{"id":"W2319265692","doi":"10.1007/s10489-016-0766-2","title":"Repeated patterns detection in big data using classification and parallelism on LERP Reduced Suffix Arrays","year":2016,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Parallelism (grammar); Suffix; Parallel computing; Artificial intelligence; Pattern recognition (psychology)","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":[0.0005569158,0.0005149669,0.0008107369,0.001783648,0.0008489722,0.001243649,0.00113835,0.0005262834,0.002086292],"category_scores_gemma":[0.003704006,0.0003162671,0.0006254168,0.003180108,0.0005578809,0.001748571,0.001025923,0.0008361919,0.001204411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004695715,"about_ca_system_score_gemma":0.001278878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001662334,"about_ca_topic_score_gemma":0.0025104,"domain_scores_codex":[0.9990683,0.000168643,0.00009492422,0.0002100334,0.0003646095,0.00009352335],"domain_scores_gemma":[0.9975375,0.0007998925,0.0002045961,0.000695357,0.000655339,0.00010728],"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":[0.001050905,0.00035835,0.008013862,0.0001906735,0.0001039126,0.0005413076,0.0003654628,0.05691819,0.0726931,0.01333011,0.007560499,0.8388736],"study_design_scores_gemma":[0.00003953572,0.000205232,0.00240987,0.00001776851,0.00003502157,0.0003336966,0.0001645372,0.9344645,0.034747,0.02250624,0.005044543,0.00003199954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1840275,0.00056824,0.8054119,0.000477628,0.000198996,0.0001453688,0.0007459255,0.005421887,0.003002587],"genre_scores_gemma":[0.461197,0.0002593945,0.5320429,0.000169652,0.0001432701,0.0001967914,0.001592924,0.0002624591,0.004135512],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002086292,"threshold_uncertainty_score":0.006979287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1438759669707695,"score_gpt":0.3030399949651068,"score_spread":0.1591640279943373,"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."}}