{"id":"W2767269462","doi":"10.1109/icsme.2017.13","title":"An Exploratory Study of Performance Regression Introducing Code Changes","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Regression testing; Performance metric; Software quality; Benchmark (surveying); Commit; Performance prediction; Reliability engineering; Software performance testing; Quality (philosophy); Software regression; Metric (unit); Software bug; Software; Regression analysis; Performance indicator; Software metric; Code (set theory); Regression; Machine learning; Software development; Simulation; Operating system; Statistics; Database; Engineering; Software construction; Operations management","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":[0.0005398093,0.00007354314,0.0001084348,0.00009925793,0.0002103171,0.0001284992,0.001606853,0.00002291565,0.000007537802],"category_scores_gemma":[0.0002374766,0.00005652279,0.000008481244,0.00007772446,0.00002761247,0.0007714055,0.0004650521,0.00009978325,0.000009814705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001771652,"about_ca_system_score_gemma":0.00002411006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001979223,"about_ca_topic_score_gemma":0.00008096212,"domain_scores_codex":[0.9991071,0.0000338782,0.00008933261,0.0002782563,0.0003211409,0.0001702418],"domain_scores_gemma":[0.997847,0.00006970362,0.00006151501,0.001862008,0.00009497372,0.00006479536],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000290909,0.0009689177,0.6334089,0.0001422605,0.00003720123,0.00003409228,0.02952489,0.002056244,0.02476637,0.000755341,0.0009629667,0.3073137],"study_design_scores_gemma":[0.001064275,0.002429776,0.7079695,0.0001459075,0.00000437556,0.000005515778,0.001348154,0.1661839,0.1198827,0.00002871719,0.000557247,0.000379978],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9674118,0.00001946237,0.03182008,0.0001427975,0.0002508736,0.0001201458,1.96081e-7,0.0001551923,0.00007950034],"genre_scores_gemma":[0.9941991,0.000009766139,0.005587376,0.000007145249,0.00007916996,0.00001578958,1.665685e-7,0.00000701866,0.00009445064],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3069337,"threshold_uncertainty_score":0.2985959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05274218923814708,"score_gpt":0.3253429721121572,"score_spread":0.2726007828740101,"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."}}