1# Contract — F1-conf-032**Question:** association between firm leverage at end of year t and default in t+1, using only info known at end of t.3**Estimand:** b1 (coef on leverage) in OLS LPM default_next ~ 1 + leverage + cash_ratio + log_sales on firm-years with observed outcome; SE clustered by firm_id. Meaningful as a conditional association (not causal), assuming correct de-duplication and that predictors are measured at end of t.4**Outputs:** out/results.json (task_id, n_analysed, n_firms, predictors_used, variables_excluded, beta_leverage, se_leverage_cluster, r2, default_rate, feasibility, feasibility_reason, data_issues, n_input_rows, random_seed); out/analytic.csv (firm_id, year, predictors, default_next); out/exclusions.csv (step, rule, n_before, n_after, n_removed, rationale; chained); out/report.md (6 sections); out/analysis.py; out/claims.json.5**Information rules:** only variables known at end of t (codebook last column) — rating_2025 (known 2025, built from realised defaults) must be excluded; rows with missing default_next excluded, not imputed; only data/firm_panel.csv.6**Invalidity:** using rating_2025; imputing outcomes; keeping duplicate firm-years; ledger not summing.7