{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01175864,0.001076528,0.0006693575,0.002895566,0.0008080893,0.001323627,0.002280884,0.001464296,0.0008240592],"category_scores_gemma":[0.08403441,0.0006616072,0.001163001,0.001392405,0.001802692,0.00307919,0.001916984,0.00236035,0.000806932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002161007,"about_ca_system_score_gemma":0.001482136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008335021,"about_ca_topic_score_gemma":0.006017161,"domain_scores_codex":[0.9898574,0.003539867,0.0006527509,0.001642347,0.003923522,0.0003840753],"domain_scores_gemma":[0.8948691,0.0408453,0.006525739,0.03248169,0.02408127,0.001196827],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.008656741,0.006175029,0.2389558,0.00387433,0.001782312,0.004460986,0.01744182,0.09618087,0.09862425,0.006699945,0.04079254,0.4763554],"study_design_scores_gemma":[0.001184404,0.01298209,0.2275329,0.0007875391,0.001537489,0.005279264,0.004562983,0.5424747,0.1367956,0.005506626,0.06068147,0.0006749864],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9793473,0.000539396,0.01073364,0.0004448917,0.00009893503,0.0006686938,0.0009867896,0.004632323,0.002548096],"genre_scores_gemma":[0.9647561,0.0003052302,0.02570479,0.0003333183,0.00004636283,0.0007476194,0.003782631,0.001814123,0.002509859],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9882414,"threshold_uncertainty_score":0.06218636,"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."}}