{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006665058,0.000216251,0.0003293,0.0003716001,0.0001097816,0.0002005117,0.001430553,0.0001152835,0.00002448698],"category_scores_gemma":[0.00007479834,0.0001709306,0.00003075229,0.0004443121,0.00008223562,0.002379816,0.0008957455,0.0001610178,0.000001598524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001441434,"about_ca_system_score_gemma":0.00004386437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004994639,"about_ca_topic_score_gemma":0.004587953,"domain_scores_codex":[0.9976921,0.0001626694,0.0004976169,0.0009952297,0.0003850435,0.0002673551],"domain_scores_gemma":[0.9985378,0.0002304047,0.0002702194,0.0008120832,0.00007096887,0.00007854046],"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":[0.00006351371,0.0001575487,0.02678201,0.000003050841,0.00003892453,0.00001274934,0.0003787649,0.003194379,0.0003297206,0.0002977673,0.00002074706,0.9687208],"study_design_scores_gemma":[0.001046546,0.00008337958,0.02508793,0.0002184458,0.00001568368,0.000001018527,0.0002755491,0.9720211,0.0000713828,0.0006039016,0.0003362768,0.000238812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3678079,0.0004412972,0.6303857,0.0003049803,0.0006353037,0.0001540084,0.0001362981,0.00002125596,0.0001132824],"genre_scores_gemma":[0.9950989,0.001705506,0.002445448,0.00007737835,0.0003435447,0.00001617435,0.0002869006,0.00000918962,0.00001690447],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9688267,"threshold_uncertainty_score":0.6970347,"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."}}