{"id":"W4372260217","doi":"10.1109/icassp49357.2023.10096198","title":"Epic-Sounds: A Large-Scale Dataset of Actions that Sound","year":2023,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geomechanica (Canada)","funders":"Engineering and Physical Sciences Research Council","keywords":"EPIC; Computer science; Sound (geography); Annotation; Pipeline (software); Class (philosophy); Audio visual; Visualization; Code (set theory); Scale (ratio); Object (grammar); Speech recognition; Artificial intelligence; Multimedia; Acoustics; Cartography","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":[0.0002193271,0.00006178489,0.00009238177,0.00008031609,0.0001374626,0.00009258263,0.0004427498,0.00002759703,0.0001616207],"category_scores_gemma":[0.00001320647,0.00005085499,0.00003119415,0.0005194538,0.00002900605,0.0004971394,0.0002792147,0.00005682358,0.0002148143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000764312,"about_ca_system_score_gemma":0.000035284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001386671,"about_ca_topic_score_gemma":0.0000455658,"domain_scores_codex":[0.999284,0.00001504732,0.0001203264,0.0002059177,0.0001744513,0.0002002208],"domain_scores_gemma":[0.999404,0.00005834509,0.00005685492,0.0004120365,0.00002210983,0.00004661336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003237822,0.0001441285,0.006256361,0.00009393454,0.00003526998,0.00001535783,0.002636875,0.0001113233,0.001149431,0.03611411,0.9322702,0.02116978],"study_design_scores_gemma":[0.0008515042,0.00007147437,0.00967499,0.00007115109,0.00002400877,0.00003743287,0.002570918,0.09626669,0.01288845,0.06012731,0.8168493,0.0005667573],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02086937,0.0000273723,0.9659474,0.001558466,0.0002820962,0.00005640462,0.0001705937,0.0002686101,0.01081966],"genre_scores_gemma":[0.9583388,0.00001935382,0.03496823,0.001827541,0.00008981694,0.00001160074,0.0002653283,0.000009665303,0.00446964],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9374694,"threshold_uncertainty_score":0.2761075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0783861517944466,"score_gpt":0.3177064082020132,"score_spread":0.2393202564075666,"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."}}