{"id":"W4389322561","doi":"10.21203/rs.3.rs-3688727/v1","title":"OSK: Optimal Subsampling Method Based on K-means Clustering for Imbalanced Big Data","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Computer science; Categorical variable; Artificial intelligence; Class (philosophy); Big data; Pattern recognition (psychology); Data mining; Machine learning","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":[0.002974993,0.0009516272,0.001522485,0.002056791,0.00098424,0.001244092,0.001844061,0.0009292716,0.001227897],"category_scores_gemma":[0.007686818,0.0004279167,0.001042423,0.001782522,0.001047607,0.001600905,0.001481534,0.001649759,0.0006218013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001171295,"about_ca_system_score_gemma":0.001798163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006074446,"about_ca_topic_score_gemma":0.006434712,"domain_scores_codex":[0.9981134,0.0005458405,0.00009856178,0.0004159606,0.0006932211,0.0001330603],"domain_scores_gemma":[0.9973441,0.0009675124,0.0002860957,0.0005194068,0.0007346778,0.0001483014],"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":[0.0004442569,0.0002239152,0.005328614,0.0002645322,0.0003109533,0.0001787604,0.0003103299,0.4816441,0.009737504,0.02282649,0.009793677,0.4689368],"study_design_scores_gemma":[0.00000820672,0.00001869239,0.0003828779,0.000006558148,0.00000914832,0.00002381642,0.00002419877,0.9899729,0.001449751,0.007278539,0.0008139745,0.00001143203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009906516,0.0003060491,0.9879111,0.0001613099,0.0001056936,0.00006305534,0.00008591251,0.001053236,0.0004071339],"genre_scores_gemma":[0.2887443,0.0002915084,0.7082121,0.0001825718,0.0001889158,0.0002211491,0.000741886,0.0002928528,0.001124637],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006074446,"threshold_uncertainty_score":0.01573342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4267506895785027,"score_gpt":0.4980191244722518,"score_spread":0.07126843489374907,"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."}}