1[2 {"id": "C1", "text": "The estimation sample has 1800 firm-years from 300 firms, after removing 40 exact duplicates and 300 firm-years (origin 2022) whose outcome was not observed.", "results_keys": ["n_analysed", "n_firms", "n_input_rows", "data_issues"], "status": "supported", "caveat": "Duplicates were assumed to be assembly errors."},3 {"id": "C2", "text": "rating_2025 breaks the information rule (it is known only in 2025 and derived from realised defaults), so it was excluded.", "results_keys": ["variables_excluded", "predictors_used"], "status": "supported", "caveat": ""},4 {"id": "C3", "text": "Conditional on cash ratio and log sales, leverage is positively associated with next-year default: beta = 0.264, firm-clustered SE 0.041, 95% CI [0.184, 0.344].", "results_keys": ["beta_leverage", "se_leverage_cluster", "ci95_leverage_cluster"], "status": "supported", "caveat": "LPM association on simulated data, not causal."},5 {"id": "C4", "text": "The baseline default rate is 0.121 and the model R^2 is 0.035. The adjusted leverage slope is close to the bivariate slope of 0.267.", "results_keys": ["default_rate", "r2", "baseline_beta_leverage_bivariate"], "status": "supported", "caveat": ""}6]7