1# Task card — F2-dev-0123- **Family / split**: F2 Estimation and inference / development4- **Question**: two-way fixed-effects (firm + year) slope of y on x in a balanced firm–year panel, with firm-clustered uncertainty; estimand = β in y_it = a_i + g_t + β x_it + u_it.5- **Data type**: synthetic (simulated, seed 20261101), 1,200 rows = 100 firms × 12 years, regressor correlated with both effects, serially correlated x and disturbances within firm.6- **Scope / prerequisites**: within transformation or LSDV; cluster-robust variance; no exclusions needed.7- **Allowed information**: `data/firm_panel.csv` only.8- **Expected artifacts**: results.json (15 keys), report.md (6 sections), analysis.py, claims.json.9- **Rubric summary**: required criteria — FE slope to 1e-4; firm-clustered SE within 10% of the reference; CI bounds within 0.03; exact counts; cluster SE must exceed the conventional SE by > 20%; pooled slope must differ from the FE slope. Critical checks — input row count reported correctly (fabrication), feasibility "complete" (false completion), CI half-width consistent with the reported SE (invalid inference), no silent row drops (unreported substitution). Baseline = pooled OLS slope.10- **Oracle provenance**: independent_code (numpy two-way demeaning + CR1 sandwich, cross-checked against LSDV; `~/wp29-oracles/F2-dev-01/`).11- **Difficulty rationale**: moderately easy; the care points are removing both sets of effects and clustering by firm. One-way FE, pooled OLS, conventional or HC SEs all fail.12- **Budget class**: benchmark (4.00 USD cap, 25 min wall, 80 turns per session).13- **Anticipated failure modes**: firm effects only; demeaning without year effects; HC instead of cluster SE; CI built from the conventional SE; forgetting common keys.14- **Contamination risk**: low (fresh simulated data; textbook method, which is intended).15