{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005937333,0.0001789097,0.0002805139,0.0001672446,0.0001879111,0.0003667031,0.001199775,0.00006838963,0.00002085802],"category_scores_gemma":[0.00003096367,0.0001171841,0.0001029098,0.0002638229,0.00004367741,0.00179453,0.0002902104,0.0007456287,0.000007053751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002037274,"about_ca_system_score_gemma":0.0001160445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002674853,"about_ca_topic_score_gemma":0.000006928246,"domain_scores_codex":[0.9983671,0.00003263325,0.0004441971,0.0002316628,0.0006118079,0.0003125389],"domain_scores_gemma":[0.9985212,0.0001103536,0.0004681704,0.0004727353,0.0001995635,0.0002279859],"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":[0.0001254693,0.0003292649,0.002643749,0.00007193616,0.000365284,0.0008571276,0.002698148,0.003248363,0.06131335,0.04235822,0.001679268,0.8843098],"study_design_scores_gemma":[0.018498,0.006734442,0.07514045,0.003385138,0.0004904059,0.0209378,0.002552737,0.5005807,0.06991534,0.1264461,0.1691722,0.006146657],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0988916,0.000139653,0.8993094,0.0003998996,0.0009484863,0.0000568346,0.000006339876,0.0000401613,0.000207652],"genre_scores_gemma":[0.281741,0.00002618759,0.7175151,0.00008112905,0.0005847266,0.00000108905,0.000002051517,0.00001575391,0.00003299519],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8781632,"threshold_uncertainty_score":0.477863,"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."}}