{"id":"W2066207574","doi":"10.1109/memb.2007.335581","title":"Multilabel associative classification categorization of MEDLINE aticles into MeSH keywords","year":2007,"lang":"en","type":"article","venue":"IEEE Engineering in Medicine and Biology Magazine","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Categorization; Classifier (UML); Associative property; Document classification; Data mining; Macro; Scalability; Artificial intelligence; Information retrieval; Pattern recognition (psychology); Machine learning; Database; Mathematics","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":[0.0007174116,0.000119083,0.0002341958,0.0003703037,0.00002461333,0.000005963121,0.0002539311,0.0001382727,0.000003426584],"category_scores_gemma":[0.0004247712,0.0000944394,0.00001494534,0.0006052175,0.0001254756,0.0001427713,0.00004545942,0.0001382842,0.000002767872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004911549,"about_ca_system_score_gemma":0.00001418219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002245432,"about_ca_topic_score_gemma":0.00002300111,"domain_scores_codex":[0.9990738,0.00002156911,0.0004003124,0.0002332026,0.00009192156,0.0001791765],"domain_scores_gemma":[0.9992303,0.0002899737,0.0001509347,0.0002015498,0.00009022382,0.00003707212],"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":[0.00001682618,0.00009622148,0.05414816,0.00007739329,0.0000363363,0.000003715164,0.002089667,0.00008127627,0.6422423,0.1837096,0.0006304125,0.1168681],"study_design_scores_gemma":[0.00368657,0.0009503293,0.5362325,0.0002093495,0.00003365678,0.00001009207,0.0007569591,0.3689626,0.07237802,0.01267422,0.003530214,0.0005755661],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3060151,0.0003789392,0.6900499,0.002660339,0.0002952886,0.0001430436,7.206713e-7,0.0001891905,0.0002674709],"genre_scores_gemma":[0.9800782,0.0002469177,0.01948422,0.00005679705,0.00006011319,0.000009015201,0.00001188279,0.00000527573,0.00004763377],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.674063,"threshold_uncertainty_score":0.3851127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03913872556567612,"score_gpt":0.3145223526739983,"score_spread":0.2753836271083222,"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."}}