{"id":"W2555880401","doi":"10.1109/spcom.2016.7746651","title":"Text compression using lexicographic permutation of binary strings","year":2016,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Lexicographical order; Lossless compression; String (physics); Computer science; Binary number; Data compression; Permutation (music); Reduction (mathematics); Rank (graph theory); Compression ratio; Compression (physics); String searching algorithm; Algorithm; Binary code; n-gram; Speech recognition; Mathematics; Combinatorics; Artificial intelligence; Arithmetic; Pattern matching; Language model; Physics","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":[0.0001126633,0.00008308307,0.0001066559,0.0001435968,0.00007935434,0.00002944737,0.000431488,0.00004108924,0.0000486049],"category_scores_gemma":[0.00001117829,0.00004739907,0.00004385893,0.0002631724,0.00004644316,0.000865463,0.0003448742,0.00003427565,0.00001011057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001269142,"about_ca_system_score_gemma":0.00002693945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005805433,"about_ca_topic_score_gemma":6.734239e-7,"domain_scores_codex":[0.9991735,0.00003630884,0.0001878738,0.0002372889,0.0002269297,0.0001380536],"domain_scores_gemma":[0.9993146,0.00006928688,0.0001059495,0.0003819083,0.00007419936,0.00005403487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001183109,0.00009485415,0.002659377,0.0000170968,0.000008621671,0.000005236654,0.0001250536,0.0001167483,0.7966795,0.01968241,0.0005921538,0.1800071],"study_design_scores_gemma":[0.001742286,0.0003437963,0.05974101,0.0007867487,0.00001456539,0.00003818596,0.0000696377,0.7417347,0.1833777,0.008310182,0.003288981,0.0005521983],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3128909,0.00005425813,0.6864137,0.0001156765,0.0001135605,0.00005280012,0.000003181153,0.00006596918,0.0002899509],"genre_scores_gemma":[0.9234973,0.00001894082,0.07633424,0.00002942491,0.00002183795,0.000001258974,0.000001634182,0.000004376855,0.00009102896],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7416179,"threshold_uncertainty_score":0.1932878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02569379645617112,"score_gpt":0.266010369188574,"score_spread":0.2403165727324029,"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."}}