{"id":"W4399197789","doi":"10.48550/arxiv.2405.18448","title":"Multi-objective Representation for Numbers in Clinical Narratives: A CamemBERT-Bio-Based Alternative to Large-Scale LLMs","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Mathematics, Computing, and Information Processing","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":"Representation (politics); Narrative; Mathematics; Forestry; Geography; Art; Literature; Political science","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"],"consensus_categories":[],"category_scores_codex":[0.0010111,0.0003365571,0.0005050828,0.0005457132,0.0001603051,0.00028152,0.001184361,0.0002561406,0.00001287578],"category_scores_gemma":[0.0002742087,0.0003722106,0.0003211465,0.0008767491,0.00008204211,0.0005018768,0.001366311,0.0006491155,0.00008042645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003418654,"about_ca_system_score_gemma":0.0004321127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001179178,"about_ca_topic_score_gemma":0.0003062584,"domain_scores_codex":[0.9973301,0.0001961651,0.0007070814,0.001218608,0.0001468659,0.0004011374],"domain_scores_gemma":[0.9977298,0.0003876097,0.000547011,0.0007453299,0.0004048225,0.0001854308],"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":[0.0002005081,0.0009424672,0.005609095,0.001447496,0.0002968266,0.0001321693,0.1180096,0.7858375,0.00002015371,0.0828997,0.002033777,0.002570773],"study_design_scores_gemma":[0.001071418,0.00007076146,0.0004341559,0.0004542969,0.00002303011,0.000001105763,0.003342321,0.9457951,0.0001796732,0.04801184,0.0002231384,0.0003932018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1715249,0.00001419005,0.8242819,0.0001659841,0.0009523339,0.0009109995,0.00002765139,0.0001867536,0.00193527],"genre_scores_gemma":[0.9109823,0.000008153282,0.08748248,0.0003948987,0.0001027996,0.0000144985,0.00002614432,0.00002362626,0.0009651346],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7394574,"threshold_uncertainty_score":0.999873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1069859715520276,"score_gpt":0.2959768351915429,"score_spread":0.1889908636395153,"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."}}