{"id":"W4406906606","doi":"10.3390/jrfm18020060","title":"Forecasting Follies: Machine Learning from Human Errors","year":2025,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008396493,0.0007177797,0.0006109073,0.001300631,0.0007080734,0.002228982,0.00105536,0.001302378,0.00290909],"category_scores_gemma":[0.0679841,0.0003512954,0.0004192778,0.001353516,0.001736741,0.003865043,0.00153029,0.002434776,0.001088253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006991346,"about_ca_system_score_gemma":0.001219477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003356652,"about_ca_topic_score_gemma":0.003060978,"domain_scores_codex":[0.9965987,0.001921843,0.0001309639,0.0005248063,0.0007082422,0.0001156205],"domain_scores_gemma":[0.9650413,0.02731388,0.002412886,0.003077654,0.001862804,0.0002914841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003352735,0.0001831647,0.03297292,0.000343128,0.000191452,0.0002201482,0.002062805,0.1695528,0.002766526,0.0574815,0.01367514,0.7202151],"study_design_scores_gemma":[0.00004456894,0.0001542389,0.01163867,0.0001983285,0.00005626365,0.0001513616,0.0004167051,0.763539,0.00367847,0.2089421,0.01108152,0.0000987403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09977015,0.001840584,0.8755184,0.008809136,0.0003857074,0.0001026051,0.0004878798,0.001819066,0.01126639],"genre_scores_gemma":[0.8340476,0.001275425,0.1581782,0.001162564,0.0005367181,0.0001562994,0.000571389,0.0002168173,0.003854988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008396493,"threshold_uncertainty_score":0.0444054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06283522607477833,"score_gpt":0.3356371096382198,"score_spread":0.2728018835634415,"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."}}