{"id":"W4251561142","doi":"10.1109/isit.2000.866306","title":"Universal lossless coding of sources with large and unbounded alphabets","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Arithmetic coding; Independent and identically distributed random variables; Distributed source coding; Alphabet; Lossless compression; Variable-length code; Asymptotically optimal algorithm; ENCODE; Shannon's source coding theorem; Entropy (arrow of time); Shannon–Fano coding; Mathematics; Entropy encoding; Computer science; Tunstall coding; Algorithm; Discrete mathematics; Huffman coding; Coding (social sciences); Context-adaptive binary arithmetic coding; Data compression; Decoding methods; Principle of maximum entropy; Binary entropy function; Random variable; Statistics","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":[0.0006964427,0.0004160524,0.0005417689,0.000822049,0.0003717616,0.0008511118,0.0009974844,0.0006184404,0.001001877],"category_scores_gemma":[0.004189692,0.0002221148,0.0003574871,0.0007918755,0.0009949526,0.001849568,0.001504268,0.000944871,0.0002808516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005049671,"about_ca_system_score_gemma":0.0005088797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004930717,"about_ca_topic_score_gemma":0.0005382426,"domain_scores_codex":[0.9995715,0.0001126374,0.000030522,0.00005470047,0.0001549197,0.00007575096],"domain_scores_gemma":[0.9984412,0.0008631393,0.0001700736,0.0002917871,0.0001825743,0.00005130454],"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":[0.0003727223,0.00004488295,0.0003825048,0.0001589813,0.00002711629,0.0002720207,0.000254625,0.1984119,0.03757718,0.5768101,0.001938652,0.1837493],"study_design_scores_gemma":[0.00002296902,0.00005372476,0.0001243067,0.00003736142,0.0000145553,0.0001397534,0.00002360079,0.8188019,0.01835945,0.1600529,0.002348098,0.00002140254],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03565443,0.0003879682,0.9606929,0.0002659374,0.00004511444,0.00002174368,0.00009834149,0.0002668959,0.002566621],"genre_scores_gemma":[0.7349557,0.0006429434,0.2602559,0.0002049985,0.0001242611,0.00009665619,0.000252257,0.00007436183,0.00339291],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001001877,"threshold_uncertainty_score":0.00368315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01250257619985981,"score_gpt":0.1971582571572464,"score_spread":0.1846556809573866,"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."}}