1{2 "critical_violations": [],3 "evaluated_utc": "2026-10-30T04:19:19.272138+00:00",4 "evaluator_version": "F2-conf-03/1.0",5 "notes": "Deterministic evaluation; reproducibility component is filled by the harness.",6 "oracle_sha256": "0d666b81610441d8b771d554984e8e665d3a308abb89683967ed394d98e0c9e1",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": "33110b6b3e0b9ab9d79ecd59bd7853bd5248f2d69d95786dfd34828f9ac2ade0",16 "required_criteria": [17 {18 "description": "Empirical coverage of the conventional 95% CI within 3 binomial MC SEs (R=2000) of the true coverage",19 "expected": {20 "coverage_conventional": 0.849917521 },22 "id": "cov_conv",23 "observed": {24 "coverage_conventional": 0.84425 },26 "passed": true,27 "tolerance": {28 "coverage_conventional": {29 "abs": 0.02565262451053248330 }31 }32 },33 {34 "description": "Empirical coverage of the HC1 95% CI within 3 binomial MC SEs (R=2000) of the true coverage",35 "expected": {36 "coverage_hc1": 0.914377537 },38 "id": "cov_hc1",39 "observed": {40 "coverage_hc1": 0.90241 },42 "passed": true,43 "tolerance": {44 "coverage_hc1": {45 "abs": 0.02009717935322454746 }47 }48 },49 {50 "description": "Exact SD of beta_hat under the design (analytical sandwich) to 1e-5 relative",51 "expected": {52 "sd_beta_exact": 0.267980592830283353 },54 "id": "sd_exact",55 "observed": {56 "sd_beta_exact": 0.2679805928302833657 },58 "passed": true,59 "tolerance": {60 "sd_beta_exact": {61 "rel": 1e-0562 }63 }64 },65 {66 "description": "Monte Carlo SD of beta_hat within 3 SEs of the sample SD at R=2000",67 "expected": {68 "sd_beta_mc": 0.2672834676978495569 },70 "id": "sd_mc",71 "observed": {72 "sd_beta_mc": 0.269647370830912673 },74 "passed": true,75 "tolerance": {76 "sd_beta_mc": {77 "abs": 0.01357486408705008778 }79 }80 },81 {82 "description": "Mean conventional SE over replications within 3 MC SEs",83 "expected": {84 "mean_se_conventional": 0.190661427669425985 },86 "id": "mean_se",87 "observed": {88 "mean_se_conventional": 0.190262310121526689 },90 "passed": true,91 "tolerance": {92 "mean_se_conventional": {93 "abs": 0.0022755354564968694 }95 }96 },97 {98 "description": "n_replications = 2000 and n_obs_per_replication = 30",99 "expected": {100 "n_obs_per_replication": 30,101 "n_replications": 2000102 },103 "id": "counts",104 "observed": {105 "n_obs_per_replication": 30,106 "n_replications": 2000107 },108 "passed": true,109 "tolerance": {110 "n_obs_per_replication": {111 "abs": 0112 },113 "n_replications": {114 "abs": 0115 }116 }117 },118 {119 "description": "conventional_ci_undercovers must be true (true coverage is far below 0.95)",120 "expected": true,121 "id": "undercover_flag",122 "observed": true,123 "passed": true,124 "tolerance": null125 },126 {127 "description": "random_seed is a non-null integer (the simulation must be seeded and reproducible)",128 "expected": "integer",129 "id": "seed_reported",130 "observed": 20261030,131 "passed": true,132 "tolerance": null133 }134 ],135 "run_id": "RC0058",136 "schema_error": "",137 "schema_valid": true,138 "scientific_success": true,139 "task_id": "F2-conf-03"140}