{"id":"W2807952920","doi":"10.1145/3180155.3182527","title":"Empirical study on the discrepancy between performance testing results from virtual and physical environments","year":2018,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Software performance testing; Virtual machine; Overhead (engineering); Empirical research; Software; Reliability engineering; Embedded system; Operating system; Software system; Engineering","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":[0.0005098404,0.0001579241,0.0001799466,0.00002354849,0.0003776418,0.00009227682,0.0005641092,0.00004005742,0.000002614653],"category_scores_gemma":[0.0001884845,0.00008232952,0.0000280522,0.0002070661,0.0001708156,0.0002990695,0.0004364015,0.0001702475,0.0002209213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002741298,"about_ca_system_score_gemma":0.00001968129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007392582,"about_ca_topic_score_gemma":0.000002891983,"domain_scores_codex":[0.998412,0.0001281701,0.0002630253,0.0005653565,0.0003959005,0.0002355231],"domain_scores_gemma":[0.9979306,0.001051379,0.00007747234,0.0008424741,0.00002061092,0.00007747958],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000215487,0.0002293302,0.9633681,0.000001392733,0.00002285403,0.000001152148,0.006431978,0.000003399305,0.00004332002,0.00004065073,0.0001518991,0.02968441],"study_design_scores_gemma":[0.0004544313,0.001447425,0.9832442,0.00002008808,0.000007881753,7.244504e-7,0.0002826623,0.01337222,0.000624593,0.000166225,0.0002447216,0.0001348561],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9942071,0.000001989777,0.003302458,0.0005069431,0.0001341726,0.0002940695,0.000006105768,0.0001055659,0.001441617],"genre_scores_gemma":[0.9984562,6.972163e-7,0.0007552291,0.0001479059,0.0004882975,0.0000140886,0.000001448321,0.000006111727,0.0001300192],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02954956,"threshold_uncertainty_score":0.33573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05316808007803812,"score_gpt":0.292990287499424,"score_spread":0.2398222074213859,"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."}}