{"id":"W1545746670","doi":"10.1109/dcc.1998.672253","title":"Higher compression from the Burrows-Wheeler transform by modified sorting","year":2002,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Substring; Sorting; Computer science; Algorithm; ASCII; Character (mathematics); Lossless compression; Sorting algorithm; Data compression; sort; Compression (physics); Encoding (memory); Compression ratio; Set (abstract data type); Theoretical computer science; Mathematics; Artificial intelligence; Information retrieval","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001097075,0.0001560458,0.0001405738,0.00001732509,0.000314283,0.0002281912,0.001209185,0.00007215769,0.001071578],"category_scores_gemma":[0.000005433844,0.0000863454,0.00006319262,0.0001560845,0.00003449644,0.0006688469,0.0002542475,0.0001875614,0.0001517101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001480677,"about_ca_system_score_gemma":0.000004989477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003961249,"about_ca_topic_score_gemma":0.000005946702,"domain_scores_codex":[0.9986671,0.000050094,0.000251855,0.0003859589,0.0003594641,0.0002854915],"domain_scores_gemma":[0.9989503,0.0001504944,0.00007085845,0.0007077091,0.00002919319,0.00009142906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007093171,0.000192232,0.0001654568,0.000004267099,0.00002669875,0.000007989043,0.001028853,0.0001418654,0.008853428,0.01619348,0.5377655,0.4356131],"study_design_scores_gemma":[0.0006817939,0.00003306489,0.0008112444,0.00003910025,0.000007145941,0.000002103428,0.00002638746,0.8173321,0.00525853,0.004564217,0.1709472,0.0002971151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005043559,0.001054027,0.9426771,0.006350622,0.0005705932,0.0002011954,0.00002491453,0.0003422557,0.04373571],"genre_scores_gemma":[0.9650859,0.00008465503,0.02503974,0.002373133,0.0002377321,0.00001945487,0.00003299547,0.00001690723,0.007109433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9600424,"threshold_uncertainty_score":0.9998416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03153017270255547,"score_gpt":0.231984474489101,"score_spread":0.2004543017865455,"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."}}