{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T17:07:10Z","timestamp":1784653630618,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":58,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,12]]},"DOI":"10.1145\/3793655.3793716","type":"proceedings-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T16:04:46Z","timestamp":1784649886000},"page":"243-248","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3238-1229","authenticated-orcid":false,"given":"Daniel","family":"Rodriguez-Cardenas","sequence":"first","affiliation":[{"name":"William & Mary, Williamsburg, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8073-8817","authenticated-orcid":false,"given":"Xiaochang","family":"Li","sequence":"additional","affiliation":[{"name":"William & Mary, Williamsburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1008-1073","authenticated-orcid":false,"given":"Marcos","family":"Macedo","sequence":"additional","affiliation":[{"name":"Queen's University, Kingston, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7965-7712","authenticated-orcid":false,"given":"Antonio","family":"Mastropaolo","sequence":"additional","affiliation":[{"name":"William & Mary, Williamsburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4489-7733","authenticated-orcid":false,"given":"Dipin","family":"Khati","sequence":"additional","affiliation":[{"name":"William & Mary, Williamsburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2208-3893","authenticated-orcid":false,"given":"Yuan","family":"Tian","sequence":"additional","affiliation":[{"name":"Queen's University, Kingston, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7627-5615","authenticated-orcid":false,"given":"Huajie","family":"Shao","sequence":"additional","affiliation":[{"name":"William & Mary, Williamsburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5626-7586","authenticated-orcid":false,"given":"Denys","family":"Poshyvanyk","sequence":"additional","affiliation":[{"name":"William & Mary, Williamsburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"[n. d.]. Benchmarking repository. https:\/\/anonymous.4open.science\/status\/benchmarking-repo-70FA. Accessed: 2025-11-24."},{"key":"e_1_3_3_1_3_2","unstructured":"Md\u00a0Basim\u00a0Uddin Ahmed Nima\u00a0Shiri Harzevili Jiho Shin Hung\u00a0Viet Pham and Song Wang. 2025. SecVulEval: Benchmarking LLMs for Real-World C\/C++ Vulnerability Detection. arxiv:https:\/\/arXiv.org\/abs\/2505.19828\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2505.19828"},{"key":"e_1_3_3_1_4_2","unstructured":"Scale AI. 2025. SWE-Bench Pro (Public Dataset). https:\/\/scale.com\/leaderboard\/swe_bench_pro_public. Accessed: 2025-11-21."},{"key":"e_1_3_3_1_5_2","unstructured":"Jacob Austin Augustus Odena Maxwell Nye Maarten Bosma Henryk Michalewski David Dohan Ellen Jiang Carrie Cai Michael Terry Quoc Le and Charles Sutton. 2021. Program Synthesis with Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2108.07732\u00a0[cs.PL]"},{"key":"e_1_3_3_1_6_2","unstructured":"SWE bench Team. 2024. SWE-bench Multimodal. https:\/\/www.swebench.com. Accessed: 2025-11-21."},{"key":"e_1_3_3_1_7_2","unstructured":"Federico Cassano John Gouwar Daniel Nguyen Sydney Nguyen Luna Phipps-Costin Donald Pinckney Ming-Ho Yee Yangtian Zi Carolyn\u00a0Jane Anderson Molly\u00a0Q Feldman Arjun Guha Michael Greenberg and Abhinav Jangda. 2022. MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation. arxiv:https:\/\/arXiv.org\/abs\/2208.08227\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2208.08227"},{"key":"e_1_3_3_1_8_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henry\u00a0P. de Freitas Ariel Herbert-Voss William Saunders John Schroeter Brook E.\u00a0D. Simpson Filip Wolski et\u00a0al. 2021. Evaluating Large Language Models Trained on Code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2107.03374 (2021). https:\/\/arxiv.org\/abs\/2107.03374"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Zimin Chen Steve Kommrusch Michele Tufano Louis-No\u00ebl Pouchet Denys Poshyvanyk and Martin Monperrus. 