{"id":"W3121427863","doi":"10.1017/s1930297500007695","title":"Performance on the Cognitive Reflection Test is stable across time","year":2018,"lang":"en","type":"article","venue":"Judgment and Decision Making","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":110,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Conservatism; Psychology; Cognition; Test (biology); Cognitive psychology; Set (abstract data type); Cognitive style; Stability (learning theory); Reflection (computer programming); Social psychology; Computer science; Machine learning","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":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003373598,0.0002232126,0.0002883868,0.0001903984,0.001264985,0.001064529,0.0005056196,0.0001156972,0.002059593],"category_scores_gemma":[0.002093897,0.0001296743,0.0001004156,0.0006531615,0.0002298443,0.0004483815,0.0003592041,0.0002122501,0.005797253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006984408,"about_ca_system_score_gemma":0.00003225674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004174,"about_ca_topic_score_gemma":0.00001274933,"domain_scores_codex":[0.9970456,0.00005059609,0.0006710369,0.0007245672,0.001113263,0.0003949882],"domain_scores_gemma":[0.9927425,0.005838146,0.0003291409,0.0005871876,0.0004138169,0.00008915747],"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":[0.0002533516,0.00006985075,0.009409419,6.683487e-7,0.000005292342,0.000003089244,0.0006533532,0.000009357773,0.0002075847,0.0000329238,0.02345329,0.9659018],"study_design_scores_gemma":[0.004082639,0.005661898,0.1827238,0.002522787,0.0001326797,0.0001764792,0.008663177,0.1889962,0.0134456,0.3928054,0.198381,0.002408347],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9832978,0.00003059424,0.0009195775,0.0003652083,0.0005613264,0.0002218661,0.00003093957,0.00004371313,0.01452894],"genre_scores_gemma":[0.9948418,0.00002456792,0.0009075574,0.002061479,0.0002416883,0.00001199885,8.954928e-7,0.00001780046,0.0018922],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9634935,"threshold_uncertainty_score":0.9999725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1468511458828891,"score_gpt":0.4260042680523236,"score_spread":0.2791531221694344,"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."}}