{"id":"W2109262879","doi":"10.1016/j.jda.2010.09.004","title":"String matching with alphabet sampling","year":2010,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Suffix; Subsequence; Longest common subsequence problem; String (physics); Alphabet; String searching algorithm; Computer science; Matching (statistics); Sampling (signal processing); Space (punctuation); Generalized suffix tree; Spamming; Suffix array; Suffix tree; Range (aeronautics); Substring; Longest increasing subsequence; Mathematics; Combinatorics; Algorithm; Artificial intelligence; Pattern matching; Data structure; Statistics; The Internet","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":[0.001909955,0.0005611511,0.001708209,0.002381757,0.000871203,0.001578558,0.001603527,0.001484351,0.005719317],"category_scores_gemma":[0.01069108,0.0005919916,0.0009741627,0.003991082,0.001040883,0.003085004,0.002644052,0.001356872,0.002131681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006200986,"about_ca_system_score_gemma":0.001365396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009299802,"about_ca_topic_score_gemma":0.001147325,"domain_scores_codex":[0.9971016,0.0009920578,0.0002171132,0.0005652305,0.0009148081,0.0002091046],"domain_scores_gemma":[0.9947531,0.002425533,0.0001978593,0.0020195,0.0004534641,0.0001504473],"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":[0.001276599,0.0003508416,0.002550717,0.0002755389,0.0001655598,0.0002792368,0.0001490532,0.116845,0.01684096,0.1013779,0.01079417,0.7490944],"study_design_scores_gemma":[0.00009570082,0.0001773262,0.0005460177,0.00003144698,0.00005726438,0.0003749651,0.00004432609,0.8325185,0.01584654,0.144555,0.005726949,0.00002596893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03289978,0.0006725189,0.9591061,0.0003643073,0.0002654862,0.0001215202,0.0003307772,0.001933194,0.004306301],"genre_scores_gemma":[0.4404212,0.0006723174,0.54514,0.0004403916,0.0003612196,0.0003359366,0.001418418,0.000445731,0.01076475],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005719317,"threshold_uncertainty_score":0.01913297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01335041713297873,"score_gpt":0.2691607421952065,"score_spread":0.2558103250622278,"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."}}