{"id":"W2058038763","doi":"10.1016/j.ymeth.2015.01.014","title":"Text mining of biomedical literature: Doing well, but we could be doing better","year":2015,"lang":"en","type":"editorial","venue":"Methods","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ottawa Hospital","funders":"European Commission","keywords":"Data science; Computational biology; Computer science; Biology","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003001078,0.0005358785,0.0009187455,0.0002111381,0.00009128437,0.00007479406,0.0007627583,0.003562858,0.00005164417],"category_scores_gemma":[0.002820832,0.0004417727,0.0003190065,0.0003115094,0.0006376124,0.000004692596,0.0005482405,0.001112246,0.000006916945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004202774,"about_ca_system_score_gemma":0.0005247946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002277604,"about_ca_topic_score_gemma":0.000004162854,"domain_scores_codex":[0.9960811,0.0008046255,0.0007520642,0.0008953843,0.0008623282,0.0006045509],"domain_scores_gemma":[0.9972363,0.0008831338,0.0004446025,0.0007739778,0.0003710026,0.0002909451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008318025,0.00004845075,0.000005964058,0.0002522384,0.0001600919,0.00002520547,0.0002300488,4.976995e-7,0.03969029,0.000001611236,0.7929376,0.1665648],"study_design_scores_gemma":[0.000732166,0.0005010058,0.000002236381,0.0005318677,0.00009958906,0.00001536799,0.0001803965,0.00002524815,0.01842185,0.0000377734,0.9789793,0.0004731849],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"methods","genre_scores_codex":[0.001333653,0.03919582,0.09164566,0.001538524,0.86016,0.0003054783,0.0007300201,0.0001213906,0.004969473],"genre_scores_gemma":[0.00008978287,0.001091146,0.6071237,0.0002344156,0.3870089,0.0000273651,0.001712469,0.00008666804,0.002625505],"genre_candidate":"editorial","genre_consensus":null,"teacher_disagreement_score":0.515478,"threshold_uncertainty_score":0.9998034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02711432373128969,"score_gpt":0.3779476610352015,"score_spread":0.3508333373039118,"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."}}