1# P4 checks2- Clean re-run of out/analysis.py: results.json byte-identical (cmp) — PASS3- analytic rows == n_analysed: PASS4- analytic firms == n_firms: PASS5- no rating_2025 in analytic: PASS6- ledger n_before-n_removed==n_after: PASS7- ledger chained: PASS8- ledger start=n_raw, end=n_analysed: PASS9- se>0: PASS10- CI contains beta: PASS11- 0<=r2<=1: PASS12- default_rate == analytic mean: PASS13- max year in analytic <=2021 (outcome observed by end 2022): PASS14- no duplicate firm-year keys: PASS15- Magnitude vs baseline: default_rate 0.121; beta_leverage 0.264 per unit leverage => ~0.026 per 0.1 leverage, plausible relative to baseline — PASS16