{"id":"W2049349451","doi":"10.1109/dcc.2010.28","title":"Lossless Data Compression via Substring Enumeration","year":2010,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Substring; Lossless compression; Lexicographical order; Compression (physics); Data compression; Enumeration; Algorithm; String (physics); Computer science; Mathematics; Compression ratio; Set (abstract data type); Combinatorics; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002271653,0.00009460706,0.00008775305,0.00004565981,0.0001887018,0.0002549807,0.002025488,0.00006024623,0.00009578186],"category_scores_gemma":[0.00001735004,0.00007239639,0.00001454552,0.0001406067,0.00002097555,0.001869671,0.001701722,0.0002084273,0.000108065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004551473,"about_ca_system_score_gemma":0.00002442008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008969635,"about_ca_topic_score_gemma":0.0000445543,"domain_scores_codex":[0.9989738,0.00002296303,0.0001580267,0.0004336759,0.0002420853,0.0001694738],"domain_scores_gemma":[0.9978739,0.00004876216,0.00005559337,0.00188747,0.00004615315,0.00008813656],"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":[0.000005454392,0.0001364951,0.001783117,0.0000107304,0.000008364794,0.00001646239,0.0001221074,0.00005418082,0.2146761,0.03364139,0.01666872,0.7328769],"study_design_scores_gemma":[0.0002127315,0.00001168772,0.002923535,0.00001103453,0.000002095033,0.00002056147,0.000004136379,0.9418296,0.01643534,0.001116689,0.0372684,0.0001642302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01451803,0.00002365647,0.9820906,0.000267164,0.001270142,0.00007674114,0.0000105261,0.000195961,0.00154718],"genre_scores_gemma":[0.7611684,0.00000590846,0.2381484,0.0001105063,0.0002138388,0.000002750781,0.0001763954,0.000006195045,0.0001676174],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9417754,"threshold_uncertainty_score":0.3763895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02874988235034151,"score_gpt":0.2778908061616329,"score_spread":0.2491409238112914,"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."}}