{"id":"W4411271527","doi":"10.1109/msr66628.2025.00125","title":"JPerfEvo: A Tool for Tracking Method-Level Performance Changes in Java Projects","year":2025,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Java; Computer science; Tracking (education); Software engineering; Programming language","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":[0.006250893,0.002112711,0.001128954,0.00847837,0.0007016165,0.002592191,0.002430178,0.001244456,0.004142636],"category_scores_gemma":[0.04460349,0.001358197,0.0009998498,0.003174194,0.0007286998,0.003902752,0.002699242,0.002525277,0.002218593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007561842,"about_ca_system_score_gemma":0.001992649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00435789,"about_ca_topic_score_gemma":0.005485319,"domain_scores_codex":[0.9933527,0.0008504259,0.0008558364,0.001770841,0.002792801,0.0003775216],"domain_scores_gemma":[0.9670417,0.01820474,0.005745763,0.004196707,0.004030914,0.0007801743],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001368898,0.001043847,0.1732643,0.002994895,0.0007281782,0.00105609,0.003248371,0.02726353,0.03470875,0.007616275,0.1740291,0.5726779],"study_design_scores_gemma":[0.0005470637,0.001277453,0.2096138,0.0008149449,0.0003313283,0.001526241,0.0007346145,0.5551954,0.07701298,0.01645562,0.1354638,0.001026624],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.09873696,0.0009938028,0.2706797,0.0003554028,0.0004125242,0.0007158312,0.01994518,0.6008955,0.00726522],"genre_scores_gemma":[0.4633513,0.001052485,0.4214041,0.0005723607,0.0002606312,0.002532199,0.04410262,0.05838622,0.008338135],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.00847837,"threshold_uncertainty_score":0.03305823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04994858510441397,"score_gpt":0.3224917502548997,"score_spread":0.2725431651504857,"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."}}