{"id":"W4399013580","doi":"10.2196/59680","title":"Is Boundary Annotation Necessary? Evaluating Boundary-Free Approaches to Improve Clinical Named Entity Annotation Efficiency: Case Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Annotation; Computer science; Boundary (topology); Information retrieval; Natural language processing; Data mining; Artificial intelligence; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005315607,0.0002738932,0.0003786339,0.0002863898,0.0004024616,0.001332686,0.001369637,0.0002425828,0.00003818709],"category_scores_gemma":[0.001215548,0.0002427039,0.0001444986,0.0009872329,0.0001547019,0.00191316,0.0009879443,0.0008462378,0.0001418084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001522152,"about_ca_system_score_gemma":0.001221502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007758629,"about_ca_topic_score_gemma":0.0000515763,"domain_scores_codex":[0.9946499,0.0002629753,0.001828929,0.0005174155,0.002239173,0.000501621],"domain_scores_gemma":[0.9974146,0.0005405318,0.0002485409,0.00115473,0.0001497768,0.0004918522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000161104,0.0005447461,0.0009868271,0.0004484285,0.00008798542,0.0005318368,0.1409219,0.0002907902,0.000004993415,0.001708752,0.003756891,0.8507008],"study_design_scores_gemma":[0.0008356233,0.0005828153,0.0003513602,0.0001232672,0.00003231557,0.0002688494,0.007575633,0.9866266,0.00001415954,0.001574836,0.001727062,0.0002875118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5557786,0.00007910983,0.439639,0.001614243,0.001286828,0.0009376308,0.000007081646,0.0002958988,0.000361579],"genre_scores_gemma":[0.921501,0.000004975785,0.07604709,0.001721075,0.0003989697,0.0002069046,0.00001402595,0.0000194007,0.00008659367],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9863358,"threshold_uncertainty_score":0.999704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.132606346198434,"score_gpt":0.4013234067763562,"score_spread":0.2687170605779222,"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."}}