{"id":"W2962968929","doi":"","title":"MIMIC-Extract","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Pipeline (software); Machine learning; Benchmark (surveying); Artificial intelligence; Raw data; Outlier; Pipeline transport; USable; Data modeling; Data mining; Database; World Wide Web","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"],"consensus_categories":[],"category_scores_codex":[0.0002146003,0.0003414606,0.000367133,0.0001909836,0.000161664,0.0001495597,0.003224151,0.0003421243,0.00007309473],"category_scores_gemma":[0.0001172047,0.0004168103,0.0002376042,0.0005905477,0.00006254499,0.0002689255,0.003350287,0.001659961,0.0005105851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002142195,"about_ca_system_score_gemma":0.0003678497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004067908,"about_ca_topic_score_gemma":0.00003424032,"domain_scores_codex":[0.997453,0.0002821816,0.0002210014,0.001503577,0.0001244028,0.0004158831],"domain_scores_gemma":[0.9974636,0.0001561893,0.0002884765,0.001616604,0.000132282,0.0003427922],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004451903,0.0001210741,0.02589858,0.0006811737,0.0001524036,0.002842746,0.001142243,0.3149773,0.00005269787,0.6429961,0.004136748,0.006954378],"study_design_scores_gemma":[0.0002346831,0.00006538609,0.005654822,0.00008595434,0.00002812725,0.000009726658,0.00002312858,0.9361482,0.00002911869,0.05034735,0.006847543,0.000525919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07573192,0.0001268977,0.9067889,0.004119074,0.001426397,0.0004108648,0.00001656156,0.001163074,0.01021631],"genre_scores_gemma":[0.9909975,0.00008301686,0.006937578,0.0006511962,0.0001745744,6.963082e-7,0.00001703886,0.00002593995,0.001112456],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9152656,"threshold_uncertainty_score":0.9998284,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1196011531810332,"score_gpt":0.2193688871490302,"score_spread":0.09976773396799696,"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."}}