{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001553408,0.0001574885,0.0004190537,0.001971701,0.00006813309,0.0002834084,0.0004354461,0.0001211813,0.0002328599],"category_scores_gemma":[0.005369562,0.0001198426,0.000131157,0.002142299,0.00005279468,0.0003089111,0.0001798688,0.0001646814,0.0001002877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001784989,"about_ca_system_score_gemma":0.00005995257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003653962,"about_ca_topic_score_gemma":0.00006068515,"domain_scores_codex":[0.9978821,0.0001471083,0.0006610053,0.0004120404,0.0006604363,0.0002373032],"domain_scores_gemma":[0.9972811,0.001514054,0.0003732154,0.0003973391,0.0003571098,0.00007720329],"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":[0.0001104452,0.0003878925,0.2397101,0.0000215462,0.00002508087,0.00001038047,0.0002374848,0.0001503858,0.0008382848,0.000179316,0.01522759,0.7431015],"study_design_scores_gemma":[0.003419291,0.0002792026,0.5417348,0.001034586,0.0002183483,0.000007824233,0.002644691,0.01206794,0.01280266,0.4189637,0.006141822,0.0006851971],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893977,0.0001523493,0.003917431,0.0006493593,0.0005010451,0.0001878646,0.00005144844,0.00001721564,0.005125606],"genre_scores_gemma":[0.9986342,0.0000336754,0.0005719947,0.0002523889,0.00001869215,0.000009869008,0.00002274415,0.00000775642,0.0004486775],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7424163,"threshold_uncertainty_score":0.6428255,"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."}}