{"id":"W4406805586","doi":"10.7717/peerj-cs.2497","title":"Random k conditional nearest neighbor for high-dimensional data","year":2025,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"k-nearest neighbors algorithm; Pattern recognition (psychology); Computer science; Large margin nearest neighbor; Nearest-neighbor chain algorithm; Feature (linguistics); Best bin first; Metric (unit); Artificial intelligence; Data mining; Nearest neighbor search; Cluster analysis","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009496667,0.0001507581,0.0001892877,0.0002688087,0.0006531522,0.0005719993,0.003294108,0.0000471516,0.00002498412],"category_scores_gemma":[0.0001358778,0.0001298802,0.000047166,0.0008670497,0.0002924053,0.00177998,0.001889365,0.0001062213,0.0000727176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003872309,"about_ca_system_score_gemma":0.0005431231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002258265,"about_ca_topic_score_gemma":0.000004017348,"domain_scores_codex":[0.9977136,0.00003776403,0.0002638547,0.0009777473,0.0006058593,0.0004011726],"domain_scores_gemma":[0.9978279,0.0003999739,0.00007973272,0.001146188,0.0004174153,0.0001287476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001158016,0.0003853332,0.0003274979,0.00006914755,0.00004808716,0.00001935054,0.0001700682,0.007568297,0.009055743,0.3003291,0.3903486,0.291563],"study_design_scores_gemma":[0.001611044,0.0000559907,0.003730395,0.00005846612,0.000007140035,0.00001023838,0.000001832613,0.9532546,0.003950672,0.02777929,0.009347665,0.0001926825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005495307,0.00005097981,0.9852903,0.006037457,0.002317209,0.0003182348,0.00008556759,0.0001628747,0.0002420492],"genre_scores_gemma":[0.4574648,0.000003236435,0.5372596,0.004381766,0.0002461167,0.00005035853,0.0002233849,0.000005730079,0.0003649623],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9456863,"threshold_uncertainty_score":0.6121327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0267616871584268,"score_gpt":0.2954529372423534,"score_spread":0.2686912500839266,"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."}}