2021. SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair. IEEE Transactions on Software Engineering 47 9 (2021). 10.1109\/TSE.2019.2940179","DOI":"10.1109\/TSE.2019.2940179"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"Matteo Ciniselli Nathan Cooper Luca Pascarella Antonio Mastropaolo Emad Aghajani Denys Poshyvanyk Massimiliano Di\u00a0Penta and Gabriele Bavota. 2022. An Empirical Study on the Usage of Transformer Models for Code Completion. IEEE Transactions on Software Engineering 48 12 (2022). 10.1109\/TSE.2021.3128234","DOI":"10.1109\/TSE.2021.3128234"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00096"},{"key":"e_1_3_3_1_12_2","unstructured":"Xueying Du Mingwei Liu Kaixin Wang Hanlin Wang Junwei Liu Yixuan Chen Jiayi Feng Chaofeng Sha Xin Peng and Yiling Lou. 2023. ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation. arxiv:https:\/\/arXiv.org\/abs\/2308.01861\u00a0[cs.CL]"},{"key":"e_1_3_3_1_13_2","unstructured":"Dan Hendrycks Steven Basart Saurav Kadavath Mantas Mazeika Akul Arora Ethan Guo Collin Burns Samir Puranik Horace He Dawn Song and Jacob Steinhardt. 2021. Measuring Coding Challenge Competence With APPS. NeurIPS (2021)."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Yasir Hussain Zhiqiu Huang Yu Zhou and Senzhang Wang. 2020. Deep Transfer Learning for Source Code Modeling. Int. J. Softw. Eng. Knowl. Eng. 30 (2020).","DOI":"10.1142\/S0218194020500230"},{"key":"e_1_3_3_1_15_2","unstructured":"Kush Jain Gabriel Synnaeve and Baptiste Rozi\u00e8re. 2025. TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark. arxiv:https:\/\/arXiv.org\/abs\/2410.00752\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2410.00752"},{"key":"e_1_3_3_1_16_2","unstructured":"Naman Jain King Han Alex Gu Wen-Ding Li Fanjia Yan Tianjun Zhang Sida Wang Armando Solar-Lezama Koushik Sen and Ion Stoica. 2024. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.07974 (2024)."},{"key":"e_1_3_3_1_17_2","unstructured":"Yuancheng Jiang Roland Yap and Zhenkai Liang. 2025. OSS-Bench: Benchmark Generator for Coding LLMs. arxiv:https:\/\/arXiv.org\/abs\/2505.12331\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2505.12331"},{"key":"e_1_3_3_1_18_2","unstructured":"Carlos\u00a0E. Jimenez John Yang Alexander Wettig Shunyu Yao Kexin Pei Ofir Press and Karthik Narasimhan. 2024. SWE-bench: Can Language Models Resolve Real-World GitHub Issues? arxiv:https:\/\/arXiv.org\/abs\/2310.06770\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2310.06770"},{"key":"e_1_3_3_1_19_2","unstructured":"Yuhang Lai Chengxi Li Yiming Wang Tianyi Zhang Ruiqi Zhong Luke Zettlemoyer Scott\u00a0Wen tau Yih Daniel Fried Sida Wang and Tao Yu. 2022. DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation. ArXiv abs\/2211.11501 (2022)."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Alexander LeClair Aakash Bansal and Collin McMillan. 2021. Ensemble Models for Neural Source Code Summarization of Subroutines. http:\/\/arxiv.org\/abs\/2107.11423 arXiv:https:\/\/arXiv.org\/abs\/2107.11423 [cs].","DOI":"10.26226\/morressier.613b5418842293c031b5b62e"},{"key":"e_1_3_3_1_21_2","unstructured":"Hwiwon Lee Ziqi Zhang Hanxiao Lu and Lingming Zhang. 2025. SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks. arxiv:https:\/\/arXiv.org\/abs\/2506.11791\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2506.11791"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1837"},{"key":"e_1_3_3_1_23_2","unstructured":"Percy Liang Rishi Bommasani Tony Lee Dimitris Tsipras Dilara Soylu Michihiro Yasunaga Yian Zhang Deepak Narayanan Yuhuai Wu Ananya Kumar Benjamin Newman Binhang Yuan Bobby Yan Ce Zhang Christian Cosgrove Christopher\u00a0D. Manning Christopher R\u00e9 Diana Acosta-Navas Drew\u00a0A. Hudson Eric Zelikman Esin Durmus Faisal Ladhak Frieda Rong Hongyu Ren Huaxiu Yao Jue Wang Keshav Santhanam Laurel Orr Lucia Zheng Mert Yuksekgonul Mirac Suzgun Nathan Kim Neel Guha Niladri Chatterji Omar Khattab Peter Henderson Qian Huang Ryan Chi Sang\u00a0Michael Xie Shibani Santurkar Surya Ganguli Tatsunori Hashimoto Thomas Icard Tianyi Zhang Vishrav Chaudhary William Wang Xuechen Li Yifan Mai Yuhui Zhang and Yuta Koreeda. 