{"id":"W4403839440","doi":"10.1080/10618600.2024.2421248","title":"Multi-label Random Subspace Ensemble Classification","year":2024,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; National Institute on Aging; National Institutes of Health; National Science Foundation","keywords":"Random forest; Random subspace method; Computer science; Classifier (UML); Subspace topology; Artificial intelligence; Ensemble learning; Linear subspace; Machine learning; Pattern recognition (psychology); Multinomial distribution; Multi-label classification; Data mining; Algorithm; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003227275,0.0001002132,0.0001621093,0.0002643539,0.00009640433,0.0003246625,0.0002666808,0.00006340264,0.00000605657],"category_scores_gemma":[0.0001352777,0.00007672436,0.00004682037,0.0004154758,0.0001205627,0.0003729838,0.00004913654,0.0002334213,0.000009321779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002099931,"about_ca_system_score_gemma":0.00009066636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001198404,"about_ca_topic_score_gemma":0.000001170106,"domain_scores_codex":[0.9989002,0.0000500041,0.0004056515,0.0001632849,0.0003637109,0.000117143],"domain_scores_gemma":[0.998675,0.0007051973,0.0001637581,0.00009006824,0.000277805,0.00008813359],"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":[0.00001607259,0.0000750331,0.0002280926,0.00002733081,0.00003990757,0.00003047697,0.0001120994,0.0001353425,0.000445291,0.8312623,0.004233099,0.163395],"study_design_scores_gemma":[0.0006846178,0.0001118303,0.01287538,0.0000306541,0.00001604471,0.00009960852,0.00002710553,0.5711164,0.00004026471,0.4118061,0.003100041,0.00009196394],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00512162,0.001215218,0.9874786,0.005680275,0.0003070421,0.00005810885,0.00001358204,0.00008575278,0.00003977627],"genre_scores_gemma":[0.5323154,0.0002235865,0.4672695,0.00008036882,0.00003298528,0.00000180146,0.000004557845,0.000004091056,0.00006769946],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5709811,"threshold_uncertainty_score":0.3130727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03378278262940175,"score_gpt":0.3029536130098509,"score_spread":0.2691708303804491,"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."}}