{"id":"W1965466476","doi":"10.1016/j.jbi.2012.05.006","title":"A study of terminology auditors’ performance for UMLS semantic type assignments","year":2012,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"New York Institute of Technology","funders":"U.S. National Library of Medicine","keywords":"Unified Medical Language System; Computer science; Audit; Terminology; Recall; Task (project management); Reliability (semiconductor); Information retrieval; Natural language processing; Sample (material); Measure (data warehouse); Semantics (computer science); Artificial intelligence; Data mining; Accounting; Linguistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0007000455,0.0001117009,0.0002985348,0.0001156607,0.00004283006,0.000006853199,0.0002647502,0.0002097289,0.00001020575],"category_scores_gemma":[0.0004715387,0.00007711385,0.0000805408,0.0001161813,0.0001899507,0.00001407222,0.00009287915,0.0001381189,0.000003867015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001466071,"about_ca_system_score_gemma":0.00009580953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.606355e-7,"about_ca_topic_score_gemma":3.129283e-7,"domain_scores_codex":[0.9984996,0.00003456631,0.000831301,0.0000466193,0.0003137106,0.0002741875],"domain_scores_gemma":[0.9988278,0.00005897105,0.0006135711,0.0001576426,0.0001716711,0.0001703668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002266213,0.01058861,0.1950772,0.001863312,0.002734861,0.0000199036,0.0191032,0.00004509471,0.08208452,0.00004431481,0.1662987,0.5198741],"study_design_scores_gemma":[0.01718295,0.07660681,0.09582121,0.0005677302,0.0008506923,0.001373037,0.02847171,0.001610213,0.06070132,0.0000956092,0.7155758,0.001142891],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941825,0.0002094989,0.004008065,0.00006134496,0.001318297,0.0001362833,0.000005126753,0.000003877248,0.00007497518],"genre_scores_gemma":[0.9934703,0.00009361665,0.005609994,0.0001002277,0.0006427719,0.000003600392,0.00001016536,0.00000744643,0.00006194421],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5492771,"threshold_uncertainty_score":0.3144611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0362487039255609,"score_gpt":0.3222454193852722,"score_spread":0.2859967154597113,"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."}}