{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0110721,0.000904542,0.0026036,0.002358812,0.001490884,0.002043613,0.002567122,0.002047441,0.001190369],"category_scores_gemma":[0.03163256,0.000595745,0.0008938054,0.002823157,0.003688496,0.002345176,0.00209702,0.003223124,0.0005657263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001263688,"about_ca_system_score_gemma":0.001274874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001416602,"about_ca_topic_score_gemma":0.001371352,"domain_scores_codex":[0.9935881,0.002797008,0.0004100456,0.001057362,0.001845284,0.0003021654],"domain_scores_gemma":[0.9784612,0.01593648,0.001538554,0.001851046,0.00189261,0.0003201098],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005745077,0.0003883047,0.00635781,0.0004666774,0.0001674913,0.0003899313,0.0007435802,0.3064873,0.006814576,0.08180723,0.006157549,0.5896451],"study_design_scores_gemma":[0.00005153758,0.00005719807,0.0005523069,0.00003555087,0.0000207199,0.0001273603,0.00005454657,0.9292979,0.003119203,0.06527814,0.00138629,0.00001930189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02067109,0.0008622344,0.9763808,0.0005382897,0.00008237992,0.00009760938,0.00004361014,0.0003458237,0.0009781491],"genre_scores_gemma":[0.3433713,0.0005646584,0.6528833,0.0004373039,0.0003365898,0.0004568759,0.0001907758,0.0001486099,0.001610652],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0110721,"threshold_uncertainty_score":0.05855554,"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."}}