{"id":"W2138523425","doi":"10.1109/dcc.1992.227475","title":"Constructing word-based text compression algorithms","year":2003,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":86,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Victoria","funders":"","keywords":"Huffman coding; Word (group theory); ASCII; Computer science; Context (archaeology); Algorithm; Compression (physics); Data compression; Alphanumeric; Sigma; Alphabet; Word problem (mathematics education); Compression ratio; Lossless compression; Theoretical computer science; Natural language processing; Artificial intelligence; Arithmetic; Mathematics; Programming language; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008133821,0.0008360915,0.0007024743,0.002816955,0.0006625699,0.001560177,0.001596576,0.001120476,0.005668475],"category_scores_gemma":[0.005498734,0.0004003473,0.0006674373,0.002616548,0.000674311,0.002075601,0.001554442,0.0009549614,0.00543822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006360229,"about_ca_system_score_gemma":0.001004332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007732165,"about_ca_topic_score_gemma":0.0006325783,"domain_scores_codex":[0.9989746,0.0001485863,0.0001386119,0.0001909927,0.0004577502,0.00008944165],"domain_scores_gemma":[0.9980865,0.0004301163,0.00009669725,0.0003046874,0.00102936,0.00005278227],"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":[0.0002134109,0.0001097352,0.0009462911,0.0003442329,0.00004957556,0.0002342513,0.0002857287,0.03346208,0.0365651,0.06221776,0.01105282,0.854519],"study_design_scores_gemma":[0.0001251609,0.0002831467,0.0007377084,0.0001384578,0.00009165685,0.0007484072,0.0002426254,0.6728899,0.1880181,0.0736453,0.06300986,0.00006969183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01064252,0.0003341727,0.9819518,0.0001342619,0.000118598,0.0002921686,0.0002361581,0.002809478,0.003480941],"genre_scores_gemma":[0.04259743,0.0004390346,0.9516012,0.0001539965,0.00009439597,0.0003440141,0.0009950468,0.0003257598,0.003449106],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005668475,"threshold_uncertainty_score":0.01896292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01936819052923327,"score_gpt":0.2530895295810157,"score_spread":0.2337213390517824,"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."}}