{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T11:01:14Z","timestamp":1785495674872,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":92,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"NSERC Discovery Grant","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3793302.3793351","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T10:42:54Z","timestamp":1785494574000},"page":"199-211","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LLM-Based Detection of Tangled Code Changes for Higher-Quality Method-Level Bug Datasets"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1220-560X","authenticated-orcid":false,"given":"Md Nahidul Islam","family":"Opu","sequence":"first","affiliation":[{"name":"Computer science, University of Manitoba, Winnipeg, Manitoba, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3823-1771","authenticated-orcid":false,"given":"Shaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer science, University of Manitoba, Winnipeg, Manitoba, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2301-6104","authenticated-orcid":false,"given":"Shaiful","family":"Chowdhury","sequence":"additional","affiliation":[{"name":"Computer science, University of Manitoba, Winnipeg, Manitoba, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Sandhini Agarwal Lama Ahmad Jason Ai Sam Altman Andy Applebaum Edwin Arbus Rahul\u00a0K Arora Yu Bai Bowen Baker Haiming Bao et\u00a0al. 2025. gpt-oss-120b & gpt-oss-20b model card. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.10925 (2025)."},{"key":"e_1_3_3_2_3_2","unstructured":"Wasi\u00a0Uddin Ahmad Saikat Chakraborty Baishakhi Ray and Kai-Wei Chang. 2021. Unified Pre-training for Program Understanding and Generation. arXiv:https:\/\/arXiv.org\/abs\/2103.06333."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2018.00088"},{"key":"e_1_3_3_2_5_2","unstructured":"Xavier Amatriain. 2024. Prompt Design and Engineering: Introduction and Advanced Methods. arXiv:https:\/\/arXiv.org\/abs\/2401.14423."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Jaehyeon Bae Seoryeong Kwon and Seunghwan Myeong. 2024. Enhancing software code vulnerability detection using gpt-4o and claude-3.5 sonnet: A study on prompt engineering techniques. Electronics 13 13 (2024) 2657.","DOI":"10.3390\/electronics13132657"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Abdul\u00a0Ali Bangash Hareem Sahar Abram Hindle and Karim Ali. 2020. On the time-based conclusion stability of cross-project defect prediction models. Empirical Software Engineering 25 6 (2020) 5047\u20135083.","DOI":"10.1007\/s10664-020-09878-9"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"V.R. Basili L.C. Briand and W.L. Melo. 1996. A Validation of Object-Oriented Design Metrics as Quality Indicators. IEEE Transactions on Software Engineering 22 10 (1996) 751\u2013761.","DOI":"10.1109\/32.544352"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3701625.3701673"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2020390.2020392"},{"key":"e_1_3_3_2_11_2","unstructured":"Ziqian Bi Keyu Chen Chiung-Yi Tseng Danyang Zhang Tianyang Wang Hongying Luo Lu Chen Junming Huang Jibin Guan Junfeng Hao et\u00a0al. 2025. Is GPT-OSS Good? A Comprehensive Evaluation of OpenAI\u2019s Latest Open Source Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.12461 (2025)."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/1595696.1595716"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"J\u00fcrgen B\u00f6rstler and Barbara Paech. 2016. The Role of Method Chains and Comments in Software Readability and Comprehension\u2014An Experiment. IEEE Transactions on Software Engineering 42 9 (2016) 886\u2013898.","DOI":"10.1109\/TSE.2016.2527791"},{"key":"e_1_3_3_2_14_2","first-page":"1877","volume-title":"Advances in Neural Information Processing Systems","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared\u00a0D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models Are Few-Shot Learners. In Advances in Neural Information Processing Systems , Vol.\u00a033. 1877\u20131901."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Marc Bruni Fabio Gabrielli Mohammad Ghafari and Martin Kropp. 