{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T06:30:20Z","timestamp":1750746620953,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1145\/3643656.3643900","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T14:59:41Z","timestamp":1723129181000},"page":"22-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Can ChatGPT Repair Non-Order-Dependent Flaky Tests?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1409-4163","authenticated-orcid":false,"given":"Yang","family":"Chen","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, Illinois, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0668-8526","authenticated-orcid":false,"given":"Reyhaneh","family":"Jabbarvand","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, Illinois, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,8]]},"reference":[{"unstructured":"2023. GitHub Repository of NODoctor. https:\/\/github.com\/Intelligent-CAT-Lab\/NODoctor.","key":"e_1_3_2_1_1_1"},{"unstructured":"2023. International Dataset of Flaky tests. https:\/\/github.com\/TestingResearchIllinois\/idoft.","key":"e_1_3_2_1_3_1"},{"unstructured":"2023. Nondex Test Flakiness Detection Tool. https:\/\/github.com\/TestingResearchIllinois\/NonDex.","key":"e_1_3_2_1_4_1"},{"unstructured":"2023. PR for test testDelimitedTextFileWriter. https:\/\/github.com\/pinterest\/secor\/pull\/1687.","key":"e_1_3_2_1_5_1"},{"unstructured":"2023. A previously-fixed NOD test. https:\/\/github.com\/querydsl\/querydsl\/pull\/2658.","key":"e_1_3_2_1_6_1"},{"unstructured":"2023. Repository alibabacloud-tairjedis-sdk. https:\/\/github.com\/alibaba\/alibabacloud-tairjedis-sdk.","key":"e_1_3_2_1_7_1"},{"unstructured":"2023. Repository biojava. https:\/\/github.com\/biojava\/biojava.","key":"e_1_3_2_1_8_1"},{"unstructured":"2023. Repository Fastjson. https:\/\/github.com\/alibaba\/fastjson.","key":"e_1_3_2_1_9_1"},{"unstructured":"2023. Repository querydsl. https:\/\/github.com\/querydsl\/querydsl.","key":"e_1_3_2_1_10_1"},{"unstructured":"2023. Repository wasp. https:\/\/github.com\/alibaba\/wasp.","key":"e_1_3_2_1_11_1"},{"key":"e_1_3_2_1_12_1","volume-title":"Unified pre-training for program understanding and generation. arXiv preprint arXiv:2103.06333","author":"Ahmad Wasi Uddin","year":"2021","unstructured":"Wasi Uddin Ahmad, Saikat Chakraborty, Baishakhi Ray, and Kai-Wei Chang. 2021. Unified pre-training for program understanding and generation. arXiv preprint arXiv:2103.06333 (2021)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_13_1","DOI":"10.1109\/ICSE43902.2021.00140"},{"key":"e_1_3_2_1_14_1","volume-title":"2018 IEEE\/ACM 40th International Conference on Software Engineering. IEEE, 433--444","author":"Bell Jonathan","year":"2018","unstructured":"Jonathan Bell, Owolabi Legunsen, Michael Hilton, Lamyaa Eloussi, Tifany Yung, and Darko Marinov. 2018. DeFlaker: Automatically detecting flaky tests. In 2018 IEEE\/ACM 40th International Conference on Software Engineering. IEEE, 433--444."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.1145\/3540250.3549162"},{"key":"e_1_3_2_1_16_1","volume-title":"Codet: Code generation with generated tests. arXiv preprint arXiv:2207.10397","author":"Chen Bei","year":"2022","unstructured":"Bei Chen, Fengji Zhang, Anh Nguyen, Daoguang Zan, Zeqi Lin, Jian-Guang Lou, and Weizhu Chen. 2022. Codet: Code generation with generated tests. arXiv preprint arXiv:2207.10397 (2022)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_17_1","DOI":"10.1145\/3597926.3598119"},{"key":"e_1_3_2_1_18_1","volume-title":"Classeval: A manually-crafted benchmark for evaluating llms on class-level code generation. arXiv preprint arXiv:2308.01861","author":"Du Xueying","year":"2023","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 preprint arXiv:2308.01861 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1145\/3395363.3397366"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.1145\/3468264.3468615"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_21_1","DOI":"10.1145\/3338906.3338945"},{"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 al. 2020. CodeBert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155 (2020).","key":"e_1_3_2_1_22_1","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_23_1","volume-title":"Incoder: A generative model for code infilling and synthesis. arXiv preprint arXiv:2204.05999","author":"Fried Daniel","year":"2022","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:2204.05999 (2022)."