{"id":"W4312438588","doi":"10.1145/3524842.3528470","title":"An empirical evaluation of GitHub copilot's code suggestions","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":281,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Correctness; Programmer; JavaScript; Programming language; Code (set theory); Source code; Java; Software engineering","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":[0.009153165,0.0008822317,0.0004234974,0.002951904,0.0006975507,0.001317989,0.001657611,0.001022952,0.002233351],"category_scores_gemma":[0.1125994,0.0003729496,0.0004211164,0.002052268,0.001154734,0.001876144,0.001579597,0.00119126,0.001076109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00132462,"about_ca_system_score_gemma":0.001234028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003553238,"about_ca_topic_score_gemma":0.005888313,"domain_scores_codex":[0.9867403,0.005405523,0.0008039844,0.001296903,0.005258209,0.000494996],"domain_scores_gemma":[0.8235909,0.1351428,0.008050979,0.008560714,0.02258204,0.002072543],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.004715511,0.004146793,0.3572329,0.005023594,0.0003712446,0.003229229,0.04137112,0.01818536,0.0417956,0.004812973,0.04697348,0.4721422],"study_design_scores_gemma":[0.000894735,0.007980724,0.5591258,0.001323191,0.0004101102,0.003824031,0.02053162,0.2133346,0.06486284,0.002695921,0.1245024,0.0005139197],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9829504,0.0002144998,0.007387805,0.00026865,0.00002797361,0.0003995998,0.001096797,0.004163304,0.003490859],"genre_scores_gemma":[0.9597022,0.0002163178,0.02949577,0.0002495834,0.00002517488,0.0005767225,0.005374507,0.001587188,0.002772538],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009153165,"threshold_uncertainty_score":0.0484072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09023633677771457,"score_gpt":0.395196726944413,"score_spread":0.3049603901666985,"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."}}