{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005789785,0.001449087,0.0007090684,0.002616395,0.0004994577,0.001172117,0.002948661,0.0008697789,0.001640281],"category_scores_gemma":[0.0312687,0.0006038101,0.0007512953,0.001334767,0.001041648,0.001314963,0.001443704,0.001323881,0.0009445624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001097015,"about_ca_system_score_gemma":0.001554127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002948461,"about_ca_topic_score_gemma":0.003848281,"domain_scores_codex":[0.9929602,0.001907076,0.0005385617,0.00112136,0.003005694,0.0004671133],"domain_scores_gemma":[0.9745418,0.01207948,0.00229532,0.006048413,0.0043895,0.0006453917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001828546,0.003377959,0.06812569,0.002654538,0.0005298004,0.001626392,0.001840715,0.1888828,0.1406339,0.00790738,0.05561858,0.5269738],"study_design_scores_gemma":[0.0006184033,0.001766307,0.04883201,0.0001747507,0.0001244542,0.0006469121,0.0004866984,0.6641321,0.2580182,0.003762542,0.02123328,0.0002043868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8166045,0.0011186,0.08638722,0.0004780568,0.0003271875,0.0007829517,0.00415437,0.08231437,0.007832728],"genre_scores_gemma":[0.791474,0.0003413799,0.1796335,0.0003871799,0.00008556143,0.0006711495,0.01811188,0.006828784,0.002466537],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005789785,"threshold_uncertainty_score":0.03061968,"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."}}