{"id":"W2052547205","doi":"10.1016/j.ijmedinf.2005.06.010","title":"A hybrid method for relation extraction from biomedical literature","year":2005,"lang":"en","type":"article","venue":"International Journal of Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Relation (database); Extraction (chemistry); Relationship extraction; Information retrieval; Data mining; Data science; Chromatography; Chemistry","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":[0.002241106,0.001205707,0.001868143,0.01490116,0.001349469,0.00343649,0.001609222,0.00143326,0.007236374],"category_scores_gemma":[0.00617819,0.0008075724,0.002174855,0.01207015,0.0004805633,0.003760453,0.002518992,0.001122558,0.005430728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004841092,"about_ca_system_score_gemma":0.002281613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002856553,"about_ca_topic_score_gemma":0.006669598,"domain_scores_codex":[0.9971715,0.000394705,0.0005587053,0.0006340746,0.001139297,0.0001018395],"domain_scores_gemma":[0.9948215,0.002956366,0.000262051,0.0006454765,0.001146822,0.0001677642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00035473,0.000292403,0.00321801,0.00172157,0.0005593479,0.0005915057,0.0006235289,0.001751907,0.03758598,0.005586544,0.01845101,0.9292634],"study_design_scores_gemma":[0.0007049027,0.001079315,0.02612705,0.001240874,0.003181079,0.01327851,0.002402017,0.3815831,0.1330335,0.06017395,0.3765807,0.0006149628],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01134604,0.001687123,0.9645719,0.0004547929,0.0001801866,0.0006264627,0.006375509,0.01241283,0.002345117],"genre_scores_gemma":[0.02550632,0.0005284757,0.9584759,0.0001398676,0.00006948623,0.0004154021,0.01076478,0.0003532273,0.003746518],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01490116,"threshold_uncertainty_score":0.02420807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0154397919275037,"score_gpt":0.3638849635772685,"score_spread":0.3484451716497648,"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."}}