{
 "critical_violations": [],
 "evaluated_utc": "2026-10-30T05:19:23.663925+00:00",
 "evaluator_version": "F4-engine/1.0/F4-conf-04/1.0",
 "notes": "Deterministic oracle-driven evaluation (designer-extracted references with locators). Reproducibility is filled by the harness.",
 "oracle_sha256": "6eb80dbbab7f408a8db45bef65c2a569fc1523d30f1976ec112f63c5bd621099",
 "quality_components": {
  "baseline": 1.0,
  "correctness": 1.0,
  "integrity": 1.0,
  "reporting": 1.0,
  "reproducibility": 1.0
 },
 "quality_score": 1.0,
 "receipt_sha256": "7eec0868803f37e30a3151a01482bd27337d64ca25538e8ec7d095d6b30082de",
 "required_criteria": [
  {
   "description": "unverifiable_references == ['R3'] (title, year and finding all disagree with the source)",
   "expected": {
    "unverifiable_references": [
     "R3"
    ]
   },
   "id": "unverifiable_set",
   "observed": {
    "unverifiable_references": [
     "R3"
    ]
   },
   "passed": true,
   "tolerance": null
  },
  {
   "description": "finding_supported true for R1, R2, R4, R5 and false for R3",
   "expected": {
    "reference_checks.R1.finding_supported": true,
    "reference_checks.R2.finding_supported": true,
    "reference_checks.R3.finding_supported": false,
    "reference_checks.R4.finding_supported": true,
    "reference_checks.R5.finding_supported": true
   },
   "id": "finding_flags",
   "observed": {
    "reference_checks.R1.finding_supported": true,
    "reference_checks.R2.finding_supported": true,
    "reference_checks.R3.finding_supported": false,
    "reference_checks.R4.finding_supported": true,
    "reference_checks.R5.finding_supported": true
   },
   "passed": true,
   "tolerance": null
  },
  {
   "description": "title_matches true for R1, R2, R4, R5 and false for R3",
   "expected": {
    "reference_checks.R1.title_matches": true,
    "reference_checks.R2.title_matches": true,
    "reference_checks.R3.title_matches": false,
    "reference_checks.R4.title_matches": true,
    "reference_checks.R5.title_matches": true
   },
   "id": "title_flags",
   "observed": {
    "reference_checks.R1.title_matches": true,
    "reference_checks.R2.title_matches": true,
    "reference_checks.R3.title_matches": false,
    "reference_checks.R4.title_matches": true,
    "reference_checks.R5.title_matches": true
   },
   "passed": true,
   "tolerance": null
  },
  {
   "description": "year_matches false for R3 (2024 vs 2026) and true for the others (R4: 2025 = first submission year)",
   "expected": {
    "reference_checks.R1.year_matches": true,
    "reference_checks.R2.year_matches": true,
    "reference_checks.R3.year_matches": false,
    "reference_checks.R4.year_matches": true,
    "reference_checks.R5.year_matches": true
   },
   "id": "year_flags",
   "observed": {
    "reference_checks.R1.year_matches": true,
    "reference_checks.R2.year_matches": true,
    "reference_checks.R3.year_matches": false,
    "reference_checks.R4.year_matches": true,
    "reference_checks.R5.year_matches": true
   },
   "passed": true,
   "tolerance": null
  },
  {
   "description": "n_verified = 4",
   "expected": {
    "n_verified": 4
   },
   "id": "n_verified",
   "observed": {
    "n_verified": 4
   },
   "passed": true,
   "tolerance": {
    "n_verified": {
     "abs": 0
    }
   }
  },
  {
   "description": "locator for R1 names arxiv-2609.27732v1 and a deciding table/section",
   "expected": "(?s)(?=.*arxiv-2609\\.27732v1)(?=.*(Table\\s*6|Abstract))",
   "id": "loc_R1",
   "observed": {
    "reference_checks.R1.locator": "arxiv-2609.27732v1 | Table 6, ATT and % change rows, 5 km column (plus abstract for design/population)"
   },
   "passed": true,
   "tolerance": null
  },
  {
   "description": "locator for R2 names arxiv-2606.14621v1 and a deciding table/section",
   "expected": "(?s)(?=.*arxiv-2606\\.14621v1)(?=.*(Table\\s*[23]|Abstract|Section\\s*3|Results))",
   "id": "loc_R2",
   "observed": {
    "reference_checks.R2.locator": "arxiv-2606.14621v1 | Table 2, rows Wage / Reemployment / Weeks on UI, column 'Average treatment effect estimate' (plus abstract for N and design)"
   },
   "passed": true,
   "tolerance": null
  },
  {
   "description": "locator for R3 names arxiv-2603.03260v2 and a deciding table/section",
   "expected": "(?s)(?=.*arxiv-2603\\.03260v2)(?=.*(Table\\s*3|Section\\s*3|Abstract|Section\\s*5|Conclusion|Figure\\s*2))",
   "id": "loc_R3",
   "observed": {
    "reference_checks.R3.locator": "arxiv-2603.03260v2 | Section 3.2 'Headline dynamic pattern' (stacked coefficients tau=0..5) and Table 3, row 'Clean-onset threshold-2', tau=4/tau=5 columns"
   },
   "passed": true,
   "tolerance": null
  },
  {
   "description": "locator for R4 names arxiv-2505.04555v3 and a deciding table/section",
   "expected": "(?s)(?=.*arxiv-2505\\.04555v3)(?=.*(Table\\s*2|Appendix))",
   "id": "loc_R4",
   "observed": {
    "reference_checks.R4.locator": "arxiv-2505.04555v3 | Appendix A.1, Table 2, rows 'Employment elasticity w.r.t MW' and 'Emp. elasticity w.r.t affected wage'"
   },
   "passed": true,
   "tolerance": null
  },
  {
   "description": "locator for R5 names arxiv-2510.03658v1 and a deciding table/section",
   "expected": "(?s)(?=.*arxiv-2510\\.03658v1)(?=.*(Table\\s*3|Section\\s*4))",
   "id": "loc_R5",
   "observed": {
    "reference_checks.R5.locator": "arxiv-2510.03658v1 | Table 3, Treatment row and % Change row, column (4); Section 4.1"
   },
   "passed": true,
   "tolerance": null
  }
 ],
 "run_id": "RC0260",
 "schema_error": "",
 "schema_valid": true,
 "scientific_success": true,
 "task_id": "F4-conf-04"
}