},{"key":"e_1_3_2_1_24_1","volume-title":"Graphcodebert: Pre-training code representations with data flow. arXiv preprint arXiv:2009.08366","author":"Guo Daya","year":"2020","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie Liu, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, et al. 2020. Graphcodebert: Pre-training code representations with data flow. arXiv preprint arXiv:2009.08366 (2020)."},{"key":"e_1_3_2_1_25_1","volume-title":"Inferfix: End-to-end program repair with llms. arXiv preprint arXiv:2303.07263","author":"Jin Matthew","year":"2023","unstructured":"Matthew Jin, Syed Shahriar, Michele Tufano, Xin Shi, Shuai Lu, Neel Sundaresan, and Alexey Svyatkovskiy. 2023. Inferfix: End-to-end program repair with llms. arXiv preprint arXiv:2303.07263 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_26_1","DOI":"10.1109\/QRS-C.2018.00031"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_27_1","DOI":"10.1145\/3377813.3381370"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_28_1","DOI":"10.1145\/3293882.3330570"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_29_1","DOI":"10.1145\/3377811.3381749"},{"volume-title":"iDFlakies: A framework for detecting and partially classifying flaky tests. In 2019 12th ieee conference on software testing, validation and verification (icst)","author":"Lam Wing","unstructured":"Wing Lam, Reed Oei, August Shi, Darko Marinov, and Tao Xie. 2019. iDFlakies: A framework for detecting and partially classifying flaky tests. In 2019 12th ieee conference on software testing, validation and verification (icst). IEEE, 312--322.","key":"e_1_3_2_1_30_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_31_1","DOI":"10.1109\/ISSRE5003.2020.00045"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_32_1","DOI":"10.1145\/3428270"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_33_1","DOI":"10.1145\/3510003.3510173"},{"key":"e_1_3_2_1_34_1","volume-title":"Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al.","author":"Li Raymond","year":"2023","unstructured":"Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al. 2023. StarCoder: may the source be with you! arXiv preprint arXiv:2305.06161 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"Yuyao Wang, and Lingming Zhang.","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. arXiv preprint arXiv:2305.01210 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_36_1","DOI":"10.1145\/2635868.2635920"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_37_1","DOI":"10.24215\/16666038.18.e16"},{"unstructured":"John Micco. 2017. The state of continuous integration testing@ google. (2017).","key":"e_1_3_2_1_38_1"},{"key":"e_1_3_2_1_39_1","volume-title":"Codegen: An open large language model for code with multi-turn program synthesis. arXiv preprint arXiv:2203.13474","author":"Nijkamp Erik","year":"2022","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:2203.13474 (2022)."},{"key":"e_1_3_2_1_40_1","volume-title":"LLM is Like a Box of Chocolates: the Non-determinism of ChatGPT in Code Generation. arXiv preprint arXiv:2308.02828","author":"Ouyang Shuyin","year":"2023","unstructured":"Shuyin Ouyang, Jie M Zhang, Mark Harman, and Meng Wang. 2023. LLM is Like a Box of Chocolates: the Non-determinism of ChatGPT in Code Generation. arXiv preprint arXiv:2308.02828 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"Rahul Krishna, Divya Sankar, Lambert Pouguem Wassi, Michele Merler, Boris Sobolev, Raju Pavuluri, Saurabh Sinha, and Reyhaneh Jabbarvand.","author":"Pan Rangeet","year":"2023","unstructured":"Rangeet Pan, Ali Reza Ibrahimzada, Rahul Krishna, Divya Sankar, Lambert Pouguem Wassi, Michele Merler, Boris Sobolev, Raju Pavuluri, Saurabh Sinha, and Reyhaneh Jabbarvand. 2023. Understanding the Effectiveness of Large Language Models in Code Translation. arXiv preprint arXiv:2308.03109 (2023)."},{"doi-asserted-by":"publisher","unstructured":"Owain Parry Gregory M. Kapfhammer Michael Hilton and Phil McMinn. 2021. A Survey of Flaky Tests. ACM Trans. Softw. Eng. Methodol. (2021) 74 pages. 10.1145\/3476105","key":"e_1_3_2_1_42_1","DOI":"10.1145\/3476105"},{"key":"e_1_3_2_1_43_1","volume-title":"TRaf: Time-based Repair for Asynchronous Wait Flaky Tests in Web Testing. arXiv preprint arXiv:2305.08592","author":"Pei Yu","year":"2023","unstructured":"Yu Pei, Jeongju Sohn, Sarra Habchi, and Mike Papadakis. 