{"id":"W2763776913","doi":"10.1007/s10664-017-9553-x","title":"Empirical study on the discrepancy between performance testing results from virtual and physical environments","year":2017,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Empirical research; Human–computer interaction; Statistics; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01208438,0.0004022687,0.000212793,0.001950532,0.0004037913,0.001010391,0.00121155,0.0007910489,0.001550394],"category_scores_gemma":[0.1673735,0.0002299647,0.0002520372,0.002023235,0.001168139,0.00166038,0.001153085,0.0008965732,0.000403039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005257123,"about_ca_system_score_gemma":0.0004437274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001399925,"about_ca_topic_score_gemma":0.001467542,"domain_scores_codex":[0.9865603,0.007598237,0.001040654,0.0009503124,0.003466655,0.0003837327],"domain_scores_gemma":[0.5521988,0.3899872,0.02617643,0.01119096,0.01877294,0.001673696],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006787559,0.0009807198,0.9544966,0.0001794757,0.0001514985,0.0002686319,0.006109002,0.003219469,0.002573441,0.001765345,0.000659971,0.02891709],"study_design_scores_gemma":[0.00004972658,0.001431972,0.9721343,0.0001191547,0.0001152594,0.0009301052,0.006096562,0.01095981,0.005315169,0.001399928,0.001412628,0.00003528786],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962841,0.00009355562,0.001996932,0.00006751205,0.000005398092,0.000008596989,0.000099138,0.00001491838,0.001429937],"genre_scores_gemma":[0.9992932,0.00003097541,0.0004088713,0.00001590547,0.000003442716,0.000005797388,0.0001305095,0.000007674442,0.0001034831],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01208438,"threshold_uncertainty_score":0.06390905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05186541589034044,"score_gpt":0.2904156404946555,"score_spread":0.2385502246043151,"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."}}