{"id":"W2059884147","doi":"10.5555/1070432.1070437","title":"A categorization theorem on suffix arrays with applications to space efficient text indexes","year":2005,"lang":"en","type":"article","venue":"Symposium on Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Suffix; Suffix array; Combinatorics; String (physics); Binary number; Permutation (music); Cardinality (data modeling); Compressed suffix array; Discrete mathematics; Generalized suffix tree; Suffix tree; Mathematics; Computer science; Arithmetic; Data mining","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002643751,0.0004033511,0.0002782527,0.0002906964,0.0004278625,0.0003647598,0.001198263,0.000109023,0.00002460739],"category_scores_gemma":[0.00001165368,0.0002925838,0.00007782297,0.0009775363,0.00007786485,0.0003628895,0.0003054802,0.0002681078,0.0005947323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001664446,"about_ca_system_score_gemma":0.00009523293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004037492,"about_ca_topic_score_gemma":0.00000990576,"domain_scores_codex":[0.9971415,0.00008672904,0.000325071,0.001065902,0.0008143178,0.000566509],"domain_scores_gemma":[0.9977365,0.0001159856,0.0001599653,0.001489461,0.000141766,0.0003563443],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001763541,0.0009787668,0.00008405824,0.00002778163,0.00006673613,0.00001905898,0.002644607,0.3102696,0.005684987,0.5390686,0.003037462,0.137942],"study_design_scores_gemma":[0.002031532,0.002513999,0.001051562,0.0002776654,0.00004553552,0.00004839049,0.0002241033,0.8057501,0.04184639,0.001910479,0.1425156,0.001784703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002046172,0.000045471,0.9809983,0.007225086,0.0002012698,0.001013717,0.00005377768,0.0003701632,0.008046043],"genre_scores_gemma":[0.7895667,0.0000510291,0.2051342,0.002038577,0.0009751138,0.0006970363,0.0001448251,0.00009224893,0.001300259],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7875205,"threshold_uncertainty_score":0.9999526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008185812719306998,"score_gpt":0.2437248519696897,"score_spread":0.2355390392503827,"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."}}