{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006697795,0.0009665433,0.002777819,0.00267571,0.001392797,0.001716876,0.003454339,0.002146996,0.001632856],"category_scores_gemma":[0.0293138,0.0007290082,0.001601852,0.002464467,0.001005689,0.003052917,0.002286861,0.002409587,0.001095471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009972726,"about_ca_system_score_gemma":0.00137489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007068911,"about_ca_topic_score_gemma":0.007252612,"domain_scores_codex":[0.9904916,0.002922638,0.0006675971,0.001604666,0.003939303,0.0003742159],"domain_scores_gemma":[0.9828508,0.007138927,0.000911873,0.002618453,0.006239391,0.0002405954],"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":[0.0006080765,0.0003052816,0.006041838,0.000300602,0.0003810336,0.0001591962,0.000390666,0.2371565,0.008980708,0.01213331,0.005242454,0.7283003],"study_design_scores_gemma":[0.00001048662,0.00005813621,0.0007345186,0.0000139341,0.000055733,0.00008974197,0.00002371672,0.9896815,0.002025088,0.006348556,0.0009345644,0.00002404566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01934878,0.0008746567,0.9778187,0.0001461462,0.000118769,0.00005218639,0.0000893248,0.000613731,0.0009377613],"genre_scores_gemma":[0.5274608,0.0005807152,0.4673849,0.000263168,0.0004427144,0.0001424534,0.0007312233,0.0002867138,0.002707298],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007068911,"threshold_uncertainty_score":0.03542173,"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."}}