{"id":"W4319777521","doi":"10.1109/tai.2023.3243596","title":"Audio Representation Learning by Distilling Video as Privileged Information","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Music and Audio Processing","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Representation (politics); Multimedia; Artificial intelligence; Political science","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003482086,0.0001514649,0.0001332162,0.0002600457,0.0006240958,0.0004247196,0.0003935884,0.00007716496,0.00007986293],"category_scores_gemma":[0.00006788876,0.0001581259,0.00008087362,0.001422649,0.0000611841,0.001664373,0.000005508467,0.0003325944,0.002215313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005652499,"about_ca_system_score_gemma":0.00006273641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007153317,"about_ca_topic_score_gemma":0.00001232852,"domain_scores_codex":[0.9984363,0.00007379,0.0004465471,0.0003278336,0.0004087342,0.0003068458],"domain_scores_gemma":[0.9991605,0.0001997505,0.0001467647,0.0002857283,0.0001128868,0.00009432376],"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":[0.00001779258,0.00004034753,0.000004265397,0.00001575429,0.00001098411,0.000003537454,0.003427195,0.1581765,0.006366015,0.002562313,0.0004945384,0.8288807],"study_design_scores_gemma":[0.00002985085,0.00008032519,0.00001298308,0.00005511744,0.000008074817,0.000005607054,0.000590656,0.5097234,0.4797377,0.005804717,0.003717521,0.0002340176],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01251344,0.00000822135,0.9834099,0.001254484,0.0008798431,0.0001607799,0.000003877487,0.0006907453,0.001078654],"genre_scores_gemma":[0.9968854,0.00005416516,0.002140743,0.00039593,0.0000471638,0.00004321062,0.000009500293,0.000008784298,0.0004151565],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9843719,"threshold_uncertainty_score":0.9985616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04134158209393263,"score_gpt":0.3015254047184407,"score_spread":0.2601838226245081,"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."}}