{"id":"W6992993283","doi":"","title":"Multi-objective Representation for Numbers in Clinical Narratives Using CamemBERT-bio","year":2024,"lang":"en","type":"preprint","venue":"Open Repository and Bibliography (University of Luxembourg)","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","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); Key (lock); Embedding; Simple (philosophy); Component (thermodynamics); Narrative","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":[],"consensus_categories":[],"category_scores_codex":[0.0005353861,0.0002015851,0.000448647,0.001745653,0.0001673969,0.0001026729,0.0004401678,0.0006082801,0.000003930839],"category_scores_gemma":[0.000009903121,0.0002169933,0.0003722622,0.001459499,0.0006019102,0.00001277129,0.001397348,0.0003443829,2.908638e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009397632,"about_ca_system_score_gemma":0.0001512148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001666503,"about_ca_topic_score_gemma":0.0002983618,"domain_scores_codex":[0.9983823,0.0002378791,0.0003020803,0.0007811775,0.0001127472,0.0001837987],"domain_scores_gemma":[0.9991028,0.00006636573,0.0002923955,0.000306979,0.0001335626,0.00009793198],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003771364,0.001237061,0.8783489,0.001999663,0.003378047,0.0002798305,0.005114629,0.0001895851,0.06884839,0.0001034327,0.02366612,0.01306297],"study_design_scores_gemma":[0.01702484,0.004453287,0.7699561,0.005054655,0.002131155,0.0002612459,0.1186586,0.006156563,0.02340632,0.01049943,0.03781075,0.004587005],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9913215,0.002642989,0.003114225,0.0001060627,0.000549025,0.0008263148,0.00008222509,0.00001639161,0.001341284],"genre_scores_gemma":[0.9553692,0.00192637,0.04172574,0.00002802388,0.0001565325,0.000008537791,0.0001005511,0.00001972324,0.0006653438],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.113544,"threshold_uncertainty_score":0.884873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06711852228574952,"score_gpt":0.369380676682088,"score_spread":0.3022621543963384,"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."}}