# Contract — F6-conf-03
**Question:** How much does the quarterly change in US unemployment (pp) respond to quarterly real GDP growth (%, not annualised), 1960Q1–2019Q4, and is the response stable across 1960Q1–1983Q4 vs 1984Q1–2019Q4?
**Estimand:** β in Δu_t = α + β g_t + ε_t (OLS, 240 quarters). u_t = mean of 3 monthly UNRATE; g_t = 100·Δln GDPC1. Meaningful as a linear projection coefficient (descriptive association, not causal); HAC inference assumes weak stationarity / mixing of (g, ε).
**Uncertainty:** Newey–West (Bartlett) HAC SE for full-sample β; lag length reported. 95% CI = β ± 1.96·SE (normal).
**Stability:** subsample OLS slopes; classical Chow F (SSR-based), df (2, n−4)=(2,236).
**Outputs:** out/results.json (keys per TASK.md table), out/figure1.png, out/table1.csv (period,n,intercept,slope,slope_se), out/report.md (6 sections), out/analysis.py, out/claims.json.
**Information rules:** only data/GDPC1.csv, data/UNRATE.csv; no quarter after 2019Q4 in any estimate; 1959Q4 levels allowed for 1960Q1 differences.
**Invalidity conditions:** missing months/quarters inside 1959Q4–2019Q4; incomplete quarters averaged; post-2019 data leaking; wrong growth definition (annualised).