{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T03:48:10Z","timestamp":1784260090136,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T00:00:00Z","timestamp":1707177600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-2313055"],"award-info":[{"award-number":["CCF-2313055"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,2,6]]},"DOI":"10.1145\/3597503.3608140","type":"proceedings-article","created":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T20:53:16Z","timestamp":1707252796000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":32,"title":["TRACED: Execution-aware Pre-training for Source Code"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3224-6876","authenticated-orcid":false,"given":"Yangruibo","family":"Ding","sequence":"first","affiliation":[{"name":"Columbia University, New York, NY, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6175-105X","authenticated-orcid":false,"given":"Benjamin","family":"Steenhoek","sequence":"additional","affiliation":[{"name":"Iowa State University, Ames, IA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5052-9808","authenticated-orcid":false,"given":"Kexin","family":"Pei","sequence":"additional","affiliation":[{"name":"Columbia University, New York, NY, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8791-1178","authenticated-orcid":false,"given":"Gail","family":"Kaiser","sequence":"additional","affiliation":[{"name":"Columbia University, New York, NY, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6797-0648","authenticated-orcid":false,"given":"Wei","family":"Le","sequence":"additional","affiliation":[{"name":"Iowa State University, Ames, IA, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3406-5235","authenticated-orcid":false,"given":"Baishakhi","family":"Ray","sequence":"additional","affiliation":[{"name":"Columbia University, New York, NY, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,2,6]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"e_1_3_2_1_2_1","volume-title":"Program Synthesis with Large Language Models. CoRR abs\/2108.07732","author":"Austin Jacob","year":"2021","unstructured":"Jacob Austin, Augustus Odena, Maxwell 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_3_1","unstructured":"David Bieber Rishab Goel Dan Zheng Hugo Larochelle and Daniel Tarlow. 2022. Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions. https:\/\/openreview.net\/forum?id=SIcz2sObJ-5"},{"key":"e_1_3_2_1_4_1","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Bieber David","year":"2020","unstructured":"David Bieber, Charles Sutton, Hugo Larochelle, and Daniel Tarlow. 2020. Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks. In Advances in Neural Information Processing Systems, Vol. 33. Curran Associates, Inc., 8626--8637. https:\/\/papers.nips.cc\/paper\/2020\/hash\/62326dc7c4f7b849d6f013ba46489d6c-Abstract.html"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462840"},{"key":"e_1_3_2_1_6_1","unstructured":"Luca Buratti Saurabh Pujar Mihaela Bornea Scott McCarley Yunhui Zheng Gaetano Rossiello Alessandro Morari Jim Laredo Veronika Thost Yufan Zhuang and Giacomo Domeniconi. 2020. Exploring Software Naturalness through Neural Language Models. arXiv:2006.12641 [cs.CL]"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549162"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3087402"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.436"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416587"},{"key":"e_1_3_2_1_12_1","unstructured":"Adam Paszke et al.. 2019. PyTorch: An Imperative Style High-Performance Deep Learning Library."},{"key":"e_1_3_2_1_13_1","unstructured":"Mark Chen et al.. 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_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_15_1","unstructured":"Yujia Li et al.. 2022. Competition-Level Code Generation with AlphaCode. ArXiv abs\/2203.07814 (2022)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","unstructured":"Daya Guo Shuai Lu Nan Duan Yanlin Wang Ming Zhou and Jian Yin. 2022. UniXcoder: Unified Cross-Modal Pre-training for Code Representation. 10.48550\/ARXIV.2203.03850","DOI":"10.48550\/ARXIV.2203.03850"},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=jLoC4ez43PZ","author":"Guo Daya","year":"2021","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie LIU, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, Michele Tufano, Shao Kun Deng, Colin Clement, Dawn Drain, Neel Sundaresan, Jian Yin, Daxin Jiang, and Ming Zhou. 2021. GraphCode{BERT}: Pre-training Code Representations with Data Flow. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=jLoC4ez43PZ"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3236085"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2012.6227135"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Nan Jiang Kevin Liu Thibaud Lutellier and Lin Tan. 2023. Impact of Code Language Models on Automated Program Repair. arXiv:2302.05020 [cs.SE]","DOI":"10.1109\/ICSE48619.2023.00125"},{"key":"e_1_3_2_1_22_1","volume-title":"KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repair. arXiv:2302.01857 [cs.SE]","author":"Jiang Nan","year":"2023","unstructured":"Nan Jiang, Thibaud Lutellier, Yiling Lou, Lin Tan, Dan Goldwasser, and Xiangyu Zhang. 2023. KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repair. arXiv:2302.01857 [cs.SE]"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00107"},{"key":"e_1_3_2_1_24_1","volume-title":"ICML","author":"Kanade Aditya","year":"2020","unstructured":"Aditya Kanade, Petros Maniatis, Gogul Balakrishnan, and Kensen Shi. 2020. Learning and evaluating contextual embedding of source code. In ICML 2020."