# Contract — F4-conf-01
**Question.** Extract specified treatment effects and their uncertainty, exactly as printed, from two extracts: Armendariz (2026) arXiv:2609.27732v1 (Swiss DCR staggered DiD; Tables 6, 7; log points; SEs in parentheses; stars) and Li, Pearson-Merkowitz & Yokum (2026) arXiv:2606.14621v1 (RI RESEA RCT; Table 2; ATEs with p-values and 95% CIs). Derive (a) a 95% CI for the Table 6 5 km ATT from its SE and (b) an SE for the Table 2 wage ATE from its 95% CI, stating the convention; recognise unreported quantities (exact p-value of HIV 5 km ATT; SE of wage ATE).
**Estimands.** The printed numbers themselves (no re-estimation). Derived values assume approximate normality of the estimator (Wald-type, symmetric CI) with critical value 1.96.
**Outputs.** out/results.json (keys listed in TASK.md: dcr_att_5km(_se), dcr_att_3km(_se), dcr_obs_5km, dcr_narcotics_att_3km(_se), dcr_fatal_att_1km(_se), dcr_hiv_att_5km(_se), dcr_hiv_att_5km_p_value, dcr_hiv_att_5km_significant_10pct, dcr_att_5km_ci_low/high, ri_wage_ate, ri_wage_ate_ci_low/high, ri_wage_ate_se_reported, ri_wage_ate_se_derived, ri_control_mean_wage, ri_reemployment_ate_pp, ri_weeks_ui_ate, ri_weeks_ui_ate_ci_low/high, locators, derivation_notes, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed); out/report.md (6 sections); out/analysis.py; out/claims.json.
**Information rules.** Only the two extracts are admissible; values as printed (sign, decimals); when a value appears in several tables use the named table (e.g. Table 6 not A19; Table 2 not Table 3); locators in prescribed format; unreported -> null with "not reported in <source>".
**Invalidity.** Using A19 / Table 3 / prose values instead of the named table; rounding; inventing a p-value; missing locator.