{"id":"W4388484811","doi":"10.1016/j.tics.2023.10.005","title":"When expert predictions fail","year":2023,"lang":"en","type":"review","venue":"Trends in Cognitive Sciences","topic":"Philosophy and History of Science","field":"Arts and Humanities","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"Defence Research and Development Canada; The Scarborough Hospital; University of Toronto; University of Waterloo","funders":"Social Sciences and Humanities Research Council of Canada; John Templeton Foundation; National Science Foundation","keywords":"Humility; Psychology; Context (archaeology); Epistemology; Cognitive science; Data science; Social psychology; Computer science; Political science","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":[0.005369522,0.000687103,0.001123601,0.001058192,0.000285753,0.002398372,0.001504401,0.002745846,0.007983662],"category_scores_gemma":[0.03069355,0.0003031462,0.0004576696,0.0008180041,0.001231827,0.003210262,0.0009777839,0.002561034,0.003440541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008437382,"about_ca_system_score_gemma":0.002433334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00368193,"about_ca_topic_score_gemma":0.006235208,"domain_scores_codex":[0.997708,0.0008639231,0.0001748115,0.0003493012,0.0007265913,0.0001773513],"domain_scores_gemma":[0.9852812,0.01138381,0.001154143,0.0005704618,0.001356179,0.0002543598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002620343,0.0001021256,0.004228056,0.003708878,0.0004232846,0.0004087125,0.0002299077,0.003256938,0.0002822657,0.02505923,0.1011612,0.8608774],"study_design_scores_gemma":[0.0002532316,0.0002812368,0.01484555,0.02221542,0.001056385,0.002422766,0.0007694972,0.01109718,0.002377499,0.3823795,0.5621536,0.0001480668],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01819619,0.816896,0.02152068,0.05194922,0.005662357,0.00009758631,0.001618729,0.0005812611,0.08347798],"genre_scores_gemma":[0.3326591,0.5968595,0.009865274,0.02958966,0.006753808,0.0001504724,0.002896462,0.0001825299,0.02104318],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.007983662,"threshold_uncertainty_score":0.02839714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6076804368050733,"score_gpt":0.4531422221793591,"score_spread":0.1545382146257142,"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."}}