{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T16:00:27Z","timestamp":1785340827698,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:00:00Z","timestamp":1775952000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100021856","name":"Ministero dell'Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","award":["E14D23001820006, and H53D23003510006"],"award-info":[{"award-number":["E14D23001820006, and H53D23003510006"]}],"id":[{"id":"10.13039\/501100021856","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,12]]},"DOI":"10.1145\/3794763.3794794","type":"proceedings-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:18:58Z","timestamp":1785338338000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["On the Impact of Code Comments for Automated Bug-Fixing: An Empirical Study"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5840-9777","authenticated-orcid":false,"given":"Antonio","family":"Vitale","sequence":"first","affiliation":[{"name":"Politecnico di Torino, Torino, Italy and University of Molise, Termoli, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5443-1303","authenticated-orcid":false,"given":"Emanuela","family":"Guglielmi","sequence":"additional","affiliation":[{"name":"University of Molise, Termoli, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1764-9685","authenticated-orcid":false,"given":"Simone","family":"Scalabrino","sequence":"additional","affiliation":[{"name":"University of Molise, Termoli, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7995-8582","authenticated-orcid":false,"given":"Rocco","family":"Oliveto","sequence":"additional","affiliation":[{"name":"University of Molise, Pesche, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,29]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"2025. Replication Package for \"On the Impact of Code Comments for Automated Bug-Fixing: An Empirical Study\". 10.5281\/zenodo.17408250","DOI":"10.5281\/zenodo.17408250"},{"key":"e_1_3_3_1_3_2","unstructured":"Wasi\u00a0Uddin Ahmad Saikat Chakraborty Baishakhi Ray and Kai-Wei Chang. 2020. A transformer-based approach for source code summarization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2005.00653 (2020)."},{"key":"e_1_3_3_1_4_2","unstructured":"Wasi\u00a0Uddin Ahmad Saikat Chakraborty Baishakhi Ray and Kai-Wei Chang. 2021. Unified pre-training for program understanding and generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2103.06333 (2021)."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Mattan\u00a0S. Ben-Shachar Daniel L\u00fcdecke and Dominique Makowski. 2020. effectsize: Estimation of Effect Size Indices and Standardized Parameters. Journal of Open Source Software 5 56 (2020) 2815. 10.21105\/joss.02815","DOI":"10.21105\/joss.02815"},{"key":"e_1_3_3_1_6_2","first-page":"780","volume-title":"International Conference on Machine Learning","author":"Berabi Berkay","year":"2021","unstructured":"Berkay Berabi, Jingxuan He, Veselin Raychev, and Martin Vechev. 2021. Tfix: Learning to fix coding errors with a text-to-text transformer. In International Conference on Machine Learning. PMLR, 780\u2013791."},{"key":"e_1_3_3_1_7_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_1_8_2","unstructured":"Federico Cassano Luisa Li Akul Sethi Noah Shinn Abby Brennan-Jones Jacob Ginesin Edward Berman George Chakhnashvili Anton Lozhkov Carolyn\u00a0Jane Anderson et\u00a0al. 2023. Can it edit? evaluating the ability of large language models to follow code editing instructions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.12450 (2023)."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678559"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Qiuyuan Chen Xin Xia Han Hu David Lo and Shanping Li. 2021. Why my code summarization model does not work: Code comment improvement with category prediction. ACM Transactions on Software Engineering and Methodology (TOSEM) 30 2 (2021) 1\u201329.","DOI":"10.1145\/3434280"},{"key":"e_1_3_3_1_11_2","unstructured":"Zimin Chen Steve Kommrusch Michele Tufano Louis-No\u00ebl Pouchet Denys Poshyvanyk and Martin Monperrus. 2019. Sequencer: Sequence-to-sequence learning for end-to-end program repair. IEEE Transactions on Software Engineering 47 9 (2019) 1943\u20131959."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Matteo Ciniselli Nathan Cooper Luca Pascarella Antonio Mastropaolo Emad Aghajani Denys Poshyvanyk Massimiliano Di\u00a0Penta and Gabriele Bavota. 2021. An empirical study on the usage of transformer models for code completion. IEEE Transactions on Software Engineering 48 12 (2021) 4818\u20134837.","DOI":"10.1109\/MSR52588.2021.00024"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Jacob Cohen. 1960. A coefficient of agreement for nominal scales. Educational and psychological measurement 20 1 (1960) 37\u201346.","DOI":"10.1177\/001316446002000104"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.4324\/9780203771587"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460945.3464951"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639095"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/2642937.2642982"},{"key":"e_1_3_3_1_18_2","unstructured":"Daniel Fried Armen Aghajanyan Jessy Lin Sida Wang Eric Wallace Freda Shi Ruiqi Zhong Wen-tau Yih Luke Zettlemoyer and Mike Lewis. 