{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000255875,0.0001627922,0.0001678476,0.00009105574,0.0002270564,0.0002087974,0.000655595,0.0000679199,0.0002572726],"category_scores_gemma":[0.0000534375,0.0001254226,0.00005738798,0.0003396069,0.0000538967,0.0005218966,0.0001911843,0.0001556889,0.0001119265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003461651,"about_ca_system_score_gemma":0.0000859607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002917261,"about_ca_topic_score_gemma":0.000002772177,"domain_scores_codex":[0.9985674,0.0001073962,0.0002364601,0.0004480523,0.0003175263,0.0003231751],"domain_scores_gemma":[0.99883,0.0001538519,0.00008959581,0.0007062177,0.00007329122,0.0001470837],"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":[0.00000487418,0.0001543457,0.002089447,0.00001619094,0.00001211378,0.00004051498,0.00007632637,0.000299536,0.001350079,0.2923489,0.007978644,0.6956291],"study_design_scores_gemma":[0.001305614,0.00006539536,0.0004903737,0.0001004522,0.000005454125,0.00007494427,0.0001557574,0.8713452,0.04561935,0.00480142,0.07547303,0.000563056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001372324,0.00009056591,0.9711008,0.0002119861,0.0006197543,0.0001089255,0.000003193258,0.0003156112,0.02617686],"genre_scores_gemma":[0.1928249,0.00000288417,0.8061996,0.0004523873,0.00004439057,0.000007912588,0.000008148889,0.00001022735,0.0004495303],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8710456,"threshold_uncertainty_score":0.5114585,"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."}}