{"id":"W2945163429","doi":"10.7717/peerj-cs.194","title":"The k conditional nearest neighbor algorithm for classification and class probability estimation","year":2019,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Western University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"k-nearest neighbors algorithm; Nonparametric statistics; Pattern recognition (psychology); Posterior probability; Computer science; Naive Bayes classifier; Benchmark (surveying); Algorithm; Artificial intelligence; Classifier (UML); Mathematics; Bayesian probability; Statistics; Support vector machine","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":[0.003376216,0.001132711,0.002344929,0.003110278,0.001313861,0.00148886,0.003306638,0.001863855,0.002883197],"category_scores_gemma":[0.01279282,0.0006358842,0.001336652,0.003738413,0.0008302159,0.002246946,0.001491211,0.003210263,0.002040013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001328772,"about_ca_system_score_gemma":0.002992702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01498136,"about_ca_topic_score_gemma":0.01314194,"domain_scores_codex":[0.9948232,0.001393347,0.0003779905,0.001049607,0.002109423,0.0002464699],"domain_scores_gemma":[0.9956369,0.001983137,0.0003383172,0.000724139,0.001216371,0.0001012925],"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":[0.0001695805,0.0001262306,0.00225715,0.0002625214,0.0001921845,0.00009949871,0.0001175327,0.1608652,0.002125977,0.02129182,0.01192167,0.8005705],"study_design_scores_gemma":[0.00001544405,0.00003097891,0.0006700875,0.00003402037,0.00002130378,0.0001585406,0.00002940205,0.9751618,0.001626117,0.01631484,0.005902444,0.00003508376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001870509,0.0004972203,0.9958548,0.00006888616,0.00007727328,0.00008700929,0.0001217311,0.0007261418,0.0006964908],"genre_scores_gemma":[0.07597314,0.000637213,0.9187502,0.0001287496,0.0001737487,0.0005227389,0.0009771399,0.0001572375,0.002679839],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01498136,"threshold_uncertainty_score":0.02978832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01833268062500404,"score_gpt":0.2739356002516186,"score_spread":0.2556029196266146,"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."}}