# Contract — F1-conf-01

Question. 12-month growth of CPIAUCSL (SA) for each month 2001-01..2026-09 and summaries. Estimands. g_t = 100(P_t/P_{t-12} − 1), P from the most recent vintage covering the month (2026-10-28 vintage for 2014-01..2026-09, 2016-07-15 vintage before). Summaries: mean over window, means 2001-01..2013-12 and 2014-01..2026-09, g at 2014-06, 2016-07, 2020-05, 2022-06, 2026-09, max/min and months. Meaningful under: the two vintages share the same base (1982–84=100) so ratios across the 2014 splice are comparable (small seasonal-factor revision inconsistency accepted). Outputs. out/results.json (keys per TASK.md table), out/analytic.csv (date,cpi,cpi_lag12,vintage_used,growth_12m; n_analysed rows), out/exclusions.csv (chained ledger), out/report.md (6 sections), out/analysis.py, out/claims.json. Availability rules. Most recent vintage per month; no interpolation/imputation; missing g_t counted; only data/. Invalidating conditions. Using the hand-assembled file uncritically; imputing missing levels; using the old vintage where the new covers the month.