{"id":"W2224038009","doi":"10.1007/978-3-319-25010-6_16","title":"Automatic Curation of Clinical Trials Data in LinkedCT","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; XML; Raw data; Data quality; Quality (philosophy); Clinical trial; Source document; Data curation; Linked data; Data science; World Wide Web; Information retrieval; Database; Bioinformatics; Semantic Web","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":[0.00807124,0.0001854969,0.0006815962,0.0001619299,0.00002063065,0.00002732872,0.001232233,0.0006017201,0.00001331458],"category_scores_gemma":[0.006297099,0.0001425121,0.00007971381,0.0001164769,0.0007806284,0.000008102636,0.0007915728,0.0003625587,0.000004118703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001926346,"about_ca_system_score_gemma":0.0006981303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001389069,"about_ca_topic_score_gemma":0.0001183259,"domain_scores_codex":[0.9974478,0.0001745335,0.001062663,0.0007436148,0.0003734319,0.0001979732],"domain_scores_gemma":[0.9978107,0.0005164957,0.0004529517,0.001032972,0.0001085205,0.00007836448],"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":[0.00001862434,0.00002646142,0.0002581231,0.00002949385,0.00001133857,0.000006885594,0.00003903242,0.0002558316,0.0004659824,0.00006597502,0.0002128861,0.9986094],"study_design_scores_gemma":[0.00491546,0.003587116,0.004145854,0.002605903,0.0001301803,0.00008849928,0.000003416702,0.7891161,0.007063571,0.0960106,0.09027129,0.002061968],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006461104,0.00281071,0.9874953,0.0004602425,0.001613473,0.00033066,0.00004741545,0.00002125998,0.0007598389],"genre_scores_gemma":[0.7058325,0.0004717466,0.2901082,0.0006690493,0.002137857,0.000006701854,0.0004270873,0.00003766287,0.0003092646],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9965474,"threshold_uncertainty_score":0.7538671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2551144569738897,"score_gpt":0.4541076386840874,"score_spread":0.1989931817101977,"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."}}