{"id":"W3158507570","doi":"","title":"A Hybrid Model for Drug-Drug Interaction Extraction from Structured Product Labeling Documents.","year":2019,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Drug; Computer science; Extraction (chemistry); Product (mathematics); Chemistry; Pharmacology; Chromatography; Mathematics; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001963792,0.00008205957,0.0001046171,0.00002353747,0.00006620258,0.00001398426,0.00009000102,0.00003618896,0.00001609591],"category_scores_gemma":[0.00004193009,0.00007118709,0.00003218903,0.00002816133,0.0001008415,0.000008556595,0.00003443631,0.00005091181,0.000002838675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004427136,"about_ca_system_score_gemma":0.00002407947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001214542,"about_ca_topic_score_gemma":0.000006066981,"domain_scores_codex":[0.9994728,0.00002753575,0.0001419484,0.0002255214,0.00004791118,0.00008431342],"domain_scores_gemma":[0.9995382,0.00006229326,0.00009632539,0.0002167864,0.00006234505,0.00002400949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007934352,0.00008693798,0.0004123781,0.0001173709,0.0001218207,6.033919e-8,0.0006458867,0.0004860896,0.8302524,0.0287957,0.001416012,0.1368719],"study_design_scores_gemma":[0.00051805,0.00005022292,0.0001396354,0.0000147766,0.00005840819,0.000003914781,0.00124887,0.001447217,0.7526033,0.2099617,0.03377016,0.0001838006],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8897752,0.001169258,0.1082337,0.0001198437,0.00007907138,0.0003532235,0.00007004684,0.00001891412,0.0001807221],"genre_scores_gemma":[0.994091,0.0001187632,0.003667681,0.00003620732,0.0001121659,0.0001340598,0.0002794069,0.0000085319,0.001552238],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1811659,"threshold_uncertainty_score":0.2902925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00845630159188394,"score_gpt":0.2821937799158072,"score_spread":0.2737374783239233,"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."}}