{"id":"W2900647770","doi":"10.1017/s1930297500006628","title":"Boosting intelligence analysts’ judgment accuracy: What works, what fails?","year":2018,"lang":"en","type":"article","venue":"Judgment and Decision Making","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada","funders":"Ministère de la Défense Nationale; Government of the United Kingdom","keywords":"Boosting (machine learning); Intelligence analysis; Psychology; Unpacking; Overconfidence effect; Cognitive psychology; Social psychology; Artificial intelligence; Computer 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1367915,0.001123835,0.00220587,0.003867469,0.001431192,0.00564121,0.002315471,0.002163631,0.001212137],"category_scores_gemma":[0.3878211,0.0005642773,0.001114128,0.00275576,0.0034023,0.0056374,0.002717599,0.002964024,0.000934987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001887286,"about_ca_system_score_gemma":0.002716636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003049109,"about_ca_topic_score_gemma":0.002852079,"domain_scores_codex":[0.8884665,0.08133651,0.004444881,0.006171598,0.01803544,0.001544995],"domain_scores_gemma":[0.5611422,0.3180176,0.02980969,0.04175717,0.0434122,0.00586119],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002112975,0.000711206,0.2733456,0.0007947647,0.001614862,0.0001029291,0.005175879,0.008329321,0.002819591,0.01017524,0.01018949,0.6846282],"study_design_scores_gemma":[0.0007698434,0.006061328,0.4569586,0.003159158,0.002733712,0.0007984838,0.007147523,0.2773588,0.03442053,0.1753881,0.03446311,0.0007409261],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7818947,0.01523717,0.1429693,0.0332836,0.001429065,0.0005325268,0.0003858088,0.001871664,0.02239608],"genre_scores_gemma":[0.9550633,0.0006107391,0.04199531,0.001300369,0.0003186575,0.00007621141,0.00008879715,0.00009764705,0.0004489099],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8632085,"threshold_uncertainty_score":0.723431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2369632656398206,"score_gpt":0.4637587489756343,"score_spread":0.2267954833358137,"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."}}