{"id":"W2109429447","doi":"10.1186/1471-2105-12-486","title":"Constructing a semantic predication gold standard from the biomedical literature","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"U.S. National Library of Medicine; National Institutes of Health","keywords":"Unified Medical Language System; Computer science; Information retrieval; Annotation; Terminology; Natural language processing; Biomedical text mining; Ontology; Task (project management); Semantic similarity; Controlled vocabulary; Artificial intelligence; Text mining; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1039598,0.001304464,0.001606439,0.03231419,0.005148577,0.005814632,0.003100591,0.002626476,0.003257273],"category_scores_gemma":[0.2559679,0.0006486081,0.002040533,0.01437126,0.003850662,0.006621789,0.01007917,0.00210213,0.002003171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003249554,"about_ca_system_score_gemma":0.006815845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002811722,"about_ca_topic_score_gemma":0.004137385,"domain_scores_codex":[0.9089855,0.03444411,0.01849769,0.01358682,0.02311136,0.001374553],"domain_scores_gemma":[0.6277125,0.226731,0.01922985,0.03628676,0.08802377,0.002016033],"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":[0.001649996,0.0008509285,0.153014,0.01617145,0.002149186,0.001959697,0.03169202,0.01398864,0.07400356,0.05769806,0.03459436,0.6122282],"study_design_scores_gemma":[0.0004357977,0.001015791,0.2612317,0.008776964,0.002800792,0.002983322,0.02373387,0.155273,0.1807093,0.1471114,0.2151193,0.0008088605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3924197,0.007573518,0.5524862,0.002918994,0.0009752749,0.002604973,0.01081107,0.004138265,0.02607198],"genre_scores_gemma":[0.5559182,0.001276806,0.4151607,0.0005459473,0.0002374831,0.003692253,0.02099749,0.0008516093,0.001319559],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1039598,"threshold_uncertainty_score":0.5497988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02397119029609484,"score_gpt":0.245456702483686,"score_spread":0.2214855121875912,"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."}}