{"id":"W4415303363","doi":"10.1080/00036846.2025.2564464","title":"Predictable by construction: assessing forecast directional accuracy of temporal aggregates*","year":2025,"lang":"en","type":"article","venue":"Applied Economics","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Forecast error; Forecast verification; Economic forecasting; Consensus forecast","routes":{"ca_aff":true,"ca_fund":true,"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":[0.04532455,0.000885456,0.0009574321,0.002653809,0.0007262778,0.002681385,0.001090531,0.001577964,0.001257629],"category_scores_gemma":[0.2289473,0.0005123607,0.00131533,0.003356382,0.002338305,0.004213104,0.002654231,0.002126816,0.0003541518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000817579,"about_ca_system_score_gemma":0.001207804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003118557,"about_ca_topic_score_gemma":0.00255297,"domain_scores_codex":[0.9776809,0.01327282,0.001648039,0.003006368,0.003838498,0.0005533094],"domain_scores_gemma":[0.6681988,0.2619516,0.03372163,0.0263852,0.008474781,0.001268004],"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":[0.001688124,0.000211448,0.5847229,0.0003283623,0.001128995,0.0004095142,0.001861069,0.1438993,0.002385406,0.03575841,0.003154617,0.2244518],"study_design_scores_gemma":[0.000134395,0.001634036,0.2138194,0.0001791473,0.0003786834,0.0005647519,0.001235257,0.6684181,0.006579488,0.1020607,0.004758919,0.0002370835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5504054,0.001035413,0.4377123,0.0008769249,0.0002227399,0.0003093051,0.001525064,0.0005668357,0.00734596],"genre_scores_gemma":[0.9526114,0.0001628788,0.0455847,0.0001203176,0.00008595577,0.0001284159,0.0009079024,0.0001006072,0.0002977414],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04532455,"threshold_uncertainty_score":0.239702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04749146483030359,"score_gpt":0.3441147451625829,"score_spread":0.2966232803322793,"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."}}