2023. TRaf: Time-based Repair for Asynchronous Wait Flaky Tests in Web Testing. arXiv preprint arXiv:2305.08592 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"2015 30th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 149--154","author":"Person Suzette","year":"2015","unstructured":"Suzette Person and Sebastian Elbaum. 2015. Test analysis: Searching for faults in tests (N). In 2015 30th IEEE\/ACM International Conference on Automated Software Engineering (ASE). IEEE, 149--154."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_45_1","DOI":"10.1145\/3379597.3387482"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_46_1","DOI":"10.1145\/3338906.3338925"},{"key":"e_1_3_2_1_47_1","volume-title":"International Conference on Machine Learning. 31693--31715","author":"Shrivastava Disha","year":"2023","unstructured":"Disha Shrivastava, Hugo Larochelle, and Daniel Tarlow. 2023. Repository-level prompt generation for large language models of code. In International Conference on Machine Learning. 31693--31715."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_48_1","DOI":"10.1109\/ACCESS.2021.3082424"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_49_1","DOI":"10.1145\/3510454.3516846"},{"key":"e_1_3_2_1_50_1","volume-title":"LeTI: Learning to Generate from Textual Interactions. arXiv preprint arXiv:2305.10314","author":"Wang Xingyao","year":"2023","unstructured":"Xingyao Wang, Hao Peng, Reyhaneh Jabbarvand, and Heng Ji. 2023. LeTI: Learning to Generate from Textual Interactions. arXiv preprint arXiv:2305.10314 (2023)."},{"key":"e_1_3_2_1_51_1","volume-title":"Nghi DQ Bui, Junnan Li, and Steven CH Hoi.","author":"Wang Yue","year":"2023","unstructured":"Yue Wang, Hung Le, Akhilesh Deepak Gotmare, Nghi DQ Bui, Junnan Li, and Steven CH Hoi. 2023. Codet5+: Open code large language models for code understanding and generation. arXiv preprint arXiv:2305.07922 (2023)."},{"key":"e_1_3_2_1_52_1","volume-title":"Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv preprint arXiv:2109.00859","author":"Wang Yue","year":"2021","unstructured":"Yue Wang, Weishi Wang, Shafiq Joty, and Steven CH Hoi. 2021. Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv preprint arXiv:2109.00859 (2021)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_53_1","DOI":"10.1145\/3510003.3510170"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_54_1","DOI":"10.1007\/978-3-030-72016-2_15"},{"key":"e_1_3_2_1_55_1","volume-title":"A prompt pattern catalog to enhance prompt engineering with chatgpt. arXiv preprint arXiv:2302.11382","author":"White Jules","year":"2023","unstructured":"Jules White, Quchen Fu, Sam Hays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, and Douglas C Schmidt. 2023. A prompt pattern catalog to enhance prompt engineering with chatgpt. arXiv preprint arXiv:2302.11382 (2023)."},{"key":"e_1_3_2_1_56_1","volume-title":"Conversational automated program repair. arXiv preprint arXiv:2301.13246","author":"Xia Chunqiu Steven","year":"2023","unstructured":"Chunqiu Steven Xia and Lingming Zhang. 2023. Conversational automated program repair. arXiv preprint arXiv:2301.13246 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_57_1","DOI":"10.1145\/3468744.3468756"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_58_1","DOI":"10.1109\/ICSE43902.2021.00018"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_59_1","DOI":"10.1109\/ICSME46990.2020.00083"}],"event":{"sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"],"acronym":"FTW '24","name":"FTW '24: 1st International Workshop on Flaky Tests","location":"Lisbon Portugal"},"container-title":["Proceedings of the 1st International Workshop on Flaky Tests"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3643656.3643900","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3643656.3643900","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:28Z","timestamp":1750287028000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3643656.3643900"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":58,"alternative-id":["10.1145\/3643656.3643900","10.1145\/3643656"],"URL":"https:\/\/doi.org\/10.1145\/3643656.3643900","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]},"assertion":[{"value":"2024-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}