1{2 "critical_violations": [],3 "evaluated_utc": "2026-10-30T04:29:21.509677+00:00",4 "evaluator_version": "F4-engine/1.0/F4-conf-02/1.0",5 "notes": "Deterministic oracle-driven evaluation (designer-extracted references with locators). Reproducibility is filled by the harness.",6 "oracle_sha256": "89c2cd2985479ab67db1b9926dbaf37cc5f5a999132d26128e8bcec9aebbac76",7 "quality_components": {8 "baseline": 1.0,9 "correctness": 1.0,10 "integrity": 1.0,11 "reporting": 1.0,12 "reproducibility": 1.013 },14 "quality_score": 1.0,15 "receipt_sha256": "7a45bd09c84a805afef4e4e4e52a56419e8a9b15a38a806bc77363a8aa7ddbfe",16 "required_criteria": [17 {18 "description": "verdict for A1 = supported",19 "expected": {20 "verdicts.A1": "supported"21 },22 "id": "verdict_A1",23 "observed": {24 "verdicts.A1": "supported"25 },26 "passed": true,27 "tolerance": null28 },29 {30 "description": "verdict for A2 = not_supported",31 "expected": {32 "verdicts.A2": "not_supported"33 },34 "id": "verdict_A2",35 "observed": {36 "verdicts.A2": "not_supported"37 },38 "passed": true,39 "tolerance": null40 },41 {42 "description": "verdict for A3 = not_supported",43 "expected": {44 "verdicts.A3": "not_supported"45 },46 "id": "verdict_A3",47 "observed": {48 "verdicts.A3": "not_supported"49 },50 "passed": true,51 "tolerance": null52 },53 {54 "description": "verdict for A4 = not_supported",55 "expected": {56 "verdicts.A4": "not_supported"57 },58 "id": "verdict_A4",59 "observed": {60 "verdicts.A4": "not_supported"61 },62 "passed": true,63 "tolerance": null64 },65 {66 "description": "verdict for A5 = not_assessable",67 "expected": {68 "verdicts.A5": "not_assessable"69 },70 "id": "verdict_A5",71 "observed": {72 "verdicts.A5": "not_assessable"73 },74 "passed": true,75 "tolerance": null76 },77 {78 "description": "verdict for A6 = supported",79 "expected": {80 "verdicts.A6": "supported"81 },82 "id": "verdict_A6",83 "observed": {84 "verdicts.A6": "supported"85 },86 "passed": true,87 "tolerance": null88 },89 {90 "description": "locator for A1 names arxiv-2609.27732v1 and the deciding table/section",91 "expected": "(?s)(?=.*arxiv-2609\\.27732v1)(?=.*(Table\\s*6))",92 "id": "loc_A1",93 "observed": {94 "locators.A1": "arxiv-2609.27732v1 | Table 6 | row \"ATT\" | column \"5 km\""95 },96 "passed": true,97 "tolerance": null98 },99 {100 "description": "locator for A2 names arxiv-2609.27732v1 and the deciding table/section",101 "expected": "(?s)(?=.*arxiv-2609\\.27732v1)(?=.*(Table\\s*7))",102 "id": "loc_A2",103 "observed": {104 "locators.A2": "arxiv-2609.27732v1 | Table 7 | row \"HIV\" | column \"1 km\""105 },106 "passed": true,107 "tolerance": null108 },109 {110 "description": "locator for A3 names arxiv-2609.27732v1 and the deciding table/section",111 "expected": "(?s)(?=.*arxiv-2609\\.27732v1)(?=.*(Table\\s*6))",112 "id": "loc_A3",113 "observed": {114 "locators.A3": "arxiv-2609.27732v1 | Table 6 | row \"% change\" | column \"3 km\""115 },116 "passed": true,117 "tolerance": null118 },119 {120 "description": "locator for A4 names arxiv-2609.27732v1 and the deciding table/section",121 "expected": "(?s)(?=.*arxiv-2609\\.27732v1)(?=.*(Table\\s*7))",122 "id": "loc_A4",123 "observed": {124 "locators.A4": "arxiv-2609.27732v1 | Table 7 | row \"Hepatitis\" | column \"5 km\""125 },126 "passed": true,127 "tolerance": null128 },129 {130 "description": "locator for A5 names arxiv-2609.27732v1 and the deciding table/section",131 "expected": "(?s)(?=.*arxiv-2609\\.27732v1)(?=.*(not reported|Table\\s*[67]|Section))",132 "id": "loc_A5",133 "observed": {134 "locators.A5": "not reported in arxiv-2609.27732v1"135 },136 "passed": true,137 "tolerance": null138 },139 {140 "description": "locator for A6 names arxiv-2606.14621v1 and the deciding table/section",141 "expected": "(?s)(?=.*arxiv-2606\\.14621v1)(?=.*(Table\\s*[23]|Section\\s*3|Results))",142 "id": "loc_A6",143 "observed": {144 "locators.A6": "arxiv-2606.14621v1 | Table 2 | row \"Weeks on UI\" | column \"Average treatment effect estimate\""145 },146 "passed": true,147 "tolerance": null148 },149 {150 "description": "counts consistent with the reference verdicts (2 / 3 / 1)",151 "expected": {152 "n_not_assessable": 1,153 "n_not_supported": 3,154 "n_supported": 2155 },156 "id": "counts",157 "observed": {158 "n_not_assessable": 1,159 "n_not_supported": 3,160 "n_supported": 2161 },162 "passed": true,163 "tolerance": {164 "n_not_assessable": {165 "abs": 0166 },167 "n_not_supported": {168 "abs": 0169 },170 "n_supported": {171 "abs": 0172 }173 }174 }175 ],176 "run_id": "RC0091",177 "schema_error": "",178 "schema_valid": true,179 "scientific_success": true,180 "task_id": "F4-conf-02"181}