{"id":"W4382469227","doi":"10.1609/aaai.v37i1.25088","title":"Denoising after Entropy-Based Debiasing a Robust Training Method for Dataset Bias with Noisy Labels","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea","keywords":"Debiasing; Computer science; Artificial intelligence; Noise reduction; Machine learning; Generalization; Entropy (arrow of time); Sampling bias; Sample (material); Pattern recognition (psychology); Statistics; Mathematics; Sample size determination; Psychology","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":[0.001453602,0.0002410972,0.0002718936,0.0002400272,0.0003102602,0.0005095204,0.001468897,0.00007712375,0.00001794002],"category_scores_gemma":[0.0009697918,0.0001723472,0.00008126881,0.001130644,0.000137578,0.0004705526,0.0002130661,0.0002730617,0.00004344409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003898314,"about_ca_system_score_gemma":0.0001750129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005287948,"about_ca_topic_score_gemma":0.00002923524,"domain_scores_codex":[0.9978948,0.00004913456,0.0004626106,0.0006665423,0.0004769724,0.000449944],"domain_scores_gemma":[0.99817,0.0004599534,0.0004213365,0.000439515,0.0004139622,0.00009522014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005882306,0.0001559383,0.001032623,0.0002716452,0.00005561773,0.00000371213,0.004659869,0.005878971,0.06990818,0.5596521,0.001084115,0.3567089],"study_design_scores_gemma":[0.00008418405,0.0002458781,0.0003936099,0.000406686,0.0000319692,0.000005573772,0.000621366,0.8491439,0.1335747,0.0140816,0.001112009,0.0002985692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03314964,0.000009125968,0.9584913,0.006945554,0.0001842493,0.0005522905,0.0001471589,0.0002331136,0.0002876013],"genre_scores_gemma":[0.8543721,0.000004622168,0.1449333,0.0003885544,0.00006363282,0.0001019233,0.0000512922,0.00002161734,0.00006287035],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8432649,"threshold_uncertainty_score":0.7028115,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2141292935997887,"score_gpt":0.3536692546631078,"score_spread":0.1395399610633191,"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."}}