{"id":"W3156363234","doi":"10.1109/tse.2020.3023955","title":"PerfJIT: Test-Level Just-in-Time Prediction for Performance Regression Introducing Commits","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Commit; Computer science; Regression; Machine learning; Regression analysis; Regression testing; Test (biology); Artificial intelligence; Performance prediction; Linear regression; Code (set theory); Data mining; Statistics; Database; Software; Set (abstract data type); Programming language; Software system; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003525876,0.0002773084,0.0003082701,0.0001984453,0.0002187931,0.0000800721,0.0005559166,0.000155968,0.00001356587],"category_scores_gemma":[0.0001532163,0.000257295,0.0001286547,0.0006584282,0.00001881322,0.0007536393,0.000008125789,0.0004229586,0.00006256537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000163366,"about_ca_system_score_gemma":0.00006217945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005043803,"about_ca_topic_score_gemma":8.748344e-7,"domain_scores_codex":[0.9981961,0.00002219003,0.0004411816,0.0005949545,0.0003401414,0.0004054892],"domain_scores_gemma":[0.9987562,0.000416364,0.0000679714,0.0004983884,0.00009942234,0.0001616823],"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":[0.0000758587,0.0002104823,0.007016627,0.0008669316,0.00003445488,0.000005089087,0.002189795,0.9203896,0.00284684,0.000008632999,0.0006258177,0.06572989],"study_design_scores_gemma":[0.0009109091,0.0004221008,0.006629386,0.0003924925,0.00001634342,0.00001633032,0.00001749479,0.966293,0.0240439,0.000002216092,0.0009031984,0.0003526545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.109336,0.00003979772,0.8879215,0.0002631723,0.0009845977,0.0004565727,0.00004447429,0.0009487269,0.000005246599],"genre_scores_gemma":[0.9306482,0.00003315564,0.06867488,0.0001396534,0.0002138826,0.0001642137,0.000004755904,0.00003722893,0.00008401972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8213122,"threshold_uncertainty_score":0.9999879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02316888172101865,"score_gpt":0.2243610363188371,"score_spread":0.2011921545978184,"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."}}