1{2 "critical_violations": [],3 "evaluated_utc": "2026-10-30T05:10:38.467327+00:00",4 "evaluator_version": "F4-engine/1.0/F4-conf-03/1.0",5 "notes": "Deterministic oracle-driven evaluation (designer-extracted references with locators). Reproducibility is filled by the harness.",6 "oracle_sha256": "23998878a286573a4841e0b223c9efb51cf0be6bfb90da9d7fe40bc4f9200bb2",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": "19875ebb2d745895426bf7bd3f8c4da587ef49cd42d3b65a60852767026f4c67",16 "required_criteria": [17 {18 "description": "E1: 100(exp(-0.431)-1) = -35.0% (Table 6 also prints -35.0%); tolerance 0.3 rejects -43.1 (log points read as percent)",19 "expected": {20 "harmonised.E1.value": -35.0141089225250521 },22 "id": "E1_value",23 "observed": {24 "harmonised.E1.value": -35.0125 },26 "passed": true,27 "tolerance": {28 "harmonised.E1.value": {29 "abs": 0.330 }31 }32 },33 {34 "description": "E2: 1.47 pp / 75.0% control mean = +1.96%; tolerance 0.06 accepts the treatment-mean denominator (1.955) and rejects 1.47",35 "expected": {36 "harmonised.E2.value": 1.9637 },38 "id": "E2_value",39 "observed": {40 "harmonised.E2.value": 1.9641 },42 "passed": true,43 "tolerance": {44 "harmonised.E2.value": {45 "abs": 0.0646 }47 }48 },49 {50 "description": "E3: -0.388 \u00d7 4.7% = -1.82%; tolerance 0.12 rejects -0.388, -38.8 and -1.55 (using 'about 4%' from the note instead of the printed 0.047)",51 "expected": {52 "harmonised.E3.value": -1.823600000000000353 },54 "id": "E3_value",55 "observed": {56 "harmonised.E3.value": -1.823657 },58 "passed": true,59 "tolerance": {60 "harmonised.E3.value": {61 "abs": 0.1262 }63 }64 },65 {66 "description": "E4: absolute change per 100,000 requires the counterfactual fatal hospitalisation rate, which the extract does not print \u2192 value null",67 "expected": {68 "harmonised.E4.value": null69 },70 "id": "E4_null",71 "observed": {72 "harmonised.E4.value": null73 },74 "passed": true,75 "tolerance": null76 },77 {78 "description": "E4 flagged harmonisable = false",79 "expected": {80 "harmonised.E4.harmonisable": false81 },82 "id": "E4_flag",83 "observed": {84 "harmonised.E4.harmonisable": false85 },86 "passed": true,87 "tolerance": null88 },89 {90 "description": "E4 missing_quantity names a baseline/counterfactual/pre-treatment level or rate",91 "expected": {92 "harmonised.E4.missing_quantity": null93 },94 "id": "E4_missing",95 "observed": {96 "harmonised.E4.missing_quantity": "counterfactual (or pre-treatment / control-group mean) level of the fatal drug-related hospitalisation rate per 100,000 inhabitants per year for the treated 5 km regions"97 },98 "passed": true,99 "tolerance": null100 },101 {102 "description": "E5: -0.0962 \u00d7 100 = -9.62 percentage points; tolerance 0.01 rejects -0.0962 and -36.85",103 "expected": {104 "harmonised.E5.value": -9.62105 },106 "id": "E5_value",107 "observed": {108 "harmonised.E5.value": -9.62109 },110 "passed": true,111 "tolerance": {112 "harmonised.E5.value": {113 "abs": 0.01114 }115 }116 },117 {118 "description": "E1, E2, E3, E5 flagged harmonisable = true",119 "expected": {120 "harmonised.E1.harmonisable": true,121 "harmonised.E2.harmonisable": true,122 "harmonised.E3.harmonisable": true,123 "harmonised.E5.harmonisable": true124 },125 "id": "flags_true",126 "observed": {127 "harmonised.E1.harmonisable": true,128 "harmonised.E2.harmonisable": true,129 "harmonised.E3.harmonisable": true,130 "harmonised.E5.harmonisable": true131 },132 "passed": true,133 "tolerance": null134 },135 {136 "description": "n_harmonised = 4, n_not_harmonisable = 1",137 "expected": {138 "n_harmonised": 4,139 "n_not_harmonisable": 1140 },141 "id": "counts",142 "observed": {143 "n_harmonised": 4,144 "n_not_harmonisable": 1145 },146 "passed": true,147 "tolerance": {148 "n_harmonised": {149 "abs": 0150 },151 "n_not_harmonisable": {152 "abs": 0153 }154 }155 },156 {157 "description": "E1 locator names the DCR source and Table 6",158 "expected": "(?s)(?=.*2609\\.27732)(?=.*Table\\s*6)",159 "id": "loc_E1",160 "observed": {161 "harmonised.E1.locator": "arxiv-2609.27732v1 | Table 6 | row 'ATT' (line 36) | column '5 km'; cross-check row '% change' (line 40) | column '5 km'"162 },163 "passed": true,164 "tolerance": null165 },166 {167 "description": "E2 locator names the RESEA source and Table 2",168 "expected": "(?s)(?=.*2606\\.14621)(?=.*Table\\s*2)",169 "id": "loc_E2",170 "observed": {171 "harmonised.E2.locator": "arxiv-2606.14621v1 | Table 2 | row 'Reemployment' (line 29) | columns 'Average treatment effect estimate' (Delta) and 'Control' (p)"172 },173 "passed": true,174 "tolerance": null175 },176 {177 "description": "E3 locator names the minimum-wage source and Table 2",178 "expected": "(?s)(?=.*2505\\.04555)(?=.*Table\\s*2)",179 "id": "loc_E3",180 "observed": {181 "harmonised.E3.locator": "arxiv-2505.04555v3 | Table 2 | row 'Employment elasticity w.r.t MW' (line 50) | column 'Estimate (SE)'; row '% MW changes' (line 60) | column 'Estimate (SE)'"182 },183 "passed": true,184 "tolerance": null185 },186 {187 "description": "E4 locator names the DCR source and Table 7",188 "expected": "(?s)(?=.*2609\\.27732)(?=.*Table\\s*7)",189 "id": "loc_E4",190 "observed": {191 "harmonised.E4.locator": "arxiv-2609.27732v1 | Table 7 | row 'Drug-related (fatal)' (line 86) | column '5 km'"192 },193 "passed": true,194 "tolerance": null195 },196 {197 "description": "E5 locator names the Benin source and Table 3",198 "expected": "(?s)(?=.*2510\\.03658)(?=.*Table\\s*3)",199 "id": "loc_E5",200 "observed": {201 "harmonised.E5.locator": "arxiv-2510.03658v1 | Table 3 | row 'Treatment' (line 49) | column '(4)'"202 },203 "passed": true,204 "tolerance": null205 },206 {207 "description": "each harmonised item states a transformation (non-empty string)",208 "expected": {209 "harmonised.E1.transformation": null,210 "harmonised.E2.transformation": null,211 "harmonised.E3.transformation": null,212 "harmonised.E5.transformation": null213 },214 "id": "transformations",215 "observed": {216 "harmonised.E1.transformation": "100*(exp(b)-1) with b = -0.431 log points -> 100*(exp(-0.431)-1) = -35.0141%, reported to 2 dp (consistent with printed '% change' -35.0%)",217 "harmonised.E2.transformation": "100*Delta/p with Delta = 1.47 pp (ATE) and p = 75.0% (control mean) -> 100*1.47/75.0 = 1.9600%, reported to 2 dp",218 "harmonised.E3.transformation": "100*eta*g with eta = -0.388 and g = 0.047 (proportional MW change) -> 100*(-0.388)*0.047 = -1.8236% (first-order/linear approximation)",219 "harmonised.E5.transformation": "100*beta with beta = -0.0962 (probability, 0-1 scale) -> 100*(-0.0962) = -9.62 pp (exact rescaling)"220 },221 "passed": true,222 "tolerance": null223 }224 ],225 "run_id": "RC0231",226 "schema_error": "",227 "schema_valid": true,228 "scientific_success": true,229 "task_id": "F4-conf-03"230}