{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001144493,0.0002604061,0.000434447,0.0003705772,0.0000729919,0.0001190591,0.0005130433,0.0001815232,0.0004892494],"category_scores_gemma":[0.0005561899,0.0001718287,0.0002330328,0.0005710689,0.00009532733,0.0002335872,0.0005239198,0.0003722292,0.00007985972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002277918,"about_ca_system_score_gemma":0.00003991423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006266601,"about_ca_topic_score_gemma":0.0002144219,"domain_scores_codex":[0.9983734,0.00007755691,0.0006227206,0.0003702574,0.0003848828,0.0001711886],"domain_scores_gemma":[0.9980688,0.0006970472,0.0005856306,0.000441458,0.0001991416,0.000007933302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008548885,0.0004837122,0.03033408,0.009853736,0.001161242,0.00002105743,0.002589089,0.05522071,0.007747422,0.7571089,0.008261612,0.1263636],"study_design_scores_gemma":[0.0001675508,0.0001942739,0.001756471,0.002502393,0.0003815743,3.479715e-7,0.001183279,0.7825241,0.1858312,0.02408575,0.0007488561,0.0006241567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6918579,0.0001368703,0.2255372,0.002586994,0.003278981,0.002696274,0.0000361674,0.0004082414,0.07346132],"genre_scores_gemma":[0.9985847,0.00002525852,0.0000289301,0.000176613,0.0004313862,0.00005494985,0.00008592341,0.00002811538,0.000584087],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7330231,"threshold_uncertainty_score":0.7006969,"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."}}