{"id":"W4417438984","doi":"10.1109/ms.2025.3644251","title":"Understanding Prompt Management in GitHub Repositories: A Call for Best Practices","year":2025,"lang":"","type":"article","venue":"IEEE Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); Kingston Health Sciences Centre; Arup Group (Canada); Queen's University","funders":"","keywords":"Readability; Best practice; Maintainability; Usability; Quality (philosophy); Software quality; Natural language","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001378233,0.00048975,0.0005169457,0.0009866256,0.0007167276,0.0009614705,0.001884548,0.0002954622,0.000006971652],"category_scores_gemma":[0.004147182,0.0005578937,0.0001821485,0.002669633,0.0001498672,0.001045857,0.0009475594,0.0006660747,0.00002615276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001990323,"about_ca_system_score_gemma":0.0006289327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002341427,"about_ca_topic_score_gemma":0.0001298192,"domain_scores_codex":[0.9953922,0.0001413185,0.0008230967,0.001499482,0.0008786226,0.001265277],"domain_scores_gemma":[0.9936082,0.004025297,0.0004059195,0.001450995,0.0003041798,0.0002053837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00209264,0.006434247,0.3350566,0.04833537,0.005702554,0.005921148,0.04584138,0.05600216,0.0006104874,0.1083,0.1263085,0.2593949],"study_design_scores_gemma":[0.03008023,0.006048512,0.03539488,0.03982906,0.001783394,0.0003115033,0.01039489,0.3877035,0.01132393,0.07570986,0.3900798,0.01134044],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004747474,0.001269162,0.9820045,0.001479755,0.006757927,0.002672269,0.00001966156,0.0004467496,0.0006025142],"genre_scores_gemma":[0.7632951,0.0003695278,0.2141754,0.0002392393,0.0005322812,0.001367506,0.000009297107,0.0001120479,0.01989963],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7678291,"threshold_uncertainty_score":0.9996873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1318205976894027,"score_gpt":0.3615659692518475,"score_spread":0.2297453715624448,"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."}}