{"id":"W3185240989","doi":"10.48550/arxiv.2102.08591","title":"Data-Driven Logistic Regression Ensembles","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Mitacs; KU Leuven","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":true,"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":[0.003496201,0.0008349172,0.001425594,0.0006577511,0.0004961099,0.0008206391,0.001477123,0.0008836262,0.001405833],"category_scores_gemma":[0.0100179,0.0004750494,0.0008815079,0.0007159345,0.0003952941,0.001028892,0.001331227,0.001700268,0.0005837114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007049795,"about_ca_system_score_gemma":0.0006992569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003204543,"about_ca_topic_score_gemma":0.003761064,"domain_scores_codex":[0.9986351,0.0007808795,0.00004654299,0.0002029881,0.0002289367,0.0001055421],"domain_scores_gemma":[0.9954796,0.002781525,0.0002867633,0.0004687431,0.0008304318,0.0001529915],"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":[0.00006788239,0.00002711498,0.001557541,0.00002195842,0.00006168725,0.00003897266,0.00002995744,0.9537196,0.0005775563,0.006391412,0.001232902,0.03627344],"study_design_scores_gemma":[0.000002746706,0.000005943062,0.00007130644,0.000001548024,0.00000328976,0.000004495982,0.000001501112,0.9978956,0.0000899844,0.001818958,0.000102227,0.000002360279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06152665,0.0004345593,0.9350793,0.000474722,0.00009171278,0.00004558538,0.0001843783,0.0005533099,0.001609711],"genre_scores_gemma":[0.87863,0.0003319537,0.1163138,0.0002016631,0.0002015509,0.0001866706,0.0007584003,0.00009156157,0.003284352],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003496201,"threshold_uncertainty_score":0.0184899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1776871658044698,"score_gpt":0.2518104073875398,"score_spread":0.07412324158307007,"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."}}