1{2 "critical_violations": [],3 "evaluated_utc": "2026-10-30T05:13:54.536676+00:00",4 "evaluator_version": "F5-conf-02/1.0",5 "notes": "Deterministic evaluation; reproducibility is filled by the harness.",6 "oracle_sha256": "f3f3f9d6197efad30f33fd30b7fd2af232f339da9f1fd4b5b538f298ec4214a5",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": "0625f7ae5e232d128fb6cc0694867686018f3350ae4a44b9260d1ad4004dd114",16 "required_criteria": [17 {18 "description": "Analytical (Marriott-Pope/Kendall) bias -(1+3rho)/n at the design values, to 1e-6",19 "expected": {20 "bias_analytical": -0.1133333333333333421 },22 "id": "bias_formula",23 "observed": {24 "bias_analytical": -0.1133333333333333425 },26 "passed": true,27 "tolerance": {28 "bias_analytical": {29 "abs": 1e-0630 }31 }32 },33 {34 "description": "Monte Carlo bias within 4 executor-MC SE + 3 reference-MC SE of the large-R reference bias (any seed accepted)",35 "expected": {36 "bias_mc": -0.12282971682534838,37 "rho_hat_mean": 0.677170283174651738 },39 "id": "bias_mc",40 "observed": {41 "bias_mc": -0.1237101032106388,42 "rho_hat_mean": 0.676289896789361243 },44 "passed": true,45 "tolerance": {46 "bias_mc": {47 "abs": 0.0044548 },49 "rho_hat_mean": {50 "abs": 0.0044551 }52 }53 },54 {55 "description": "Reported Monte Carlo standard error of the bias within 25% of sd(rho_hat)/sqrt(R)",56 "expected": {57 "bias_mc_se": 0.001055942222404161558 },59 "id": "bias_mc_se",60 "observed": {61 "bias_mc_se": 0.00105297137438056262 },63 "passed": true,64 "tolerance": {65 "bias_mc_se": {66 "rel": 0.2567 }68 }69 },70 {71 "description": "Reported discrepancy (bias_mc - bias_analytical)/bias_mc_se within 3.5 of the reference (-8.6; the formula is only first-order accurate at n=30, rho=0.8)",72 "expected": {73 "discrepancy_se_units": -8.99327945272776474 },75 "id": "discrepancy",76 "observed": {77 "discrepancy_se_units": -9.85475021427801578 },79 "passed": true,80 "tolerance": {81 "discrepancy_se_units": {82 "abs": 3.583 }84 }85 },86 {87 "description": "n_replications and random_seed equal the design values",88 "expected": {89 "n_replications": 20000,90 "random_seed": 2026102991 },92 "id": "design_followed",93 "observed": {94 "n_replications": 20000,95 "random_seed": 2026102996 },97 "passed": true,98 "tolerance": {99 "n_replications": {100 "abs": 0101 },102 "random_seed": {103 "abs": 0104 }105 }106 },107 {108 "description": "Both the analytical and the Monte Carlo bias are negative (downward bias)",109 "expected": "both < 0",110 "id": "sign",111 "observed": {112 "bias_analytical": -0.11333333333333334,113 "bias_mc": -0.1237101032106388114 },115 "passed": true,116 "tolerance": null117 },118 {119 "description": "report.md states that the formula is an asymptotic / order-1/n approximation (regex: asymptot|large[- ]sample|large[- ]n|O\\(1/n|order 1/n|first[- ]order|higher[- ]order|to order|approximat)",120 "expected": "report.md states the asymptotic/approximate nature of the bias formula",121 "id": "asymptotic_nature_stated",122 "observed": true,123 "passed": true,124 "tolerance": null125 }126 ],127 "run_id": "RC0245",128 "schema_error": "",129 "schema_valid": true,130 "scientific_success": true,131 "task_id": "F5-conf-02"132}