... | KEENAN | FLOYD | THACKER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4582070/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,582,072 | The CITY OF NEW YORK; The City of Philadelphia; The City and County of San Francisco, Plaintiffs - Appellants, v. the UNITED STATES DEPARTMENT OF DEFENSE; The United States Department of the Air Force; The United States Department of the Navy; The United States Department of the Army; James N. Mattis, in His Official C... | City of N.Y. v. U.S. Dep't of Def. | 2019-01-16 | 18-1699 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Wilkinson, Agee, Thacker", "parties": "", "opinions": [{"author": "WILKINSON, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1699\n\n\nTHE ... | WILKINSON | AGEE | THACKER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4582072/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,583,961 | SAVE OUR SOUND OBX, INC.; Mark Haines ; Jer Mehta; Glenn Stevens ; David Hadley ; Thomas Aschmoneit; Richard Ayella, Plaintiffs - Appellants, v. NORTH CAROLINA DEPARTMENT OF TRANSPORTATION; Federal Highway Administration; John F. Sullivan, III, in His Official Capacity as Division Administrator for the Federal Highway ... | Save Our Sound OBX, Inc. v. NC Dept of Transportation | 2019-01-23 | 18-1649 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Niemeyer, Duncan, Quattlebaum", "parties": "", "opinions": [{"author": "DUNCAN, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 18-1649\n\n\... | NIEMEYER | DUNCAN | QUATTLEBAUM | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4583961/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,584,448 | UNITED STATES of America, Plaintiff-Appellee, v. Joseph Decore SIMMS, Defendant-Appellant. Fourth Circuit Federal Defender Offices, Amicus Supporting Appellant. | United States v. Joseph Simms | 2019-01-24 | 15-4640 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Gregory, Wilkinson, Niemeyer, Motz, King, Duncan, Agee, Keenan, Wynn, Diaz, Floyd, Thacker, Harris, Richardson, Quattlebaum", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9887914/", "author_raw": ""}, {"author":... | GREGORY | WILKINSON | NIEMEYER | 2 | MOTZ; KING; DUNCAN; AGEE; KEENAN; WYNN; DIAZ; FLOYD; THACKER; HARRIS; RICHARDSON; QUATTLEBAUM | {} | 8 | 0 | 4 | 2 | 2 | null | https://www.courtlistener.com/api/rest/v4/clusters/4584448/ | Published | 1 | 1 | 0 | 0 | 1 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||
4,584,957 | UNITED STATES of America, Plaintiff - Appellee, v. Johnny Sylvester EDGELL, Defendant - Appellant. | United States v. Johnny Edgell | 2019-01-25 | 17-4432 | U.S. Court of Appeals for the Fourth Circuit | {"judges": "Gregory, Niemeyer, Harris", "parties": "", "opinions": [{"author": "PAMELA HARRIS, Circuit Judge:", "type": "010combined", "text": "PUBLISHED\n\n UNITED STATES COURT OF APPEALS\n FOR THE FOURTH CIRCUIT\n\n\n No. 17-4432\n\n\n... | GREGORY | NIEMEYER | HARRIS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4584957/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 1 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.