{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008213527,0.0007464631,0.0008321976,0.001036398,0.0005345352,0.001266204,0.0009448077,0.001224675,0.003300947],"category_scores_gemma":[0.06368936,0.0004369469,0.001262662,0.0007104266,0.0007741544,0.0014506,0.001626608,0.002123196,0.00169551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003462906,"about_ca_system_score_gemma":0.0007641274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001262087,"about_ca_topic_score_gemma":0.001200187,"domain_scores_codex":[0.9913571,0.002276707,0.001205325,0.001731255,0.003023923,0.0004056102],"domain_scores_gemma":[0.9649339,0.01288222,0.009405733,0.006267389,0.005364722,0.001146028],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003783403,0.00461366,0.7358806,0.0006821752,0.001704548,0.001023075,0.004378901,0.002088891,0.01522945,0.002758492,0.01355404,0.2143028],"study_design_scores_gemma":[0.0001328937,0.003758867,0.9656218,0.0001352762,0.0002078471,0.00114836,0.0005847677,0.002429064,0.009443247,0.003673534,0.01273726,0.0001270082],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9460854,0.0006967083,0.02352274,0.001010434,0.0003520094,0.001385583,0.002089902,0.0005954723,0.02426181],"genre_scores_gemma":[0.97765,0.0002605048,0.01224771,0.0005071129,0.0001197679,0.001350839,0.002155686,0.0001709629,0.005537327],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008213527,"threshold_uncertainty_score":0.04343778,"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."}}