2022. Holistic Evaluation of Language Models. http:\/\/arxiv.org\/abs\/2211.09110 arXiv:https:\/\/arXiv.org\/abs\/2211.09110 [cs]."},{"key":"e_1_3_3_1_24_2","unstructured":"Shanchao Liang Spandan Garg and Roshanak\u00a0Zilouchian Moghaddam. 2025. The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason. arxiv:https:\/\/arXiv.org\/abs\/2506.12286\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2506.12286"},{"key":"e_1_3_3_1_25_2","unstructured":"Chao Liu Xuanlin Bao Hongyu Zhang Neng Zhang Haibo Hu Xiaohong Zhang and Meng Yan. 2023. Improving ChatGPT Prompt for Code Generation. arxiv:https:\/\/arXiv.org\/abs\/2305.08360\u00a0[cs.SE]"},{"key":"e_1_3_3_1_26_2","unstructured":"Jiawei Liu Chunqiu\u00a0Steven Xia Yuyao Wang and Lingming Zhang. 2023. Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation. arxiv:https:\/\/arXiv.org\/abs\/2305.01210\u00a0[cs.SE]"},{"key":"e_1_3_3_1_27_2","unstructured":"Shuai Lu Daya Guo Shuo Ren Junjie Huang Alexey Svyatkovskiy Ambrosio Blanco Colin Clement Dawn Drain Daxin Jiang Duyu Tang Ge Li Lidong Zhou Linjun Shou Long Zhou Michele Tufano Ming Gong Ming Zhou Nan Duan Neel Sundaresan Shao\u00a0Kun Deng Shengyu Fu and Shujie Liu. 2021. CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation. arxiv:https:\/\/arXiv.org\/abs\/2102.04664\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2102.04664"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Yuxing Ma Tapajit Dey Chris Bogart Sadika Amreen Marat Valiev Adam Tutko David Kennard Russell Zaretzki and Audris Mockus. 2021. World of code: Enabling a research workflow for mining and analyzing the universe of open source vcs data. Empirical Software Engineering 26 2 (2021).","DOI":"10.1007\/s10664-020-09905-9"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","unstructured":"Antonio Mastropaolo Nathan Cooper David\u00a0Nader Palacio Simone Scalabrino Denys Poshyvanyk Rocco Oliveto and Gabriele Bavota. 2023. Using Transfer Learning for Code-Related Tasks. IEEE Transactions on Software Engineering 49 4 (2023). 10.1109\/TSE.2022.3183297","DOI":"10.1109\/TSE.2022.3183297"},{"key":"e_1_3_3_1_30_2","unstructured":"Antonio Mastropaolo Simone Scalabrino Nathan Cooper David\u00a0Nader Palacio Denys Poshyvanyk Rocco Oliveto and Gabriele Bavota. 2021. Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks. arxiv:https:\/\/arXiv.org\/abs\/2102.02017\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2102.02017"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380418"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","unstructured":"Kevin Moran Ali Yachnes George Purnell Junayed Mahmud Michele Tufano Carlos\u00a0Bernal Cardenas Denys Poshyvanyk and Zach H\u2019Doubler. 2022. An Empirical Investigation into the Use of Image Captioning for Automated Software Documentation. 10.1109\/SANER53432.2022.00069","DOI":"10.1109\/SANER53432.2022.00069"},{"key":"e_1_3_3_1_33_2","unstructured":"Niels M\u00fcndler Mark\u00a0Niklas M\u00fcller Jingxuan He and Martin Vechev. 2025. SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents. arxiv:https:\/\/arXiv.org\/abs\/2406.12952\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2406.12952"},{"key":"e_1_3_3_1_34_2","unstructured":"Anh\u00a0Tuan Nguyen and Tien\u00a0N. Nguyen. 2015. Graph-based statistical language model for code(ICSE \u201915). 11\u00a0pages."},{"key":"e_1_3_3_1_35_2","unstructured":"Changan Niu Chuanyi Li Vincent Ng and Bin Luo. 2023. CrossCodeBench: Benchmarking Cross-Task Generalization of Source Code Models. arxiv:https:\/\/arXiv.org\/abs\/2302.04030\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2302.04030"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEMT55343.2022.9969493"},{"key":"e_1_3_3_1_37_2","unstructured":"OpenAI and Princeton NLP. 2024. Introducing SWE-bench Verified. https:\/\/openai.com\/index\/introducing-swe-bench-verified\/. Accessed: 2025-11-21."