{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002320298,0.001362469,0.001526968,0.0009318787,0.0006263201,0.001053815,0.002737279,0.00217557,0.001407476],"category_scores_gemma":[0.005789895,0.0006250907,0.00105131,0.0008383285,0.0008507379,0.00357198,0.001861305,0.002708121,0.0006104966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008977166,"about_ca_system_score_gemma":0.0008551592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005502913,"about_ca_topic_score_gemma":0.007134654,"domain_scores_codex":[0.9990193,0.0002598546,0.00003952544,0.0003372939,0.0002325333,0.0001114787],"domain_scores_gemma":[0.9971803,0.001289728,0.0002988077,0.0004477613,0.0006611829,0.0001221075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002515703,0.0001381461,0.002602093,0.00005184204,0.0001072487,0.0000986891,0.0001496029,0.8665044,0.00361193,0.0103623,0.002500292,0.1136219],"study_design_scores_gemma":[0.000003286626,0.00002155088,0.00008137539,0.000002814701,0.00001061569,0.000008193917,0.000003439185,0.9969268,0.0003087989,0.002446749,0.0001832487,0.000003108521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05571728,0.0005393912,0.9403747,0.0005009222,0.00009349128,0.0000410657,0.0001544225,0.0008699702,0.001708643],"genre_scores_gemma":[0.8532011,0.0004708951,0.136778,0.0005031805,0.0002744091,0.0002313715,0.0007677271,0.0001847872,0.007588591],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005502913,"threshold_uncertainty_score":0.01227111,"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."}}