# Log

• 2026-10-30 P0: read TASK.md, codebook; contract written.
• 2026-10-30 P1: audit done; decisions: drop rating_2025 (look-ahead), drop 40 exact duplicates, drop 300 rows with unobserved outcome (2022).
• 2026-10-30 P2: baseline default_rate 0.1211 and bivariate leverage slope computed in analysis.py.
• 2026-10-30 P3: analysis.py implemented (OLS, firm-clustered SE, statsmodels default small-sample correction). No randomness.
• 2026-10-30 P4: clean re-run identical; all consistency checks pass.
• 2026-10-30 P5: report and claims written.