},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/2594291.2594321"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME58846.2023.00040"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380416"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00021"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","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 Trans. Softw. Eng. Methodol. 28 4 Article 19 (sep 2019) 29\u00a0pages. 10.1145\/3340544","DOI":"10.1145\/3340544"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2019.00046"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510621"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00027"},{"key":"e_1_3_3_1_46_2","unstructured":"Shiqi Wang Zheng Li Haifeng Qian Chenghao Yang Zijian Wang Mingyue Shang Varun Kumar Samson Tan Baishakhi Ray Parminder Bhatia Ramesh Nallapati Murali\u00a0Krishna Ramanathan Dan Roth and Bing Xiang. 2022. ReCode: Robustness Evaluation of Code Generation Models. http:\/\/arxiv.org\/abs\/2212.10264 arXiv:https:\/\/arXiv.org\/abs\/2212.10264 [cs]."},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","unstructured":"Cody Watson Nathan Cooper David\u00a0Nader Palacio Kevin Moran and Denys Poshyvanyk. 2022. A Systematic Literature Review on the Use of Deep Learning in Software Engineering Research. ACM Trans. Softw. Eng. Methodol. 31 2 Article 32 (March 2022) 58\u00a0pages. 10.1145\/3485275","DOI":"10.1145\/3485275"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380429"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3545945.3569830"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2019.8668043"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/2970276.2970326"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2015.38"},{"key":"e_1_3_3_1_53_2","unstructured":"Robert White and Jens Krinke. 2020. ReAssert: Deep Learning for Assert Generation. http:\/\/arxiv.org\/abs\/2011.09784 arXiv:https:\/\/arXiv.org\/abs\/2011.09784 [cs]."},{"key":"e_1_3_3_1_54_2","unstructured":"Frank\u00a0F. Xu Uri Alon Graham Neubig and Vincent\u00a0J. Hellendoorn. 2022. A Systematic Evaluation of Large Language Models of Code. http:\/\/arxiv.org\/abs\/2202.13169 arXiv:https:\/\/arXiv.org\/abs\/2202.13169 [cs]."},{"key":"e_1_3_3_1_55_2","unstructured":"Zhiqiang Yuan Junwei Liu Qiancheng Zi Mingwei Liu Xin Peng and Yiling Lou. 2023. Evaluating Instruction-Tuned Large Language Models on Code Comprehension and Generation. arxiv:https:\/\/arXiv.org\/abs\/2308.01240\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2308.01240"},{"key":"e_1_3_3_1_56_2","unstructured":"Daoguang Zan Zhirong Huang Ailun Yu Shaoxin Lin Yifan Shi Wei Liu Dong Chen Zongshuai Qi Hao Yu Lei Yu Dezhi Ran Muhan Zeng Bo Shen Pan Bian Guangtai Liang Bei Guan Pengjie Huang Tao Xie Yongji Wang and Qianxiang Wang. 2024. SWE-bench-java: A GitHub Issue Resolving Benchmark for Java. arxiv:https:\/\/arXiv.org\/abs\/2408.14354\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2408.14354"},{"key":"e_1_3_3_1_57_2","unstructured":"Wojciech Zaremba Greg Brockman and OpenAI. 2021. OpenAI Codex. https:\/\/openai.com\/blog\/openai-codex\/"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599790"},{"key":"e_1_3_3_1_59_2","unstructured":"Yaqin Zhou Shangqing Liu Jingkai Siow Xiaoning Du and Yang Liu. 2019. Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks. arxiv:https:\/\/arXiv.org\/abs\/1909.03496\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/1909.03496"}],"event":{"name":"FORGE '26: IEEE\/ACM Third International Conference on AI Foundation Models and Software Engineering","location":"Rio de Janeiro , Brazil","acronym":"FORGE '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2026 IEEE\/ACM Third International Conference on AI Foundation Models and Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3793655.3793716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T16:48:54Z","timestamp":1784652534000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3793655.3793716"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":58,"alternative-id":["10.1145\/3793655.3793716","10.1145\/3793655"],"URL":"https:\/\/doi.org\/10.1145\/3793655.3793716","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-07-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}