{"id":"W2400935260","doi":"10.1137/1.9781611973440.88","title":"Efficient Matching of Substrings in Uncertain Sequences","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Substring; Subsequence; Computer science; Sequence (biology); Matching (statistics); Scalability; Trajectory; Data mining; Theoretical computer science; Data structure; Mathematics; Programming language; Database","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":[0.0003071954,0.00003882353,0.00006609751,0.00005271039,0.00002332391,0.00002941413,0.0004493609,0.0000130879,0.000004644775],"category_scores_gemma":[0.00001361728,0.00003174465,0.00001264534,0.0002745817,0.00002027707,0.00005259453,0.00009223975,0.00002666563,0.00001209419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009249778,"about_ca_system_score_gemma":0.00001543063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005903715,"about_ca_topic_score_gemma":0.00002057896,"domain_scores_codex":[0.9995106,0.00001428926,0.0001289748,0.0001501879,0.00009863784,0.00009725694],"domain_scores_gemma":[0.9996094,0.00007070848,0.00003751902,0.0002439801,0.00001556813,0.00002288214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[4.915631e-7,0.00007288051,0.001060687,0.00001239199,0.000002226913,9.954848e-7,0.001176237,0.0161449,0.002908693,0.8215358,0.00009723273,0.1569874],"study_design_scores_gemma":[0.00009574077,0.000017522,0.00420979,0.00002085307,5.74886e-7,0.000002087782,0.00007842205,0.985707,0.002933444,0.006298338,0.0005636232,0.00007253591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3278972,0.000006515394,0.6683537,0.0003415678,0.00002626345,0.00003265681,8.611671e-7,0.00003267068,0.003308554],"genre_scores_gemma":[0.7933101,6.872796e-7,0.2065819,0.00004578238,0.000006089061,0.000004655501,7.129373e-7,0.000001158845,0.00004885307],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9695622,"threshold_uncertainty_score":0.1294509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01540583498905401,"score_gpt":0.2560108658142202,"score_spread":0.2406050308251662,"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."}}