{"id":"W4212816054","doi":"10.1145/3488560.3498376","title":"An Ensemble Model for Combating Label Noise","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Artificial intelligence; Noise (video); Machine learning; Artificial neural network; Consistency (knowledge bases); Pattern recognition (psychology); Image (mathematics); Set (abstract data type); Matching (statistics); Measure (data warehouse); Function (biology); Data mining; Mathematics; Statistics","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":[0.001118041,0.0001021537,0.0001072106,0.000117108,0.0004134099,0.0002982916,0.00484807,0.00002133498,0.00001670262],"category_scores_gemma":[0.0006502795,0.00008489472,0.00002009392,0.0001455766,0.00004793071,0.0008387347,0.003159606,0.0002330814,9.146743e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002861283,"about_ca_system_score_gemma":0.0001311248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002119464,"about_ca_topic_score_gemma":0.00000411261,"domain_scores_codex":[0.9985311,0.00002242133,0.0002110771,0.0004912479,0.000554279,0.0001898934],"domain_scores_gemma":[0.9988223,0.0001143767,0.000159587,0.0005627071,0.0002689614,0.00007210849],"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":[0.0002435007,0.0003721188,0.01345357,0.0000933733,0.00005726516,4.115659e-7,0.003191984,0.0009620961,0.07399175,0.7485186,0.005198983,0.1539163],"study_design_scores_gemma":[0.0003975346,0.000155261,0.0006797203,0.00002618944,0.000004467938,0.000004280431,0.0005952767,0.9946638,0.0004841402,0.002242041,0.0006526155,0.00009462829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8992205,0.00003764257,0.07265512,0.01833172,0.0004097637,0.0007189075,0.001381486,0.000148762,0.00709605],"genre_scores_gemma":[0.9331508,0.0000151087,0.06607331,0.0002146057,0.0000377583,0.00004433429,0.0002027465,0.000007696831,0.0002536105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9937018,"threshold_uncertainty_score":0.9009001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1640580261696732,"score_gpt":0.3756783905798501,"score_spread":0.2116203644101769,"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."}}