{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009140293,0.00009461735,0.0001446532,0.0001240458,0.00004202206,0.00004150418,0.0001451387,0.0000984332,7.400851e-7],"category_scores_gemma":[0.00005825071,0.00007709584,0.00004877545,0.0001517041,0.00002094056,0.000003109576,0.000009833008,0.0001602181,4.155354e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002644835,"about_ca_system_score_gemma":0.0001573018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004987021,"about_ca_topic_score_gemma":0.0000191962,"domain_scores_codex":[0.9993595,0.00001324999,0.0001625949,0.0001273855,0.00007047643,0.0002667794],"domain_scores_gemma":[0.9993426,0.00001144381,0.00002855057,0.00005816214,0.000041224,0.0005180278],"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":[0.00009999396,0.0001394964,0.005474919,0.00005052831,0.0002858859,0.0004820509,0.0005650527,0.0291766,0.08045401,0.0120949,0.03585507,0.8353215],"study_design_scores_gemma":[0.002350014,0.010941,0.1147486,0.0001425353,0.0001105103,0.007457369,0.00006756926,0.3043714,0.009805365,0.001040771,0.5470244,0.001940529],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5720757,0.002751088,0.4238888,0.000764551,0.0002273386,0.00004980925,0.000001062021,0.00001010902,0.0002315155],"genre_scores_gemma":[0.9748285,0.0000227914,0.02389545,0.0006025648,0.0006144805,7.196635e-7,0.000001672613,0.000004984571,0.0000288399],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8333809,"threshold_uncertainty_score":0.3143877,"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."}}