{"id":"W3008558269","doi":"10.48550/arxiv.2002.09026","title":"Multi-label Sound Event Retrieval Using a Deep Learning-based Siamese Structure with a Pairwise Presence Matrix","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Event (particle physics); Sound (geography); Pairwise comparison; Speech recognition; Soundscape; Artificial intelligence; Audio signal; Acoustics; Speech coding","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":[0.0001938159,0.0005365771,0.000492087,0.0003456131,0.0004073514,0.000382616,0.00189937,0.0002969753,0.00004155466],"category_scores_gemma":[0.00009817075,0.0005374845,0.0001547129,0.001570635,0.0002133314,0.0005006763,0.001632356,0.001324435,0.000014516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002367289,"about_ca_system_score_gemma":0.000645219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006337239,"about_ca_topic_score_gemma":0.0000310699,"domain_scores_codex":[0.996927,0.0002606226,0.0002640543,0.001716429,0.0002808323,0.0005510318],"domain_scores_gemma":[0.9977534,0.0001141681,0.0005870911,0.0009484001,0.0002708558,0.0003260685],"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":[0.0002035342,0.0001075161,0.005020607,0.0003450686,0.00008628914,0.001161621,0.000692273,0.9906107,0.0006946353,0.0007116598,0.00004039777,0.0003257557],"study_design_scores_gemma":[0.001352204,0.00009142327,0.0002843715,0.0002995372,0.0001017447,0.00001644513,0.0001105003,0.9937384,0.0003008194,0.002977177,0.00006947284,0.0006579459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2856329,0.0001729123,0.7132364,0.0001600557,0.0001836926,0.0002972501,0.000008809501,0.0002841034,0.00002384847],"genre_scores_gemma":[0.9431095,0.00001986765,0.05627049,0.0002296271,0.00009176077,2.777933e-7,0.00001296876,0.0000399731,0.0002256047],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6574765,"threshold_uncertainty_score":0.9997077,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08251389631676702,"score_gpt":0.2272457621811828,"score_spread":0.1447318658644158,"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."}}