{"id":"W4312298943","doi":"10.1007/978-3-031-20980-2_26","title":"Harnessing Uncertainty - Multi-label Dysfluency Classification with Uncertain Labels","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Music and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Certainty; Computer science; Artificial intelligence; Machine learning; Uncertain data; Data mining; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.001096839,0.0006939837,0.0006143075,0.0007952779,0.001024591,0.001024146,0.003782519,0.000258144,0.00008943636],"category_scores_gemma":[0.00008000759,0.0005871627,0.00008396087,0.001346821,0.0008966975,0.001358181,0.001292798,0.001287273,0.00002331276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007781036,"about_ca_system_score_gemma":0.001640996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006885637,"about_ca_topic_score_gemma":0.0000733683,"domain_scores_codex":[0.9946661,0.00007641038,0.0006254,0.002238423,0.001517279,0.0008763607],"domain_scores_gemma":[0.9969296,0.0003373508,0.0006271975,0.001551619,0.0003445655,0.000209636],"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":[0.00001017474,0.00007582759,0.00009366252,0.00007799298,0.00001457904,0.0001249128,0.001176708,0.03737226,0.0005074607,0.02151183,0.00002746931,0.9390071],"study_design_scores_gemma":[0.000718671,0.0001933051,0.0001673433,0.0005828547,0.00001588901,0.0001033959,0.000001173047,0.9673859,0.0003171992,0.02652725,0.002975544,0.001011414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001859593,0.0006214629,0.9925081,0.001995654,0.001030458,0.0004271583,0.000007389628,0.0002844833,0.002939378],"genre_scores_gemma":[0.08405259,0.00005395811,0.9097121,0.004591281,0.0003670089,0.00005057372,0.00002521325,0.00008084602,0.001066474],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9379957,"threshold_uncertainty_score":0.999658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04531384017437876,"score_gpt":0.2778400262541542,"score_spread":0.2325261860797754,"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."}}