# Contract — F4-conf-02 (written 2026-10-30)

Question: For each of six literature-review assertions (A1–A6), judge from the cited extract only whether it is supported / not_supported / not_assessable. Estimands: six categorical verdicts, each with one locator and one-sentence reason. Meaningful under the rules: "supported" needs every element (sign, magnitude, uncertainty, significance, population) to be printed or arithmetically implied; partial errors -> not_supported; not_assessable only when the extract has no bearing quantity. Conventions: % change = 100(exp(b)-1); 95% CI = b ± 1.96·SE (2.0 acceptable). Outputs: out/results.json (verdicts, locators, reasons, n_supported, n_not_supported, n_not_assessable, task_id="F4-conf-02", feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed=null); out/report.md (Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues); out/analysis.py; out/claims.json. Information rules: extracts only; no memory of papers; values as printed. Invalidity: using outside knowledge; verdict not tied to a printed line; extracts missing/corrupted (hash mismatch).