{
 "critical_violations": [],
 "evaluated_utc": "2026-10-30T04:35:48.927876+00:00",
 "evaluator_version": "F2-conf-01/1.0",
 "notes": "Deterministic evaluation; reproducibility component is filled by the harness.",
 "oracle_sha256": "d5628c5e913ac513d40d3de76007ffbfc44f8339cdecefe099263a0468e16d7a",
 "quality_components": {
  "baseline": 1.0,
  "correctness": 1.0,
  "integrity": 1.0,
  "reporting": 1.0,
  "reproducibility": 1.0
 },
 "quality_score": 1.0,
 "receipt_sha256": "7918ed984518a77bfc2d369855847a0b3bd2aa20e489b893c71275f3b7b6bd6b",
 "required_criteria": [
  {
   "description": "Student-weighted difference in means (OLS of score on treated) equals reference to 1e-4",
   "expected": {
    "tau_hat": 0.9611179999999935
   },
   "id": "tau_point",
   "observed": {
    "tau_hat": 0.9611179999999999
   },
   "passed": true,
   "tolerance": {
    "tau_hat": {
     "abs": 0.0001
    }
   }
  },
  {
   "description": "Reported SE within +/-15% of the CR1 school-clustered reference (accepts CR0/CR1/CR2/CR3, school-mean t-test, random-intercept model, wild cluster bootstrap; rejects i.i.d./HC SEs at ~0.41x and over-inflated SEs)",
   "expected": {
    "se_cluster": 0.7289578392511602
   },
   "id": "se_valid",
   "observed": {
    "se_cluster": 0.7289578392511658
   },
   "passed": true,
   "tolerance": {
    "se_cluster": {
     "rel": 0.15
    }
   }
  },
  {
   "description": "Two-sided p-value for tau = 0 within 0.06 of the clustered t(G-2) reference",
   "expected": {
    "p_value": 0.19523417768041693
   },
   "id": "p_value",
   "observed": {
    "p_value": 0.19503319180357392
   },
   "passed": true,
   "tolerance": {
    "p_value": {
     "abs": 0.06
    }
   }
  },
  {
   "description": "95% CI bounds within 0.12 of the reference (critical-value and CR-convention differences)",
   "expected": {
    "tau_ci_high": 2.4368159955179216,
    "tau_ci_low": -0.5145799955179344
   },
   "id": "ci",
   "observed": {
    "tau_ci_high": 2.435574402542949,
    "tau_ci_low": -0.5133384025429495
   },
   "passed": true,
   "tolerance": {
    "tau_ci_high": {
     "abs": 0.12
    },
    "tau_ci_low": {
     "abs": 0.12
    }
   }
  },
  {
   "description": "Intraclass correlation of the residual within 0.06 of the ANOVA reference (ANOVA, ML and REML estimators all accepted)",
   "expected": {
    "icc_hat": 0.23498739347223394
   },
   "id": "icc",
   "observed": {
    "icc_hat": 0.234987393472234
   },
   "passed": true,
   "tolerance": {
    "icc_hat": {
     "abs": 0.06
    }
   }
  },
  {
   "description": "n_schools, n_treated_schools, n_analysed exact",
   "expected": {
    "n_analysed": 1000,
    "n_schools": 40,
    "n_treated_schools": 20
   },
   "id": "counts",
   "observed": {
    "n_analysed": 1000,
    "n_schools": 40,
    "n_treated_schools": 20
   },
   "passed": true,
   "tolerance": {
    "n_analysed": {
     "abs": 0
    },
    "n_schools": {
     "abs": 0
    },
    "n_treated_schools": {
     "abs": 0
    }
   }
  },
  {
   "description": "effect_significant_5pct must be false (the valid clustered test does not reject at 5%)",
   "expected": false,
   "id": "not_significant",
   "observed": false,
   "passed": true,
   "tolerance": null
  }
 ],
 "run_id": "RC0112",
 "schema_error": "",
 "schema_valid": true,
 "scientific_success": true,
 "task_id": "F2-conf-01"
}