{"id":"W7015086753","doi":"","title":"Security Evaluations of GitHub's Copilot","year":2023,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Blackberry (Canada)","funders":"","keywords":"Vulnerability (computing); Set (abstract data type); Code (set theory); Vulnerability management; Vulnerability assessment","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":[0.005682412,0.001424746,0.0006921401,0.002735126,0.0006452734,0.00126696,0.00273574,0.001540049,0.003197075],"category_scores_gemma":[0.03229318,0.0005374503,0.0008563615,0.001266548,0.001142105,0.001923583,0.002416085,0.001991081,0.00182141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00133417,"about_ca_system_score_gemma":0.001164765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003397877,"about_ca_topic_score_gemma":0.005841816,"domain_scores_codex":[0.9942307,0.002092373,0.0004129388,0.0006535392,0.002158329,0.0004521359],"domain_scores_gemma":[0.969218,0.01755693,0.002227701,0.00468747,0.004793236,0.001516637],"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":[0.01341656,0.007024542,0.06318218,0.009178644,0.001075318,0.003932066,0.01257099,0.04535922,0.06969567,0.007974947,0.2293025,0.5372874],"study_design_scores_gemma":[0.003890619,0.01733955,0.1641061,0.002626877,0.0006135355,0.006339153,0.004966899,0.4347773,0.1203884,0.006671094,0.2375091,0.0007713527],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9324548,0.002274378,0.01448727,0.001256054,0.0003867682,0.001007227,0.003800828,0.02830424,0.01602841],"genre_scores_gemma":[0.8795843,0.001466562,0.07746422,0.001023238,0.0001114914,0.001048813,0.02373035,0.007098513,0.008472648],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005682412,"threshold_uncertainty_score":0.03005183,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01982891360351652,"score_gpt":0.2579441519695853,"score_spread":0.2381152383660687,"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."}}