{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005726657,0.000325224,0.0003718939,0.00004390189,0.0008331382,0.0003431992,0.001285021,0.00009798792,0.00000119779],"category_scores_gemma":[0.002631089,0.0002095858,0.00007699371,0.0001461731,0.0001037611,0.0005612588,0.0008974085,0.0005230891,0.00006718292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008039021,"about_ca_system_score_gemma":0.00002825397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004746005,"about_ca_topic_score_gemma":8.098745e-7,"domain_scores_codex":[0.9977145,0.00007865388,0.0003974784,0.0007924361,0.0005756842,0.0004412191],"domain_scores_gemma":[0.9955497,0.002408924,0.000164482,0.001666217,0.00002234464,0.0001882988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001148703,0.0001292879,0.9871262,0.000006361628,0.00003558017,0.000008731225,0.001971386,0.0005078947,0.00001327423,0.000004386058,0.0000645593,0.01012088],"study_design_scores_gemma":[0.0005541903,0.0004320145,0.9775656,0.00007456738,0.00001564189,0.000001980627,0.0000392073,0.02026502,0.0001475565,0.00004720168,0.0005758479,0.0002811091],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9726922,0.00001294208,0.02563806,0.0006464387,0.0002984372,0.0003462607,0.00001760869,0.0003029568,0.00004510116],"genre_scores_gemma":[0.9969145,0.000002045174,0.002395164,0.00007529029,0.0005102393,0.00004031332,0.000003728524,0.00002298375,0.00003570499],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02422234,"threshold_uncertainty_score":0.854666,"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."}}