2022. Incoder: A generative model for code infilling and synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.05999 (2022)."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3608134"},{"key":"e_1_3_3_1_20_2","unstructured":"Daya Guo Shuo Ren Shuai Lu Zhangyin Feng Duyu Tang Shujie Liu Long Zhou Nan Duan Alexey Svyatkovskiy Shengyu Fu et\u00a0al. 2020. Graphcodebert: Pre-training code representations with data flow. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.08366 (2020)."},{"key":"e_1_3_3_1_21_2","unstructured":"Daya Guo Qihao Zhu Dejian Yang Zhenda Xie Kai Dong Wentao Zhang Guanting Chen Xiao Bi Yu Wu YK Li et\u00a0al. 2024. DeepSeek-Coder: When the Large Language Model Meets Programming\u2013The Rise of Code Intelligence. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.14196 (2024)."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379597.3387449"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Soneya\u00a0Binta Hossain Nan Jiang Qiang Zhou Xiaopeng Li Wen-Hao Chiang Yingjun Lyu Hoan Nguyen and Omer Tripp. 2024. A deep dive into large language models for automated bug localization and repair. Proceedings of the ACM on Software Engineering 1 FSE (2024) 1471\u20131493.","DOI":"10.1145\/3660773"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00181"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Kai Huang Jian Zhang Xinlei Bao Xu Wang and Yang Liu. 2025. Comprehensive Fine-Tuning Large Language Models of Code for Automated Program Repair. IEEE Transactions on Software Engineering (2025).","DOI":"10.1109\/TSE.2025.3532759"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00125"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00107"},{"key":"e_1_3_3_1_28_2","first-page":"1206","volume-title":"Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering","author":"Kim Kisub","year":"2024","unstructured":"Kisub Kim, Jounghoon Kim, Byeongjo Park, Dongsun Kim, Chun\u00a0Yong Chong, Yuan Wang, Tiezhu Sun, Daniel Tang, Jacques Klein, and Tegawend\u00e9\u00a0F Bissyand\u00e9. 2024. DataRecipe\u2014How to Cook the Data for CodeLLM?. In Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering. 1206\u20131218."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Taku Kudo and John Richardson. 2018. Sentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1808.06226 (2018).","DOI":"10.18653\/v1\/D18-2012"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Alexander LeClair and Collin McMillan. 2019. Recommendations for datasets for source code summarization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1904.02660 (2019).","DOI":"10.18653\/v1\/N19-1394"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","first-page":"1554","DOI":"10.1145\/3650212.3680381","volume-title":"Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","author":"Lin Bo","year":"2024","unstructured":"Bo Lin, Shangwen Wang, Ming Wen, Liqian Chen, and Xiaoguang Mao. 2024. One size does not fit all: Multi-granularity patch generation for better automated program repair. In Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis. 1554\u20131566."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510154"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Yue Liu Chakkrit Tantithamthavorn Yonghui Liu and Li Li. 2024. On the reliability and explainability of language models for program generation. ACM Transactions on Software Engineering and Methodology 33 5 (2024) 1\u201326.","DOI":"10.1145\/3641540"},{"key":"e_1_3_3_1_34_2","unstructured":"Scott\u00a0M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3395363.3397369"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME52107.2021.00021"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643916.3644400"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Antonio Mastropaolo Nathan Cooper David\u00a0Nader Palacio Simone Scalabrino Denys Poshyvanyk Rocco Oliveto and Gabriele Bavota. 2022. Using transfer learning for code-related tasks. IEEE Transactions on Software Engineering 49 4 (2022) 1580\u20131598.","DOI":"10.1109\/TSE.2022.3183297"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3511561"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00041"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623351"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/2597008.2597149"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"crossref","unstructured":"Quinn McNemar. 1947. Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika 12 2 (1947) 153\u2013157.","DOI":"10.1007\/BF02295996"},{"key":"e_1_3_3_1_44_2","unstructured":"Martin Monperrus Matias Martinez He Ye Fernanda Madeiral Thomas Durieux and Zhongxing Yu. 2021. Megadiff: A dataset of 600k java source code changes categorized by diff size. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.04631 (2021)."},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00073"},{"key":"e_1_3_3_1_46_2","unstructured":"Erik Nijkamp Bo Pang Hiroaki Hayashi Lifu Tu Huan Wang Yingbo Zhou Silvio Savarese and Caiming Xiong. 2022. Codegen: An open large language model for code with multi-turn program synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.13474 (2022)."