{"id":"W4390970405","doi":"10.1371/journal.pdig.0000417","title":"Peer review of GPT-4 technical report and systems card","year":2024,"lang":"en","type":"article","venue":"PLOS Digital Health","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Institute on Minority Health and Health Disparities; National Institute of Biomedical Imaging and Bioengineering; Fogarty International Center; Gordon and Betty Moore Foundation; National Heart, Lung, and Blood Institute; Radiological Society of North America; National Institutes of Health; National Science Foundation","keywords":"Transparency (behavior); CLARITY; Intellectual property; Accountability; Health care; Harm; Business; Public relations; Political science; Computer science; Computer security","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":[0.0006906357,0.00007872831,0.0003468884,0.00006463083,0.00003105968,0.00003647486,0.00003080401,0.00005551807,0.00001086494],"category_scores_gemma":[0.0009122181,0.00006212549,0.0000514786,0.0002023825,0.00005359708,0.0001172731,0.00001735761,0.0001665266,0.00003734701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001501893,"about_ca_system_score_gemma":0.0007609337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002618561,"about_ca_topic_score_gemma":0.000004625324,"domain_scores_codex":[0.9984181,0.00001858163,0.0006814105,0.000215626,0.0004890831,0.0001771918],"domain_scores_gemma":[0.9989353,0.0001268867,0.00008663268,0.0002265621,0.0004146554,0.0002099209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005785991,0.0005569987,0.02022242,0.3808767,0.0001089729,0.0004715717,0.00148482,5.240785e-7,0.0001393685,0.004589183,0.2399074,0.3515842],"study_design_scores_gemma":[0.00008130912,0.00276586,0.006530843,0.2145816,0.0002400289,0.01129379,0.00211856,0.0005780812,0.0007347717,0.001941475,0.7586102,0.0005233813],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.1696211,0.5784799,0.0003390349,0.1863114,0.002150177,0.003553829,0.0001444185,0.0005265861,0.05887356],"genre_scores_gemma":[0.9826998,0.01170263,0.00005997492,0.001078174,0.0003089839,0.00003715001,0.0001478468,0.00001781972,0.003947651],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8130787,"threshold_uncertainty_score":0.2533404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2373284398045087,"score_gpt":0.4738384137552404,"score_spread":0.2365099739507317,"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."}}