{"id":"W4367672983","doi":"10.1016/j.jss.2023.111734","title":"GitHub Copilot AI pair programmer: Asset or Liability?","year":2023,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":340,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University; Polytechnique Montréal","funders":"Fonds de recherche du Québec; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Programmer; Liability; Asset (computer security); Computer science; Computer security; Software engineering; Business; Programming language; Finance","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":[0.001574341,0.0001533978,0.0003745779,0.0002257547,0.0001475814,0.0004063418,0.0005187945,0.00009184073,0.000002090503],"category_scores_gemma":[0.001203567,0.0001018429,0.00009060877,0.0006106605,0.00005098329,0.0004502911,0.0001671575,0.0002499911,0.00001071821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004102232,"about_ca_system_score_gemma":0.0001692993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006388364,"about_ca_topic_score_gemma":0.000002201473,"domain_scores_codex":[0.9983994,0.0001156986,0.0005481407,0.000222527,0.0004299803,0.0002841927],"domain_scores_gemma":[0.9980904,0.0006223114,0.0003392537,0.0003743999,0.0003871284,0.0001865151],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005067293,0.0001811112,0.3830893,0.0008204465,0.0001137595,0.0007929514,0.001290335,0.0001311827,0.00002099889,0.001226787,0.4864551,0.1258274],"study_design_scores_gemma":[0.00529501,0.01362432,0.2095333,0.009799542,0.0002130666,0.01530536,0.0006704932,0.06383058,0.0003097507,0.07838491,0.5998933,0.003140385],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.118728,0.00224751,0.8568392,0.004014459,0.002888534,0.0007184925,0.00001811884,0.01447877,0.0000668486],"genre_scores_gemma":[0.8570566,0.00008884296,0.1411578,0.0003965842,0.0003848065,0.00003106478,0.000002584753,0.00003328644,0.0008484633],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7383286,"threshold_uncertainty_score":0.4153034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0401045157013695,"score_gpt":0.3012254088637339,"score_spread":0.2611208931623644,"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."}}