# Contract (F2-dev-01)

• Question: within-firm, within-year association of y with x in a balanced firm-year panel.
• Estimand: beta in y_it = a_i + g_t + beta x_it + u_it (firm and year effects unrestricted, may correlate with x). Meaningful under strict exogeneity of x conditional on FE, and requires within variation in x after two-way demeaning.
• Uncertainty: firm-clustered SE (arbitrary within-firm dependence, independence across firms); 95% CI from se_cluster.
• Outputs: out/results.json (task_id, beta_pooled, beta_fe, se_conventional, se_cluster, beta_ci_low, beta_ci_high, n_firms, n_years, n_analysed, feasibility, feasibility_reason, data_issues, n_input_rows, random_seed), out/report.md (Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues), out/analysis.py, out/claims.json.
• Information rules: only data/firm_panel.csv.
• Invalid/impossible if: data missing, no within variation in x, too few clusters, duplicate firm-year keys unresolved.