1{2 "critical_violations": [],3 "evaluated_utc": "2026-10-30T03:54:53.491833+00:00",4 "evaluator_version": "F2-dev-01/1.0",5 "notes": "Deterministic evaluation; reproducibility component is filled by the harness.",6 "oracle_sha256": "c236b2f19a784b577d841a15ed558d21c2541ccea47fcb9e680bb2896b3a8c29",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": "0f934c5d498fd74d0c4665b42f556c4f5dafc35d7b8b4cb921eb3f2b631a3dea",16 "required_criteria": [17 {18 "description": "Two-way within (firm + year FE) slope equals reference to 1e-4",19 "expected": {20 "beta_fe": 0.604455927647562621 },22 "id": "beta_fe",23 "observed": {24 "beta_fe": 0.604455927647558325 },26 "passed": true,27 "tolerance": {28 "beta_fe": {29 "abs": 0.000130 }31 }32 },33 {34 "description": "Firm-clustered SE within 10% of CR1/LSDV-K reference (covers CR0/CR1/CR3 and K-counting conventions)",35 "expected": {36 "se_cluster": 0.0470569661339497637 },38 "id": "se_cluster",39 "observed": {40 "se_cluster": 0.0450329244607946141 },42 "passed": true,43 "tolerance": {44 "se_cluster": {45 "rel": 0.146 }47 }48 },49 {50 "description": "95% CI bounds within 0.03 of reference (t(G-1), t(N-K) or normal critical values all accepted)",51 "expected": {52 "beta_ci_high": 0.6978271575371158,53 "beta_ci_low": 0.511084697758009554 },55 "id": "ci",56 "observed": {57 "beta_ci_high": 0.693811019738677,58 "beta_ci_low": 0.515100835556439659 },60 "passed": true,61 "tolerance": {62 "beta_ci_high": {63 "abs": 0.0364 },65 "beta_ci_low": {66 "abs": 0.0367 }68 }69 },70 {71 "description": "n_firms, n_years, n_analysed exact",72 "expected": {73 "n_analysed": 1200,74 "n_firms": 100,75 "n_years": 1276 },77 "id": "counts",78 "observed": {79 "n_analysed": 1200,80 "n_firms": 100,81 "n_years": 1282 },83 "passed": true,84 "tolerance": {85 "n_analysed": {86 "abs": 087 },88 "n_firms": {89 "abs": 090 },91 "n_years": {92 "abs": 093 }94 }95 },96 {97 "description": "Reported cluster SE must exceed reported conventional SE by at least 20% (within-firm serial correlation in x and u)",98 "expected": "se_cluster > 1.20 * se_conventional",99 "id": "se_ordering",100 "observed": {101 "se_cluster": 0.04503292446079461,102 "se_conventional": 0.03257621113089328103 },104 "passed": true,105 "tolerance": null106 },107 {108 "description": "Reported pooled slope must differ from reported FE slope by more than 0.05 (the executor must actually have removed the effects)",109 "expected": "|beta_pooled - beta_fe| > 0.05",110 "id": "pooled_differs",111 "observed": {112 "beta_fe": 0.6044559276475583,113 "beta_pooled": 1.2683992620112563114 },115 "passed": true,116 "tolerance": null117 }118 ],119 "run_id": "RP0010",120 "schema_error": "",121 "schema_valid": true,122 "scientific_success": true,123 "task_id": "F2-dev-01"124}