1{2 "critical_violations": [],3 "evaluated_utc": "2026-10-30T03:33:10.431734+00:00",4 "evaluator_version": "F2-smoke-01/1.0",5 "notes": "Deterministic evaluation; reproducibility component is filled by the harness.",6 "oracle_sha256": "09c41858f3e534a31189c09ef6d7b2f8f4e4f1a222c073a42c460f42508aeffa",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": "2c18384db157ca5369f7cb72e987ca22624b00ad8b6bb386ff913daddd134016",16 "required_criteria": [17 {18 "description": "OLS slope equals reference to 1e-4",19 "expected": {20 "beta_hat": 0.805080597566637321 },22 "id": "beta_point",23 "observed": {24 "beta_hat": 0.805080597566636925 },26 "passed": true,27 "tolerance": {28 "beta_hat": {29 "abs": 0.000130 }31 }32 },33 {34 "description": "Cluster-robust SE within 8% of CR1 reference (covers CR1/CR0/CR3 conventions and t vs normal)",35 "expected": {36 "se_cluster": 0.0731381344374704137 },38 "id": "se_cluster",39 "observed": {40 "se_cluster": 0.0731381344374704341 },42 "passed": true,43 "tolerance": {44 "se_cluster": {45 "rel": 0.0846 }47 }48 },49 {50 "description": "95% CI bounds within 0.03 of reference (t(G-1) or normal critical values both accepted)",51 "expected": {52 "beta_ci_high": 0.9520571814220071,53 "beta_ci_low": 0.658104013711267554 },55 "id": "ci",56 "observed": {57 "beta_ci_high": 0.9520571814220067,58 "beta_ci_low": 0.65810401371126759 },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_analysed and n_clusters exact",72 "expected": {73 "n_analysed": 2000,74 "n_clusters": 5075 },76 "id": "counts",77 "observed": {78 "n_analysed": 2000,79 "n_clusters": 5080 },81 "passed": true,82 "tolerance": {83 "n_analysed": {84 "abs": 085 },86 "n_clusters": {87 "abs": 088 }89 }90 },91 {92 "description": "Reported cluster SE must exceed reported conventional SE (the design has strong within-cluster correlation)",93 "expected": "se_cluster > se_ols",94 "id": "se_ordering",95 "observed": {96 "se_cluster": 0.07313813443747043,97 "se_ols": 0.0241151695272731198 },99 "passed": true,100 "tolerance": null101 }102 ],103 "run_id": "RD0001",104 "schema_error": "",105 "schema_valid": true,106 "scientific_success": true,107 "task_id": "F2-smoke-01"108}