{"id":"W4390144702","doi":"10.31234/osf.io/p82nx","title":"Effect of Calibration Training on the Calibration of Intelligence Analysts’ Judgments","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Competitive and Knowledge Intelligence","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Waterloo; Defence Research and Development Canada","funders":"","keywords":"Calibration; Overconfidence effect; Task (project management); Training (meteorology); Metacognition; Computer science; Binary classification; Artificial intelligence; Uncorrelated; Baseline (sea); Machine learning; Econometrics; Statistics; Psychology; Social psychology; Mathematics; Engineering; Cognition","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":[0.003692628,0.0005244111,0.0004311812,0.0003877686,0.0003598071,0.0007452442,0.0005560923,0.0007051498,0.002321702],"category_scores_gemma":[0.04696786,0.0002836618,0.0001887744,0.0003158302,0.000631488,0.000622612,0.0007329286,0.001016817,0.0003497092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005612198,"about_ca_system_score_gemma":0.0006997895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00194414,"about_ca_topic_score_gemma":0.001848964,"domain_scores_codex":[0.9977853,0.001007656,0.0001858556,0.0004100627,0.0003930167,0.0002180527],"domain_scores_gemma":[0.9425394,0.03819059,0.007658943,0.004968292,0.004251174,0.002391591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.03994095,0.03039513,0.1533473,0.0007572851,0.000643676,0.0003782064,0.01377955,0.0164093,0.1805281,0.000880938,0.003113491,0.559826],"study_design_scores_gemma":[0.001098788,0.03398415,0.8176048,0.0002789257,0.0006216583,0.0004480478,0.002433529,0.01898907,0.117345,0.00217835,0.004765931,0.0002517232],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9983347,0.00008839525,0.0003915868,0.00005497376,0.0000180389,0.0000264227,0.00001701313,0.00003051746,0.001038344],"genre_scores_gemma":[0.9980129,0.00006158402,0.001120193,0.00005089733,0.00001859282,0.00003255938,0.00004809405,0.0000096156,0.0006455285],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003692628,"threshold_uncertainty_score":0.01952869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.085346990382933,"score_gpt":0.3032241783836251,"score_spread":0.2178771880006921,"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."}}