1{2 "task_id": "F4-conf-02",3 "verdicts": {4 "A1": "supported",5 "A2": "not_supported",6 "A3": "not_supported",7 "A4": "not_supported",8 "A5": "not_assessable",9 "A6": "supported"10 },11 "locators": {12 "A1": "arxiv-2609.27732v1 | Table 6 | row \"ATT\" | column \"5 km\"",13 "A2": "arxiv-2609.27732v1 | Table 7 | row \"HIV\" | column \"1 km\"",14 "A3": "arxiv-2609.27732v1 | Table 6 | row \"% change\" | column \"3 km\"",15 "A4": "arxiv-2609.27732v1 | Table 7 | row \"Hepatitis\" | column \"5 km\"",16 "A5": "not reported in arxiv-2609.27732v1",17 "A6": "arxiv-2606.14621v1 | Table 2 | row \"Weeks on UI\" | column \"Average treatment effect estimate\""18 },19 "reasons": {20 "A1": "Table 6 prints the 5 km ATT as -0.431** with SE (0.210), ** denoting p<0.05, and a % change of -35.0% (100(exp(-0.431)-1) = -35.0%), matching every element of the assertion.",21 "A2": "Table 7 prints the 1 km HIV ATT as +0.063 (SE 0.801), positive and insignificant, so the claimed negative sign (-0.063) and the claimed fall in HIV hospitalisations are contradicted.",22 "A3": "Table 6 converts the 3 km ATT of -0.283 to a -24.7% change (100(exp(-0.283)-1) = -24.7%), not 28.3%, so the stated magnitude is contradicted (28.3% is the log-point coefficient read directly as a percentage).",23 "A4": "With ATT -0.406 and SE (0.250), the 95% CI is -0.406 +/- 1.96*0.250 = [-0.896, 0.084], which includes zero (the asserted [-0.66, -0.16] is only +/- 1 SE), and the estimate carries no significance star.",24 "A5": "The extract reports ATTs only by buffer (Table 6), outcome category (Table 7) and estimator (Table A19) and never by sex, so a men-versus-women comparison can be neither confirmed nor refuted.",25 "A6": "Table 2 gives the ATE of RESEA selection on weeks on UI as -1.99 weeks (95% CI [-2.24, -1.75], p<0.001) with a control mean of 17.3 weeks, and 1.99/17.3 = 11.5% as also stated in the results text."26 },27 "n_supported": 2,28 "n_not_supported": 3,29 "n_not_assessable": 1,30 "feasibility": "complete",31 "feasibility_reason": null,32 "data_issues": [33 {34 "issue": "arxiv-2609.27732v1: Table A19 CS-DR column prints SE (0.218) for the same ATT -0.431 for which Table 6 (5 km) prints SE (0.210).",35 "handling": "A1 judged against Table 6 (the table the assertion describes); significance at 5% holds under either SE (|b|/SE = 2.05 or 1.98 > 1.96), noted in report."36 },37 {38 "issue": "arxiv-2609.27732v1: Table A19 note says 640 never-treated comparison regions, whereas Tables 6, 7, A19 body and Figure 6 note say 608.",39 "handling": "Recorded; not decisive for any assertion."40 },41 {42 "issue": "arxiv-2609.27732v1: abstract says fatal hospitalisations fall by 35%, but Table 7 5 km fatal ATT -0.354 implies -29.8%, matching Section 6.1 ('approximately 30%').",43 "handling": "Recorded; no assertion concerns fatal outcomes; tables preferred over abstract text."44 },45 {46 "issue": "arxiv-2609.27732v1: text announces five diagnostic sub-categories, Figure 7 note says four, Table 7 note gives ICD codes for four.",47 "handling": "Recorded; not decisive for any assertion."48 },49 {50 "issue": "arxiv-2606.14621v1: rendering defect 'p ¡ 0.001' in the short-term weeks-on-UI sentence (should read p < 0.001).",51 "handling": "Read as p < 0.001 (consistent with Table 2); not decisive."52 },53 {54 "issue": "arxiv-2606.14621v1: results text prints the weeks-on-UI CI as reduction magnitudes [1.75, 2.24] while Tables 2 and 3 print signed [-2.24, -1.75].",55 "handling": "Treated as equivalent sign conventions; A6 judged against Table 2."56 }57 ],58 "n_input_rows": {59 "assertions.json": 6,60 "README.md": 14,61 "sources/arxiv-2609.27732v1.txt": 134,62 "sources/arxiv-2606.14621v1.txt": 5863 },64 "n_analysed": 6,65 "random_seed": null,66 "baseline_verdicts_number_match": {67 "A1": "all_numbers_found",68 "A2": "all_numbers_found",69 "A3": "some_number_missing",70 "A4": "some_number_missing",71 "A5": "all_numbers_found",72 "A6": "all_numbers_found"73 },74 "computation_details": {75 "A1": {76 "b": -0.431,77 "se": 0.21,78 "z": 2.0524,79 "pct": -35.0180 },81 "A2": {82 "b": 0.063,83 "se": 0.80184 },85 "A3": {86 "b": -0.283,87 "se": 0.279,88 "pct": -24.65,89 "printed_pct": "-24.7%"90 },91 "A4": {92 "b": -0.406,93 "se": 0.25,94 "ci_196": [95 -0.896,96 0.08497 ],98 "ci_200": [99 -0.906,100 0.094101 ],102 "crit_to_exclude_zero": 1.624103 },104 "A5": {105 "n_sex_mentions": 0106 },107 "A6": {108 "ate": -1.99,109 "ci": [110 -2.24,111 -1.75112 ],113 "control_mean": 17.3,114 "rel_pct": 11.5115 }116 },117 "conventions": {118 "pct_change": "100*(exp(b)-1)",119 "ci_crit": 1.96,120 "ci_crit_alt": 2.0121 }122}