{"id":"W4285121201","doi":"10.1109/tse.2022.3188005","title":"Automated Generation and Evaluation of JMH Microbenchmark Suites From Unit Tests","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Unit testing; Programming language; Eclipse; Software; 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":[],"consensus_categories":[],"category_scores_codex":[0.0005375441,0.0001274642,0.000146993,0.0001850656,0.000204311,0.00003522435,0.0002095166,0.0000473949,0.00006202367],"category_scores_gemma":[0.0000370235,0.0001345351,0.00004902017,0.0004489724,0.00001426699,0.0002788312,0.00000698027,0.0001693771,0.000003385482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001141614,"about_ca_system_score_gemma":0.00008105818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008743109,"about_ca_topic_score_gemma":0.000009087946,"domain_scores_codex":[0.9987985,0.00008938498,0.0002542108,0.000279273,0.0004374624,0.0001411783],"domain_scores_gemma":[0.9991788,0.0002356129,0.00006390141,0.0003464402,0.0001293854,0.00004583628],"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":[0.000004082391,0.00007406266,0.001327345,0.00003277399,0.00003866587,9.444437e-7,0.000647462,0.9634128,0.01441292,0.00001434051,0.000063862,0.01997073],"study_design_scores_gemma":[0.0003793609,0.00007629703,0.01171314,0.00002535297,0.0000309217,0.00001013438,0.00002026553,0.9633403,0.02413383,0.00001206062,0.0001019915,0.0001563378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5130058,0.0001260397,0.4856916,0.00001131082,0.0005895888,0.0001436701,0.00002538454,0.0004047929,0.000001793811],"genre_scores_gemma":[0.977937,0.000008533674,0.02187372,0.00001667799,0.00002600365,0.0001040278,0.00001297991,0.00001185771,0.000009243907],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4649311,"threshold_uncertainty_score":0.5486181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02317426977577853,"score_gpt":0.2505865902937494,"score_spread":0.2274123205179709,"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."}}