{"id":"W4408244453","doi":"10.1109/tpami.2025.3548516","title":"Rate-Distortion Theory in Coding for Machines and Its Applications","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Intel Labs","keywords":"Computer science; Rate–distortion theory; Artificial intelligence; Codec; Machine vision; Coding (social sciences); Computer vision; Popularity; Distortion (music); Machine learning; Image compression; Data compression; Image processing; Image (mathematics); Computer hardware","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001889752,0.0001212007,0.0001634929,0.0003980139,0.0001386209,0.00004423658,0.00008067663,0.00004706578,0.00001821377],"category_scores_gemma":[0.000003495414,0.0001177376,0.0000641646,0.0005832426,0.00002671812,0.00006800456,0.000001469694,0.0001254424,0.000001393067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000275749,"about_ca_system_score_gemma":0.000005367599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005418184,"about_ca_topic_score_gemma":0.0003459674,"domain_scores_codex":[0.999396,0.00001791497,0.0002275103,0.0002115637,0.0000367985,0.0001101652],"domain_scores_gemma":[0.9996419,0.0001409516,0.00002487279,0.0001292294,0.00003311257,0.00002992991],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009806689,0.00005525239,0.0001675215,0.0001475227,0.0001399258,2.217316e-7,0.00008463212,0.0193488,0.002880226,0.001384713,0.000007705583,0.9757737],"study_design_scores_gemma":[0.00009145541,0.0000160957,0.0004970346,0.00005155279,0.0004025019,0.000001143865,0.00003755336,0.8084505,0.1840991,0.005793983,0.0003605891,0.0001985088],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002138756,0.0005908951,0.9965216,0.0001370945,0.00002735762,0.0002844024,0.00005606999,0.0001259279,0.0001179065],"genre_scores_gemma":[0.9973709,0.000978964,0.0008147519,0.00009950922,0.000006795077,0.0005208669,0.00001071694,0.00001052546,0.0001869475],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9957069,"threshold_uncertainty_score":0.4801202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0133337557402204,"score_gpt":0.2809330496364791,"score_spread":0.2675992938962587,"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."}}