{"id":"W2119878143","doi":"10.1109/dcc.1997.582019","title":"A corpus for the evaluation of lossless compression algorithms","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":201,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Lossless compression; Computer science; Data compression; Compression (physics); Algorithm; Lossy compression; Natural language processing; Compression ratio; The Internet; Artificial intelligence; Information retrieval; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006866207,0.00008331861,0.000108157,0.00003777754,0.0001646623,0.00006152405,0.0007749632,0.00003761768,0.0001266991],"category_scores_gemma":[0.00004694941,0.00004669423,0.00005663539,0.0001701579,0.00003829916,0.000315317,0.0002286929,0.00005083454,0.00001362689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001707914,"about_ca_system_score_gemma":0.00001752514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003691091,"about_ca_topic_score_gemma":0.000002709492,"domain_scores_codex":[0.9988036,0.00006581896,0.0001957799,0.0002228212,0.0005699323,0.0001420258],"domain_scores_gemma":[0.9986304,0.0002791527,0.0001108326,0.0006241729,0.0003184415,0.00003697086],"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":[0.000003471672,0.00009342821,0.000036159,0.000007843476,0.00001210139,2.508832e-7,0.000211842,0.0009117508,0.000716382,0.008575198,0.01249126,0.9769403],"study_design_scores_gemma":[0.0006043383,0.00004794286,0.0008071303,0.00001880346,0.00001643736,0.000003852299,0.00001826461,0.9846759,0.003307327,0.002171629,0.00825726,0.00007112412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001312245,0.001046666,0.9949529,0.0005454665,0.0004516458,0.0004762967,0.000009919913,0.00005111498,0.001153792],"genre_scores_gemma":[0.8531061,0.0001099907,0.1455445,0.0002329611,0.0001641707,0.000139517,0.00001077778,0.00001111827,0.0006808886],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9837641,"threshold_uncertainty_score":0.1904135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.125841513504027,"score_gpt":0.326270749231966,"score_spread":0.200429235727939,"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."}}