{"id":"W2778964950","doi":"10.48550/arxiv.1712.07431","title":"Text Indexing and Searching in Sublinear Time","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Combinatorics; Binary logarithm; Log-log plot; Sublinear function; Alphabet; Search engine indexing; Space (punctuation); Mathematics; Physics; Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001631624,0.002598497,0.002319978,0.003076809,0.001456448,0.005617679,0.005109304,0.002399424,0.03641501],"category_scores_gemma":[0.01378769,0.0010977,0.002236541,0.008400056,0.001840395,0.01555934,0.005227453,0.002690772,0.02738029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003935974,"about_ca_system_score_gemma":0.005405052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005163703,"about_ca_topic_score_gemma":0.01106903,"domain_scores_codex":[0.9918211,0.0007955711,0.0007355542,0.001952878,0.003528284,0.001166765],"domain_scores_gemma":[0.9897138,0.003590486,0.0005940978,0.004698007,0.001059386,0.0003443657],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001638723,0.0004567727,0.001846538,0.001209213,0.0002139752,0.0002750834,0.0004400328,0.01484917,0.02576931,0.06968921,0.1455453,0.7380668],"study_design_scores_gemma":[0.0009103778,0.0003821641,0.001889623,0.0002316581,0.0003390623,0.001465001,0.0004656628,0.361097,0.04570055,0.4592848,0.1280594,0.0001746604],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03530291,0.006856227,0.8212081,0.007432749,0.001432549,0.0009761889,0.009630698,0.05967926,0.05748131],"genre_scores_gemma":[0.1939968,0.002060198,0.7297742,0.002400962,0.001107181,0.001336028,0.016787,0.004859816,0.04767793],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03641501,"threshold_uncertainty_score":0.1218203,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07549430422908276,"score_gpt":0.2056374929897745,"score_spread":0.1301431887606917,"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."}}