{"id":"W1525672751","doi":"10.1186/1471-2105-6-75","title":"Ranking the whole MEDLINE database according to a large training set using text indexing","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Genomics","funders":"U.S. National Library of Medicine; Universität Stuttgart; Ontario Genomics Institute; Stem Cell Network; Ontario Genomics; Ontario Innovation Trust","keywords":"MEDLINE; Computer science; Information retrieval; Relevance (law); Ranking (information retrieval); Set (abstract data type); Controlled vocabulary; Vocabulary; Subject (documents); National library; Natural language processing; Artificial intelligence; World Wide Web; Library science; Linguistics","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":[0.0008698193,0.0001963722,0.0001949099,0.00007809043,0.0003090305,0.00008705474,0.0004041817,0.0001649112,0.00001270591],"category_scores_gemma":[0.0005625029,0.00013992,0.00008788806,0.0002244121,0.00008543025,0.00001503675,0.0003886552,0.0001899667,0.00003877805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002870168,"about_ca_system_score_gemma":0.0001327515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007061779,"about_ca_topic_score_gemma":0.00008101606,"domain_scores_codex":[0.9986007,0.00004427507,0.0004278917,0.0001905902,0.0002374101,0.0004991293],"domain_scores_gemma":[0.9991676,0.00006796503,0.0001414011,0.0004442146,0.00004964709,0.0001291816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004260755,0.0002082332,0.01516463,0.0006256358,0.0003895705,0.00001287308,0.03127192,0.01754221,0.1356456,0.0007485806,0.02207419,0.7758905],"study_design_scores_gemma":[0.00169141,0.0001810273,0.0004726954,0.0002686554,0.00007153354,0.0001166225,0.03167439,0.5340252,0.008998353,0.00002825094,0.4217753,0.0006966008],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3958236,0.0004027969,0.6016808,0.0005964215,0.0002251555,0.0002778766,0.0001188782,0.0000659462,0.0008085968],"genre_scores_gemma":[0.6413625,0.00002077733,0.3548814,0.002684714,0.0006727587,0.00001382874,0.0001997331,0.00002590135,0.0001384488],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7751939,"threshold_uncertainty_score":0.5705771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07540264134123546,"score_gpt":0.330097927578299,"score_spread":0.2546952862370636,"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."}}