1[2 {"id":"C1","text":"At h=1 the employment-augmented direct model lowers RMSE relative to the naive forecast by about 9% (0.743 vs 0.814 pp).","results_keys":["rmse_model_h1","rmse_naive_h1","rel_improvement_rmse_h1"],"status":"supported","caveat":"DM p≈0.048, borderline; current-vintage data, not real time."},3 {"id":"C2","text":"At h=3 the model lowers RMSE relative to naive by about 21% (0.902 vs 1.140 pp).","results_keys":["rmse_model_h3","rmse_naive_h3","rel_improvement_rmse_h3"],"status":"supported","caveat":"Not statistically significant (DM p≈0.105); 48 overlapping origins."},4 {"id":"C3","text":"The model also has lower MAE than naive at both horizons.","results_keys":["mae_model_h1","mae_naive_h1","mae_model_h3","mae_naive_h3"],"status":"supported","caveat":"Same evaluation window and vintage caveats."},5 {"id":"C4","text":"All forecasts respect the publication-lag rule (GDP <= t-2, employment <= t-1).","results_keys":["last_target_date_available","last_predictor_date_available"],"status":"supported","caveat":"Verified programmatically from the ledger; simulates timing only, not vintages."}6]7