{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2149568,0.002429281,0.002809617,0.02342934,0.005309296,0.01766306,0.009875565,0.006894047,0.003502523],"category_scores_gemma":[0.293678,0.003035181,0.001845046,0.01776026,0.0293193,0.03766417,0.01180518,0.01263205,0.003598975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007318465,"about_ca_system_score_gemma":0.01711188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007317709,"about_ca_topic_score_gemma":0.009847852,"domain_scores_codex":[0.789187,0.1458358,0.03294713,0.01235798,0.01823666,0.001435553],"domain_scores_gemma":[0.5153903,0.2991873,0.0277429,0.06283832,0.08872668,0.006114454],"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":[0.0003403772,0.0004773401,0.007899763,0.01231334,0.0001241118,0.0009237124,0.0500807,0.003854539,0.01561026,0.3488904,0.06746679,0.4920187],"study_design_scores_gemma":[0.0001691856,0.0002729469,0.005266161,0.01128732,0.0001398065,0.00130597,0.01965222,0.02255514,0.01303216,0.5046791,0.4211498,0.0004901489],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006766012,0.009523025,0.9220136,0.04917865,0.001152536,0.002684607,0.001420469,0.001718175,0.005542841],"genre_scores_gemma":[0.01193568,0.002206436,0.9754847,0.001956212,0.0005332645,0.004617312,0.001822016,0.0004774419,0.0009670536],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2149568,"threshold_uncertainty_score":0.968098,"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."}}