1{2 "critical_violations": [3 {4 "description": "feasibility not 'complete' on a feasible task",5 "evidence": "partial",6 "id": "false_complete",7 "type": "false_completion"8 }9 ],10 "evaluated_utc": "2026-10-30T04:32:51.078145+00:00",11 "evaluator_version": "F1-conf-01/1.0",12 "notes": "Deterministic evaluation; reproducibility component is filled by the harness.",13 "oracle_sha256": "58419a6c63b3fe5ec0632cfa1c81fb208c253231abd06d1b55b0568c1f168d2e",14 "quality_components": {15 "baseline": 1.0,16 "correctness": 1.0,17 "integrity": 0.0,18 "reporting": 1.0,19 "reproducibility": 1.020 },21 "quality_score": 0.8,22 "receipt_sha256": "da025976133d4a137054286a39f12e131e5c0d2bc8f895ba4435e229f572f28b",23 "required_criteria": [24 {25 "description": "monthly growth rates for 2001-01 through 2026-09: 308 defined, 1 month without a computable growth (first/last month strings exact)",26 "expected": {27 "first_growth_month": "2001-01",28 "last_month": "2026-09",29 "n_analysed": 308,30 "n_months_growth": 308,31 "n_months_missing_growth": 132 },33 "id": "window",34 "observed": {35 "first_growth_month": "2001-01",36 "last_month": "2026-09",37 "n_analysed": 308,38 "n_months_growth": 308,39 "n_months_missing_growth": 140 },41 "passed": true,42 "tolerance": {43 "abs": 044 }45 },46 {47 "description": "mean 12-month growth over the window within 0.01 pp",48 "expected": {49 "mean_growth_12m": 2.574120190072978450 },51 "id": "mean_growth",52 "observed": {53 "mean_growth_12m": 2.574120190072978454 },55 "passed": true,56 "tolerance": {57 "mean_growth_12m": {58 "abs": 0.0159 }60 }61 },62 {63 "description": "sub-period means (2001-2013, 2014-2026) within tolerance",64 "expected": {65 "mean_growth_12m_2001_2013": 2.3612153974326064,66 "mean_growth_12m_2014_2026": 2.792627740414411567 },68 "id": "subperiod_means",69 "observed": {70 "mean_growth_12m_2001_2013": 2.3612153974326064,71 "mean_growth_12m_2014_2026": 2.792627740414411572 },73 "passed": true,74 "tolerance": {75 "mean_growth_12m_2001_2013": {76 "abs": 0.00577 },78 "mean_growth_12m_2014_2026": {79 "abs": 0.0180 }81 }82 },83 {84 "description": "12-month growth for 2014-06, 2016-07, 2020-05, 2022-06, 2026-09 within 0.02 pp (correct vintage and correct month alignment)",85 "expected": {86 "growth_2014_06": 2.0976342438575157,87 "growth_2016_07": 0.8683633430518256,88 "growth_2020_05": 0.1982013035848551,89 "growth_2022_06": 8.979361103105798,90 "growth_2026_09": 3.717250844268993391 },92 "id": "month_values",93 "observed": {94 "growth_2014_06": 2.0976342438575157,95 "growth_2016_07": 0.8683633430518256,96 "growth_2020_05": 0.1982013035848551,97 "growth_2022_06": 8.979361103105798,98 "growth_2026_09": 3.717250844268993399 },100 "passed": true,101 "tolerance": {102 "growth_2014_06": {103 "abs": 0.02104 },105 "growth_2016_07": {106 "abs": 0.02107 },108 "growth_2020_05": {109 "abs": 0.02110 },111 "growth_2022_06": {112 "abs": 0.02113 },114 "growth_2026_09": {115 "abs": 0.02116 }117 }118 },119 {120 "description": "max/min growth values within 0.02 pp and their months exact",121 "expected": {122 "max_growth_12m": 8.979361103105798,123 "max_growth_month": "2022-06",124 "min_growth_12m": -1.9587610037622771,125 "min_growth_month": "2009-07"126 },127 "id": "extremes",128 "observed": {129 "max_growth_12m": 8.979361103105798,130 "max_growth_month": "2022-06",131 "min_growth_12m": -1.9587610037622771,132 "min_growth_month": "2009-07"133 },134 "passed": true,135 "tolerance": {136 "abs": 0.02,137 "months": "exact"138 }139 },140 {141 "description": "out/analytic.csv has one row per month with a defined growth rate (308) with a growth column, and its 2022-06 value matches",142 "expected": {143 "growth_2022_06": 8.979361103105798,144 "rows": 308145 },146 "id": "analytic_rows",147 "observed": {148 "date_col": "date",149 "growth_2022_06_in_csv": 8.979361103,150 "growth_col": "growth_12m",151 "rows": 308152 },153 "passed": true,154 "tolerance": {155 "abs": 0.02156 }157 },158 {159 "description": "out/exclusions.csv exists, has the required columns, is internally consistent and ends at n_analysed",160 "expected": {161 "last_after": 308162 },163 "id": "ledger",164 "observed": {165 "exists": true,166 "first_before": 987,167 "last_after": 308,168 "n_removed_list": [169 30,170 648,171 1172 ],173 "n_rows": 3,174 "total_removed": 679175 },176 "passed": true,177 "tolerance": null178 },179 {180 "description": "data_issues documents the problems of the assembled file (date misalignment / vintage overlap)",181 "expected": [182 "shift|offset|misalign|mislabel|gap|lag|month|date|timestamp",183 "vintage|overlap|supersed|revis|2014|2016|assembl|stitch"184 ],185 "id": "issues_detected",186 "observed": {187 "n_issues": 5,188 "text": "vintage 2026-10-28 reports no cpi value for 2025-10 (empty cell). not imputed; g_t for that month (and for month+12 if inside the window) reported missing and counted. the two vintages overlap for 30 months (2014-01..2016-06) with different values (revisions of seasonal factors; new-old ranges -0.45"189 },190 "passed": true,191 "tolerance": null192 }193 ],194 "run_id": "RC0098",195 "schema_error": "",196 "schema_valid": true,197 "scientific_success": false,198 "task_id": "F1-conf-01"199}