{"id":"W2122152276","doi":"10.1016/j.jet.2011.06.015","title":"Nonmanipulable Bayesian testing","year":2011,"lang":"en","type":"article","venue":"Journal of Economic Theory","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Contrast (vision); Probabilistic logic; Bayesian probability; Computer science; Set (abstract data type); Process (computing); Test (biology); Machine learning; Econometrics; Artificial intelligence; Mathematics","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007860591,0.0001330077,0.00043252,0.0003869621,0.0001016692,0.000178792,0.001104236,0.00007785771,0.003947072],"category_scores_gemma":[0.0018208,0.0000978184,0.0002370563,0.000120505,0.00008930123,0.0007273366,0.0001126342,0.0002194595,0.00126063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001192888,"about_ca_system_score_gemma":0.0001832278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001467911,"about_ca_topic_score_gemma":0.00001049242,"domain_scores_codex":[0.9977794,0.0001577151,0.001416639,0.0002321458,0.0001926834,0.0002214337],"domain_scores_gemma":[0.9961609,0.001670181,0.001347615,0.0004571695,0.0001874359,0.0001767082],"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":[0.0002297026,0.000145162,0.03311419,0.000001578288,0.00004729803,0.0001201657,0.001041802,0.0006831456,0.0002740514,0.02241729,0.006429288,0.9354963],"study_design_scores_gemma":[0.0003448864,0.0001919317,0.004688262,0.00002683053,0.00002530345,0.0003716693,0.0009836335,0.0006326819,0.0004577101,0.9867374,0.005378028,0.000161677],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9315288,0.00009106947,0.003926671,0.00004897862,0.001754055,0.00004057412,0.000003925957,0.00001089129,0.06259505],"genre_scores_gemma":[0.9878981,0.000005067508,0.01064275,0.0001407479,0.0002900979,4.892858e-7,9.092932e-8,0.0000166175,0.001006031],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9643201,"threshold_uncertainty_score":0.999517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.338175378747531,"score_gpt":0.3873039713669915,"score_spread":0.04912859261946051,"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."}}