# Contract (P0)

Question. Real-time out-of-sample accuracy of 1- and 2-quarter-ahead forecasts of US real GDP growth (A191RL1Q225SBEA, % q/q SAAR) at 8 origins (vintage dates 2024-01-31 … 2025-12-31), naive vs one simple model, evaluated against first releases. Estimands. RMSE and MAE per horizon h∈{1,2} for naive and model (8 errors each); rel. improvement 1−RMSE_model/RMSE_naive per h; mean |current − first release| over the 8 h=1 target quarters. Meaningful under: each origin uses only its own vintage file; actuals = first release; with n=8 these are descriptive, high-variance statistics. Outputs. out/forecasts.csv (32 rows, cols origin_date,target_date,horizon,forecast,actual,model,vintage_date,train_last_date,train_last_value,n_train); out/results.json (task_id, model_name, model_description, n_origins, first_origin, last_origin, rmse/mae naive/model h1/h2, rel_improvement_rmse_h1/h2, mean_abs_revision_h1_targets, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed); out/report.md (6 sections); out/analysis.py; out/claims.json. Information rules. At origin d only vintage file d; current_vintage only for revision stat; h counted from last quarter in the vintage; naive = last value of vintage. Invalidity. Using current vintage or later vintages for estimation; missing first release for a target (would make it partial); wrong target alignment.