{"id":"W3184843218","doi":"","title":"Data-Driven Diverse Ensembles of Logistic Regression Models","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Ensemble learning; Computer science; Logistic regression; Machine learning; Artificial intelligence; Classifier (UML); Ensemble forecasting; Regularization (linguistics); Data mining; Regression; Mathematics; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003218417,0.0008615609,0.001473246,0.0009505697,0.0005280438,0.001173494,0.001911174,0.001190115,0.001059628],"category_scores_gemma":[0.008080912,0.0006741696,0.001246413,0.000910413,0.0005990569,0.001341734,0.001618821,0.00202309,0.0004443359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007550005,"about_ca_system_score_gemma":0.0007539418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002227467,"about_ca_topic_score_gemma":0.003363315,"domain_scores_codex":[0.998889,0.0005163325,0.00004765166,0.0002198582,0.0002399292,0.00008726657],"domain_scores_gemma":[0.9974046,0.00148831,0.0002673006,0.0003063866,0.0003993344,0.0001339602],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004817112,0.00003225937,0.001981116,0.00003274576,0.00009026325,0.00008993648,0.00006548868,0.929267,0.001857305,0.01918557,0.001248988,0.04610102],"study_design_scores_gemma":[0.000001371652,0.000006777,0.00007373399,0.000002809673,0.000003064639,0.00000939087,0.000001867541,0.9941707,0.0001643573,0.005357734,0.0002043108,0.000003803464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01473112,0.0002012554,0.9839617,0.0001342266,0.00002785,0.00001823541,0.00007299458,0.0003420196,0.0005107347],"genre_scores_gemma":[0.6318441,0.0004517022,0.3619432,0.0002237056,0.000168321,0.0002857426,0.001012606,0.0002429803,0.003827546],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003218417,"threshold_uncertainty_score":0.01702082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2136697823894985,"score_gpt":0.2542195155682975,"score_spread":0.04054973317879901,"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."}}