{"id":"W4415695224","doi":"10.2139/ssrn.5614171","title":"Predictable by Construction: Assessing Forecast Directional Accuracy of Temporal Aggregates ","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Monetary Policy and Economic Impact","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Aggregate (composite); Forecast error; Sign (mathematics); Approximation error; Power (physics); Observational error; Type I and type II errors","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005913729,0.0004660777,0.0004835959,0.001871419,0.0003767957,0.001860573,0.0007208961,0.0008008101,0.002125446],"category_scores_gemma":[0.04036262,0.0004139101,0.0005223468,0.002249144,0.0003509292,0.001845433,0.001271745,0.000835706,0.0006899189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005390332,"about_ca_system_score_gemma":0.001142622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01711866,"about_ca_topic_score_gemma":0.01119543,"domain_scores_codex":[0.9986306,0.0004626427,0.0001251947,0.0003050582,0.0003785394,0.00009783014],"domain_scores_gemma":[0.9837896,0.008764954,0.00201896,0.002626043,0.002325518,0.0004749743],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001708643,0.0001410724,0.4623715,0.0001460953,0.0005418428,0.0001487459,0.0005129881,0.3338583,0.003143905,0.00990997,0.009220827,0.178296],"study_design_scores_gemma":[0.00007732725,0.0001927588,0.107424,0.00004026664,0.00009349303,0.00007150306,0.0002030071,0.8782055,0.002655257,0.008351781,0.002641527,0.00004371278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8524149,0.0006793927,0.1336143,0.0004021311,0.0002183801,0.0000750502,0.005864649,0.001221838,0.005509375],"genre_scores_gemma":[0.9711217,0.0001553376,0.02334313,0.00003122813,0.0000567438,0.00003026821,0.004613903,0.0001612756,0.0004864869],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01711866,"threshold_uncertainty_score":0.03403807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04021538290869205,"score_gpt":0.2600064277167724,"score_spread":0.2197910448080803,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}