2025. Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models. arXiv:https:\/\/arXiv.org\/abs\/2502.06039.","DOI":"10.1109\/Forge66646.2025.00018"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Raymond\u00a0PL Buse and Westley\u00a0R Weimer. 2009. Learning a metric for code readability. IEEE Transactions on software engineering 36 4 (2009) 546\u2013558.","DOI":"10.1109\/TSE.2009.70"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3545258.3545267"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00002"},{"key":"e_1_3_3_2_19_2","unstructured":"Robert Chew John Bollenbacher Michael Wenger Jessica Speer and Annice Kim. 2023. LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Coding. arXiv:https:\/\/arXiv.org\/abs\/2306.14924."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Shaiful Chowdhury Stephanie Borle Stephen Romansky and Abram Hindle. 2019. Greenscaler: training software energy models with automatic test generation. Empirical Software Engineering 24 4 (2019) 1649\u20131692.","DOI":"10.1007\/s10664-018-9640-7"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Shaiful Chowdhury Gias Uddin Hadi Hemmati and Reid Holmes. 2024. Method-Level Bug Prediction: Problems and Promises. ACM Transactions on Software Engineering and Methodology 33 4 (2024) 1\u201331.","DOI":"10.1145\/3640331"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3527975"},{"key":"e_1_3_3_2_23_2","unstructured":"christine fisher. 2020. Boeing found another software bug on the 737 Max. https:\/\/www.engadget.com\/2020-02-06-boeing-737-max-software-bug.html [Online; last accessed 2025-07-18]."},{"key":"e_1_3_3_2_24_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_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2015.7081844"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3691620.3694996"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Zhangyin Feng Daya Guo Duyu Tang Nan Duan Xiaocheng Feng Ming Gong Linjun Shou Bing Qin Ting Liu Daxin Jiang et\u00a0al. 2020. Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2002.08155 (2020).","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/2372251.2372285"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Yossi Gil and Gal Lalouche. 2017. On the Correlation between Size and Metric Validity. Empirical Software Engineering 22 (2017) 1\u201327.","DOI":"10.1007\/s10664-017-9513-5"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Louie Giray. 2023. Prompt Engineering with ChatGPT: A Guide for Academic Writers. Annals of Biomedical Engineering 51 12 (2023) 2629\u20132633.","DOI":"10.1007\/s10439-023-03272-4"},{"key":"e_1_3_3_2_31_2","unstructured":"Google DeepMind. 2024. Advancing Gemini: December 2024 Update. https:\/\/blog.google\/technology\/google-deepmind\/google-gemini-ai-update-december-2024\/ [Online; last accessed: 2025-07-11]."},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00135"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC.2017.153"},{"key":"e_1_3_3_2_34_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_2_35_2","doi-asserted-by":"crossref","unstructured":"Hideaki Hata Osamu Mizuno and Tohru Kikuno. 2012. Bug Prediction Based on Fine-Grained Module Histories. 200\u2013210.","DOI":"10.1109\/ICSE.2012.6227193"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Steffen Herbold Alexander Trautsch Benjamin Ledel Alireza Aghamohammadi Taher\u00a0A. Ghaleb Kuljit\u00a0Kaur Chahal Tim Bossenmaier Bhaveet Nagaria Philip Makedonski Matin\u00a0Nili Ahmadabadi Kristof Szabados Helge Spieker Matej Madeja Nathaniel Hoy Valentina Lenarduzzi Shangwen Wang Gema Rodr\u00edguez-P\u00e9rez Ricardo Colomo-Palacios Roberto Verdecchia Paramvir Singh Yihao Qin Debasish Chakroborti Willard Davis Vijay Walunj Hongjun Wu Diego Marcilio Omar Alam Abdullah Aldaeej Idan Amit Burak Turhan Simon Eismann Anna-Katharina Wickert Ivano Malavolta Mat\u00fa\u0161 Sul\u00edr Fatemeh Fard Austin\u00a0Z. Henley Stratos Kourtzanidis Eray Tuzun Christoph Treude Simin\u00a0Maleki Shamasbi Ivan Pashchenko Marvin Wyrich James Davis Alexander Serebrenik Ella Albrecht Ethem\u00a0Utku Aktas Daniel Str\u00fcber and Johannes Erbel. 