{
 "critical_violations": [],
 "evaluated_utc": "2026-10-30T04:23:35.770362+00:00",
 "evaluator_version": "F3-conf-02/1.0",
 "notes": "Deterministic evaluation; reproducibility filled by the harness. Vintage discipline is verified from train_last_date/train_last_value/n_train and the naive rows.",
 "oracle_sha256": "eedec7d03dd243b4193827a51afdac386dae16fd206fe289174b0f9fb316ba82",
 "quality_components": {
  "baseline": 1.0,
  "correctness": 1.0,
  "integrity": 1.0,
  "reporting": 1.0,
  "reproducibility": 1.0
 },
 "quality_score": 1.0,
 "receipt_sha256": "3d3ac20a08cebbcb032948087567a45044bc7278826c74c17f82f16c36102d04",
 "required_criteria": [
  {
   "description": "Naive RMSE/MAE at h=1 (last observation of the origin vintage vs first-release actual) exact, rel 1e-6",
   "expected": {
    "mae_naive_h1": 1.6874999999999996,
    "rmse_naive_h1": 2.0102860492974624
   },
   "id": "naive_h1",
   "observed": {
    "mae_naive_h1": 1.6874999999999996,
    "rmse_naive_h1": 2.0102860492974624
   },
   "passed": true,
   "tolerance": {
    "mae_naive_h1": {
     "rel": 1e-06
    },
    "rmse_naive_h1": {
     "rel": 1e-06
    }
   }
  },
  {
   "description": "Naive RMSE/MAE at h=2 exact, rel 1e-6",
   "expected": {
    "mae_naive_h2": 1.8124999999999998,
    "rmse_naive_h2": 2.265226258014859
   },
   "id": "naive_h2",
   "observed": {
    "mae_naive_h2": 1.8124999999999998,
    "rmse_naive_h2": 2.265226258014859
   },
   "passed": true,
   "tolerance": {
    "mae_naive_h2": {
     "rel": 1e-06
    },
    "rmse_naive_h2": {
     "rel": 1e-06
    }
   }
  },
  {
   "description": "mean_abs_revision_h1_targets = mean |current vintage - first release| over the 8 h=1 targets, rel 1e-6",
   "expected": {
    "mean_abs_revision_h1_targets": 0.5625000000000001
   },
   "id": "revision",
   "observed": {
    "mean_abs_revision_h1_targets": 0.5625000000000001
   },
   "passed": true,
   "tolerance": {
    "mean_abs_revision_h1_targets": {
     "rel": 1e-06
    }
   }
  },
  {
   "description": "n_origins = 8",
   "expected": {
    "n_origins": 8
   },
   "id": "counts",
   "observed": {
    "n_origins": 8
   },
   "passed": true,
   "tolerance": {
    "n_origins": {
     "abs": 0
    }
   }
  },
  {
   "description": "forecasts.csv: 32 rows, vintage = origin, targets = last vintage quarter + h, training data = that vintage, naive = last vintage value, actual = first release",
   "expected": {
    "n_rows": 32
   },
   "id": "forecasts_chronology",
   "observed": {
    "actual_mismatches": 0,
    "bad_rows": 0,
    "model_rows": 16,
    "n_rows": 32,
    "naive_rows": 16
   },
   "passed": true,
   "tolerance": null
  },
  {
   "description": "model RMSE/MAE agree with forecasts.csv (rel 1e-5)",
   "expected": null,
   "id": "model_errors_consistent",
   "observed": {
    "h1": {
     "mae_from_csv": 1.23365530925,
     "mae_reported": 1.2336553091736995,
     "rmse_from_csv": 1.4854810378040033,
     "rmse_reported": 1.4854810377410896
    },
    "h2": {
     "mae_from_csv": 1.0297873006249998,
     "mae_reported": 1.0297873006202798,
     "rmse_from_csv": 1.4000730375905803,
     "rmse_reported": 1.4000730374931272
    }
   },
   "passed": true,
   "tolerance": {
    "rel": 1e-05
   }
  },
  {
   "description": "rel_improvement = 1 - rmse_model/rmse_naive (abs 1e-6)",
   "expected": null,
   "id": "rel_improvement_consistent",
   "observed": {
    "h1": {
     "expected": 0.26105986844000484,
     "reported": 0.26105986844000484
    },
    "h2": {
     "expected": 0.38192794978454503,
     "reported": 0.38192794978454503
    }
   },
   "passed": true,
   "tolerance": {
    "abs": 1e-06
   }
  }
 ],
 "run_id": "RC0070",
 "schema_error": "",
 "schema_valid": true,
 "scientific_success": true,
 "task_id": "F3-conf-02"
}