{"id":"W4412946543","doi":"10.1016/j.cognition.2025.106277","title":"When metrics matter: How reasoning in different metrics impacts judgments of uncertainty","year":2025,"lang":"en","type":"article","venue":"Cognition","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Anderson School of Management, University of California, Los Angeles","keywords":"Psychology; Cognitive psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01606054,0.0006297601,0.0008854517,0.002330958,0.0009844258,0.01229121,0.001483609,0.004101661,0.007082143],"category_scores_gemma":[0.1892868,0.0007967838,0.0009790284,0.001864808,0.004608135,0.01611463,0.003045492,0.003878634,0.0008251069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001872465,"about_ca_system_score_gemma":0.001845916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004882027,"about_ca_topic_score_gemma":0.003758424,"domain_scores_codex":[0.9821911,0.01075243,0.0006913559,0.002181821,0.003286694,0.0008965934],"domain_scores_gemma":[0.8755041,0.09933529,0.008882723,0.006273801,0.006885206,0.003119008],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.004062621,0.002551741,0.2534821,0.001306721,0.002391207,0.001031469,0.03227613,0.03141594,0.02867799,0.3768596,0.01275154,0.253193],"study_design_scores_gemma":[0.0002189285,0.0003182825,0.129539,0.0003284905,0.0005932637,0.0003405134,0.005951686,0.05378247,0.004879572,0.7976597,0.006096314,0.0002917737],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8753598,0.001659982,0.06155916,0.01031064,0.0002803232,0.0001127568,0.0003188543,0.0002030654,0.05019535],"genre_scores_gemma":[0.9910409,0.0001696194,0.007447891,0.0005426767,0.00004995856,0.00002697399,0.0001048939,0.0001204282,0.0004966719],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01606054,"threshold_uncertainty_score":0.08493727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.105027229615467,"score_gpt":0.3821977714926075,"score_spread":0.2771705418771405,"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."}}