2022. A Fine-Grained Data Set and Analysis of Tangling in Bug Fixing Commits. Empirical Software Engineering 27 6 (2022) 125.","DOI":"10.1007\/s10664-021-10083-5"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Kim Herzig Sascha Just and Andreas Zeller. 2016. The Impact of Tangled Code Changes on Defect Prediction Models. Empirical Software Engineering 21 2 (2016) 303\u2013336.","DOI":"10.1007\/s10664-015-9376-6"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2013.6624018"},{"key":"e_1_3_3_2_39_2","volume-title":"annual meeting of the American Educational Research Association","author":"Hess Melinda\u00a0R","year":"2004","unstructured":"Melinda\u00a0R Hess and Jeffrey\u00a0D Kromrey. 2004. Robust confidence intervals for effect sizes: A comparative study of Cohen\u2019sd and Cliff\u2019s delta under non-normality and heterogeneous variances. In annual meeting of the American Educational Research Association , Vol.\u00a01."},{"key":"e_1_3_3_2_40_2","unstructured":"Tiancheng Hu and Nigel Collier. 2024. Quantifying the Persona Effect in LLM Simulations. arXiv:https:\/\/arXiv.org\/abs\/2402.10811."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR66628.2025.00038"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Ziwei Ji Nayeon Lee Rita Frieske Tiezheng Yu Dan Su Yan Xu Etsuko Ishii Ye\u00a0Jin Bang Andrea Madotto and Pascale Fung. 2023. Survey of Hallucination in Natural Language Generation. ACM Comput. Surv. 55 12 (2023) 248:1\u2013248:38.","DOI":"10.1145\/3571730"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-58547-0_17"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/2597008.2597798"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/2642937.2642997"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"crossref","unstructured":"Takeshi Kojima Shixiang\u00a0Shane Gu Machel Reid Yutaka Matsuo and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems 35 (2022) 22199\u201322213.","DOI":"10.52202\/068431-1613"},{"key":"e_1_3_3_2_47_2","unstructured":"Jinhyuk Lee Zhuyun Dai Xiaoqi Ren Blair Chen Daniel Cer Jeremy\u00a0R Cole Kai Hui Michael Boratko Rajvi Kapadia Wen Ding et\u00a0al. 2024. Gecko: Versatile text embeddings distilled from large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.20327 (2024)."},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Mosh Levy Alon Jacoby and Yoav Goldberg. 2024. Same Task More Tokens: The Impact of Input Length on the Reasoning Performance of Large Language Models. arXiv:https:\/\/arXiv.org\/abs\/2402.14848.","DOI":"10.18653\/v1\/2024.acl-long.818"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549171"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"crossref","unstructured":"Pengfei Liu Weizhe Yuan Jinlan Fu Zhengbao Jiang Hiroaki Hayashi and Graham Neubig. 2023. Pre-Train Prompt and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing. ACM Comput. Surv. 55 9 (2023) 195:1\u2013195:35.","DOI":"10.1145\/3560815"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2018.00047"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"crossref","unstructured":"Yu Liu Duantengchuan Li Kaili Wang Zhuoran Xiong Fobo Shi Jian Wang Bing Li and Bo Hang. 2024. Are LLMs Good at Structured Outputs? A Benchmark for Evaluating Structured Output Capabilities in LLMs. Information Processing & Management 61 5 (2024) 103809.","DOI":"10.1016\/j.ipm.2024.103809"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Wei Ma Shangqing Liu Mengjie Zhao Xiaofei Xie Wenhang Wang Qiang Hu Jie Zhang and Yang Liu. 2024. Unveiling code pre-trained models: Investigating syntax and semantics capacities. ACM Transactions on Software Engineering and Methodology 33 7 (2024) 1\u201329.","DOI":"10.1145\/3664606"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"crossref","unstructured":"Guillermo Macbeth Eugenia Razumiejczyk and Rub\u00e9n\u00a0Daniel Ledesma. 2011. Cliff\u2019s Delta Calculator: A non-parametric effect size program for two groups of observations. Universitas Psychologica 10 2 (2011) 545\u2013555.","DOI":"10.11144\/Javeriana.upsy10-2.cdcp"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE59848.2023.00055"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"crossref","unstructured":"Thomas\u00a0J McCabe. 