{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003236062,0.0001455419,0.0001314466,0.0001338724,0.0001015006,0.00009468535,0.0008922328,0.0000823187,0.000005597423],"category_scores_gemma":[0.00004233921,0.0001058041,0.00001190081,0.0002750737,0.00004540296,0.0004162303,0.0004771389,0.0001241487,0.00003113425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006105034,"about_ca_system_score_gemma":0.00002958399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001517885,"about_ca_topic_score_gemma":0.00003932772,"domain_scores_codex":[0.9984494,0.00004425747,0.0002972914,0.0007757307,0.0002061155,0.0002271594],"domain_scores_gemma":[0.9983311,0.0001147143,0.000126313,0.001327262,0.00003219554,0.00006835992],"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":[0.00001958998,0.00003732165,0.0001309019,0.000004833391,0.000003100243,0.000003880729,0.0001260322,0.00004642957,0.1635901,0.004631651,0.00002190083,0.8313842],"study_design_scores_gemma":[0.0004145687,0.00013016,0.01994771,0.0003284332,0.00000842753,0.00002511787,0.0001557193,0.6445598,0.3261616,0.006089502,0.001558292,0.0006206365],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1615393,0.00002177857,0.8376385,0.0001531787,0.0002523383,0.0001657744,0.00001004586,0.00007155324,0.0001475071],"genre_scores_gemma":[0.9903046,0.0001851157,0.009282473,0.00007694307,0.00009372513,0.00001516297,0.00001468364,0.000009427143,0.0000178811],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8307636,"threshold_uncertainty_score":0.4314564,"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."}}