{
 "critical_violations": [],
 "evaluated_utc": "2026-10-30T05:13:12.569266+00:00",
 "evaluator_version": "F5-conf-02/1.0",
 "notes": "Deterministic evaluation; reproducibility is filled by the harness.",
 "oracle_sha256": "f3f3f9d6197efad30f33fd30b7fd2af232f339da9f1fd4b5b538f298ec4214a5",
 "quality_components": {
  "baseline": 1.0,
  "correctness": 1.0,
  "integrity": 1.0,
  "reporting": 1.0,
  "reproducibility": 1.0
 },
 "quality_score": 1.0,
 "receipt_sha256": "f0c5a1e21e80fc1893ec959eabb215e688e465f77aae272f2b4472a19e49d7b4",
 "required_criteria": [
  {
   "description": "Analytical (Marriott-Pope/Kendall) bias -(1+3rho)/n at the design values, to 1e-6",
   "expected": {
    "bias_analytical": -0.11333333333333334
   },
   "id": "bias_formula",
   "observed": {
    "bias_analytical": -0.11333333333333334
   },
   "passed": true,
   "tolerance": {
    "bias_analytical": {
     "abs": 1e-06
    }
   }
  },
  {
   "description": "Monte Carlo bias within 4 executor-MC SE + 3 reference-MC SE of the large-R reference bias (any seed accepted)",
   "expected": {
    "bias_mc": -0.12282971682534838,
    "rho_hat_mean": 0.6771702831746517
   },
   "id": "bias_mc",
   "observed": {
    "bias_mc": -0.1237101032106388,
    "rho_hat_mean": 0.6762898967893612
   },
   "passed": true,
   "tolerance": {
    "bias_mc": {
     "abs": 0.00445
    },
    "rho_hat_mean": {
     "abs": 0.00445
    }
   }
  },
  {
   "description": "Reported Monte Carlo standard error of the bias within 25% of sd(rho_hat)/sqrt(R)",
   "expected": {
    "bias_mc_se": 0.0010559422224041615
   },
   "id": "bias_mc_se",
   "observed": {
    "bias_mc_se": 0.001052971374380562
   },
   "passed": true,
   "tolerance": {
    "bias_mc_se": {
     "rel": 0.25
    }
   }
  },
  {
   "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)",
   "expected": {
    "discrepancy_se_units": -8.993279452727764
   },
   "id": "discrepancy",
   "observed": {
    "discrepancy_se_units": -9.854750214278015
   },
   "passed": true,
   "tolerance": {
    "discrepancy_se_units": {
     "abs": 3.5
    }
   }
  },
  {
   "description": "n_replications and random_seed equal the design values",
   "expected": {
    "n_replications": 20000,
    "random_seed": 20261029
   },
   "id": "design_followed",
   "observed": {
    "n_replications": 20000,
    "random_seed": 20261029
   },
   "passed": true,
   "tolerance": {
    "n_replications": {
     "abs": 0
    },
    "random_seed": {
     "abs": 0
    }
   }
  },
  {
   "description": "Both the analytical and the Monte Carlo bias are negative (downward bias)",
   "expected": "both < 0",
   "id": "sign",
   "observed": {
    "bias_analytical": -0.11333333333333334,
    "bias_mc": -0.1237101032106388
   },
   "passed": true,
   "tolerance": null
  },
  {
   "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)",
   "expected": "report.md states the asymptotic/approximate nature of the bias formula",
   "id": "asymptotic_nature_stated",
   "observed": true,
   "passed": true,
   "tolerance": null
  }
 ],
 "run_id": "RC0248",
 "schema_error": "",
 "schema_valid": true,
 "scientific_success": true,
 "task_id": "F5-conf-02"
}