{"id":"W1999882329","doi":"10.1016/j.csda.2010.11.017","title":"Ensemble classification of paired data","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Deutsche Forschungsgemeinschaft","keywords":"Resampling; Linear discriminant analysis; Random forest; Boosting (machine learning); Artificial intelligence; Logistic regression; Statistics; Computer science; Pattern recognition (psychology); Bootstrap aggregating; Gradient boosting; Machine learning; 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":[0.001061903,0.0001607453,0.0004562614,0.0001843985,0.0001168708,0.00004236113,0.001083918,0.00007096833,0.0002508655],"category_scores_gemma":[0.004590682,0.0001545077,0.00004593537,0.0006456198,0.0001713048,0.0002664998,0.0005556222,0.0002081854,0.0000121445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001324932,"about_ca_system_score_gemma":0.0001139979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008812069,"about_ca_topic_score_gemma":0.0005610223,"domain_scores_codex":[0.9977745,0.0001376559,0.000698162,0.0006560362,0.0005414633,0.0001921584],"domain_scores_gemma":[0.9928268,0.003907555,0.0004196015,0.002300755,0.0004256644,0.0001195786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000178361,0.0002135303,0.0009531697,0.00006368467,0.0007180644,0.000004915031,0.00004601369,0.002032109,0.0004856902,0.9313731,0.01058442,0.05350747],"study_design_scores_gemma":[0.000106064,0.000008696429,0.006596958,0.000002758242,0.0008754394,9.788599e-7,0.000008293214,0.5269997,0.000006538972,0.4645837,0.0007147841,0.00009603835],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001465772,0.00001260651,0.9677617,0.00009686649,0.00009088033,0.0001288871,0.0301974,0.00003531772,0.0002105689],"genre_scores_gemma":[0.19314,0.000007634348,0.7814763,0.00002369592,0.00004689697,0.000004152608,0.02522677,0.00001617091,0.00005834541],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5249676,"threshold_uncertainty_score":0.630064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.348479546028191,"score_gpt":0.4900812899065639,"score_spread":0.1416017438783729,"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."}}