{"id":"W4402810568","doi":"10.1007/s10664-024-10540-x","title":"An empirical study on developers’ shared conversations with ChatGPT in GitHub pull requests and issues","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Kingston Health Sciences Centre; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Empirical research; World Wide Web","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":[0.01299181,0.0006965402,0.0005079514,0.004032798,0.003769369,0.003892378,0.001626523,0.00250241,0.002508942],"category_scores_gemma":[0.1399758,0.0008522568,0.0003186162,0.003182028,0.002551586,0.004598358,0.005423313,0.003768639,0.000941303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002620476,"about_ca_system_score_gemma":0.00364496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008414458,"about_ca_topic_score_gemma":0.01874821,"domain_scores_codex":[0.9821352,0.01018018,0.001015465,0.0015799,0.003776306,0.00131303],"domain_scores_gemma":[0.6831768,0.2468683,0.02538194,0.01087254,0.02309958,0.01060082],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0005828495,0.002333528,0.3527232,0.0004974414,0.00008020607,0.002650559,0.586355,0.0004093833,0.008148996,0.001100625,0.002696382,0.04242202],"study_design_scores_gemma":[0.00009921704,0.00124257,0.5169258,0.0004474453,0.0001125956,0.00138554,0.4573595,0.004113826,0.005138655,0.001156501,0.01185124,0.0001671278],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9964309,0.00005750894,0.001066646,0.000238836,0.00001631885,0.00009264048,0.0001236068,0.00007567047,0.001897929],"genre_scores_gemma":[0.9957259,0.00007200631,0.001585345,0.0001931627,0.00002675437,0.0001884493,0.0003042335,0.0001045524,0.001799734],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9870082,"threshold_uncertainty_score":0.06870812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02246664634692374,"score_gpt":0.3286231495348124,"score_spread":0.3061565031878887,"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."}}