{"id":"W4386224103","doi":"10.3390/jcm12175550","title":"Examining the Validity of ChatGPT in Identifying Relevant Nephrology Literature: Findings and Implications","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Medicine; Internal medicine; External validity; Nephrology; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006209067,0.00006897694,0.0005008747,0.0002601607,0.00005210525,0.000005863868,0.0001022083,0.0001337918,0.00002910521],"category_scores_gemma":[0.0112911,0.00003937063,0.00006522005,0.0006450033,0.0002675338,0.00007736668,0.00002876096,0.0006883493,0.000004058308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001930792,"about_ca_system_score_gemma":0.000151298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003403164,"about_ca_topic_score_gemma":0.0000177206,"domain_scores_codex":[0.9975328,0.0002046639,0.001761643,0.0001214963,0.0002262459,0.0001531296],"domain_scores_gemma":[0.9944745,0.004324305,0.0005334986,0.0001829109,0.0003464254,0.0001383038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002332721,0.00009569184,0.8808818,0.0001744473,0.00003924222,0.00004822733,0.00646115,0.000003257018,0.002633548,0.0004463237,0.005560807,0.1034222],"study_design_scores_gemma":[0.0002619711,0.001202405,0.9853632,0.001106921,0.00007909105,0.0002040074,0.002204246,0.0001351804,0.0002453556,0.006934911,0.002229715,0.00003297996],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9263487,0.0008518302,0.0001273052,0.07154623,0.0008823733,0.0001356599,7.412681e-7,0.000006018029,0.0001011441],"genre_scores_gemma":[0.9906308,0.006283092,0.0001642878,0.001570309,0.001282434,0.000003268317,0.000003461955,0.000006850551,0.00005548149],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1044813,"threshold_uncertainty_score":0.9970372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5086633924811425,"score_gpt":0.5614521106476769,"score_spread":0.05278871816653441,"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."}}