{"id":"W4401543513","doi":"10.1145/3643991.3645072","title":"Analyzing Developer Use of ChatGPT Generated Code in Open Source GitHub Projects","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Open source; Source code; Code (set theory); Programming language; Open source software; Code review; Software engineering; World Wide Web; Static program analysis; Software; Software development; Set (abstract data type)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004857621,0.0001092125,0.000167124,0.0002875473,0.00003633943,0.0006356419,0.0008416256,0.00005029929,0.000007566259],"category_scores_gemma":[0.0002629618,0.00008706166,0.00002488351,0.001341516,0.00002355758,0.0007078091,0.0007053817,0.0001096943,0.00001109088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004451735,"about_ca_system_score_gemma":0.0002339327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001492891,"about_ca_topic_score_gemma":0.0001270897,"domain_scores_codex":[0.9989918,0.00006002288,0.0002420112,0.0003840199,0.0001256442,0.0001964392],"domain_scores_gemma":[0.9992101,0.0002422671,0.00003476014,0.0003953244,0.00007970822,0.00003789679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002182687,0.0002763733,0.1639099,0.0002847764,0.0001205985,0.0003277532,0.009849302,0.001807732,0.004850145,0.03053304,0.1576345,0.6303841],"study_design_scores_gemma":[0.0001897854,0.00008926373,0.005121493,0.0006816745,0.000007022544,0.00004799952,0.00001084106,0.9511747,0.02355518,0.004347918,0.01432994,0.000444112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06085172,0.0001927066,0.9310867,0.00038975,0.0001050874,0.0002602438,0.000001339312,0.006374544,0.000737875],"genre_scores_gemma":[0.4715604,0.000007586821,0.5271007,0.0001760442,0.00001196737,0.0000203689,0.000001689918,0.00001200354,0.001109248],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.949367,"threshold_uncertainty_score":0.6129509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0982006071357781,"score_gpt":0.3196408188539973,"score_spread":0.2214402117182192,"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."}}