{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007883941,0.0001035525,0.0002460667,0.00005830468,0.00005226929,0.00001161424,0.00007810203,0.0001183722,0.00007324373],"category_scores_gemma":[0.005564745,0.00005252759,0.00009437854,0.0002934979,0.0002939222,0.00001437756,0.00001538915,0.0002860574,0.00001892974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000825624,"about_ca_system_score_gemma":0.00003470484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006876871,"about_ca_topic_score_gemma":0.000002372262,"domain_scores_codex":[0.9989471,0.0001508567,0.0003504987,0.0002330029,0.0001825887,0.0001359897],"domain_scores_gemma":[0.9718473,0.02779439,0.00009882887,0.0001769221,0.00004186419,0.0000407216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003457226,0.0002344671,0.003859017,0.0000910473,0.0008313626,0.00002516346,0.00205721,0.00003188643,0.009900846,0.07407093,0.002391966,0.9030489],"study_design_scores_gemma":[0.008775525,0.02153485,0.09613948,0.01266949,0.004229285,0.0001322191,0.006696275,0.03234487,0.7617329,0.05315822,0.001610289,0.0009765367],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9257112,0.000429749,0.03749031,0.005256402,0.0004902186,0.001040944,0.00002393689,0.00005521357,0.02950203],"genre_scores_gemma":[0.9986565,0.00009680462,0.00002309107,0.0009546421,0.00008234007,0.00009122288,0.00003299323,0.00001196276,0.00005044025],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9020723,"threshold_uncertainty_score":0.6661921,"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."}}