{"id":"W4239270184","doi":"10.1109/asonam.2016.7752351","title":"Frequent and non-frequent pattern detection in big data streams: An experimental simulation in 1 trillion data points","year":2016,"lang":"en","type":"article","venue":"2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Big data; String (physics); Suffix; Data mining; Data stream mining; Point (geometry); Data structure; Data modeling; Database; Operating system","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":[0.00219085,0.0006189452,0.0008066111,0.00100575,0.0005902515,0.000747135,0.001212535,0.001019576,0.001383677],"category_scores_gemma":[0.01165203,0.0002831055,0.000694452,0.001452085,0.0007580554,0.001338691,0.0007729488,0.001259581,0.000325456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000585261,"about_ca_system_score_gemma":0.0008081075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004802254,"about_ca_topic_score_gemma":0.003641641,"domain_scores_codex":[0.9984475,0.000408028,0.0001399856,0.0002632488,0.0005073298,0.000233956],"domain_scores_gemma":[0.9870935,0.009103874,0.0004598091,0.001201523,0.001581999,0.0005592952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006092344,0.006237814,0.07239095,0.0008972996,0.0005066714,0.001937929,0.00102379,0.7305239,0.02902328,0.007109474,0.01194872,0.1323077],"study_design_scores_gemma":[0.0001211624,0.0006724235,0.006225909,0.00001437593,0.00002928274,0.0001742474,0.0002190501,0.981308,0.008784307,0.001792911,0.0006389015,0.00001939312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.979575,0.000266906,0.01714283,0.0003296491,0.0001147328,0.0001321826,0.0007577303,0.0006885314,0.000992362],"genre_scores_gemma":[0.968205,0.000166069,0.02901318,0.00007961653,0.00002844593,0.0001397627,0.001639199,0.00004088249,0.0006878039],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004802254,"threshold_uncertainty_score":0.01158643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08813651274119436,"score_gpt":0.365066864245738,"score_spread":0.2769303515045436,"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."}}