{"id":"W2098163860","doi":"10.1109/isit.2002.1023562","title":"The compression performance of grammar-based codes revisited","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Lossless compression; Computer science; Redundancy (engineering); Grammar; Arithmetic coding; Data compression; Coding (social sciences); Benchmark (surveying); Encoding (memory); Theoretical computer science; Algorithm; Context-adaptive binary arithmetic coding; Artificial intelligence; Mathematics; Linguistics","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":[0.0003525957,0.00008044854,0.000103566,0.0000289704,0.0002503434,0.00007273834,0.0006620544,0.00002819156,0.0000210115],"category_scores_gemma":[0.000037294,0.00004276748,0.00003526589,0.0002317166,0.00005267486,0.0002313744,0.000113894,0.00007079512,0.0000125075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007480034,"about_ca_system_score_gemma":0.00003893242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009816395,"about_ca_topic_score_gemma":8.882283e-7,"domain_scores_codex":[0.99915,0.00008798424,0.0001898426,0.0001727722,0.0002390735,0.0001603738],"domain_scores_gemma":[0.9989306,0.0001740986,0.00008885995,0.0006743586,0.00008606897,0.00004601328],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007873102,0.0003440273,0.01384671,0.0001402919,0.00003051873,0.000006625457,0.0001468634,0.001827742,0.01329269,0.5520548,0.03120038,0.3870307],"study_design_scores_gemma":[0.0004582134,0.0001395159,0.004082293,0.0001034057,0.000003458791,0.000004400386,0.00001119486,0.8165603,0.06932427,0.0008088331,0.1083406,0.0001635544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03890357,0.0004997822,0.9521003,0.0002141634,0.0002308443,0.0001638044,0.000002942815,0.0001122231,0.007772398],"genre_scores_gemma":[0.9165286,0.000083205,0.08290437,0.0001386199,0.00001106451,0.00000522644,0.00000420234,0.000004087477,0.0003206467],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.877625,"threshold_uncertainty_score":0.1925464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01244905434516906,"score_gpt":0.2333816414575799,"score_spread":0.2209325871124109,"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."}}