{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:05:53Z","timestamp":1781885153924,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":61,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"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\/3706598.3714141","type":"proceedings-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T14:16:17Z","timestamp":1745849777000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Enhancing Computational Notebooks with Code+Data Space Versioning"],"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":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"key":"e_1_3_3_3_2_2","volume-title":"Nbdime github repository","year":"2023","unstructured":"2023. Nbdime github repository. https:\/\/github.com\/jupyter\/nbdime"},{"key":"e_1_3_3_3_3_2","series-title":"(OSDI\u201916)","first-page":"265","volume-title":"Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek\u00a0G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. TensorFlow: a system for large-scale machine learning. In Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (Savannah, GA, USA) (OSDI\u201916). USENIX Association, USA, 265\u2013283."},{"key":"e_1_3_3_3_4_2","unstructured":"Mode Analytics. [n.d.]. Modern Business Intelligence. https:\/\/mode.com\/\/."},{"key":"e_1_3_3_3_5_2","unstructured":"Apache Arrow. 2024. PyArrow - Apache Arrow Python bindings. https:\/\/arrow.apache.org\/docs\/python\/index.html."},{"key":"e_1_3_3_3_6_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_3_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376729"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3595360.3595855"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3595360.3595855"},{"key":"e_1_3_3_3_10_2","unstructured":"Dan Pristupov Tanya Pristupova. [n.d.]. Fork: a Fast and Friendly Git Client. https:\/\/fork.dev Accessed: 2024-12-06."},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"crossref","unstructured":"Taijara\u00a0Loiola De\u00a0Santana Paulo Anselmo da Mota\u00a0Silveira Neto Eduardo\u00a0Santana De\u00a0Almeida and Iftekhar Ahmed. 2024. Bug Analysis in Jupyter Notebook Projects: An Empirical Study. ACM Transactions on Software Engineering and Methodology 33 4 (2024) 1\u201334.","DOI":"10.1145\/3641539"},{"key":"e_1_3_3_3_12_2","volume-title":"COMPUTER GRAPHICS forum","author":"Eckelt Klaus","year":"2024","unstructured":"Klaus Eckelt, Kiran Gadhave, Alexander Lex, and Marc Streit. 2024. Loops: Leveraging Provenance and Visualization to Support Exploratory Data Analysis in Notebooks. In COMPUTER GRAPHICS forum , Vol.\u00a043."},{"key":"e_1_3_3_3_13_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_3_14_2","unstructured":"GitHub. [n.d.]. GitHub: Build and ship software on a single collaborative platform. https:\/\/github.com Accessed: 2024-12-06."},{"key":"e_1_3_3_3_15_2","unstructured":"GitKraken. 2024. Best Git GUI Clients for 2024. https:\/\/www.gitkraken.com\/blog\/best-git-gui-client An article comparing the best Git GUI clients available in 2024."},{"key":"e_1_3_3_3_16_2","unstructured":"Google. [n.d.]. Google Colab. https:\/\/colab.research.google.com\/."},{"key":"e_1_3_3_3_17_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_3_18_2","doi-asserted-by":"crossref","unstructured":"Jesse Harden Elizabeth Christman Nurit Kirshenbaum Mahdi Belcaid Jason Leigh and Chris North. 2023. \u201cThere is no reason anybody should be using 1D anymore\u201d: Design and Evaluation of 2D Jupyter Notebooks. Graphics Interface 2023 (2023).","DOI":"10.1109\/VL\/HCC53370.2022.9833128"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/VL\/HCC53370.2022.9833128"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","unstructured":"Charles\u00a0R. Harris K.\u00a0Jarrod Millman St\u00e9fan\u00a0J. van\u00a0der Walt Ralf Gommers Pauli Virtanen David Cournapeau Eric Wieser Julian Taylor Sebastian Berg Nathaniel\u00a0J. Smith Robert Kern Matti Picus Stephan Hoyer Marten\u00a0H. van Kerkwijk Matthew Brett Allan Haldane Jaime\u00a0Fern\u00e1ndez del R\u00edo Mark Wiebe Pearu Peterson Pierre G\u00e9rard-Marchant Kevin Sheppard Tyler Reddy Warren Weckesser Hameer Abbasi Christoph Gohlke and Travis\u00a0E. Oliphant. 2020. Array programming with NumPy. Nature 585 7825 (Sept. 2020) 357\u2013362. 10.1038\/s41586-020-2649-2","DOI":"10.1038\/s41586-020-2649-2"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300500"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376177"},{"key":"e_1_3_3_3_23_2","unstructured":"HuggingFace. 2024. HuggingFace - Pipelines. https:\/\/huggingface.co\/docs\/transformers\/en\/main_classes\/pipelines. (Date accessed: July 10 2024)."},{"key":"e_1_3_3_3_24_2","unstructured":"IPython Development Team. 2024. IPython Configuration Callbacks. https:\/\/ipython.readthedocs.io\/en\/stable\/config\/callbacks.html Accessed: 2024-09-10."},{"key":"e_1_3_3_3_25_2","unstructured":"Project Jupyter. 2023. Jupyter Notebook. https:\/\/jupyter.org\/."},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025626"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300322"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLHCC.2018.8506576"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173748"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3573843"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445048"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626246.3654752"},{"key":"e_1_3_3_3_33_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_3_34_2","doi-asserted-by":"publisher","unstructured":"Zhaoheng Li Pranav Gor Rahul Prabhu Hui Yu Yuzhou Mao and Yongjoo Park. 2023. ElasticNotebook: Enabling Live Migration for Computational Notebooks. Proc. VLDB Endow. 17 2 (oct 2023) 119\u2013133. 10.14778\/3626292.3626296","DOI":"10.14778\/3626292.3626296"},{"key":"e_1_3_3_3_35_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_3_36_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_3_37_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_3_38_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_3_39_2","unstructured":"Wes McKinney. 