{"id":"W3188412909","doi":"10.24963/ijcai.2021/449","title":"Multi-level Generative Models for Partial Label Learning with Non-random Label Noise","year":2021,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; Canadian Institute for Advanced Research","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Artificial intelligence; Generator (circuit theory); Noise (video); Pattern recognition (psychology); Feature (linguistics); Multi-label classification; Machine learning; Noise reduction; Image (mathematics); Power (physics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001905044,0.0001592598,0.000217216,0.00003202242,0.000341467,0.0002881963,0.0002710081,0.00005233852,0.0000179844],"category_scores_gemma":[0.00004088477,0.0001198768,0.0000384444,0.0002417324,0.00003578542,0.0006563638,0.0001478705,0.0001340881,0.00001110436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001864998,"about_ca_system_score_gemma":0.0002698772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001334481,"about_ca_topic_score_gemma":0.00003589165,"domain_scores_codex":[0.9987749,0.00004227876,0.0001786866,0.0004812666,0.0001967927,0.0003260599],"domain_scores_gemma":[0.9992074,0.0000951902,0.00008125554,0.000229205,0.0002910709,0.00009591343],"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":[0.0003764568,0.001515558,0.0005254885,0.0003094201,0.0003924567,0.0002244209,0.01948016,0.1966734,0.1829917,0.05022061,0.007842264,0.539448],"study_design_scores_gemma":[0.004426724,0.00006827241,0.00002318002,0.00003670753,0.00001111689,0.000009680762,0.00007583196,0.9505283,0.04358641,0.0004192629,0.0006039911,0.000210529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008443562,0.0001123032,0.98862,0.001098991,0.0001167796,0.0001639305,0.00000297128,0.0001059842,0.001335492],"genre_scores_gemma":[0.2035369,0.00000716149,0.787659,0.001445175,0.0001042223,0.00005500971,0.000006221562,0.00001368028,0.007172626],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7538549,"threshold_uncertainty_score":0.4888435,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08759312322648306,"score_gpt":0.2919987879936194,"score_spread":0.2044056647671363,"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."}}