{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T04:41:20Z","timestamp":1773895280479,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T00:00:00Z","timestamp":1745539200000},"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":["2312561"],"award-info":[{"award-number":["2312561"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Center for Supercomputing Applications","award":["1-100025-320003-320054-A33"],"award-info":[{"award-number":["1-100025-320003-320054-A33"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,26]]},"DOI":"10.1145\/3706599.3719928","type":"proceedings-article","created":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T20:03:57Z","timestamp":1745438637000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Large-scale Evaluation of Notebook Checkpointing with AI Agents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5877-6202","authenticated-orcid":false,"given":"Hanxi","family":"Fang","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2881-8501","authenticated-orcid":false,"given":"Supawit","family":"Chockchowwat","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3315-6055","authenticated-orcid":false,"given":"Hari","family":"Sundaram","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3786-6214","authenticated-orcid":false,"given":"Yongjoo","family":"Park","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"[n.d.]. GitHub Copilot. https:\/\/github.com\/features\/copilot. Accessed: 2025-01-23."},{"key":"e_1_3_3_1_3_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et\u00a0al. 2023. Gpt-4 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023)."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Benjamin Baumer and Dana Udwin. 2015. R markdown. Wiley Interdisciplinary Reviews: Computational Statistics 7 3 (2015) 167\u2013177.","DOI":"10.1002\/wics.1348"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376729"},{"key":"e_1_3_3_1_6_2","volume-title":"Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (conditionally accepted with minor revisions)","author":"Fang Hanxi","year":"2025","unstructured":"Hanxi Fang, Supawit Chockchowwat, Hari Sundaram, and Yongjoo Park. 2025. Enhancing Computational Notebooks with Code+Data Space Versioning. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (conditionally accepted with minor revisions)."},{"key":"e_1_3_3_1_7_2","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:https:\/\/arXiv.org\/abs\/2204.05999 (2022)."},{"key":"e_1_3_3_1_8_2","unstructured":"Git SCM. 2024. Git GUI Clients. https:\/\/git-scm.com\/downloads\/guis A list of graphical user interface (GUI) clients for Git."},{"key":"e_1_3_3_1_9_2","unstructured":"Google. [n.d.]. Google Colab. https:\/\/colab.research.google.com\/."},{"key":"e_1_3_3_1_10_2","volume-title":"Data Science Workflow: Overview and Challenges","author":"Guo Phillip","year":"2013","unstructured":"Phillip Guo. 2013. Data Science Workflow: Overview and Challenges. https:\/\/cacm.acm.org\/blogcacm\/data-science-workflow-overview-and-challenges\/"},{"key":"e_1_3_3_1_11_2","unstructured":"Siyuan Guo Cheng Deng Ying Wen Hechang Chen Yi Chang and Jun Wang. 2024. DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.17453 (2024)."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376177"},{"key":"e_1_3_3_1_13_2","unstructured":"Noah Hollmann Samuel M\u00fcller and Frank Hutter. 2024. Large language models for automated data science: Introducing caafe for context-aware automated feature engineering. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_1_14_2","unstructured":"Sirui Hong Yizhang Lin Bang Liu Bangbang Liu Binhao Wu Ceyao Zhang Chenxing Wei Danyang Li Jiaqi Chen Jiayi Zhang et\u00a0al. 2024. Data interpreter: An llm agent for data science. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.18679 (2024)."},{"key":"e_1_3_3_1_15_2","unstructured":"Project Jupyter. 2023. Jupyter Notebook. https:\/\/jupyter.org\/."},{"key":"e_1_3_3_1_16_2","unstructured":"Kaggle. [n.d.]. Titanic - Machine Learning from Disaster. https:\/\/www.kaggle.com\/competitions\/titanic."},{"key":"e_1_3_3_1_17_2","unstructured":"Kaggle. [n.d.]. Top Spotify Podcast Episodes (Daily Updated). https:\/\/www.kaggle.com\/datasets\/daniilmiheev\/top-spotify-podcasts-daily-updated."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300322"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173748"},{"key":"e_1_3_3_1_20_2","volume-title":"9th USENIX Workshop on the Theory and Practice of Provenance (TaPP 2017)","author":"Koop David","year":"2017","unstructured":"David Koop and Jay Patel. 2017. Dataflow notebooks: encoding and tracking dependencies of cells. In 9th USENIX Workshop on the Theory and Practice of Provenance (TaPP 2017)."},{"key":"e_1_3_3_1_21_2","unstructured":"Zhaoheng Li Supawit Chockchowwat Ribhav Sahu Areet Sheth and Yongjoo Park. 2024. Kishu: Time-Traveling for Computational Notebooks. arxiv:https:\/\/arXiv.org\/abs\/2406.13856\u00a0[cs.DB] https:\/\/arxiv.org\/abs\/2406.13856"},{"key":"e_1_3_3_1_22_2","unstructured":"Zhaoheng Li Pranav Gor Rahul Prabhu Hui Yu Yuzhou Mao and Yongjoo Park. 2023. ElasticNotebook: Enabling Live Migration for Computational Notebooks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.11083 (2023)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Jiali Liu Nadia Boukhelifa and James\u00a0R Eagan. 2019. Understanding the role of alternatives in data analysis practices. IEEE transactions on visualization and computer graphics 26 1 (2019) 66\u201376.","DOI":"10.1109\/TVCG.2019.2934593"},{"key":"e_1_3_3_1_24_2","volume-title":"Version Control with Git: Powerful tools and techniques for collaborative software development","author":"Loeliger Jon","year":"2012","unstructured":"Jon Loeliger and Matthew McCullough. 2012. Version Control with Git: Powerful tools and techniques for collaborative software development. O\u2019Reilly Media, Inc."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","unstructured":"Naga\u00a0Nithin Manne Shilvi Satpati Tanu Malik Amitabha Bagchi Ashish Gehani and Amitabh Chaudhary. 2022. CHEX: multiversion replay with ordered checkpoints. Proc. VLDB Endow. 15 6 (feb 2022) 1297\u20131310. 10.14778\/3514061.3514075","DOI":"10.14778\/3514061.3514075"},{"key":"e_1_3_3_1_26_2","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:https:\/\/arXiv.org\/abs\/2203.13474 (2022)."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580997"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173606"},{"key":"e_1_3_3_1_29_2","unstructured":"Noah Shinn Federico Cassano Ashwin Gopinath Karthik Narasimhan and Shunyu Yao. 2024. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290607.3313027"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502123"},{"key":"e_1_3_3_1_32_2","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Fei Xia Ed Chi Quoc\u00a0V Le Denny Zhou et\u00a0al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022) 24824\u201324837."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3520312.3534862"},{"key":"e_1_3_3_1_34_2","unstructured":"Shunyu Yao Jeffrey Zhao Dian Yu Nan Du Izhak Shafran Karthik Narasimhan and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.03629 (2022)."}],"event":{"name":"CHI EA '25: Extended Abstracts of the CHI Conference on Human Factors in Computing Systems","location":"Yokohama Japan","acronym":"CHI EA '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706599.3719928","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706599.3719928","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706599.3719928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:35Z","timestamp":1750295915000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706599.3719928"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,25]]},"references-count":33,"alternative-id":["10.1145\/3706599.3719928","10.1145\/3706599"],"URL":"https:\/\/doi.org\/10.1145\/3706599.3719928","relation":{},"subject":[],"published":{"date-parts":[[2025,4,25]]},"assertion":[{"value":"2025-04-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}