{"id":"W4252516057","doi":"10.31234/osf.io/fb9ej","title":"Improving Probability Judgment in Intelligence Analysis: From Structured Analysis to Statistical Aggregation","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Bayes' theorem; Intelligence analysis; Contrast (vision); Coherence (philosophical gambling strategy); Computer science; Range (aeronautics); Value (mathematics); Econometrics; Machine learning; Artificial intelligence; Statistics; Bayesian probability; Mathematics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002872018,0.0003109446,0.001016167,0.00178202,0.00006629228,0.0005647368,0.001575158,0.0002940969,0.002637902],"category_scores_gemma":[0.002676331,0.0002382828,0.0004360648,0.0060669,0.00007213982,0.00008602232,0.001505098,0.0005080304,0.0001703028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003236197,"about_ca_system_score_gemma":0.0001699736,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008525844,"about_ca_topic_score_gemma":0.01681236,"domain_scores_codex":[0.9943874,0.0002670401,0.001683113,0.001954647,0.001401868,0.0003059469],"domain_scores_gemma":[0.9948677,0.001303208,0.0006216314,0.002550086,0.000479566,0.000177782],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004565541,0.0001475333,0.1231855,0.00001634168,0.00104604,0.000002174971,0.0006520832,0.6477941,0.0001143997,0.005998998,0.00064118,0.2203561],"study_design_scores_gemma":[0.00002717197,0.00002183225,0.1009831,0.00001329387,0.0009222119,6.152266e-8,0.000124775,0.5800052,0.0007190066,0.3168471,0.00006379082,0.0002724427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.221945,0.00001547881,0.7756954,0.0003522176,0.00007968499,0.0009686745,0.0005294112,0.00008715744,0.0003269498],"genre_scores_gemma":[0.6941656,0.000001760589,0.3051385,0.00007405355,0.00002273568,0.0001574985,0.0002875228,0.000007354293,0.0001449159],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4722207,"threshold_uncertainty_score":0.9982738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1179080405819306,"score_gpt":0.4026068097760591,"score_spread":0.2846987691941285,"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."}}