{"id":"W4400680805","doi":"10.1109/saner60148.2024.00051","title":"Assessing the Security of GitHub Copilot's Generated Code - A Targeted Replication Study","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Replication (statistics); Code (set theory); Computer security; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005751262,0.00009073329,0.0001048843,0.00009135039,0.0001031948,0.0002958083,0.0004928966,0.00003206593,0.0000146494],"category_scores_gemma":[0.00008556123,0.0000609998,0.00003343964,0.0008984446,0.00003648499,0.0007840747,0.0001745047,0.0001378953,0.000007101586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000463962,"about_ca_system_score_gemma":0.00006394462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006148355,"about_ca_topic_score_gemma":0.00002267145,"domain_scores_codex":[0.9988798,0.0001185845,0.0002482393,0.0004275141,0.0002127586,0.0001131015],"domain_scores_gemma":[0.9986813,0.0001064655,0.00007187183,0.0009588287,0.000155988,0.00002552666],"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":[0.00001999837,0.001214057,0.001965014,0.0002028914,0.0002893341,0.00007187457,0.01158298,0.0006901459,0.3760673,0.1549803,0.01938163,0.4335344],"study_design_scores_gemma":[0.0001465161,0.0003130359,0.002456391,0.00003397953,0.00001578408,0.00003049785,0.0004047594,0.2809254,0.6920682,0.01799889,0.005397182,0.0002093304],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09363031,0.000150047,0.9028041,0.0004738253,0.0001697872,0.000416801,0.000001811868,0.001503718,0.0008496296],"genre_scores_gemma":[0.9656909,0.000005422975,0.0339551,0.00009782124,0.00002648571,0.00006449354,0.000001584611,0.000008603209,0.0001496112],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8720605,"threshold_uncertainty_score":0.2852486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0330620081521336,"score_gpt":0.3597331503014953,"score_spread":0.3266711421493617,"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."}}