{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002300687,0.0001955537,0.0002048626,0.0002560889,0.0000582403,0.0003415568,0.0002827995,0.00006900248,0.000006560736],"category_scores_gemma":[0.0001910583,0.0001585691,0.00002415208,0.0008067499,0.00001947942,0.0004137968,0.00008213975,0.0003977001,0.00002457435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008168244,"about_ca_system_score_gemma":0.00007779609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002378741,"about_ca_topic_score_gemma":0.00001739525,"domain_scores_codex":[0.9986868,0.00004846399,0.000196757,0.0005202646,0.0002692335,0.000278487],"domain_scores_gemma":[0.9992749,0.0002289652,0.00001618117,0.0002878332,0.00003696666,0.0001551459],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001035282,0.000365225,0.9487107,0.00007463278,0.00006850626,0.000644298,0.01812269,0.02584665,0.00002272456,0.0003345281,0.0006142805,0.005185381],"study_design_scores_gemma":[0.0003656194,0.0007821737,0.6056481,0.0002370563,0.00001355089,0.00002778319,0.0002251062,0.3858392,0.00002410309,0.00009545854,0.006314842,0.0004270187],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8303592,0.0002386783,0.1625915,0.005457629,0.0001481623,0.0001695661,0.000003382883,0.001016584,0.00001522378],"genre_scores_gemma":[0.9665133,0.000005856543,0.03307217,0.0001736267,0.00009296907,0.00001437327,0.000006697845,0.00002583323,0.00009522626],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3599926,"threshold_uncertainty_score":0.6466262,"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."}}