{"id":"W2158040974","doi":"10.1016/s1386-5056(02)00050-3","title":"Getting to the (c)ore of knowledge: mining biomedical literature","year":2002,"lang":"en","type":"article","venue":"International Journal of Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":125,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Biomedical text mining; Computer science; Categorization; Data science; Reading (process); Knowledge extraction; The Internet; Domain (mathematical analysis); Information extraction; Process (computing); Information retrieval; Scientific literature; World Wide Web; Text mining; Natural language processing; Data mining; Artificial intelligence; Linguistics","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":[0.0009536603,0.00009191423,0.0001618395,0.0001224762,0.00003198664,0.00003448685,0.001035239,0.0002235267,0.0001199218],"category_scores_gemma":[0.002495457,0.00005376382,0.0001180422,0.0001461779,0.0001889043,0.000008441531,0.0002370298,0.0002894848,0.00001206288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001377416,"about_ca_system_score_gemma":0.00008467176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.505205e-7,"about_ca_topic_score_gemma":0.000002062405,"domain_scores_codex":[0.9979374,0.00004305441,0.0007533681,0.00005222098,0.001071123,0.00014283],"domain_scores_gemma":[0.998814,0.0001083009,0.0003275723,0.0001222599,0.0004255643,0.0002023118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007038104,0.0002369634,0.000464835,0.00005931998,0.0003444827,0.00005142712,0.009927181,0.00003163334,0.00158536,0.0001742314,0.2693364,0.7177178],"study_design_scores_gemma":[0.001114488,0.0006502457,0.0003988016,0.0008163113,0.00002382703,0.001030393,0.002405491,0.006223293,0.002344466,0.0000490263,0.9847972,0.0001464681],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8942865,0.006779899,0.04879126,0.04184795,0.004668454,0.0001350984,0.00005117002,0.00001678097,0.003422881],"genre_scores_gemma":[0.9780927,0.000757246,0.01601185,0.002762478,0.002069232,0.000002267662,0.0000246435,0.000009956771,0.0002696459],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7175713,"threshold_uncertainty_score":0.2987475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01995399975705435,"score_gpt":0.3176598346977935,"score_spread":0.2977058349407391,"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."}}