{"id":"W2950603471","doi":"10.48550/arxiv.1101.5376","title":"Succincter Text Indexing with Wildcards","year":2011,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Compressed suffix array; Search engine indexing; Suffix; Suffix array; Space (punctuation); Computer science; Combinatorics; Binary logarithm; Matching (statistics); Alphabet; Word (group theory); Algorithm; Data structure; Mathematics; Theoretical computer science; Suffix tree; Information retrieval; Statistics","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":[0.001403674,0.000801323,0.001788175,0.002240444,0.0009190872,0.002957491,0.002355206,0.001438894,0.006243992],"category_scores_gemma":[0.01366888,0.0005839964,0.0007657945,0.006641733,0.001702556,0.01187331,0.003488306,0.001817542,0.004206023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001006208,"about_ca_system_score_gemma":0.001597659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0010891,"about_ca_topic_score_gemma":0.001410922,"domain_scores_codex":[0.9974136,0.000442448,0.0004068791,0.0005105605,0.0009824027,0.0002441754],"domain_scores_gemma":[0.9899516,0.003948251,0.0008650149,0.004014771,0.0009983433,0.0002220718],"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":[0.001527271,0.0005008762,0.003075764,0.0007733202,0.00008111854,0.0005803811,0.0008853943,0.04801209,0.05253988,0.1400978,0.03871901,0.7132071],"study_design_scores_gemma":[0.0003353841,0.0006828635,0.001051416,0.0001309252,0.00007118641,0.001376307,0.000512975,0.5418941,0.08259199,0.3308768,0.04035363,0.0001223677],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0946469,0.001537915,0.8862653,0.001755986,0.0004517425,0.0002867063,0.002685484,0.007073686,0.005296279],"genre_scores_gemma":[0.2884346,0.001037593,0.6910915,0.0009791689,0.0005659334,0.0004314974,0.00777743,0.000939189,0.008743045],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006243992,"threshold_uncertainty_score":0.02088827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06240961777366939,"score_gpt":0.1682849665940609,"score_spread":0.1058753488203915,"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."}}