1976. A complexity measure. IEEE Transactions on software Engineering4 (1976) 308\u2013320.","DOI":"10.1109\/TSE.1976.233837"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"crossref","unstructured":"Patrick\u00a0E McKnight and Julius Najab. 2010. Mann-Whitney U Test. The Corsini encyclopedia of psychology (2010) 1\u20131.","DOI":"10.1002\/9780470479216.corpsy0524"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"crossref","unstructured":"T. Menzies J. Greenwald and A. Frank. 2007. Data Mining Static Code Attributes to Learn Defect Predictors. IEEE Transactions on Software Engineering 33 1 (2007) 2\u201313.","DOI":"10.1109\/TSE.2007.256941"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"crossref","unstructured":"Ran Mo Shaozhi Wei Qiong Feng and Zengyang Li. 2022. An Exploratory Study of Bug Prediction at the Method Level. Information and Software Technology 144 (2022) 106794.","DOI":"10.1016\/j.infsof.2021.106794"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCAM.2018.00030"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639187"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.1992.242525"},{"key":"e_1_3_3_2_63_2","unstructured":"OpenAI. 2025. GPT-4o mini: Advancing Cost-Efficient Intelligence. https:\/\/openai.com\/index\/gpt-4o-mini-advancing-cost-efficient-intelligence\/ [Online; last accessed: 2025-07-11]."},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409693"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"crossref","unstructured":"Luca Pascarella Fabio Palomba and Alberto Bacchelli. 2020. On the Performance of Method-Level Bug Prediction: A Negative Result. Journal of Systems and Software 161 (2020) 110493.","DOI":"10.1016\/j.jss.2019.110493"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"crossref","unstructured":"Alina Petukhova Jo\u00e3o\u00a0P. Matos-Carvalho and Nuno Fachada. 2024. Text Clustering with Large Language Model Embeddings.","DOI":"10.1016\/j.ijcce.2024.11.004"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCAM.2017.26"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3639476.3639764"},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2017.74"},{"key":"e_1_3_3_2_70_2","doi-asserted-by":"crossref","unstructured":"Omar Shaikh Hongxin Zhang William Held Michael Bernstein and Diyi Yang. 2023. On Second Thought Let\u2019s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning. arXiv:https:\/\/arXiv.org\/abs\/2212.08061.","DOI":"10.18653\/v1\/2023.acl-long.244"},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468551"},{"key":"e_1_3_3_2_72_2","doi-asserted-by":"crossref","unstructured":"Thomas Shippey Tracy Hall Steve Counsell and David Bowes. 2016. So You Need More Method Level Datasets for Your Software Defect Prediction? Voil\u00e0!(ESEM \u201916).","DOI":"10.1145\/2961111.2962620"},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"crossref","unstructured":"Mifta Sintaha Noor Nashid and Ali Mesbah. 2023. Katana: Dual slicing based context for learning bug fixes. ACM Transactions on Software Engineering and Methodology 32 4 (2023) 1\u201327.","DOI":"10.1145\/3579640"},{"key":"e_1_3_3_2_74_2","unstructured":"sixsentix. 2024. Most expensive software bugs in history: Sixsentix. https:\/\/www.sixsentix.com\/insights\/ten-most-expensive-bugs-in-history-part-1 [Online; last accessed 2025-07-18]."},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE55347.2025.00240"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2015.24"},{"key":"e_1_3_3_2_77_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_2_78_2","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. In Advances in Neural Information Processing Systems , Vol.\u00a030."},{"key":"e_1_3_3_2_79_2","unstructured":"Henrique\u00a0Schechter Vera Sahil Dua Biao Zhang Daniel Salz Ryan Mullins Sindhu\u00a0Raghuram Panyam Sara Smoot Iftekhar Naim Joe Zou Feiyang Chen et\u00a0al. 2025. Embeddinggemma: Powerful and lightweight text representations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.20354 (2025)."