},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"crossref","unstructured":"Devon\u00a0H O\u2019Dell. 2017. The Debugging Mindset: Understanding the psychology of learning strategies leads to effective problem-solving skills. Queue 15 1 (2017) 71\u201390.","DOI":"10.1145\/3055301.3068754"},{"key":"e_1_3_3_1_48_2","first-page":"311","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311\u2013318."},{"key":"e_1_3_3_1_49_2","first-page":"55","volume-title":"Neural Networks: Tricks of the trade","author":"Prechelt Lutz","year":"2002","unstructured":"Lutz Prechelt. 2002. Early stopping-but when? In Neural Networks: Tricks of the trade. Springer, 55\u201369."},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639086"},{"key":"e_1_3_3_1_51_2","unstructured":"Colin Raffel Noam Shazeer Adam Roberts Katherine Lee Sharan Narang Michael Matena Yanqi Zhou Wei Li and Peter\u00a0J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research 21 140 (2020) 1\u201367."},{"key":"e_1_3_3_1_52_2","unstructured":"Shuo Ren Daya Guo Shuai Lu Long Zhou Shujie Liu Duyu Tang Neel Sundaresan Ming Zhou Ambrosio Blanco and Shuai Ma. 2020. Codebleu: a method for automatic evaluation of code synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.10297 (2020)."},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549145"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"crossref","unstructured":"Chia-Yi Su and Collin McMillan. 2024. Distilled GPT for source code summarization. Automated Software Engineering 31 1 (2024) 22.","DOI":"10.1007\/s10515-024-00421-4"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417058"},{"key":"e_1_3_3_1_56_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et\u00a0al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.13971 (2023)."},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"crossref","unstructured":"Michele Tufano Cody Watson Gabriele Bavota Massimiliano\u00a0Di Penta Martin White and Denys Poshyvanyk. 2019. An empirical study on learning bug-fixing patches in the wild via neural machine translation. ACM Transactions on Software Engineering and Methodology (TOSEM) 28 4 (2019) 1\u201329.","DOI":"10.1145\/3340544"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510621"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00203"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1109\/MSR59073.2023.00035","volume-title":"2023 IEEE\/ACM 20th International Conference on Mining Software Repositories (MSR)","author":"Dam Tim van","year":"2023","unstructured":"Tim van Dam, Maliheh Izadi, and Arie van Deursen. 2023. Enriching source code with contextual data for code completion models: An empirical study. In 2023 IEEE\/ACM 20th International Conference on Mining Software Repositories (MSR). IEEE, 170\u2013182."},{"key":"e_1_3_3_1_61_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"crossref","unstructured":"Antonio Vitale Rocco Oliveto and Simone Scalabrino. 2024. A Catalog of Data Smells for Coding Tasks. ACM Transactions on Software Engineering and Methodology (2024).","DOI":"10.1145\/3707457"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00112"},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616256"},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"crossref","unstructured":"Yue Wang Hung Le Akhilesh\u00a0Deepak Gotmare Nghi\u00a0DQ Bui Junnan Li and Steven\u00a0CH Hoi. 2023. Codet5+: Open code large language models for code understanding and generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.07922 (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.68"},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"crossref","unstructured":"Yue Wang Weishi Wang Shafiq Joty and Steven\u00a0CH Hoi. 2021. Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2109.00859 (2021).","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"e_1_3_3_1_67_2","unstructured":"Martin Weyssow Xin Zhou Kisub Kim David Lo and Houari Sahraoui. 2023. Exploring parameter-efficient fine-tuning techniques for code generation with large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.10462 (2023)."},{"key":"e_1_3_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.5555\/2349018"},{"key":"e_1_3_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510222"},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380427"},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468544"},{"key":"e_1_3_3_1_72_2","doi-asserted-by":"crossref","unstructured":"Armin Zirak and Hadi Hemmati. 2024. Improving automated program repair with domain adaptation. ACM Transactions on Software Engineering and Methodology 33 3 (2024) 1\u201343.","DOI":"10.1145\/3631972"}],"event":{"name":"ICPC '26: 34th IEEE\/ACM International Conference on Program Comprehension","location":"Rio de Janeiro , Brazil","acronym":"ICPC '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2026 34th IEEE\/ACM International Conference on Program Comprehension"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3794763.3794794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:19:47Z","timestamp":1785338387000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3794763.3794794"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":71,"alternative-id":["10.1145\/3794763.3794794","10.1145\/3794763"],"URL":"https:\/\/doi.org\/10.1145\/3794763.3794794","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-07-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}