{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T09:15:48Z","timestamp":1783242948915,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,5]]},"DOI":"10.1145\/3805760.3814925","type":"proceedings-article","created":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T08:46:13Z","timestamp":1783241173000},"page":"340-348","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6800-0344","authenticated-orcid":false,"given":"Yeheng","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7168-6332","authenticated-orcid":false,"given":"Chaoxiang","family":"Xie","sequence":"additional","affiliation":[{"name":"Hohai University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9738-7072","authenticated-orcid":false,"given":"Yuling","family":"Shi","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0251-8200","authenticated-orcid":false,"given":"Wenhao","family":"Zeng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7909-2576","authenticated-orcid":false,"given":"Yongpan","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3063-9425","authenticated-orcid":false,"given":"Hongyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0529-6408","authenticated-orcid":false,"given":"Xiaodong","family":"Gu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Program Synthesis with Large Language Models. CoRR abs\/2108.07732","author":"Austin Jacob","year":"2021","unstructured":"Jacob Austin, Augustus Odena, Maxwell I. Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie J. Cai, Michael Terry, Quoc V. Le, and Charles Sutton. 2021. Program Synthesis with Large Language Models. CoRR abs\/2108.07732 (2021). arXiv:2108.07732 https:\/\/arxiv.org\/abs\/2108.07732"},{"key":"e_1_3_2_1_2_1","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Pond\u00e9 de Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman Alex Ray Raul Puri Gretchen Krueger Michael Petrov Heidy Khlaaf Girish Sastry Pamela Mishkin Brooke Chan Scott Gray Nick Ryder Mikhail Pavlov Alethea Power Lukasz Kaiser Mohammad Bavarian Clemens Winter Philippe Tillet Felipe Petroski Such Dave Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William Hebgen Guss Alex Nichol Alex Paino Nikolas Tezak Jie Tang Igor Babuschkin Suchir Balaji Shantanu Jain William Saunders Christopher Hesse Andrew N. Carr Jan Leike Joshua Achiam Vedant Misra Evan Morikawa Alec Radford Matthew Knight Miles Brundage Mira Murati Katie Mayer Peter Welinder Bob McGrew Dario Amodei Sam McCandlish Ilya Sutskever and Wojciech Zaremba. 2021. Evaluating Large Language Models Trained on Code. CoRR abs\/2107.03374 (2021). arXiv:2107.03374 https:\/\/arxiv.org\/abs\/2107.03374"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2507.23361"},{"key":"e_1_3_2_1_4_1","volume-title":"Premise Order Matters in Reasoning with Large Language Models. In Forty-first International Conference on Machine Learning, ICML 2024","author":"Chen Xinyun","year":"2024","unstructured":"Xinyun Chen, Ryan A. Chi, Xuezhi Wang, and Denny Zhou. 2024. Premise Order Matters in Reasoning with Large Language Models. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024 (Proceedings of Machine Learning Research, Vol. 235), Ruslan Salakhutdinov, Zico Kolter, Katherine A. Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (Eds.). PMLR \/ OpenReview.net, 6596-6620. https:\/\/proceedings.mlr.press\/v235\/chen24i.html"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2405.01573"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2308.01861"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2025.FINDINGS-EMNLP.993"},{"key":"e_1_3_2_1_8_1","unstructured":"GitHub. 2026. GitHub REST API Documentation. https:\/\/docs.github.com\/en\/ rest."},{"key":"e_1_3_2_1_9_1","volume-title":"Understanding and Execution. In Forty-first International Conference on Machine Learning, ICML 2024","author":"Gu Alex","year":"2024","unstructured":"Alex Gu, Baptiste Rozi\u00e8re, Hugh James Leather, Armando Solar-Lezama, Gabriel Synnaeve, and Sida Wang. 2024. CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024 (Proceedings of Machine Learning Research, Vol. 235), Ruslan Salakhutdinov, Zico Kolter, Katherine A. Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (Eds.). PMLR \/ OpenReview.net, 16568-16621. https:\/\/proceedings.mlr.press\/ v235\/gu24c.html"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2411.15594"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2401.14196"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3695988"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2601.00376"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2025"},{"key":"e_1_3_2_1_15_1","unstructured":"Minghao Hu Qiang Zeng and Lannan Luo. 2026. Zero-Shot Vulnerability Detection in Low-Resource Smart Contracts Through Solidity-Only Training. arXiv:2603.21058 [cs.CR] https:\/\/arxiv.org\/abs\/2603.21058"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2403.07974"},{"key":"e_1_3_2_1_17_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Jimenez Carlos E.","year":"2024","unstructured":"Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R. Narasimhan. 2024. SWE-bench: Can Language Models Resolve Real-world Github Issues?. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=VTF8yNQM66"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.ACL-LONG.367"},{"key":"e_1_3_2_1_19_1","volume-title":"Jia Li, Chenghao Mou, Yacine Jernite, Margaret Mitchell, Carlos Mu\u00f1oz Ferrandis, Sean Hughes, Thomas Wolf, Dzmitry Bahdanau, Leandro von Werra, and Harm de Vries.","author":"Kocetkov Denis","year":"2023","unstructured":"Denis Kocetkov, Raymond Li, Loubna Ben Allal, Jia Li, Chenghao Mou, Yacine Jernite, Margaret Mitchell, Carlos Mu\u00f1oz Ferrandis, Sean Hughes, Thomas Wolf, Dzmitry Bahdanau, Leandro von Werra, and Harm de Vries. 