{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001461189,0.0001634305,0.0002645065,0.0002643135,0.0001337781,0.0001056206,0.0006607387,0.0001122345,0.000006902647],"category_scores_gemma":[0.0001506455,0.0001248786,0.00006607058,0.0007981678,0.00001900371,0.0005459748,0.0001705669,0.0001265225,0.00001164945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009848693,"about_ca_system_score_gemma":0.0001970109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006643708,"about_ca_topic_score_gemma":0.000166982,"domain_scores_codex":[0.9985587,0.00006251746,0.0003118049,0.0004967629,0.0001704332,0.0003997867],"domain_scores_gemma":[0.9989197,0.0003011721,0.00005967322,0.0005567578,0.0001334184,0.00002926039],"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":[0.00004008152,0.0001239318,0.068675,0.001021616,0.00002359442,0.000001848753,0.00210454,0.0002796011,0.0008210252,0.008193135,0.001206612,0.917509],"study_design_scores_gemma":[0.002344613,0.0003919427,0.1752804,0.000729065,0.00001666436,0.00001856773,0.0002879137,0.7204908,0.08057304,0.001737518,0.01734486,0.000784608],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2183788,0.0000911567,0.7765686,0.001312264,0.0006915717,0.001015341,0.000002197969,0.0002391238,0.001700926],"genre_scores_gemma":[0.7909324,0.00002903255,0.2060827,0.0006320633,0.00005818707,0.0003763706,0.000001470002,0.000007088249,0.001880704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9167244,"threshold_uncertainty_score":0.5092402,"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."}}