{"id":"W3174705979","doi":"10.48550/arxiv.2106.10311","title":"Universal Rate-Distortion-Perception Representations for Lossy Compression","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Toronto","funders":"","keywords":"MNIST database; Encoder; Lossy compression; Distortion (music); Perception; Computer science; Theoretical computer science; Context (archaeology); Algorithm; Representation (politics); Mathematics; Artificial intelligence; Deep learning","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":[0.0002216174,0.0003524303,0.0003798197,0.0003167196,0.0003859626,0.0002157649,0.001978595,0.0003360624,0.00007602394],"category_scores_gemma":[0.00009584726,0.0004261191,0.0002927773,0.0005414271,0.0001252006,0.001361212,0.002961613,0.0005140012,0.00002089432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004342788,"about_ca_system_score_gemma":0.0002588464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001336453,"about_ca_topic_score_gemma":0.00003300812,"domain_scores_codex":[0.9973112,0.0002811885,0.0003048253,0.001632159,0.000125443,0.0003451702],"domain_scores_gemma":[0.9965163,0.000251781,0.0004119484,0.002144206,0.0004859761,0.0001897597],"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":[0.0003515284,0.001067617,0.002530144,0.0006209436,0.0003503092,0.0008597205,0.001706974,0.5915077,0.01882063,0.3334363,0.03412599,0.01462223],"study_design_scores_gemma":[0.001206424,0.0001012664,0.003032799,0.0005038309,0.0001260364,0.00001015059,0.0006161942,0.9106377,0.006015776,0.0709251,0.005663956,0.001160811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03751192,0.00004515345,0.9594147,0.00014304,0.0007548411,0.0006670647,0.00009398357,0.0007882002,0.0005810524],"genre_scores_gemma":[0.9189158,0.0002346215,0.07839671,0.0000972825,0.00008849131,0.00001087379,0.0005958176,0.00002934346,0.001631062],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8814039,"threshold_uncertainty_score":0.999819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0844820733269245,"score_gpt":0.243399075118297,"score_spread":0.1589170017913725,"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."}}