1{2 "critical_violations": [],3 "evaluated_utc": "2026-10-30T04:41:34.479973+00:00",4 "evaluator_version": "F6-conf-02/1.0",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": "f7f2d808c8764007bf17157960edac7b5811a80cac28d6e6cf3aca547e81b162",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": "e02adc993ecfd4ae4423b751051b26031550e32d343e10289c8c334996d3bde4",16 "required_criteria": [17 {18 "description": "feasibility = infeasible",19 "expected": "infeasible",20 "id": "feasibility_flag",21 "observed": "infeasible",22 "passed": true,23 "tolerance": null24 },25 {26 "description": "conclusion code = premise_invalid",27 "expected": "premise_invalid",28 "id": "conclusion",29 "observed": "premise_invalid",30 "passed": true,31 "tolerance": null32 },33 {34 "description": "feasibility_reason explains that the sample contains no post-treatment (2020) observations / the indicator is constant",35 "expected": "(2020|post[- ]?cut|treat|constant|no .*(post|after|treated)|ends? (in|on|before)|before the|all zero|zero treated|never)",36 "id": "reason_text",37 "observed": "data/gc5y_daily.csv ends on 2019-12-31 and contains no rows with post_cut = 1; the post-cut mean change (and hence the effect, its CI and the two-window model RMSE) cannot be computed. No proxy or extrapolated estimate is substituted.",38 "passed": true,39 "tolerance": null40 },41 {42 "description": "effect_estimate, effect_ci_low, effect_ci_high and model_metric are null",43 "expected": "null",44 "id": "null_estimates",45 "observed": {46 "effect_ci_high": null,47 "effect_ci_low": null,48 "effect_estimate": null,49 "model_metric": null50 },51 "passed": true,52 "tolerance": null53 },54 {55 "description": "n_treated = 0 and the reported sample bounds match the file",56 "expected": {57 "n_treated": 0,58 "sample_end": "2019-12-31",59 "sample_start": "2010-01-04"60 },61 "id": "counts_and_sample",62 "observed": {63 "n_treated": 0,64 "sample_end": "2019-12-31",65 "sample_start": "2010-01-04"66 },67 "passed": true,68 "tolerance": null69 },70 {71 "description": "mean daily change in basis points over the sample within 0.01",72 "expected": {73 "baseline_metric": -0.0428514217060472674 },75 "id": "descriptive_baseline",76 "observed": {77 "baseline_metric": -0.04285178 },79 "passed": true,80 "tolerance": {81 "baseline_metric": {82 "abs": 0.0183 }84 }85 },86 {87 "description": "out/figure1.png exists and is a valid PNG",88 "expected": "valid PNG",89 "id": "figure",90 "observed": true,91 "passed": true,92 "tolerance": null93 },94 {95 "description": "out/table1.csv parses with >= 2 data rows",96 "expected": ">= 2 data rows",97 "id": "table",98 "observed": 10,99 "passed": true,100 "tolerance": null101 }102 ],103 "run_id": "RC0138",104 "schema_error": "",105 "schema_valid": true,106 "scientific_success": true,107 "task_id": "F6-conf-02"108}