{"id":"W4367054037","doi":"10.1007/s11227-023-05283-3","title":"Multivariate outlier filtering for A-NFVLearn: an advanced deep VNF resource usage forecasting technique","year":2023,"lang":"en","type":"article","venue":"The Journal of Supercomputing","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ericsson (Canada); École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Quality of service; Resource (disambiguation); Distributed computing; Key (lock); Virtual network; Data mining; Computer network; Operating system","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003904141,0.000200585,0.0003111426,0.0002066817,0.0005613493,0.0001749214,0.001369148,0.00007922773,0.000003413604],"category_scores_gemma":[0.0003929981,0.0001434763,0.0001559175,0.0006712861,0.00003869797,0.000689408,0.0004611466,0.0004483635,0.000004534394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005143253,"about_ca_system_score_gemma":0.00004024139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001206919,"about_ca_topic_score_gemma":0.000003404151,"domain_scores_codex":[0.9980381,0.0002212183,0.0006185405,0.0002392421,0.0003199721,0.0005629346],"domain_scores_gemma":[0.9974666,0.001473166,0.0003270107,0.0004259854,0.0001776053,0.0001296661],"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":[0.0001172932,0.00006018695,0.0006029829,0.00006318123,0.00007003777,0.00008497822,0.0112057,0.377917,0.0226087,0.000539974,0.0004702113,0.5862597],"study_design_scores_gemma":[0.0007253232,0.0003824544,0.001122118,0.0003168984,0.00002232964,0.0004661433,0.0007381068,0.9893486,0.00209147,0.001928987,0.002593865,0.0002637161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1983083,0.000109652,0.8003832,0.0003240649,0.0003405958,0.0002506121,0.000001049764,0.0002130814,0.00006947927],"genre_scores_gemma":[0.7380729,0.0000122283,0.2610785,0.0001947202,0.000562533,0.000006721323,0.000001772514,0.00003795995,0.00003261781],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6114316,"threshold_uncertainty_score":0.5850795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04845123249999152,"score_gpt":0.2814806096692189,"score_spread":0.2330293771692274,"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."}}