{"id":"W2747940070","doi":"10.3758/s13428-017-0963-x","title":"The cognitive reflection test is robust to multiple exposures","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":159,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Test (biology); Computer science; Cognition; Reflection (computer programming); Psychology; Cognitive psychology; Artificial intelligence; Statistics; Mathematics; Geology; Programming language; Neuroscience","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03896362,0.0001426981,0.0001825726,0.0003001801,0.01193834,0.001874274,0.002291562,0.0002174209,0.0002477342],"category_scores_gemma":[0.07929762,0.0001126192,0.0001073136,0.00066219,0.002255302,0.0003597655,0.0008875641,0.001069147,0.0002110179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003653772,"about_ca_system_score_gemma":0.0005069834,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01434024,"about_ca_topic_score_gemma":0.008990362,"domain_scores_codex":[0.991716,0.003976754,0.0002850147,0.0005540193,0.002200087,0.001268076],"domain_scores_gemma":[0.9864343,0.009926327,0.0001046476,0.00116418,0.001880696,0.0004898285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001134802,0.000244665,0.1228525,0.000006941428,0.00001300542,0.00004942892,0.006269635,2.824372e-7,0.0181916,0.001043918,0.02313568,0.8280789],"study_design_scores_gemma":[0.0006315969,0.0006912937,0.3756223,0.0001420731,0.00002639289,0.000006634591,0.02690391,0.00006895861,0.1150427,0.003872205,0.4764803,0.0005116041],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5714381,0.0006645868,0.03476397,0.08071434,0.002368182,0.01751791,0.0001731018,0.00108721,0.2912726],"genre_scores_gemma":[0.891676,0.0003528389,0.07499979,0.00008365303,0.0005656469,0.003277599,0.000002077639,0.00005754788,0.02898485],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8275672,"threshold_uncertainty_score":0.9991619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7821180915133141,"score_gpt":0.736822124123797,"score_spread":0.04529596738951713,"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."}}