{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002696083,0.0001417489,0.0001372353,0.00002824003,0.00008304662,0.00004850897,0.0003348812,0.0002816901,0.00003272493],"category_scores_gemma":[0.0004709978,0.00008753873,0.00007559605,0.0001464844,0.0004095775,0.000006965219,0.0001437473,0.000170636,0.00002397524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001202625,"about_ca_system_score_gemma":0.0001069384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001763146,"about_ca_topic_score_gemma":0.00003388577,"domain_scores_codex":[0.9990197,0.00004589926,0.0003383127,0.0001514015,0.0002196671,0.00022505],"domain_scores_gemma":[0.9992341,0.00005943364,0.0001504075,0.0003946897,0.0000665492,0.00009486608],"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":[0.0008547199,0.0002878252,0.1084736,0.0005950453,0.0006155969,0.00001861033,0.0213968,0.000003469933,0.003704329,0.003382863,0.1911726,0.6694945],"study_design_scores_gemma":[0.009496952,0.00397347,0.06002337,0.001940355,0.0006224198,0.0006748791,0.05302471,0.05701807,0.04511306,0.00658309,0.7585659,0.002963738],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3362449,0.003320761,0.6426624,0.001078712,0.001596228,0.0007622557,0.001315261,0.0002687432,0.01275072],"genre_scores_gemma":[0.4109987,0.0002233901,0.5843148,0.001138955,0.0007719934,0.00003398136,0.002168985,0.00003013708,0.0003190857],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6665307,"threshold_uncertainty_score":0.3569725,"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."}}