{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001010537,0.0004420379,0.0003399428,0.0008046374,0.0004220893,0.001950056,0.002403961,0.0002395375,0.00002187589],"category_scores_gemma":[0.0001684336,0.0003573995,0.00007509415,0.001079615,0.000485312,0.0007506652,0.0009368806,0.001191396,0.000179295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002272499,"about_ca_system_score_gemma":0.0004311409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004899496,"about_ca_topic_score_gemma":0.0001131066,"domain_scores_codex":[0.9963416,0.00003236652,0.0004697321,0.001785326,0.0008612682,0.000509635],"domain_scores_gemma":[0.9971607,0.0003888501,0.0002774686,0.001739109,0.0002926788,0.0001412362],"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":[0.000009902273,0.00003011621,0.0006474872,0.0001266708,0.0000328399,0.0001961004,0.001139188,0.0648354,0.000536992,0.09499523,0.00002372454,0.8374264],"study_design_scores_gemma":[0.0002849321,0.0002606845,0.0007838272,0.0008485552,0.00002223925,0.000252595,2.565556e-7,0.9100974,0.001817134,0.07654312,0.00812446,0.0009647918],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002703976,0.0002470794,0.9871588,0.001112829,0.0009343594,0.0002545939,0.000009432824,0.0005480767,0.009464409],"genre_scores_gemma":[0.4608009,0.00003123239,0.5313178,0.0008624782,0.0006667173,0.00002603493,0.0000589006,0.00009265886,0.006143182],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.845262,"threshold_uncertainty_score":0.9998878,"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."}}