{
  "task_id": "F1-conf-03",
  "n_analysed": 1800,
  "n_firms": 300,
  "predictors_used": [
    "leverage",
    "cash_ratio",
    "log_sales"
  ],
  "variables_excluded": [
    {
      "variable": "rating_2025",
      "reason": "Assigned in the 2025 review using realised default history through 2022 and sample-average leverage; not known at end of year t (look-ahead leakage). In the data every observed default is in rating D."
    },
    {
      "variable": "firm_id",
      "reason": "identifier; used only for clustering, not as a predictor"
    },
    {
      "variable": "year",
      "reason": "origin-year index; not part of the specified model"
    },
    {
      "variable": "default_next",
      "reason": "outcome variable"
    }
  ],
  "beta_leverage": 0.2637836102938267,
  "se_leverage_cluster": 0.0407569280434615,
  "r2": 0.03490564212216729,
  "default_rate": 0.12111111111111111,
  "feasibility": "complete",
  "feasibility_reason": null,
  "data_issues": [
    {
      "issue": "40 exact duplicate rows (40 duplicated firm_id-year keys, all identical copies)",
      "handling": "dropped duplicates keeping one copy; panel becomes 300 firms x 7 years"
    },
    {
      "issue": "rating_2025 is a final-vintage field built from future defaults (information leakage)",
      "handling": "excluded from predictors and from out/analytic.csv"
    },
    {
      "issue": "default_next missing for 300 deduplicated rows, by year: {2022: 300}",
      "handling": "excluded from estimation (outcome not observed at data cut); not imputed"
    }
  ],
  "n_input_rows": {
    "firm_panel.csv": 2140
  },
  "random_seed": null,
  "beta_cash_ratio": -0.18594837465723182,
  "beta_log_sales": -0.007342181807581363,
  "intercept": 0.08997926409935522,
  "ci95_leverage_low": 0.18390149920815163,
  "ci95_leverage_high": 0.34366572137950174,
  "p_leverage_cluster": 9.663918872288981e-11,
  "se_leverage_classical": 0.035820571091069786,
  "n_rows_after_dedupe": 2100
}