{"id":"W4401900459","doi":"10.1007/s41060-024-00624-8","title":"A nearest neighbor-based approach for improving the reliability of multiclass probabilistic classifiers","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Probabilistic logic; Probabilistic classification; k-nearest neighbors algorithm; Reliability (semiconductor); Artificial intelligence; Computer science; Benchmark (surveying); Multiclass classification; Machine learning; Multivariate statistics; Class (philosophy); Pattern recognition (psychology); Support vector machine; Data mining; Naive Bayes classifier","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":[0.00366928,0.0000716389,0.0001071359,0.0002076174,0.0001091834,0.0006113321,0.003030501,0.00002348657,0.000001089302],"category_scores_gemma":[0.002753324,0.00004324158,0.00004235343,0.0004799801,0.0004481551,0.001735257,0.0003511246,0.0001793932,3.790369e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007124379,"about_ca_system_score_gemma":0.000858118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002438153,"about_ca_topic_score_gemma":0.000002444588,"domain_scores_codex":[0.9983611,0.00003813604,0.0003755935,0.0003103542,0.0007933027,0.0001215104],"domain_scores_gemma":[0.9976903,0.0004831797,0.0002543633,0.0005447681,0.0009614111,0.00006602827],"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":[0.0001589841,0.0006567154,0.007396546,0.000651634,0.0001769226,0.00002639642,0.001306347,0.04273214,0.01688494,0.2491875,0.003157773,0.6776641],"study_design_scores_gemma":[0.0001539189,0.00006578201,0.001281296,0.00003554012,0.00002452341,0.00001994086,0.00008165255,0.9938179,0.0001304901,0.0006849658,0.00365354,0.00005048317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005766807,0.0001086369,0.9880603,0.005395249,0.0003652295,0.00009804415,0.00008280197,0.00001256817,0.000110368],"genre_scores_gemma":[0.914734,0.00001536292,0.08501385,0.00009924276,0.0001020955,0.000001496812,0.00001895978,0.000002977125,0.00001203093],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9510857,"threshold_uncertainty_score":0.589509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05976447993703259,"score_gpt":0.3409420003058778,"score_spread":0.2811775203688452,"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."}}