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380342"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.62"},{"key":"e_1_3_2_1_27_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. CoRR abs\/1412.6980 (2015)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2991079.2991102"},{"key":"e_1_3_2_1_31_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR abs\/1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR abs\/1907.11692 (2019). arXiv:1907.11692 http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_1_32_1","volume-title":"Shengyu Fu, and Shujie Liu.","author":"Lu Shuai","year":"2021","unstructured":"Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin B. 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 Kun Deng, Shengyu Fu, and Shujie Liu. 2021. CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation. CoRR abs\/2102.04664 (2021)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10139"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.10166"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510096"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2112.00114"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510144"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468607"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549147"},{"key":"e_1_3_2_1_40_1","volume-title":"Trex: Learning Execution Semantics from Micro-Traces for Binary Similarity. CoRR abs\/2012.08680","author":"Pei Kexin","year":"2020","unstructured":"Kexin Pei, Zhou Xuan, Junfeng Yang, Suman Jana, and Baishakhi Ray. 2020. Trex: Learning Execution Semantics from Micro-Traces for Binary Similarity. CoRR abs\/2012.08680 (2020). arXiv:2012.08680 https:\/\/arxiv.org\/abs\/2012.08680"},{"key":"e_1_3_2_1_41_1","volume-title":"Project CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks. CoRR abs\/2105.12655","author":"Puri Ruchir","year":"2021","unstructured":"Ruchir Puri, David S. Kung, Geert Janssen, Wei Zhang, Giacomo Domeniconi, Vladimir Zolotov, Julian Dolby, Jie Chen, Mihir R. Choudhury, Lindsey Decker, Veronika Thost, Luca Buratti, Saurabh Pujar, and Ulrich Finkler. 2021. Project CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks. CoRR abs\/2105.12655 (2021). arXiv:2105.12655 https:\/\/arxiv.org\/abs\/2105.12655"},{"key":"e_1_3_2_1_42_1","first-page":"140","article-title":"2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research 21, 140 (2020), 1--67. http:\/\/jmlr.org\/papers\/v21\/20-074.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884848"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","unstructured":"Scott Reed and Nando de Freitas. 2016. Neural Programmer-Interpreters. arXiv:1511.06279 [cs]. 10.48550\/arXiv.1511.06279","DOI":"10.48550\/arXiv.1511.06279"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","unstructured":"Beatriz Souza and Michael Pradel. 2023. LExecutor: Learning-Guided Execution. arXiv:2302.02343 [cs]. 10.48550\/arXiv.2302.02343","DOI":"10.48550\/arXiv.2302.02343"},{"key":"e_1_3_2_1_46_1","unstructured":"Ke Wang Rishabh Singh and Zhendong Su. 2018. Dynamic Neural Program Embeddings for Program Repair. https:\/\/openreview.net\/forum?id=BJuWrGW0Z"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3385412.3385999"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","unstructured":"Xin Wang Yasheng Wang Fei Mi Pingyi Zhou Yao Wan Xiao Liu Li Li Hao Wu Jin Liu and Xin Jiang. 2021. SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation. 10.48550\/ARXIV.2108.04556","DOI":"10.48550\/ARXIV.2108.04556"},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021.","author":"Wang Yue","unstructured":"Yue Wang, Weishi Wang, Shafiq Joty, and Steven C.H. Hoi. 2021. CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021."},{"key":"e_1_3_2_1_50_1","volume-title":"A Systematic Evaluation of Large Language Models of Code. arXiv preprint arXiv:2202.13169","author":"Xu Frank F","year":"2022","unstructured":"Frank F Xu, Uri Alon, Graham Neubig, and Vincent J Hellendoorn. 2022. A Systematic Evaluation of Large Language Models of Code. arXiv preprint arXiv:2202.13169 (2022)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556926"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","unstructured":"Wojciech Zaremba and Ilya Sutskever. 2015. Learning to Execute. 10.48550\/arXiv.1410.4615","DOI":"10.48550\/arXiv.1410.4615"},{"key":"e_1_3_2_1_53_1","volume-title":"Why Programs Fail: A Guide to Systematic Debugging","author":"Zeller Andreas","unstructured":"Andreas Zeller. 2005. Why Programs Fail: A Guide to Systematic Debugging. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP52600.2021.00020"},{"key":"e_1_3_2_1_55_1","volume-title":"Devign: Effective vulnerability identification by learning comprehensive program semantics via graph neural networks. In Advances in Neural Information Processing Systems. 10197--10207.","author":"Zhou Yaqin","year":"2019","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. In Advances in Neural Information Processing Systems. 10197--10207."}],"event":{"name":"ICSE '24: IEEE\/ACM 46th International Conference on Software Engineering","location":"Lisbon Portugal","acronym":"ICSE '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3608140","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3597503.3608140","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3597503.3608140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:48:45Z","timestamp":1750182525000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3608140"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,6]]},"references-count":55,"alternative-id":["10.1145\/3597503.3608140","10.1145\/3597503"],"URL":"https:\/\/doi.org\/10.1145\/3597503.3608140","relation":{},"subject":[],"published":{"date-parts":[[2024,2,6]]},"assertion":[{"value":"2024-02-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}