{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001567656,0.0002338343,0.0003302261,0.0002219619,0.0003347878,0.004024273,0.0002524566,0.0001048531,0.000566921],"category_scores_gemma":[0.004541328,0.0001930193,0.00007556748,0.0003172893,0.0001233662,0.002845693,0.0002721523,0.0001711933,0.0001087991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008250024,"about_ca_system_score_gemma":0.00004120912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002657496,"about_ca_topic_score_gemma":0.00001697478,"domain_scores_codex":[0.9980062,0.0001172022,0.0006064001,0.0004524643,0.0004655242,0.0003521882],"domain_scores_gemma":[0.9917542,0.007147945,0.0003249999,0.0004565088,0.0002037364,0.0001125597],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005998183,0.00004611878,0.0001082058,0.00002731242,0.0000263777,0.000005012456,0.001863208,0.000005728998,0.00008681897,0.0079902,0.005119251,0.9846618],"study_design_scores_gemma":[0.0003511666,0.0001476962,0.0005507582,0.007060645,0.0001207754,0.00002643414,0.092204,0.005400483,0.002889814,0.8838962,0.006793987,0.00055808],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1646944,0.004818582,0.8256859,0.0005947999,0.003323269,0.00033056,0.000001128618,0.0001167161,0.0004347366],"genre_scores_gemma":[0.4698703,0.004511731,0.5242966,0.000826447,0.0003309927,0.00002290091,0.000003608082,0.00002523597,0.0001121117],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9841037,"threshold_uncertainty_score":0.9970096,"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."}}