{
 "critical_violations": [],
 "evaluated_utc": "2026-10-30T04:01:39.156705+00:00",
 "evaluator_version": "F3-dev-01/1.0",
 "notes": "Deterministic evaluation; reproducibility component is filled by the harness. Full-sample re-estimation leaks are NOT detectable on this series (documented in REFERENCE.md); the bound catches smoothing/foresight leaks.",
 "oracle_sha256": "3c7498c1f70346124c8233d46ab30a2eef957ec2e3437b34674287f93b43016a",
 "quality_components": {
  "baseline": 1.0,
  "correctness": 1.0,
  "integrity": 1.0,
  "reporting": 1.0,
  "reproducibility": 1.0
 },
 "quality_score": 1.0,
 "receipt_sha256": "9aeac40c1e2777afd5aec03b96c2888b5c52992c39a2615d88650c82e18ea854",
 "required_criteria": [
  {
   "description": "Naive RMSE and MAE at h=1 equal the exact reference (rel 1e-6); 35 evaluated pairs (target 2025-10 missing)",
   "expected": {
    "mae_naive_h1": 0.09142857142857148,
    "rmse_naive_h1": 0.11710800875382403
   },
   "id": "naive_h1",
   "observed": {
    "mae_naive_h1": 0.09142857142857148,
    "rmse_naive_h1": 0.11710800875382403
   },
   "passed": true,
   "tolerance": {
    "mae_naive_h1": {
     "rel": 1e-06
    },
    "rmse_naive_h1": {
     "rel": 1e-06
    }
   }
  },
  {
   "description": "Naive RMSE and MAE at h=3 equal the exact reference (rel 1e-6)",
   "expected": {
    "mae_naive_h3": 0.12000000000000005,
    "rmse_naive_h3": 0.15856499343441843
   },
   "id": "naive_h3",
   "observed": {
    "mae_naive_h3": 0.12000000000000005,
    "rmse_naive_h3": 0.15856499343441843
   },
   "passed": true,
   "tolerance": {
    "mae_naive_h3": {
     "rel": 1e-06
    },
    "rmse_naive_h3": {
     "rel": 1e-06
    }
   }
  },
  {
   "description": "n_origins = 36, n_evaluated_h1 = 35, n_evaluated_h3 = 35",
   "expected": {
    "n_evaluated_h1": 35,
    "n_evaluated_h3": 35,
    "n_origins": 36
   },
   "id": "counts",
   "observed": {
    "n_evaluated_h1": 35,
    "n_evaluated_h3": 35,
    "n_origins": 36
   },
   "passed": true,
   "tolerance": {
    "n_evaluated_h1": {
     "abs": 0
    },
    "n_evaluated_h3": {
     "abs": 0
    },
    "n_origins": {
     "abs": 0
    }
   }
  },
  {
   "description": "forecasts.csv: 144 rows, target = origin + h, naive forecast = last observation <= origin, actual matches data",
   "expected": {
    "n_rows": 144
   },
   "id": "forecasts_chronology",
   "observed": {
    "actual_mismatches": 0,
    "model_rows": 72,
    "n_rows": 144,
    "naive_rows": 72
   },
   "passed": true,
   "tolerance": null
  },
  {
   "description": "model RMSE/MAE in results.json agree with forecasts.csv (rel 1e-5)",
   "expected": "recomputed from forecasts.csv",
   "id": "model_errors_consistent",
   "observed": {
    "h1": {
     "mae_from_csv": 0.09570395608571439,
     "mae_reported": 0.09570395610285726,
     "n": 35,
     "rmse_from_csv": 0.11990235381546835,
     "rmse_reported": 0.11990235383143451
    },
    "h3": {
     "mae_from_csv": 0.12127537962857148,
     "mae_reported": 0.1212753795742857,
     "n": 35,
     "rmse_from_csv": 0.15976465923570302,
     "rmse_reported": 0.1597646592179836
    }
   },
   "passed": true,
   "tolerance": {
    "rel": 1e-05
   }
  },
  {
   "description": "rel_improvement_rmse_h* = 1 - rmse_model/rmse_naive (abs 1e-6)",
   "expected": null,
   "id": "rel_improvement_consistent",
   "observed": {
    "h1": {
     "expected": -0.02386126369448016,
     "reported": -0.02386126369448016
    },
    "h3": {
     "expected": -0.00756576692989519,
     "reported": -0.00756576692989519
    }
   },
   "passed": true,
   "tolerance": {
    "abs": 1e-06
   }
  },
  {
   "description": "data_issues mentions the missing 2025-10 observation",
   "expected": "mention of 2025-10",
   "id": "data_issue_reported",
   "observed": "[{\"issue\": \"Missing UNRATE value at 2025-10-01 (empty field).\", \"handling\": \"Kept as missing. Naive forecast at origin 2025-10-01 uses 2025-09-01. AR estimation uses complete cases only; for forecasting, the missing level is replaced by the model's own forecast from data before it. (origin, horizon)",
   "passed": true,
   "tolerance": null
  }
 ],
 "run_id": "RP0022",
 "schema_error": "",
 "schema_valid": true,
 "scientific_success": true,
 "task_id": "F3-dev-01"
}