{
 "critical_violations": [],
 "evaluated_utc": "2026-10-30T04:16:32.104127+00:00",
 "evaluator_version": "F2-conf-03/1.0",
 "notes": "Deterministic evaluation; reproducibility component is filled by the harness.",
 "oracle_sha256": "0d666b81610441d8b771d554984e8e665d3a308abb89683967ed394d98e0c9e1",
 "quality_components": {
  "baseline": 1.0,
  "correctness": 1.0,
  "integrity": 1.0,
  "reporting": 1.0,
  "reproducibility": 1.0
 },
 "quality_score": 1.0,
 "receipt_sha256": "be49e0be49504f8899c5d6177d4c9863309e601d29ac67b3caf43af2705db187",
 "required_criteria": [
  {
   "description": "Empirical coverage of the conventional 95% CI within 3 binomial MC SEs (R=2000) of the true coverage",
   "expected": {
    "coverage_conventional": 0.8499175
   },
   "id": "cov_conv",
   "observed": {
    "coverage_conventional": 0.844
   },
   "passed": true,
   "tolerance": {
    "coverage_conventional": {
     "abs": 0.025652624510532483
    }
   }
  },
  {
   "description": "Empirical coverage of the HC1 95% CI within 3 binomial MC SEs (R=2000) of the true coverage",
   "expected": {
    "coverage_hc1": 0.9143775
   },
   "id": "cov_hc1",
   "observed": {
    "coverage_hc1": 0.902
   },
   "passed": true,
   "tolerance": {
    "coverage_hc1": {
     "abs": 0.020097179353224547
    }
   }
  },
  {
   "description": "Exact SD of beta_hat under the design (analytical sandwich) to 1e-5 relative",
   "expected": {
    "sd_beta_exact": 0.2679805928302833
   },
   "id": "sd_exact",
   "observed": {
    "sd_beta_exact": 0.2679805928302833
   },
   "passed": true,
   "tolerance": {
    "sd_beta_exact": {
     "rel": 1e-05
    }
   }
  },
  {
   "description": "Monte Carlo SD of beta_hat within 3 SEs of the sample SD at R=2000",
   "expected": {
    "sd_beta_mc": 0.26728346769784955
   },
   "id": "sd_mc",
   "observed": {
    "sd_beta_mc": 0.2696473708309126
   },
   "passed": true,
   "tolerance": {
    "sd_beta_mc": {
     "abs": 0.013574864087050087
    }
   }
  },
  {
   "description": "Mean conventional SE over replications within 3 MC SEs",
   "expected": {
    "mean_se_conventional": 0.1906614276694259
   },
   "id": "mean_se",
   "observed": {
    "mean_se_conventional": 0.1902623101215266
   },
   "passed": true,
   "tolerance": {
    "mean_se_conventional": {
     "abs": 0.00227553545649686
    }
   }
  },
  {
   "description": "n_replications = 2000 and n_obs_per_replication = 30",
   "expected": {
    "n_obs_per_replication": 30,
    "n_replications": 2000
   },
   "id": "counts",
   "observed": {
    "n_obs_per_replication": 30,
    "n_replications": 2000
   },
   "passed": true,
   "tolerance": {
    "n_obs_per_replication": {
     "abs": 0
    },
    "n_replications": {
     "abs": 0
    }
   }
  },
  {
   "description": "conventional_ci_undercovers must be true (true coverage is far below 0.95)",
   "expected": true,
   "id": "undercover_flag",
   "observed": true,
   "passed": true,
   "tolerance": null
  },
  {
   "description": "random_seed is a non-null integer (the simulation must be seeded and reproducible)",
   "expected": "integer",
   "id": "seed_reported",
   "observed": 20261030,
   "passed": true,
   "tolerance": null
  }
 ],
 "run_id": "RC0055",
 "schema_error": "",
 "schema_valid": true,
 "scientific_success": true,
 "task_id": "F2-conf-03"
}