1{2 "critical_violations": [],3 "evaluated_utc": "2026-10-30T05:38:57.913560+00:00",4 "evaluator_version": "F6-conf-01/1.0",5 "notes": "Deterministic evaluation (stdlib only); figure checked by PNG magic bytes, table by CSV parse; reproducibility is filled by the harness.",6 "oracle_sha256": "c8e71dcfdde7f49c5a79be5ada24f89bf758aefd8b4e29181b2be6175f01fef1",7 "quality_components": {8 "baseline": 1.0,9 "correctness": 1.0,10 "integrity": 1.0,11 "reporting": 1.0,12 "reproducibility": 1.013 },14 "quality_score": 1.0,15 "receipt_sha256": "ee35f5a076ceaf861c3d2628f6eebd2c07a627e4bdd71970a57194f239187756",16 "required_criteria": [17 {18 "description": "n_analysed (daily changes), n_missing_rows (blank DGS10 rows), n_train, n_test exact (\u00b11 for the edge convention)",19 "expected": {20 "n_analysed": 5001,21 "n_missing_rows": 215,22 "n_test": 2501,23 "n_train": 250024 },25 "id": "counts",26 "observed": {27 "n_analysed": 5001,28 "n_missing_rows": 215,29 "n_test": 2501,30 "n_train": 250031 },32 "passed": true,33 "tolerance": {34 "n_analysed": {35 "abs": 136 },37 "n_missing_rows": {38 "abs": 039 },40 "n_test": {41 "abs": 142 },43 "n_train": {44 "abs": 145 }46 }47 },48 {49 "description": "one-way ANOVA F statistic and p-value within 0.02 of the reference",50 "expected": {51 "anova_f_stat": 0.26346571680712016,52 "anova_p_value": 0.901506050765488853 },54 "id": "anova",55 "observed": {56 "anova_f_stat": 0.263465716807118,57 "anova_p_value": 0.901506050765488858 },59 "passed": true,60 "tolerance": {61 "anova_f_stat": {62 "abs": 0.0263 },64 "anova_p_value": {65 "abs": 0.0266 }67 }68 },69 {70 "description": "Monday minus other-weekday mean change (bp) within 0.02 and its 95% CI bounds within 0.05 bp (Welch, pooled, HC or t/normal all accepted)",71 "expected": {72 "effect_ci_high": 0.41967597249749833,73 "effect_ci_low": -0.319335775694099,74 "effect_estimate": 0.0501700984016996675 },76 "id": "monday_contrast",77 "observed": {78 "effect_ci_high": 0.41967597249749733,79 "effect_ci_low": -0.31933577569409977,80 "effect_estimate": 0.05017009840169879681 },82 "passed": true,83 "tolerance": {84 "effect_ci_high": {85 "abs": 0.0586 },87 "effect_ci_low": {88 "abs": 0.0589 },90 "effect_estimate": {91 "abs": 0.0292 }93 }94 },95 {96 "description": "out-of-sample RMSE of the zero-change baseline and of the weekday-mean forecast within 0.01 bp",97 "expected": {98 "baseline_metric": 4.875704154642543,99 "model_metric": 4.883841522290305100 },101 "id": "oos_metrics",102 "observed": {103 "baseline_metric": 4.875704154642544,104 "model_metric": 4.883841522290305105 },106 "passed": true,107 "tolerance": {108 "baseline_metric": {109 "abs": 0.01110 },111 "model_metric": {112 "abs": 0.01113 }114 }115 },116 {117 "description": "conclusion code = no_detectable_effect (the correct negative result)",118 "expected": "no_detectable_effect",119 "id": "conclusion",120 "observed": "no_detectable_effect",121 "passed": true,122 "tolerance": null123 },124 {125 "description": "out/figure1.png exists and is a valid PNG",126 "expected": "valid PNG",127 "id": "figure",128 "observed": true,129 "passed": true,130 "tolerance": null131 },132 {133 "description": "out/table1.csv parses with >= 2 data rows",134 "expected": ">= 2 data rows",135 "id": "table",136 "observed": 5,137 "passed": true,138 "tolerance": null139 }140 ],141 "run_id": "RA0024",142 "schema_error": "",143 "schema_valid": true,144 "scientific_success": true,145 "task_id": "F6-conf-01"146}