{"id":"W4394905977","doi":"10.48550/arxiv.2404.10171","title":"Are Medium-Sized Transformers Models still Relevant for Medical Records Processing?","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données; Université de Montréal","keywords":"Narrative; Psychology; Artificial intelligence; Computer science; Linguistics; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00112955,0.0005681269,0.0007371992,0.0004822044,0.0002304223,0.0002204416,0.003022583,0.0009259069,0.00005540304],"category_scores_gemma":[0.0003892335,0.0005806783,0.0004573921,0.0008099942,0.0001877508,0.0003737275,0.001698388,0.0024771,0.00004869488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004553006,"about_ca_system_score_gemma":0.002440174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002818666,"about_ca_topic_score_gemma":0.0004284315,"domain_scores_codex":[0.9958607,0.00025263,0.0005502839,0.002104607,0.0004554083,0.0007763999],"domain_scores_gemma":[0.9970044,0.0003980005,0.0005105451,0.001041794,0.0004394723,0.0006058247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007686664,0.0005180408,0.00204445,0.02191352,0.0007462604,0.004561113,0.007081627,0.4328316,0.00001061517,0.4097164,0.009496795,0.1103109],"study_design_scores_gemma":[0.0005831646,0.00007811913,0.00009343576,0.001086417,0.00008765131,0.00001665746,0.0001041153,0.8260275,0.00001306006,0.1688205,0.002564955,0.0005244261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02954253,0.0005508526,0.9549192,0.008090405,0.002593915,0.001131578,0.00007826037,0.001140571,0.001952741],"genre_scores_gemma":[0.9878785,0.0003998312,0.008417342,0.0006178031,0.0003174355,0.00001924773,0.00003203757,0.00007892081,0.002238887],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.958336,"threshold_uncertainty_score":0.9998242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07830069375804545,"score_gpt":0.2480306589230999,"score_spread":0.1697299651650544,"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."}}