{"id":"W3206818284","doi":"10.48550/arxiv.2110.07082","title":"The Impact of Spatiotemporal Augmentations on Self-Supervised Audiovisual Representation Learning","year":2021,"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":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Perception; Lossy compression; Benchmark (surveying); Supervised learning; Representation (politics); Transformation (genetics); Feature learning; Machine learning; Artificial neural network; Psychology","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":[0.0002615151,0.0002093612,0.0002395625,0.0001370491,0.0004254647,0.0002551971,0.0008624932,0.0001281262,0.00002432792],"category_scores_gemma":[0.0000711411,0.0001844988,0.0003008599,0.0006381478,0.00007435713,0.0004025839,0.0007498213,0.0004783531,0.000008194997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002189307,"about_ca_system_score_gemma":0.0005292027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004743813,"about_ca_topic_score_gemma":0.00001979305,"domain_scores_codex":[0.9984398,0.0002927776,0.0002321667,0.0006599078,0.0001453436,0.0002300283],"domain_scores_gemma":[0.998318,0.0002291917,0.0004264176,0.0007027246,0.0002399898,0.00008367742],"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":[0.00004646323,0.0002239083,0.02120654,0.00007924945,0.0003761009,0.0001061839,0.003436879,0.9529473,0.0004008867,0.01100365,0.0003985964,0.009774197],"study_design_scores_gemma":[0.0005007733,0.0001346137,0.01707041,0.0001633102,0.00004837793,0.000002719086,0.0006000576,0.9770792,0.001080348,0.00300205,0.00002644644,0.0002916672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6950828,0.00004512244,0.3025219,0.00008926603,0.0001933659,0.000147951,0.000002059101,0.0001155066,0.001801998],"genre_scores_gemma":[0.9974019,0.000148722,0.001841916,0.00002796089,0.0000531689,0.00000102295,0.00002333204,0.00001140697,0.0004905633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3023191,"threshold_uncertainty_score":0.7523642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08479737383591522,"score_gpt":0.248482000304569,"score_spread":0.1636846264686537,"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."}}