{"id":"W6884851608","doi":"10.13026/1wf7-pm14","title":"Asclepius-R : Clinical Large Language Model Built On MIMIC-III Discharge Summaries","year":2023,"lang":"en","type":"dataset","venue":"PhysioNet","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Usability; Resource (disambiguation); Language model; Benchmark (surveying); Data modeling","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":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001407663,0.001167343,0.001724142,0.0004743994,0.0003886016,0.0001958139,0.001846832,0.0008969682,0.0004152072],"category_scores_gemma":[0.0008140653,0.001045313,0.0008179669,0.0007400648,0.0002650053,0.0002763123,0.001568667,0.002318981,0.2145655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001689511,"about_ca_system_score_gemma":0.0002957659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001430119,"about_ca_topic_score_gemma":0.002481632,"domain_scores_codex":[0.9932975,0.0005383408,0.001328464,0.001830529,0.001541597,0.001463561],"domain_scores_gemma":[0.994339,0.0007504549,0.0007825882,0.003506882,0.000127675,0.0004933508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005952444,0.001457544,0.00001077387,0.0002036604,0.0002784739,0.00009351994,0.000104229,0.0002629197,0.0001763833,0.0001355195,0.9965583,0.0001234025],"study_design_scores_gemma":[0.002017937,0.0002176913,0.0003667133,0.0004079063,0.0003270525,0.00000166807,0.0000978875,0.005517733,0.00004514962,0.0005558995,0.9891565,0.001287864],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.003268395,0.0002000103,0.000008273073,0.0001537392,0.001436202,0.0008399743,0.9931257,0.0008280398,0.0001396195],"genre_scores_gemma":[0.001074676,0.000596441,0.00005941331,0.0008571642,0.002020332,0.0002013948,0.9923133,0.0005057608,0.002371478],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.2141503,"threshold_uncertainty_score":0.9999827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06624195068223274,"score_gpt":0.3947683611672638,"score_spread":0.3285264104850311,"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."}}