{"id":"W4392931294","doi":"10.1109/icassp48485.2024.10446280","title":"Leveraging Noisy Labels of Nearest Neighbors for Label Correction and Sample Selection","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Benchmark (surveying); Artificial intelligence; Context (archaeology); Pattern recognition (psychology); Feature selection; Representation (politics); Sample (material); Selection (genetic algorithm); Feature (linguistics); Machine learning; Noise (video); Data mining; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0002265001,0.00005635354,0.00006427256,0.0000929124,0.0000847211,0.0001555482,0.00009709965,0.00002906546,0.000009731314],"category_scores_gemma":[0.0001597883,0.00004974256,0.00001531423,0.0002925901,0.00001229215,0.000322041,0.00003595925,0.00007054243,0.000004269554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001861761,"about_ca_system_score_gemma":0.00003454409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004539909,"about_ca_topic_score_gemma":0.00004348081,"domain_scores_codex":[0.9994624,0.00002432698,0.0001126988,0.000231418,0.0000783278,0.00009085918],"domain_scores_gemma":[0.9994146,0.0003595756,0.00003086591,0.0001187243,0.00004974913,0.00002644674],"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":[0.00001097703,0.00004506089,0.00792841,0.0001619863,0.00002367766,3.174617e-7,0.000933159,0.0003501857,0.01000377,0.1260312,0.008353873,0.8461574],"study_design_scores_gemma":[0.0001119919,0.00007872149,0.005492042,0.00002321883,0.00000565241,0.00000671614,0.00002361641,0.9718165,0.001860457,0.001796218,0.01871963,0.00006528346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01339033,0.00008877561,0.9841812,0.0009046671,0.0005321253,0.00009551128,0.000004445527,0.0002263014,0.0005766859],"genre_scores_gemma":[0.9248282,0.00001836497,0.07402323,0.0000691128,0.00005831349,0.00001308151,0.00001810529,0.000006506707,0.0009651327],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9714662,"threshold_uncertainty_score":0.2028443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02627878256437166,"score_gpt":0.2902214161389274,"score_spread":0.2639426335745558,"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."}}