1# Verification checks (P4)2- [PASS] Clean re-run (deleted results.json/analytic.csv/exclusions.csv, re-ran) → results.json byte-identical.3- [PASS] analytic rows == n_analysed (308)4- [PASS] n_growth + n_missing == 309 window months5- [PASS] ledger n_before − n_removed == n_after on each row6- [PASS] ledger chained; starts at 834+153=987 stacked rows, ends at n_analysed7- [PASS] growth_12m recomputed from cpi/cpi_lag12 columns8- [PASS] vintage_used = 2016-07-15 before 2014-01, 2026-10-28 from 2014-019- [PASS] overall mean equals count-weighted mean of sub-period means (156, 152 months)10- [PASS] max equals analytic max and equals growth_2022_0611- [PASS] no 2025-10 row; analytic dates within 2001-01..2026-0912- [PASS] magnitudes plausible (|g| < 15%); window mean 2.57% vs baseline 2001–13 mean 2.36% (same order)13- No CIs/SEs: estimands are deterministic transforms of published data (no sampling uncertainty).14