{"id":"W4411604797","doi":"10.1177/0272989x251346788","title":"Forewarning Artificial Intelligence about Cognitive Biases","year":2025,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Healthcare cost, quality, practices","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canada Research Chairs","keywords":"Cognition; Cognitive bias; Psychology; Vigilance (psychology); Cognitive psychology; Generative grammar; Artificial intelligence; Computer science","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009017221,0.0002319658,0.0004857712,0.0004014766,0.001618827,0.00004815408,0.0005255815,0.0005874561,0.005619884],"category_scores_gemma":[0.2388162,0.0001967191,0.0001104898,0.0009803494,0.0002433623,0.0002583092,0.0006283603,0.002344656,0.001460811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002219682,"about_ca_system_score_gemma":0.001634817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000217322,"about_ca_topic_score_gemma":0.0009175247,"domain_scores_codex":[0.9927369,0.002561665,0.00171633,0.0006248384,0.001510311,0.0008499777],"domain_scores_gemma":[0.9280269,0.07005209,0.0004873533,0.0004169729,0.0006162269,0.0004004469],"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":[0.0002394742,0.00008174098,0.01181937,0.0001454238,0.00002247295,0.00008686049,0.001551485,0.000004599199,0.000005653241,0.01550456,0.002382048,0.9681563],"study_design_scores_gemma":[0.001660298,0.0005491867,0.1128731,0.1537574,0.0002738207,0.00003078272,0.07259896,0.04672677,0.0003072641,0.484035,0.1257177,0.001469829],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3141544,0.0009743712,0.6543444,0.01010548,0.004082058,0.0009160563,0.00002115377,0.0002510448,0.015151],"genre_scores_gemma":[0.9692348,0.0002109169,0.00323386,0.02618687,0.0006287494,0.0001250167,0.00001545354,0.00002714027,0.0003371659],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9666865,"threshold_uncertainty_score":0.999957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7150225695664488,"score_gpt":0.6469278259500016,"score_spread":0.06809474361644718,"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."}}