},{"key":"e_1_3_3_2_80_2","doi-asserted-by":"crossref","unstructured":"Zixu Wang Weiyuan Tong Peng Li Guixin Ye Hao Chen Xiaoqing Gong and Zhanyong Tang. 2023. BugPre: An Intelligent Software Version-to-Version Bug Prediction System Using Graph Convolutional Neural Networks. Complex & Intelligent Systems 9 4 (2023) 3835\u20133855.","DOI":"10.1007\/s40747-022-00848-w"},{"key":"e_1_3_3_2_81_2","doi-asserted-by":"crossref","unstructured":"Supatsara Wattanakriengkrai Patanamon Thongtanunam Chakkrit Tantithamthavorn Hideaki Hata and Kenichi Matsumoto. 2022. Predicting Defective Lines Using a Model-Agnostic Technique. IEEE Transactions on Software Engineering 48 5 (2022) 1480\u20131496.","DOI":"10.1109\/TSE.2020.3023177"},{"key":"e_1_3_3_2_82_2","unstructured":"Jason Wei Maarten Bosma Vincent\u00a0Y. Zhao Kelvin Guu Adams\u00a0Wei Yu Brian Lester Nan Du Andrew\u00a0M. Dai and Quoc\u00a0V. Le. 2022. Finetuned Language Models Are Zero-Shot Learners. arXiv:https:\/\/arXiv.org\/abs\/2109.01652."},{"key":"e_1_3_3_2_83_2","doi-asserted-by":"crossref","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Brian Ichter Fei Xia Ed Chi Quoc Le and Denny Zhou. 2023. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. arXiv:https:\/\/arXiv.org\/abs\/2201.11903.","DOI":"10.52202\/068431-1800"},{"key":"e_1_3_3_2_84_2","doi-asserted-by":"crossref","unstructured":"Sheng-Bin Xu Si-Yu Chen Yuan Yao and Feng Xu. 2025. Detecting and Untangling Composite Commits via Attributed Graph Modeling. Journal of Computer Science and Technology 40 1 (2025) 119\u2013137.","DOI":"10.1007\/s11390-024-2943-9"},{"key":"e_1_3_3_2_85_2","unstructured":"Jia-Yu Yao Kun-Peng Ning Zhen-Hui Liu Mu-Nan Ning Yu-Yang Liu and Li Yuan. 2024. LLM Lies: Hallucinations Are Not Bugs but Features as Adversarial Examples. arXiv:https:\/\/arXiv.org\/abs\/2310.01469."},{"key":"e_1_3_3_2_86_2","unstructured":"Hongbin Ye Tong Liu Aijia Zhang Wei Hua and Weiqiang Jia. 2023. Cognitive Mirage: A Review of Hallucinations in Large Language Models. arXiv:https:\/\/arXiv.org\/abs\/2309.06794."},{"key":"e_1_3_3_2_87_2","doi-asserted-by":"crossref","unstructured":"Shouyu Yin Shikai Guo Hui Li Chenchen Li Rong Chen Xiaochen Li and He Jiang. 2025. Line-Level Defect Prediction by Capturing Code Contexts With Graph Convolutional Networks. IEEE Transactions on Software Engineering 51 1 (2025) 172\u2013191.","DOI":"10.1109\/TSE.2024.3503723"},{"key":"e_1_3_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE55347.2025.00011"},{"key":"e_1_3_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER60148.2024.00082"},{"key":"e_1_3_3_2_90_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.814"},{"key":"e_1_3_3_2_91_2","doi-asserted-by":"crossref","unstructured":"Tianming Zheng Haojun Liu Hang Xu Xiang Chen Ping Yi and Yue Wu. 2024. Few-VulD: A Few-shot learning framework for software vulnerability detection. Computers & Security 144 (2024) 103992.","DOI":"10.1016\/j.cose.2024.103992"},{"key":"e_1_3_3_2_92_2","unstructured":"Denny Zhou Nathanael Sch\u00e4rli Le Hou Jason Wei Nathan Scales Xuezhi Wang Dale Schuurmans Claire Cui Olivier Bousquet Quoc Le et\u00a0al. 2022. Least-to-most prompting enables complex reasoning in large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.10625 (2022)."},{"key":"e_1_3_3_2_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/PROMISE.2007.10"}],"event":{"name":"MSR '26: 23rd International Conference on Mining Software Repositories","location":"Rio de Janeiro Brazil","acronym":"MSR '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 23rd International Conference on Mining Software Repositories"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3793302.3793351","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T10:45:33Z","timestamp":1785494733000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3793302.3793351"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":92,"alternative-id":["10.1145\/3793302.3793351","10.1145\/3793302"],"URL":"https:\/\/doi.org\/10.1145\/3793302.3793351","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-07-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}