{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001709978,0.0001186874,0.0001047896,0.00008167111,0.0008171412,0.001052339,0.001125265,0.00003865477,0.000002249382],"category_scores_gemma":[0.0001486451,0.00008718733,0.0000320408,0.0004796811,0.0003686189,0.001188962,0.0002824228,0.0001253256,0.0000445729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007407946,"about_ca_system_score_gemma":0.0002142841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009757418,"about_ca_topic_score_gemma":0.000002894956,"domain_scores_codex":[0.9982074,0.00006765746,0.0002357491,0.0007005546,0.0004981109,0.0002905388],"domain_scores_gemma":[0.9981267,0.0004903812,0.0001608269,0.0007790727,0.0003402563,0.0001027506],"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":[0.00000243423,0.00002585024,0.001430208,0.000011118,0.000002423648,9.617201e-8,0.0001057623,0.0006635652,0.0003647642,0.2735528,0.0003654408,0.7234756],"study_design_scores_gemma":[0.000185441,0.00007841911,0.1442086,0.000005894579,0.000001872117,0.000008785947,0.000004685796,0.8333433,0.00005909189,0.01505371,0.006949361,0.0001008435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007737174,0.00002742212,0.9843647,0.00640761,0.0005913663,0.000539531,0.00001078156,0.0001349576,0.0001863861],"genre_scores_gemma":[0.5014479,0.00000448724,0.4980343,0.0002060281,0.00008697593,0.00006405531,0.00004104739,0.000004761543,0.0001104217],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8326797,"threshold_uncertainty_score":0.9999847,"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."}}