{"id":"W4383903547","doi":"10.1109/tnsm.2023.3293806","title":"ML Models for Detecting QoE Degradation in Low-Latency Applications: A Cloud-Gaming Case Study","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Network and Service Management","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Anomaly detection; Robustness (evolution); Cloud computing; Data mining; Latency (audio); Machine learning; Metrics; Artificial intelligence; Real-time computing; Computer network","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":[0.0004298639,0.0001601151,0.0001426163,0.0002837015,0.0006340274,0.0001214085,0.0002653965,0.00005402178,0.000001609763],"category_scores_gemma":[3.34981e-7,0.0001728903,0.00004909234,0.001930994,0.000009027201,0.0002730499,0.00001525001,0.0001344647,0.000009931647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005619218,"about_ca_system_score_gemma":0.0000105803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002184087,"about_ca_topic_score_gemma":0.0009270251,"domain_scores_codex":[0.9986727,0.00004270466,0.0003342092,0.000517452,0.000138465,0.0002944174],"domain_scores_gemma":[0.9992437,0.0001002327,0.00008006458,0.0004585822,0.00005749669,0.00005994518],"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":[0.0000148363,0.0002971821,0.00001539353,0.0001319057,0.00004922351,0.00004614564,0.0009526524,0.5025407,0.00001177114,0.003809669,0.00004192279,0.4920886],"study_design_scores_gemma":[0.0005211525,0.0001160491,0.00006613121,0.00004575036,0.00003830437,0.00003310256,0.002219903,0.9908403,0.0000802545,0.005255038,0.0005667237,0.0002173317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0346716,0.00001690834,0.9617305,0.0003460532,0.000125734,0.002362991,0.000002925106,0.0005391664,0.0002041199],"genre_scores_gemma":[0.9738206,0.0001744036,0.02067188,0.0002635017,0.00005465012,0.004836847,0.00000249658,0.00001927006,0.0001563153],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9410586,"threshold_uncertainty_score":0.7050262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02832418174741278,"score_gpt":0.2668916230136526,"score_spread":0.2385674412662398,"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."}}