{
 "critical_violations": [],
 "evaluated_utc": "2026-10-30T03:33:59.459225+00:00",
 "evaluator_version": "F2-smoke-01/1.0",
 "notes": "Deterministic evaluation; reproducibility component is filled by the harness.",
 "oracle_sha256": "09c41858f3e534a31189c09ef6d7b2f8f4e4f1a222c073a42c460f42508aeffa",
 "quality_components": {
  "baseline": 1.0,
  "correctness": 1.0,
  "integrity": 1.0,
  "reporting": 1.0,
  "reproducibility": 1.0
 },
 "quality_score": 1.0,
 "receipt_sha256": "188b47e9cec1113f59092b72944a4f1246220cbd235c87a02986990615c951b8",
 "required_criteria": [
  {
   "description": "OLS slope equals reference to 1e-4",
   "expected": {
    "beta_hat": 0.8050805975666373
   },
   "id": "beta_point",
   "observed": {
    "beta_hat": 0.8050805975666369
   },
   "passed": true,
   "tolerance": {
    "beta_hat": {
     "abs": 0.0001
    }
   }
  },
  {
   "description": "Cluster-robust SE within 8% of CR1 reference (covers CR1/CR0/CR3 conventions and t vs normal)",
   "expected": {
    "se_cluster": 0.07313813443747041
   },
   "id": "se_cluster",
   "observed": {
    "se_cluster": 0.07313813443747041
   },
   "passed": true,
   "tolerance": {
    "se_cluster": {
     "rel": 0.08
    }
   }
  },
  {
   "description": "95% CI bounds within 0.03 of reference (t(G-1) or normal critical values both accepted)",
   "expected": {
    "beta_ci_high": 0.9520571814220071,
    "beta_ci_low": 0.6581040137112675
   },
   "id": "ci",
   "observed": {
    "beta_ci_high": 0.9520571814220067,
    "beta_ci_low": 0.658104013711267
   },
   "passed": true,
   "tolerance": {
    "beta_ci_high": {
     "abs": 0.03
    },
    "beta_ci_low": {
     "abs": 0.03
    }
   }
  },
  {
   "description": "n_analysed and n_clusters exact",
   "expected": {
    "n_analysed": 2000,
    "n_clusters": 50
   },
   "id": "counts",
   "observed": {
    "n_analysed": 2000,
    "n_clusters": 50
   },
   "passed": true,
   "tolerance": {
    "n_analysed": {
     "abs": 0
    },
    "n_clusters": {
     "abs": 0
    }
   }
  },
  {
   "description": "Reported cluster SE must exceed reported conventional SE (the design has strong within-cluster correlation)",
   "expected": "se_cluster > se_ols",
   "id": "se_ordering",
   "observed": {
    "se_cluster": 0.07313813443747041,
    "se_ols": 0.02411516952727311
   },
   "passed": true,
   "tolerance": null
  }
 ],
 "run_id": "RD0004",
 "schema_error": "",
 "schema_valid": true,
 "scientific_success": true,
 "task_id": "F2-smoke-01"
}