{"id":"W4402332012","doi":"10.1002/acp.4236","title":"The effect of calibration training on the calibration of intelligence analysts' judgments","year":2024,"lang":"en","type":"article","venue":"Applied Cognitive Psychology","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Defence Research and Development Canada","funders":"","keywords":"Psychology; Calibration; Training (meteorology); Applied psychology; Cognitive psychology; Social psychology; Statistics","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":[0.003729909,0.0003539009,0.0003053908,0.0004055125,0.0003090406,0.0005536334,0.000476768,0.0004818851,0.00187564],"category_scores_gemma":[0.04623873,0.0002286645,0.0001404742,0.0002443479,0.0005153971,0.0004593714,0.0005567335,0.0008051743,0.000249753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004190463,"about_ca_system_score_gemma":0.0004576353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001339798,"about_ca_topic_score_gemma":0.001315928,"domain_scores_codex":[0.9978268,0.001101886,0.0001556957,0.0003027474,0.0004393526,0.0001734314],"domain_scores_gemma":[0.954394,0.02905507,0.007466279,0.003502157,0.003666669,0.001915727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"nonrandomized_trial","study_design_scores_codex":[0.02785526,0.02054492,0.226653,0.0005085149,0.00044373,0.0003124601,0.01429914,0.00955463,0.1270686,0.000686701,0.002922489,0.5691506],"study_design_scores_gemma":[0.0005716617,0.02608541,0.8676106,0.0001997811,0.0002894019,0.0004724754,0.002297148,0.01452834,0.08374628,0.001160376,0.002893184,0.0001454618],"study_design_candidate":"nonrandomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9987614,0.00006204727,0.0003993201,0.00004677565,0.00001088487,0.00001665167,0.000009372257,0.00002181157,0.0006717808],"genre_scores_gemma":[0.9989007,0.00002972264,0.0007690741,0.00002247889,0.00000842588,0.00001307098,0.0000155721,0.000003476468,0.0002375061],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003729909,"threshold_uncertainty_score":0.01972586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04862864532436076,"score_gpt":0.3927501088103708,"score_spread":0.34412146348601,"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."}}