# Contract — F1-conf-03

Question. Association between leverage at end of year t and default in t+1, using only info known at end of t. Estimand. b1 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 descriptive (not causal) conditional association, assuming correct row assembly (one row per firm-year) and outcomes measured without imputation. Info rule. Only variables known at end of t. rating_2025 (known 2025, built from realised defaults through 2022 => leakage) must be excluded. default_next is the outcome only. firm_id/year are identifiers, not predictors. 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; out/exclusions.csv; out/report.md; out/analysis.py; out/claims.json. Invalidity. Using rating_2025; imputing missing outcomes; double-counting duplicate rows; no observed outcomes.