{"id":"W4403069814","doi":"10.1007/978-3-031-72117-5_19","title":"Detecting Noisy Labels with Repeated Cross-Validations","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Speech recognition; Computer vision","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":[0.02765269,0.002922324,0.00453218,0.003578972,0.002232267,0.003279669,0.006578107,0.006013082,0.003156069],"category_scores_gemma":[0.05186299,0.001620147,0.002816327,0.002213106,0.003071556,0.003570227,0.004832553,0.004884321,0.003229006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00154592,"about_ca_system_score_gemma":0.001584899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003998031,"about_ca_topic_score_gemma":0.006715288,"domain_scores_codex":[0.9704735,0.012639,0.002619153,0.007105174,0.005828193,0.001334901],"domain_scores_gemma":[0.9276101,0.04160589,0.00294813,0.01681592,0.01014878,0.0008711667],"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":[0.001383186,0.0008628018,0.0128469,0.0004607672,0.001194274,0.0004956506,0.0005028581,0.1783961,0.02980752,0.007030016,0.009703412,0.7573165],"study_design_scores_gemma":[0.00003534272,0.0001698463,0.001605462,0.00005878374,0.0001170874,0.0001909957,0.0000621149,0.9769689,0.01115858,0.008258888,0.001334034,0.00003994602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04471445,0.0007478567,0.9490638,0.0001787255,0.0001895306,0.0001523094,0.000176433,0.003901121,0.0008758728],"genre_scores_gemma":[0.4045584,0.0002023605,0.5841198,0.000480859,0.0001919995,0.0003882771,0.002459452,0.001838941,0.005760012],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02765269,"threshold_uncertainty_score":0.1462432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01910617231870945,"score_gpt":0.2828571323118246,"score_spread":0.2637509599931152,"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."}}