{"id":"W3142663085","doi":"10.14778/3447689.3447695","title":"On the string matching with <i>k</i> differences in DNA databases","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Substring; Suffix tree; String (physics); String searching algorithm; Combinatorics; Pattern matching; Trie; Bounded function; Speedup; Sequence (biology); Tree (set theory); Computer science; Alphabet; Matching (statistics); Time complexity; Mathematics; Algorithm; Data structure; Artificial intelligence; Parallel computing; Biology","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":[0.003506611,0.001440837,0.002291923,0.003326591,0.001649401,0.003285393,0.004348255,0.002403203,0.002971702],"category_scores_gemma":[0.01189561,0.001054951,0.002021713,0.008600943,0.002655583,0.01582088,0.004411452,0.00247032,0.001920589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00196886,"about_ca_system_score_gemma":0.001694864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002881856,"about_ca_topic_score_gemma":0.001667199,"domain_scores_codex":[0.9931162,0.001652394,0.0008150213,0.001749548,0.002106691,0.0005601773],"domain_scores_gemma":[0.9932326,0.00369048,0.0006250975,0.001677863,0.0005588987,0.0002152029],"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":[0.001148483,0.0004460657,0.00369423,0.001452404,0.0001917575,0.0005685095,0.0008751458,0.06753888,0.03169319,0.1338106,0.0118594,0.7467214],"study_design_scores_gemma":[0.0002392081,0.0007153724,0.002101129,0.0002288257,0.0002315095,0.002531277,0.0004304843,0.6883934,0.04084031,0.2229141,0.04116912,0.0002052941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01920339,0.003567646,0.9724867,0.0006592704,0.0001271374,0.000172799,0.0001470597,0.001691816,0.001944191],"genre_scores_gemma":[0.1039908,0.002985797,0.8881436,0.0005373278,0.0003031745,0.0002882314,0.0006802765,0.0003691016,0.002701692],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004348255,"threshold_uncertainty_score":0.01854497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02468333589081975,"score_gpt":0.2204707003077575,"score_spread":0.1957873644169377,"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."}}