{"id":"W2089922777","doi":"10.1109/cjece.2009.5599423","title":"CLASS: a general approach to classifying categorical sequences","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Electrical and Computer Engineering","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Categorical variable; Classifier (UML); Artificial intelligence; Computer science; False positive paradox; Matching (statistics); Class (philosophy); Pattern recognition (psychology); Data mining; Machine learning; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003486036,0.001420211,0.001537064,0.01060718,0.0018318,0.004165297,0.003959777,0.002789469,0.004683882],"category_scores_gemma":[0.0117015,0.0004497847,0.002372822,0.008662655,0.001976022,0.005892895,0.002777683,0.002447414,0.002633378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001467517,"about_ca_system_score_gemma":0.003498295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004221188,"about_ca_topic_score_gemma":0.003806206,"domain_scores_codex":[0.9955449,0.0007492268,0.0006198048,0.001196339,0.001596236,0.0002933999],"domain_scores_gemma":[0.9946866,0.001857544,0.0004912064,0.001235871,0.001398729,0.0003300157],"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":[0.0003615683,0.0003468663,0.01304431,0.0009740128,0.0002394831,0.0002538065,0.0007655131,0.01230793,0.008676919,0.08831909,0.0241848,0.8505257],"study_design_scores_gemma":[0.0001016591,0.0005383941,0.008252207,0.0004763398,0.0002018423,0.002689179,0.001379028,0.4179016,0.01633106,0.3463064,0.2055703,0.000252018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007569716,0.0007758891,0.9809539,0.0005394625,0.0002412903,0.0006572347,0.002495732,0.003712913,0.003053875],"genre_scores_gemma":[0.05724614,0.0006754275,0.9325227,0.0003953366,0.0002715158,0.0009214416,0.004477056,0.0002596278,0.003230746],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01060718,"threshold_uncertainty_score":0.01843613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01047453220872711,"score_gpt":0.2062926951565196,"score_spread":0.1958181629477925,"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."}}