{"id":"W3211419495","doi":"","title":"Divide-and-Conquer Hard-thresholding Rules in High-dimensional Imbalanced Classification","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Divide and conquer algorithms; Thresholding; Artificial intelligence; Computer science; Curse of dimensionality; Class (philosophy); Linear discriminant analysis; Pattern recognition (psychology); Machine learning; Population; Feature (linguistics); Data mining; Algorithm","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004527436,0.0003568355,0.0004481113,0.0004643975,0.0001381835,0.000291561,0.001477136,0.0003954417,0.00002698801],"category_scores_gemma":[0.00009205631,0.0004335311,0.0001070872,0.000593547,0.0001590666,0.0009102322,0.002330072,0.0007321184,0.00003256876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000377657,"about_ca_system_score_gemma":0.0002558254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000209849,"about_ca_topic_score_gemma":0.00004360912,"domain_scores_codex":[0.9971585,0.0002223805,0.0003775752,0.00168981,0.0001710532,0.0003806363],"domain_scores_gemma":[0.9974113,0.0001471495,0.0003693997,0.001706169,0.0002271166,0.0001388811],"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":[0.00003683094,0.0002551621,0.03396668,0.0001605943,0.00009519587,0.000373453,0.0003025003,0.01325633,0.00768807,0.9375455,0.001023916,0.005295755],"study_design_scores_gemma":[0.001010979,0.00003698991,0.3076156,0.0005149762,0.00005239263,0.00001591262,0.0000676601,0.560078,0.004242972,0.1247195,0.0004716526,0.001173364],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4709468,0.00009945221,0.5272099,0.0004936878,0.0002992911,0.0002692658,0.00003497742,0.0003625666,0.0002839839],"genre_scores_gemma":[0.9795609,0.0003413792,0.01925756,0.0002038033,0.0000439463,0.000008681596,0.0002630422,0.00002173715,0.0002989814],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.812826,"threshold_uncertainty_score":0.9998116,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08232278468603461,"score_gpt":0.2092757065039635,"score_spread":0.1269529218179289,"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."}}