{"id":"W4411552578","doi":"10.1109/icse55347.2025.00059","title":"Measuring the Runtime Performance of C++ Code Written by Humans Using Github Copilot","year":2025,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Code (set theory); Source code; Parallel computing; Operating system; 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":[0.0003437899,0.00008705452,0.0001236182,0.00007834394,0.0002206561,0.00007875806,0.0008757851,0.00003099653,0.000006286911],"category_scores_gemma":[0.0000150824,0.00006276493,0.00003544382,0.000385664,0.0000541979,0.000172192,0.000267572,0.00008495076,0.000003095597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002474578,"about_ca_system_score_gemma":0.00005424469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005121598,"about_ca_topic_score_gemma":0.000002231925,"domain_scores_codex":[0.9992276,0.00004565728,0.0002207736,0.0001878132,0.0001649364,0.0001531863],"domain_scores_gemma":[0.9993258,0.0000527205,0.00007708607,0.0004203888,0.0001057051,0.00001827626],"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":[0.00007710701,0.0008731813,0.07694201,0.0006013836,0.0004700432,0.000004875062,0.004018462,0.3090163,0.06134276,0.2656877,0.2135073,0.06745885],"study_design_scores_gemma":[0.0001294028,0.00003492317,0.0009284407,0.00007399767,0.000005845719,0.000001339392,0.000009067284,0.9462007,0.05024832,0.0002818618,0.001984884,0.0001012608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06061325,0.0001588637,0.9248922,0.0004157786,0.00008058727,0.0001048168,8.086699e-7,0.0002708564,0.01346283],"genre_scores_gemma":[0.8938267,0.0000278385,0.1041888,0.0003918582,0.000009904395,0.00000325172,6.851442e-7,0.000004107312,0.001546892],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8332134,"threshold_uncertainty_score":0.2559479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03200102663015766,"score_gpt":0.2642953910220069,"score_spread":0.2322943643918493,"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."}}