2011. pandas: a foundational Python library for data analysis and statistics. Python for high performance and scientific computing 14 9 (2011) 1\u20139."},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"crossref","unstructured":"Chandrasekaran Mohan Don Haderle Bruce Lindsay Hamid Pirahesh and Peter Schwarz. 1992. ARIES: A transaction recovery method supporting fine-granularity locking and partial rollbacks using write-ahead logging. ACM Transactions on Database Systems (TODS) 17 1 (1992) 94\u2013162.","DOI":"10.1145\/128765.128770"},{"key":"e_1_3_3_3_41_2","first-page":"561","volume-title":"13th { USENIX} Symposium on Operating Systems Design and Implementation ({ OSDI} 18)","author":"Moritz Philipp","year":"2018","unstructured":"Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael\u00a0I Jordan, et\u00a0al. 2018. Ray: A distributed framework for emerging { AI} applications. In 13th { USENIX} Symposium on Operating Systems Design and Implementation ({ OSDI} 18). 561\u2013577."},{"key":"e_1_3_3_3_42_2","unstructured":"Paperspace. 2024. NVIDIA H100 for AI & ML Workloads | Cloud GPU Platform. https:\/\/www.paperspace.com\/."},{"key":"e_1_3_3_3_43_2","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga et\u00a0al. 2019. Pytorch: An imperative style high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_3_44_2","unstructured":"Pierre Vigier. [n.d.]. Commit Graph Drawing Algorithms. https:\/\/pvigier.github.io\/2019\/05\/06\/commit-graph-drawing-algorithms.html Accessed: 2024-12-10."},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"crossref","unstructured":"Luigi Quaranta Fabio Calefato and Filippo Lanubile. 2022. Eliciting best practices for collaboration with computational notebooks. Proceedings of the ACM on Human-Computer Interaction 6 CSCW1 (2022) 1\u201341.","DOI":"10.1145\/3512934"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580997"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"crossref","unstructured":"Dhivyabharathi Ramasamy Cristina Sarasua Alberto Bacchelli and Abraham Bernstein. 2023. Visualising data science workflows to support third-party notebook comprehension: an empirical study. Empirical Software Engineering 28 3 (2023) 58.","DOI":"10.1007\/s10664-023-10289-9"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"crossref","unstructured":"Lars Reimann and G\u00fcnter Kniesel-W\u00fcnsche. 2023. An Alternative to Cells for Selective Execution of Data Science Pipelines. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.14556 (2023).","DOI":"10.1109\/ICSE-NIER58687.2023.00029"},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"crossref","unstructured":"Adam Rule Amanda Birmingham Cristal Zuniga Ilkay Altintas Shih-Cheng Huang Rob Knight Niema Moshiri Mai\u00a0H Nguyen Sara\u00a0Brin Rosenthal Fernando P\u00e9rez et\u00a0al. 2019. Ten simple rules for writing and sharing computational analyses in Jupyter Notebooks. e1007007\u00a0pages.","DOI":"10.1371\/journal.pcbi.1007007"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"crossref","unstructured":"Russell Sears and Eric Brewer. 2009. Segment-based recovery: write-ahead logging revisited. Proceedings of the VLDB Endowment 2 1 (2009) 490\u2013501.","DOI":"10.14778\/1687627.1687683"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3426428.3426924"},{"key":"e_1_3_3_3_52_2","unstructured":"Micah\u00a0J Smith J\u00fcrgen Cito and Kalyan Veeramachaneni. 2021. Meeting in the notebook: a notebook-based environment for micro-submissions in data science collaborations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2103.15787 (2021)."},{"key":"e_1_3_3_3_53_2","volume-title":"Sublime Merge","author":"Ltd Sublime HQ Pty","year":"2024","unstructured":"Sublime HQ Pty Ltd. 2024. Sublime Merge. https:\/\/www.sublimemerge.com\/ Version control software for Git repositories."},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290607.3313027"},{"key":"e_1_3_3_3_55_2","unstructured":"Satish Venkatesan. 2022. Automatic Restoration and Management of Computational Notebooks. Ph.D. Dissertation. Virginia Tech."},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502123"},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"crossref","unstructured":"April\u00a0Yi Wang Anant Mittal Christopher Brooks and Steve Oney. 2019. How data scientists use computational notebooks for real-time collaboration. Proceedings of the ACM on Human-Computer Interaction 3 CSCW (2019) 1\u201330.","DOI":"10.1145\/3359141"},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376740"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416585"},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519653"},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445527"},{"key":"e_1_3_3_3_62_2","first-page":"15","volume-title":"9th USENIX Symposium on Networked Systems Design and Implementation (NSDI 12)","author":"Zaharia Matei","year":"2012","unstructured":"Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauly, Michael\u00a0J. Franklin, Scott Shenker, and Ion Stoica. 2012. Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing. In 9th USENIX Symposium on Networked Systems Design and Implementation (NSDI 12). USENIX Association, 15\u201328."}],"event":{"name":"CHI 2025: CHI Conference on Human Factors in Computing Systems","location":"Yokohama Japan","acronym":"CHI '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706598.3714141","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706598.3714141","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706598.3714141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T05:28:24Z","timestamp":1751606904000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706598.3714141"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,25]]},"references-count":61,"alternative-id":["10.1145\/3706598.3714141","10.1145\/3706598"],"URL":"https:\/\/doi.org\/10.1145\/3706598.3714141","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"}}]}}