SPB Git

spb/wp29_uqo

Public
3.6 KB · 155 lines json
1{2 "critical_violations": [],3 "evaluated_utc": "2026-10-30T04:18:39.650957+00:00",4 "evaluator_version": "F3-conf-02/1.0",5 "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.",6 "oracle_sha256": "eedec7d03dd243b4193827a51afdac386dae16fd206fe289174b0f9fb316ba82",7 "quality_components": {8  "baseline": 0.5,9  "correctness": 0.42857142857142855,10  "integrity": 1.0,11  "reporting": 1.0,12  "reproducibility": 1.013 },14 "quality_score": 0.7214,15 "receipt_sha256": "328d4695c99ecdce440976dcd32ec06927e082f328b0814921675e2ccc402d5d",16 "required_criteria": [17  {18   "description": "Naive RMSE/MAE at h=1 (last observation of the origin vintage vs first-release actual) exact, rel 1e-6",19   "expected": {20    "mae_naive_h1": 1.6874999999999996,21    "rmse_naive_h1": 2.010286049297462422   },23   "id": "naive_h1",24   "observed": {25    "mae_naive_h1": 1.6875,26    "rmse_naive_h1": 2.010327   },28   "passed": false,29   "tolerance": {30    "mae_naive_h1": {31     "rel": 1e-0632    },33    "rmse_naive_h1": {34     "rel": 1e-0635    }36   }37  },38  {39   "description": "Naive RMSE/MAE at h=2 exact, rel 1e-6",40   "expected": {41    "mae_naive_h2": 1.8124999999999998,42    "rmse_naive_h2": 2.26522625801485943   },44   "id": "naive_h2",45   "observed": {46    "mae_naive_h2": 1.8125,47    "rmse_naive_h2": 2.265248   },49   "passed": false,50   "tolerance": {51    "mae_naive_h2": {52     "rel": 1e-0653    },54    "rmse_naive_h2": {55     "rel": 1e-0656    }57   }58  },59  {60   "description": "mean_abs_revision_h1_targets = mean |current vintage - first release| over the 8 h=1 targets, rel 1e-6",61   "expected": {62    "mean_abs_revision_h1_targets": 0.562500000000000163   },64   "id": "revision",65   "observed": {66    "mean_abs_revision_h1_targets": 0.562567   },68   "passed": true,69   "tolerance": {70    "mean_abs_revision_h1_targets": {71     "rel": 1e-0672    }73   }74  },75  {76   "description": "n_origins = 8",77   "expected": {78    "n_origins": 879   },80   "id": "counts",81   "observed": {82    "n_origins": 883   },84   "passed": true,85   "tolerance": {86    "n_origins": {87     "abs": 088    }89   }90  },91  {92   "description": "forecasts.csv: 32 rows, vintage = origin, targets = last vintage quarter + h, training data = that vintage, naive = last vintage value, actual = first release",93   "expected": {94    "n_rows": 3295   },96   "id": "forecasts_chronology",97   "observed": {98    "actual_mismatches": 0,99    "bad_rows": 0,100    "model_rows": 16,101    "n_rows": 32,102    "naive_rows": 16103   },104   "passed": true,105   "tolerance": null106  },107  {108   "description": "model RMSE/MAE agree with forecasts.csv (rel 1e-5)",109   "expected": null,110   "id": "model_errors_consistent",111   "observed": {112    "h1": {113     "mae_from_csv": 1.2336553749999999,114     "mae_reported": 1.2337,115     "rmse_from_csv": 1.4854812413428937,116     "rmse_reported": 1.4855117    },118    "h2": {119     "mae_from_csv": 1.029787375,120     "mae_reported": 1.0298,121     "rmse_from_csv": 1.4000729511988383,122     "rmse_reported": 1.4001123    }124   },125   "passed": false,126   "tolerance": {127    "rel": 1e-05128   }129  },130  {131   "description": "rel_improvement = 1 - rmse_model/rmse_naive (abs 1e-6)",132   "expected": null,133   "id": "rel_improvement_consistent",134   "observed": {135    "h1": {136     "expected": 0.2610555638461921,137     "reported": 0.2611138    },139    "h2": {140     "expected": 0.38190888221790575,141     "reported": 0.3819142    }143   },144   "passed": false,145   "tolerance": {146    "abs": 1e-06147   }148  }149 ],150 "run_id": "RC0063",151 "schema_error": "",152 "schema_valid": true,153 "scientific_success": false,154 "task_id": "F3-conf-02"155}
Files · 152a55b8fa2830f50fa35e5aed99c0037f713345
Menu

Theme