{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004850192,0.001500285,0.001236846,0.001293881,0.000489147,0.003092744,0.001819098,0.001752872,0.002467709],"category_scores_gemma":[0.02140116,0.0007220119,0.0009564374,0.00165542,0.003535039,0.006344766,0.003967257,0.004907161,0.0007621584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002501966,"about_ca_system_score_gemma":0.0009465308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006259385,"about_ca_topic_score_gemma":0.0003425339,"domain_scores_codex":[0.9968368,0.00115953,0.000172518,0.0005460212,0.001041748,0.0002433061],"domain_scores_gemma":[0.9910231,0.005566379,0.0007048611,0.001766897,0.0007602028,0.0001786323],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000167227,0.00006314456,0.0003260032,0.00021864,0.000040503,0.0001036457,0.0002549229,0.08996552,0.005245871,0.8406773,0.001733638,0.06120364],"study_design_scores_gemma":[0.00002780167,0.0001977042,0.0003467054,0.00012358,0.00003270107,0.0003597167,0.00006598978,0.4006678,0.008247371,0.5839913,0.00588523,0.0000539597],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009449121,0.001632387,0.9829172,0.0005002149,0.00004798091,0.00004812279,0.0001051587,0.0002064122,0.00509337],"genre_scores_gemma":[0.6409168,0.003717426,0.3479635,0.000661522,0.0003006821,0.0004329512,0.0003252088,0.0003578153,0.005324162],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004850192,"threshold_uncertainty_score":0.02565056,"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."}}