{"id":"W2107141268","doi":"10.1093/bioinformatics/btn381","title":"Multi-dimensional classification of biomedical text: Toward automated, practical provision of high-utility text to diverse users","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":134,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Categorization; Annotation; Sentence; Information retrieval; Task (project management); Variety (cybernetics); Artificial intelligence; Information extraction; Natural language processing; Focus (optics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002942927,0.0001479503,0.0002567589,0.00009603956,0.00006607016,0.000004996842,0.0001920243,0.0003148756,0.0000237356],"category_scores_gemma":[0.001019374,0.0001163167,0.00008715648,0.0001962473,0.0005531384,0.00001073784,0.0002080403,0.0001056208,0.00003155041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001736057,"about_ca_system_score_gemma":0.0002437071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003693705,"about_ca_topic_score_gemma":0.000004413275,"domain_scores_codex":[0.9985437,0.00004760734,0.000602001,0.0001883295,0.000397725,0.0002205896],"domain_scores_gemma":[0.998969,0.00005985909,0.0002592399,0.0003441514,0.0001891164,0.0001785889],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.001777382,0.003518075,0.01767985,0.001177802,0.0003886589,0.0000306197,0.004495988,0.0001144024,0.6743467,0.0003105,0.1696994,0.1264606],"study_design_scores_gemma":[0.006448968,0.005280703,0.4896058,0.0003183202,0.0001778205,0.000314303,0.004903708,0.2125539,0.1962359,0.00004060416,0.08287705,0.001242917],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9777558,0.00004206966,0.02092932,0.0005631018,0.0001929897,0.0002619649,0.0001035395,0.00006594668,0.0000852286],"genre_scores_gemma":[0.8155844,0.00002662776,0.1840431,0.0001039469,0.00002985259,0.000006330787,0.0001514795,0.000007048716,0.00004715193],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4781109,"threshold_uncertainty_score":0.4743259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05631967128910629,"score_gpt":0.3222240203340662,"score_spread":0.2659043490449599,"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."}}