{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T02:07:01Z","timestamp":1776737221815,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T00:00:00Z","timestamp":1709769600000},"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":[[2024,3,7]]},"DOI":"10.1145\/3626252.3630874","type":"proceedings-article","created":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T18:17:20Z","timestamp":1709835440000},"page":"1230-1236","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Implications of ChatGPT for Data Science Education"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1950-7819","authenticated-orcid":false,"given":"Yiyin","family":"Shen","sequence":"first","affiliation":[{"name":"University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0047-3885","authenticated-orcid":false,"given":"Xinyi","family":"Ai","sequence":"additional","affiliation":[{"name":"University of California, San Diego, San Diego, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6848-2208","authenticated-orcid":false,"given":"Adalbert Gerald","family":"Soosai Raj","sequence":"additional","affiliation":[{"name":"University of California, San Diego, San Diego, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1642-8286","authenticated-orcid":false,"given":"Rogers Jeffrey","family":"Leo John","sequence":"additional","affiliation":[{"name":"Independent Researcher, Madison, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7925-9183","authenticated-orcid":false,"given":"Meenakshi","family":"Syamkumar","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,3,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Ask Me Anything: A simple strategy for prompting language models. arXiv preprint arXiv:2210.02441","author":"Arora Simran","year":"2022","unstructured":"Simran Arora, Avanika Narayan, Mayee F Chen, Laurel J Orr, Neel Guha, Kush Bhatia, Ines Chami, Frederic Sala, and Christopher R\u00e9. 2022. Ask Me Anything: A simple strategy for prompting language models. arXiv preprint arXiv:2210.02441 (2022)."},{"key":"e_1_3_2_1_2_1","volume-title":"Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, et al.","year":"2021","unstructured":"021)]% austin2021program, Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, et al. 2021. Program synthesis with large language models. arXiv preprint arXiv:2108.07732 (2021)."},{"key":"e_1_3_2_1_3_1","volume-title":"Education in the Era of Generative Artificial Intelligence (AI): Understanding the Potential Benefits of ChatGPT in Promoting Teaching and Learning. Available at SSRN 4337484","author":"Baidoo-Anu David","year":"2023","unstructured":"David Baidoo-Anu and Leticia Owusu Ansah. 2023. Education in the Era of Generative Artificial Intelligence (AI): Understanding the Potential Benefits of ChatGPT in Promoting Teaching and Learning. Available at SSRN 4337484 (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3545945.3569759"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557079"},{"key":"e_1_3_2_1_6_1","volume-title":"Lin (Eds.)","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877--1901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_2_1_7_1","unstructured":"Tyler Caraza-Harter and Meenakshi Syamkumar. 2023. Data Science Programming II. https:\/\/www.msyamkumar.com\/cs320\/s23\/schedule.html"},{"key":"e_1_3_2_1_8_1","volume-title":"Training and evaluating a jupyter notebook data science assistant. arXiv preprint arXiv:2201.12901","author":"Chandel Shubham","year":"2022","unstructured":"Shubham Chandel, Colin B Clement, Guillermo Serrato, and Neel Sundaresan. 2022. Training and evaluating a jupyter notebook data science assistant. arXiv preprint arXiv:2201.12901 (2022)."},{"key":"e_1_3_2_1_9_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3545945.3569823"},{"key":"e_1_3_2_1_11_1","unstructured":"Thomas Donoghue Bradley Voytek and Shannon Ellis. 2020. Data Science in Practice. https:\/\/datascienceinpractice.github.io\/docs\/index.html"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511861.3511863"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, J. Vanschoren and S. Yeung (Eds.)","volume":"1","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Steven Basart, Saurav Kadavath, Mantas Mazeika, Akul Arora, Ethan Guo, Collin Burns, Samir Puranik, Horace He, Dawn Song, and Jacob Steinhardt. 2021. Measuring Coding Challenge Competence With APPS. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, J. Vanschoren and S. Yeung (Eds.), Vol. 1. Curran. https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/c24cd76e1ce41366a4bbe8a49b02a028-Paper-round2.pdf"},{"key":"e_1_3_2_1_14_1","unstructured":"Tabarak Khan. [n. d.]. What are tokens and how to count them? https:\/\/help.openai.com\/en\/articles\/4936856-what-are-tokens-and-how-to-count-them"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"18345","author":"Lai Yuhang","year":"2023","unstructured":"Yuhang Lai, Chengxi Li, Yiming Wang, Tianyi Zhang, Ruiqi Zhong, Luke Zettlemoyer, Wen-Tau Yih, Daniel Fried, Sida Wang, and Tao Yu. 2023. DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation. In Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 18319--18345. https:\/\/proceedings.mlr.press\/v202\/lai23b.html"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"2882","author":"Lake Brenden","year":"2018","unstructured":"Brenden Lake and Marco Baroni. 2018. Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks. In Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 80), Jennifer Dy and Andreas Krause (Eds.). PMLR, 2873--2882. https:\/\/proceedings.mlr.press\/v80\/lake18a.html"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3545945.3569770"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3545945.3569785"},{"key":"e_1_3_2_1_19_1","unstructured":"Julian McAuley. 2022. CSE 158\/258: Web Mining and Recommender Systems. https:\/\/cseweb.ucsd.edu\/classes\/fa22\/cse258-a\/"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2023.111734"},{"key":"e_1_3_2_1_21_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_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3501385.3543957"},{"key":"e_1_3_2_1_23_1","unstructured":"Jessica Shieh. 2023. Best practices for prompt engineering with OpenAI API. https:\/\/help.openai.com\/en\/articles\/6654000-best-practices-for-prompt-engineering-with-openai-api"},{"key":"e_1_3_2_1_24_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_25_1","volume-title":"Chi","author":"Zhou Denny","year":"2022","unstructured":"Denny Zhou, Nathanael Sch\"arli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Olivier Bousquet, Quoc Le, and Ed Chi. 2022. Least-to-most prompting enables complex reasoning in large language models. arXiv preprint arXiv:2205.10625 (2022)."}],"event":{"name":"SIGCSE 2024: The 55th ACM Technical Symposium on Computer Science Education","location":"Portland OR USA","acronym":"SIGCSE 2024","sponsor":["SIGCSE ACM Special Interest Group on Computer Science Education"]},"container-title":["Proceedings of the 55th ACM Technical Symposium on Computer Science Education V. 1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626252.3630874","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626252.3630874","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:32:57Z","timestamp":1755750777000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626252.3630874"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,7]]},"references-count":25,"alternative-id":["10.1145\/3626252.3630874","10.1145\/3626252"],"URL":"https:\/\/doi.org\/10.1145\/3626252.3630874","relation":{},"subject":[],"published":{"date-parts":[[2024,3,7]]},"assertion":[{"value":"2024-03-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}