{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007875492,0.0015332,0.002096612,0.00140653,0.001484143,0.002150403,0.003712918,0.002227948,0.001593761],"category_scores_gemma":[0.04313555,0.0006111044,0.0009705409,0.001622022,0.002483338,0.004171401,0.004002017,0.003945753,0.001429349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001386142,"about_ca_system_score_gemma":0.002555946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003623472,"about_ca_topic_score_gemma":0.00851437,"domain_scores_codex":[0.9916522,0.003471637,0.0004054196,0.002043579,0.002042901,0.0003843036],"domain_scores_gemma":[0.9796008,0.00773025,0.002109716,0.007538336,0.002548128,0.0004727496],"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":[0.001017154,0.0005649644,0.03361233,0.0006037835,0.0003004128,0.0004693238,0.001168775,0.1183731,0.0173971,0.03867012,0.02549103,0.7623319],"study_design_scores_gemma":[0.00009493102,0.0001653551,0.002326671,0.0001306528,0.00007991043,0.0003040123,0.0002769867,0.8934588,0.01877414,0.07634611,0.007967906,0.00007446703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04748094,0.0006146668,0.9458541,0.0007788345,0.0002200126,0.0001469698,0.0004048951,0.002940768,0.001558806],"genre_scores_gemma":[0.5244664,0.0003206168,0.4681218,0.0008550148,0.0002465564,0.0003339787,0.002102156,0.0007483932,0.002805023],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007875492,"threshold_uncertainty_score":0.04165006,"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."}}