{"id":"W2893743957","doi":"10.1017/s1930297500006240","title":"How generalizable is good judgment? A multi-task, multi-benchmark study","year":2017,"lang":"en","type":"article","venue":"Judgment and Decision Making","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Consistency (knowledge bases); Coherence (philosophical gambling strategy); Psychology; Task (project management); Cognitive psychology; Quality (philosophy); Axiom; Social psychology; Computer science; Artificial intelligence; Mathematics; Statistics; Epistemology","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":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004093754,0.0005773568,0.0009551508,0.0006141643,0.002384938,0.00911426,0.002403296,0.0002474845,0.0005075136],"category_scores_gemma":[0.002305811,0.0004308652,0.000347076,0.0003165666,0.0001874564,0.001696834,0.001903326,0.0003613411,0.0004515566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001247125,"about_ca_system_score_gemma":0.00006833987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008612473,"about_ca_topic_score_gemma":0.0003349857,"domain_scores_codex":[0.9938061,0.0001585321,0.001356581,0.001867625,0.00206399,0.0007471461],"domain_scores_gemma":[0.9938281,0.001141529,0.001257999,0.003035591,0.0003836534,0.0003531534],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001198768,0.0008098748,0.1484112,0.000003014258,0.00003832201,0.0001022469,0.0008207912,0.00009757371,0.0001850798,0.00006410572,0.009974505,0.8393734],"study_design_scores_gemma":[0.02121766,0.001734245,0.4833037,0.0008398346,0.0004356361,0.0001274151,0.01564992,0.1432549,0.0005366998,0.1428047,0.1860072,0.00408797],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9557912,0.000397364,0.03914011,0.0006589344,0.002006057,0.000853288,0.00004811151,0.00007412244,0.001030822],"genre_scores_gemma":[0.926681,0.00006106991,0.06813366,0.0005923138,0.0001791065,0.00004869392,0.000002226476,0.00004743097,0.00425443],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8352854,"threshold_uncertainty_score":0.9998143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.23110184384626,"score_gpt":0.4355178639077162,"score_spread":0.2044160200614563,"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."}}