{"id":"W4410359261","doi":"10.1109/tcc.2025.3570093","title":"Data-Related Parameter Selection for Training Deep Learning Models Predicting Application Performance Degradation in Clouds","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Cloud Computing","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); Concordia University","funders":"","keywords":"Computer science; Cloud computing; Selection (genetic algorithm); Artificial intelligence; Deep learning; Degradation (telecommunications); Machine learning; Training (meteorology); Training set; Telecommunications; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001412773,0.0002702855,0.0002939281,0.0004690946,0.0008847348,0.0001918447,0.0009590528,0.0001522538,0.000001024102],"category_scores_gemma":[0.00003167805,0.0002974297,0.00009964833,0.001459922,0.00003347688,0.000171545,0.00003607885,0.0006628563,0.000004621701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002250257,"about_ca_system_score_gemma":0.00007050548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006439521,"about_ca_topic_score_gemma":0.00005715726,"domain_scores_codex":[0.9973502,0.0001735276,0.000709584,0.0009607705,0.0002827536,0.0005231613],"domain_scores_gemma":[0.9982515,0.0007268804,0.0002424608,0.0006202291,0.0001006807,0.00005825056],"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":[0.00001281574,0.00005723909,0.0001334297,0.00003737033,0.00003213557,2.220209e-7,0.0007185596,0.590995,0.00004985147,0.0006646147,0.000005789904,0.407293],"study_design_scores_gemma":[0.0008238383,0.0001130011,0.0002478118,0.0002252701,0.00003669449,0.000007059818,0.000243933,0.9963052,0.0005859,0.0009021953,0.0002491582,0.0002599097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3037843,0.00002623743,0.6940028,0.0001784753,0.0007290616,0.0004955621,0.000001589344,0.000475379,0.0003066109],"genre_scores_gemma":[0.9650751,0.000006778127,0.03439069,0.000114979,0.00008780904,0.00005894966,0.00001346035,0.00002331261,0.000228957],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6612908,"threshold_uncertainty_score":0.9999478,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04050212508381733,"score_gpt":0.2702386310834526,"score_spread":0.2297365059996352,"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."}}