{"id":"W4386843758","doi":"10.1109/dcc55655.2023.00023","title":"Computing matching statistics on Wheeler DFAs","year":2023,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"HORIZON EUROPE Health; National Human Genome Research Institute; Science and Engineering Research Council; National Institute of Allergy and Infectious Diseases; Gruppo Nazionale per il Calcolo Scientifico; National Institutes of Health; EGI; Israel Institute for Biological Research; Natural Sciences and Engineering Research Council of Canada; European Commission; Istituto Nazionale di Alta Matematica \"Francesco Severi\"; National Science Foundation","keywords":"Computer science; String searching algorithm; Suffix tree; Compressed suffix array; Deterministic finite automaton; Automaton; Pattern matching; Prefix; Tree (set theory); Matching (statistics); Subroutine; Algorithm; Theoretical computer science; Approximate string matching; String (physics); Suffix; Data structure; Mathematics; Combinatorics; Artificial intelligence; Programming language; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001186073,0.0006396936,0.001359722,0.003736835,0.0008995874,0.002417965,0.001855957,0.001482985,0.004011158],"category_scores_gemma":[0.01671117,0.0005409466,0.000863958,0.004989949,0.001309438,0.006659928,0.002165623,0.001101612,0.001934005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001974677,"about_ca_system_score_gemma":0.001476533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003939725,"about_ca_topic_score_gemma":0.006028248,"domain_scores_codex":[0.9975539,0.0003633563,0.0002949878,0.000751388,0.0007917679,0.0002445763],"domain_scores_gemma":[0.9935467,0.003277353,0.0006372839,0.001493915,0.0008763649,0.0001683775],"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":[0.0005966457,0.0001825821,0.008744922,0.0002850175,0.0001346899,0.0003990288,0.0005060555,0.2669064,0.03076966,0.3068396,0.005737084,0.3788984],"study_design_scores_gemma":[0.00002167909,0.00006941206,0.0007791145,0.00002949003,0.00002591969,0.0001276667,0.00010887,0.6720557,0.01840356,0.3026519,0.005679236,0.00004740258],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07415304,0.0002716164,0.9164064,0.0001919803,0.00006220757,0.00009845114,0.001650948,0.004698219,0.002467314],"genre_scores_gemma":[0.5117162,0.000292635,0.477879,0.0002706137,0.00007597213,0.0003809083,0.004276784,0.0007574415,0.004350423],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004011158,"threshold_uncertainty_score":0.01432729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02391902105475247,"score_gpt":0.2826896403153684,"score_spread":0.258770619260616,"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."}}