{"id":"W3031217404","doi":"10.1587/transfun.2019eap1063","title":"Compression by Substring Enumeration Using Sorted Contingency Tables","year":2020,"lang":"en","type":"article","venue":"IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Substring; Lexicographical order; Upper and lower bounds; Enumeration; Algorithm; Mathematics; Encoding (memory); Computer science; Combinatorics; Data structure; Artificial intelligence","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":[0.0002566896,0.0001693483,0.000217561,0.0001081288,0.00106552,0.0002944687,0.001566133,0.00005275683,0.00001160406],"category_scores_gemma":[0.00000293064,0.0001584389,0.00005770815,0.0006476236,0.0002489369,0.0009831177,0.0001473346,0.0002278177,0.000001943073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003425963,"about_ca_system_score_gemma":0.00009973909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000940892,"about_ca_topic_score_gemma":0.00001369235,"domain_scores_codex":[0.9984739,0.0001371627,0.0003859961,0.0004211616,0.0003113884,0.000270384],"domain_scores_gemma":[0.9987699,0.0001808609,0.0002187446,0.0006344739,0.00008035915,0.000115702],"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":[0.00005061394,0.001380053,0.0006832033,0.00008615656,0.0001730208,0.00000137318,0.002847458,0.01851227,0.1791631,0.04349851,0.0005588082,0.7530455],"study_design_scores_gemma":[0.0003277717,0.000492933,0.00004496006,0.00006389535,0.00001504714,0.000006322232,0.00008263379,0.9796969,0.01504694,0.000276889,0.003753308,0.0001923585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02981483,0.003524005,0.9649289,0.001252551,0.00007683037,0.0001945026,0.00003522996,0.00008275765,0.0000904434],"genre_scores_gemma":[0.8485987,0.001474861,0.1495841,0.0002901115,0.00001324545,0.000009738463,0.00001720284,0.000006555583,0.000005449713],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9611847,"threshold_uncertainty_score":0.8195226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0477770078403256,"score_gpt":0.286274005145385,"score_spread":0.2384969973050594,"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."}}