{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005704325,0.0007156334,0.001727705,0.002247447,0.001260931,0.001445402,0.002494635,0.001527953,0.001505224],"category_scores_gemma":[0.0188017,0.0005658878,0.001230871,0.002670342,0.001208592,0.002274653,0.00161081,0.002081081,0.0009109296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001835205,"about_ca_system_score_gemma":0.001842405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01092246,"about_ca_topic_score_gemma":0.01087742,"domain_scores_codex":[0.9946929,0.001898824,0.0003180146,0.001112539,0.001762883,0.0002148774],"domain_scores_gemma":[0.9903257,0.00551874,0.000844554,0.001547408,0.001559153,0.0002043996],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001922903,0.0001252158,0.005713346,0.0003220154,0.0001618314,0.0002539938,0.0001857853,0.7170073,0.002397556,0.0303701,0.005336151,0.2379344],"study_design_scores_gemma":[0.000003833807,0.00001587625,0.000404419,0.000009744067,0.000004669369,0.00004914622,0.00001412792,0.9900354,0.0004341782,0.008431795,0.0005849397,0.00001199244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007866791,0.0005599377,0.9902396,0.0001460414,0.00005165612,0.00005874101,0.0001215425,0.0004874171,0.0004682709],"genre_scores_gemma":[0.3614139,0.0008823875,0.6332721,0.0001926785,0.0001455071,0.0004326614,0.001344063,0.0001755211,0.002141189],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01092246,"threshold_uncertainty_score":0.03016776,"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."}}