{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005249115,0.001339544,0.001351477,0.008991401,0.003543436,0.002151984,0.002712629,0.001785261,0.01627619],"category_scores_gemma":[0.04688392,0.0006589828,0.0007654684,0.01091591,0.002545881,0.003041453,0.002982469,0.002032705,0.006437319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002598722,"about_ca_system_score_gemma":0.002398358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01160944,"about_ca_topic_score_gemma":0.01674316,"domain_scores_codex":[0.9894124,0.003201853,0.001412732,0.001002439,0.004680838,0.0002897019],"domain_scores_gemma":[0.9313816,0.03340641,0.001935561,0.01162273,0.02038937,0.001264368],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009882909,0.001488114,0.004758611,0.006948742,0.0001688317,0.0015021,0.004133499,0.01106961,0.02394697,0.01644052,0.427819,0.5007358],"study_design_scores_gemma":[0.0009492924,0.001264109,0.05441325,0.001614226,0.0002021327,0.004539313,0.00401463,0.04522739,0.06345784,0.01339212,0.8104768,0.0004489063],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.362641,0.01556206,0.2115877,0.004254941,0.002684238,0.01323947,0.2718037,0.01637288,0.101854],"genre_scores_gemma":[0.2563574,0.00392528,0.2779827,0.0007410576,0.000758428,0.01370693,0.4103568,0.003941732,0.03222965],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01627619,"threshold_uncertainty_score":0.05444926,"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."}}