{"id":"W4313424993","doi":"10.1017/s1930297500004320","title":"Too soon to tell if the US intelligence community prediction market is more accurate than intelligence reports: Commentary on","year":2019,"lang":"en","type":"article","venue":"Judgment and Decision Making","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada","funders":"Ministère de la Défense Nationale","keywords":"Imputation (statistics); Intelligence analysis; Actuarial science; Econometrics; Economics; Psychology; Computer science; Missing data; Machine learning; Computer security","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":[],"consensus_categories":[],"category_scores_codex":[0.004762175,0.0002370846,0.0002718688,0.000244761,0.0007531189,0.0005363045,0.001020827,0.00009711082,0.0005961579],"category_scores_gemma":[0.0007064756,0.0001479106,0.0001155193,0.000819533,0.0001106472,0.0002655854,0.0009119329,0.0004769094,0.0001844475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008592901,"about_ca_system_score_gemma":0.00001950589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001145841,"about_ca_topic_score_gemma":0.00003090417,"domain_scores_codex":[0.9967184,0.0001876976,0.0009819585,0.0006005359,0.001221007,0.0002904093],"domain_scores_gemma":[0.9944473,0.003094597,0.0004137341,0.001727606,0.0001987557,0.0001180384],"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":[0.0002321928,0.0001464323,0.02040023,0.000006756717,0.00001601828,0.000006863803,0.001881659,0.001874189,0.00008894071,0.0007380004,0.2871265,0.6874822],"study_design_scores_gemma":[0.0002270184,0.001391253,0.08189747,0.001372495,0.00006338525,0.0001439985,0.01192834,0.1789255,0.005805738,0.4212192,0.29603,0.0009955539],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8111276,0.00005786625,0.1758035,0.005159922,0.0004945986,0.001095785,0.00004266416,0.0001168651,0.006101194],"genre_scores_gemma":[0.9822948,0.00006579757,0.008412826,0.008578572,0.00006793902,0.00005728656,0.000005653844,0.0000163081,0.0005008259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6864867,"threshold_uncertainty_score":0.6527511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1131901529247397,"score_gpt":0.4007133235420235,"score_spread":0.2875231706172838,"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."}}