{"id":"W1480287196","doi":"10.1186/1471-2105-7-356","title":"New directions in biomedical text annotation: definitions, guidelines and corpus construction","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":169,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Annotation; Computer science; Task (project management); Information retrieval; Natural language processing; Categorization; Set (abstract data type); Biomedical text mining; Executable; Focus (optics); Artificial intelligence; Unified Medical Language System; Text corpus; Text mining","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001253207,0.0001048881,0.0001126463,0.0001004408,0.00007273565,0.00003059929,0.00006404593,0.0001870185,0.00001333659],"category_scores_gemma":[0.0002373942,0.00009265472,0.00003305998,0.0001851076,0.0001994557,0.000007173261,0.00004409807,0.00007030617,0.00001227307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001047973,"about_ca_system_score_gemma":0.0001247868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001180169,"about_ca_topic_score_gemma":0.000263921,"domain_scores_codex":[0.9991825,0.00001821956,0.0004092055,0.0001196076,0.0001131846,0.0001572942],"domain_scores_gemma":[0.9996256,0.00002950721,0.0000881013,0.000127362,0.00005932805,0.0000701621],"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":[0.00009850562,0.0001528681,0.0546947,0.0002000894,0.00004063789,0.000004897346,0.0002322914,0.0001241631,0.003986531,0.006740004,0.152099,0.7816263],"study_design_scores_gemma":[0.003625215,0.0005532669,0.06640336,0.0001755859,0.00005594333,0.0006293616,0.002148588,0.01968591,0.003054662,0.006025677,0.8968548,0.0007876422],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2429122,0.007520903,0.7344451,0.00269443,0.001332532,0.0004804686,0.0001386629,0.0002165928,0.01025908],"genre_scores_gemma":[0.0188722,0.00097537,0.9784367,0.0002871386,0.0004337459,0.00001600552,0.0004533347,0.00001175452,0.0005137247],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7808387,"threshold_uncertainty_score":0.377835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03638827609910656,"score_gpt":0.2788558833373014,"score_spread":0.2424676072381949,"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."}}