{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005911778,0.00006190158,0.0000897076,0.00004167694,0.00008612584,0.00006176783,0.0002619937,0.00002120204,0.00004805267],"category_scores_gemma":[0.000002383132,0.0000426934,0.000009729875,0.000126053,0.00004379721,0.000418987,0.0002296181,0.00003910423,0.000004201705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005348754,"about_ca_system_score_gemma":0.000006124701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003497508,"about_ca_topic_score_gemma":0.00001315373,"domain_scores_codex":[0.9994813,0.00001425035,0.00007034212,0.0001705225,0.0001360352,0.0001275025],"domain_scores_gemma":[0.9996315,0.0000332072,0.00004169402,0.0002148121,0.00002913655,0.00004970627],"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":[0.00003731092,0.0005946089,0.02634027,0.0001242108,0.0001102481,0.0001408493,0.006879163,0.0001010643,0.002632505,0.8120602,0.008196588,0.142783],"study_design_scores_gemma":[0.002424872,0.0003556484,0.007796305,0.0001398084,0.00001500211,0.0000572243,0.0007415105,0.9634539,0.007542811,0.001058799,0.01599343,0.000420724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1990798,0.0001873137,0.7961838,0.0001681362,0.00004065634,0.00004995177,0.000004683342,0.00006315933,0.004222544],"genre_scores_gemma":[0.9701959,0.00003189805,0.02926651,0.00005176775,0.00001113832,3.819932e-7,8.886472e-7,0.000002747816,0.0004387949],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9633528,"threshold_uncertainty_score":0.1740986,"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."}}