{"id":"W7145257302","doi":"","title":"Compression by Substring Enumeration Using Sorted Contingency Tables","year":2020,"lang":"en","type":"article","venue":"Institutional Repositories DataBase (IRDB)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science","keywords":"Substring; Lexicographical order; Enumeration; Upper and lower bounds; Contingency table; Encoding (memory); Compression (physics); Table (database)","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":[0.0001544008,0.0002348895,0.0002252386,0.00005519725,0.0009897375,0.0004712853,0.0007225122,0.0000841224,0.0000217524],"category_scores_gemma":[0.0001881667,0.0002195863,0.00005834469,0.0004395831,0.0001086165,0.003378917,0.0007254676,0.0002334218,0.00002036457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009438864,"about_ca_system_score_gemma":0.0002698679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004937751,"about_ca_topic_score_gemma":0.000005818362,"domain_scores_codex":[0.9978057,0.00007629465,0.0004669949,0.0006591098,0.0006865815,0.0003053456],"domain_scores_gemma":[0.9987091,0.00007846813,0.0002203416,0.0005355419,0.0002152519,0.0002413187],"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":[0.0000913339,0.0002247585,0.005493807,0.0001131755,0.00007247721,0.000246053,0.000471919,0.00361079,0.9026603,0.06120379,0.01916669,0.006644886],"study_design_scores_gemma":[0.001109709,0.00009062105,0.0005818928,0.0004126396,0.00003858051,0.0001501965,0.0000586892,0.5757229,0.1696088,0.0002046775,0.2512521,0.0007691976],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03739907,0.001086567,0.9581438,0.0003311166,0.001620532,0.0002065265,0.0005227778,0.0002799862,0.0004095678],"genre_scores_gemma":[0.8423375,0.00008683739,0.1527822,0.0004499892,0.001396381,0.00002343119,0.00284082,0.00002260103,0.00006020986],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8053616,"threshold_uncertainty_score":0.895447,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03307146768172269,"score_gpt":0.2559402002473943,"score_spread":0.2228687325656716,"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."}}