2023. The Stack: 3 TB of permissively licensed source code. Trans. Mach. Learn. Res. 2023 (2023). https:\/\/openreview.net\/forum?id=pxpbTdUEpD"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2412.05579"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2507.23348"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.FINDINGS-ACL.214"},{"key":"e_1_3_2_1_23_1","unstructured":"Raymond Li Loubna Ben Allal Yangtian Zi Niklas Muennighoff Denis Kocetkov Chenghao Mou Marc Marone Christopher Akiki Jia Li Jenny Chim Qian Liu Evgenii Zheltonozhskii Terry Yue Zhuo Thomas Wang Olivier Dehaene Mishig Davaadorj Joel Lamy-Poirier Jo\u00e3o Monteiro Oleh Shliazhko Nicolas Gontier Nicholas Meade Armel Zebaze Ming-Ho Yee Logesh Kumar Umapathi Jian Zhu Benjamin Lipkin Muhtasham Oblokulov Zhiruo Wang Rudra Murthy V Jason T. Stillerman Siva Sankalp Patel Dmitry Abulkhanov Marco Zocca Manan Dey Zhihan Zhang Nour Fahmy Urvashi Bhattacharyya Wenhao Yu Swayam Singh Sasha Luccioni Paulo Villegas Maxim Kunakov Fedor Zhdanov Manuel Romero Tony Lee Nadav Timor Jennifer Ding Claire Schlesinger Hailey Schoelkopf Jan Ebert Tri Dao Mayank Mishra Alex Gu Jennifer Robinson Carolyn Jane Anderson Brendan Dolan-Gavitt Danish Contractor Siva Reddy Daniel Fried Dzmitry Bahdanau Yacine Jernite Carlos Mu\u00f1oz Ferrandis Sean Hughes Thomas Wolf Arjun Guha Leandro von Werra and Harm de Vries. 2023. StarCoder: may the source be with you! Trans. Mach. Learn. Res. 2023 (2023). https:\/\/openreview.net\/forum?id=KoFOg41haE"},{"key":"e_1_3_2_1_24_1","volume-title":"Rigorous Evaluation of Large Language Models for Code Generation. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Liu Jiawei","year":"2023","unstructured":"Jiawei Liu, Chunqiu Steven Xia, Yuyao Wang, and Lingming Zhang. 2023. Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 -16, 2023, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/ 43e9d647ccd3e4b7b5baab53f0368686-Abstract-Conference.html"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1985793.1985809"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2601.03267"},{"key":"e_1_3_2_1_27_1","unstructured":"Google DeepMind or Gemini Team. 2026. Gemini 3 Pro Model Card. Technical Report. Google DeepMind. https:\/\/storage.googleapis.com\/deepmind-media\/ Model-Cards\/Gemini-3-Pro-Model-Card.pdf"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2509.14635"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2510.26130"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/P16-1009"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE63991.2025.00020"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2410.01215"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2602.01785"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE55347.2025.00005"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Qwen Team. 2025. Qwen3 Technical Report. CoRR abs\/2505.09388 (2025). doi:10. 48550\/ARXIV.2505.09388 arXiv:2505.09388 10.48550\/ARXIV.2505.09388","DOI":"10.1149\/MA2025-01502505mtgabs"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.ACL-LONG.754"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2601.16746"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2603.27850"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/D19-1670"},{"key":"e_1_3_2_1_40_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Xu Can","year":"2024","unstructured":"Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, Qingwei Lin, and Daxin Jiang. 2024. WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id= CfXh93NDgH"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623316"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","unstructured":"Qiming Zhu Jialun Cao Yaojie Lu Hongyu Lin Xianpei Han Le Sun and Shing- Chi Cheung. 2025. DOMAINEVAL: An Auto-Constructed Benchmark for Multi- Domain Code Generation. In Thirty-Ninth AAAI Conference on Artificial Intelligence Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence Fifteenth Symposium on Educational Advances in Artificial Intelligence AAAI 2025 Philadelphia PA USA February 25 -March 4 2025 Toby Walsh Julie Shah and Zico Kolter (Eds.). AAAI Press 26148-26156. doi:10.1609\/AAAI.V39I24.34811 10.1609\/AAAI.V39I24.34811","DOI":"10.1609\/AAAI.V39I24.34811"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","unstructured":"Terry Yue Zhuo Minh Chien Vu Jenny Chim Han Hu Wenhao Yu Ratnadira Widyasari Imam Nur Bani Yusuf Haolan Zhan Junda He Indraneil Paul Simon Brunner Chen Gong Thong Hoang Armel Randy Zebaze Xiaoheng Hong Wen-Ding Li Jean Kaddour Ming Xu Zhihan Zhang Prateek Yadav Naman Jain Alex Gu Zhoujun Cheng Jiawei Liu Qian Liu Zijian Wang David Lo Binyuan Hui Niklas Muennighoff Daniel Fried Xiaoning Du Harm de Vries and Leandro von Werra. 2024. BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions. CoRR abs\/2406.15877 (2024). doi:10.48550\/ARXIV.2406.15877 arXiv:2406.15877 10.48550\/ARXIV.2406.15877","DOI":"10.48550\/ARXIV.2406.15877"}],"event":{"name":"AIware '26: 3rd ACM International Conference on AI-Powered Software","location":"Montreal QC Canada","acronym":"AIware '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 3rd ACM International Conference on AI-Powered Software"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805760.3814925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T08:47:38Z","timestamp":1783241258000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805760.3814925"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":45,"alternative-id":["10.1145\/3805760.3814925","10.1145\/3805760"],"URL":"https:\/\/doi.org\/10.1145\/3805760.3814925","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}