{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:44:57Z","timestamp":1773798297802,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T00:00:00Z","timestamp":1739318400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"European Research Council","doi-asserted-by":"publisher","award":["ERC, TOPS, 101039090"],"award-info":[{"award-number":["ERC, TOPS, 101039090"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,2,12]]},"DOI":"10.1145\/3641554.3701974","type":"proceedings-article","created":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T09:19:36Z","timestamp":1740043176000},"page":"896-902","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["BugSpotter: Automated Generation of Code Debugging Exercises"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2998-096X","authenticated-orcid":false,"given":"Victor-Alexandru","family":"P?durean","sequence":"first","affiliation":[{"name":"MPI-SWS, Saarbr\u00fccken, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5150-9806","authenticated-orcid":false,"given":"Paul","family":"Denny","sequence":"additional","affiliation":[{"name":"University of Auckland, Auckland, New Zealand"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9922-0668","authenticated-orcid":false,"given":"Adish","family":"Singla","sequence":"additional","affiliation":[{"name":"MPI-SWS, Saarbr\u00fccken, Germany"}]}],"member":"320","published-online":{"date-parts":[[2025,2,18]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS).","author":"Ahmed Umair Z.","year":"2020","unstructured":"Umair Z. Ahmed, Maria Christakis, Aleksandr Efremov, Nigel Fernandez, Ahana Ghosh, Abhik Roychoudhury, and Adish Singla. 2020. Synthesizing Tasks for Block-based Programming. In Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_2_1","unstructured":"Georg Brandl Matth\u00e4us Chajdas and Jean Abou-Samra. 2006. Pygments. https:\/\/pygments.org\/."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626252.3630786"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the Learning and Teaching in Computing and Engineering (LaTiCE).","author":"Chen Mei-Wen","year":"2013","unstructured":"Mei-Wen Chen, Cheng-Chih Wu, and Yu-Tzu Lin. 2013. Novices' Debugging Behaviors in VB Programming. In Proceedings of the Learning and Teaching in Computing and Engineering (LaTiCE)."},{"key":"e_1_3_2_1_5_1","volume-title":"The \u03c72 Test of Goodness of Fit. The Annals of Mathematical Statistics","author":"Cochran William G","year":"1952","unstructured":"William G Cochran. 1952. The \u03c72 Test of Goodness of Fit. The Annals of Mathematical Statistics (1952)."},{"key":"e_1_3_2_1_6_1","volume-title":"A Coefficient of Agreement for Nominal Scales. Educational and Psychological Measurement","author":"Cohen Jacob","year":"1960","unstructured":"Jacob Cohen. 1960. A Coefficient of Agreement for Nominal Scales. Educational and Psychological Measurement (1960)."},{"key":"e_1_3_2_1_7_1","volume-title":"Generative AI for Education (GAIED): Advances, Opportunities, and Challenges. CoRR","author":"Denny Paul","year":"2024","unstructured":"Paul Denny, Sumit Gulwani, Neil T. Heffernan, Tanja K\u00e4ser, Steven Moore, Anna N. Rafferty, and Adish Singla. 2024a. Generative AI for Education (GAIED): Advances, Opportunities, and Challenges. CoRR, Vol. abs\/2402.01580 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the Technical Symposium on Computer Science Education (SIGCSE).","author":"Denny Paul","unstructured":"Paul Denny, Juho Leinonen, James Prather, Andrew Luxton-Reilly, Thezyrie Amarouche, Brett A. Becker, and Brent N. Reeves. 2024b. Prompt Problems: A New Programming Exercise for the Generative AI Era. In Proceedings of the Technical Symposium on Computer Science Education (SIGCSE)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1953163.1953299"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3364510.3366170"},{"key":"e_1_3_2_1_11_1","volume-title":"Eddie Antonio Santos, and Sami Sarsa","author":"Denny Paul","year":"2024","unstructured":"Paul Denny, James Prather, Brett A. Becker, James Finnie-Ansley, Arto Hellas, Juho Leinonen, Andrew Luxton-Reilly, Brent N. Reeves, Eddie Antonio Santos, and Sami Sarsa. 2024c. Computing Education in the Era of Generative AI. Commun. ACM (2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1080\/08993400802114508"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-11644-5_3"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626252.3630863"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626252.3630897"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the Technical Symposium on Computer Science Education (SIGCSE).","author":"Kafai Yasmin B.","unstructured":"Yasmin B. Kafai, David DeLiema, Deborah A. Fields, Gary Lewandowski, and Colleen M. Lewis. 2019. Rethinking Debugging as Productive Failure for CS Education. In Proceedings of the Technical Symposium on Computer Science Education (SIGCSE)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287324.3287371"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks.","author":"Kotalwar Nachiket","year":"2024","unstructured":"Nachiket Kotalwar, Alkis Gotovos, and Adish Singla. 2024. Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation. In Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-13296-9_2"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the Technical Symposium on Computer Science Education (SIGCSE).","author":"Leinonen Juho","unstructured":"Juho Leinonen, Arto Hellas, Sami Sarsa, Brent N. Reeves, Paul Denny, James Prather, and Brett A. Becker. 2023. Using Large Language Models to Enhance Programming Error Messages. In Proceedings of the Technical Symposium on Computer Science Education (SIGCSE)."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the Australasian Computing Education Conference (ACE).","author":"Li Chen","unstructured":"Chen Li, Emily Chan, Paul Denny, Andrew Luxton-Reilly, and Ewan D. Tempero. 2019. Towards a Framework for Teaching Debugging. In Proceedings of the Australasian Computing Education Conference (ACE)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3502718.3524789"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-64302-6_19"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3636243.3636245"},{"key":"e_1_3_2_1_25_1","volume-title":"Debugging: A Review of the Literature from an Educational Perspective. Computer Science Education","author":"McCauley Ren\u00e9e","year":"2008","unstructured":"Ren\u00e9e McCauley, Sue Fitzgerald, Gary Lewandowski, Laurie Murphy, Beth Simon, Lynda Thomas, and Carol Zander. 2008. Debugging: A Review of the Literature from an Educational Perspective. Computer Science Education (2008)."},{"key":"e_1_3_2_1_26_1","unstructured":"Ismael Villegas Molina Audria Montalvo Benjamin Ochoa Paul Denny and Leo Porter. 2024. Leveraging LLM Tutoring Systems for Non-Native English Speakers in Introductory CS Courses."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1352135.1352191"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the International Conference on Educational Data Mining (EDM).","author":"Nguyen Manh Hung","year":"2024","unstructured":"Manh Hung Nguyen, Sebastian Tschiatschek, and Adish Singla. 2024. Large Language Models for In-Context Student Modeling: Synthesizing Student's Behavior in Visual Programming from One-Shot Observation. In Proceedings of the International Conference on Educational Data Mining (EDM)."},{"key":"e_1_3_2_1_29_1","unstructured":"OpenAI. 2023. ChatGPT. https:\/\/openai.com\/blog\/chatgpt."},{"key":"e_1_3_2_1_30_1","unstructured":"OpenAI. 2024a. Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/."},{"key":"e_1_3_2_1_31_1","unstructured":"OpenAI. 2024b. OpenAI Platform Models. https:\/\/platform.openai.com\/docs\/models."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks.","author":"P\u0103durean Victor-Alexandru","year":"2024","unstructured":"Victor-Alexandru P\u0103durean and Adish Singla. 2024. Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming. In Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks."},{"key":"e_1_3_2_1_33_1","volume-title":"Neural Task Synthesis for Visual Programming. Transactions on Machine Learning Research (TMLR)","author":"P\u0103durean Victor-Alexandru","year":"2024","unstructured":"Victor-Alexandru P\u0103durean, Georgios Tzannetos, and Adish Singla. 2024. Neural Task Synthesis for Visual Programming. Transactions on Machine Learning Research (TMLR) (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the International Conference on Educational Data Mining (EDM).","author":"Phung Tung","year":"2023","unstructured":"Tung Phung, Jos\u00e9 Cambronero, Sumit Gulwani, Tobias Kohn, Rupak Majumdar, Adish Singla, and Gustavo Soares. 2023a. Generating High-Precision Feedback for Programming Syntax Errors using Large Language Models. In Proceedings of the International Conference on Educational Data Mining (EDM)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568812.3603476"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3636555.3636846"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the Working Group Reports of the Conference on Innovation and Technology in Computer Science Education (ItiCSE).","author":"Kate","unstructured":"Kate Sanders et al. 2013. The Canterbury QuestionBank: Building a Repository of Multiple-Choice CS1 and CS2 Questions. In Proceedings of the Working Group Reports of the Conference on Innovation and Technology in Computer Science Education (ItiCSE)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3501385.3543957"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3657604.3662039"},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS).","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3408877.3432374"}],"event":{"name":"SIGCSE TS 2025: The 56th ACM Technical Symposium on Computer Science Education","location":"Pittsburgh PA USA","acronym":"SIGCSE TS 2025","sponsor":["SIGCSE ACM Special Interest Group on Computer Science Education"]},"container-title":["Proceedings of the 56th ACM Technical Symposium on Computer Science Education V. 1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641554.3701974","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641554.3701974","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T06:32:23Z","timestamp":1755757943000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641554.3701974"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,12]]},"references-count":41,"alternative-id":["10.1145\/3641554.3701974","10.1145\/3641554"],"URL":"https:\/\/doi.org\/10.1145\/3641554.3701974","relation":{},"subject":[],"published":{"date-parts":[[2025,2,12]]},"assertion":[{"value":"2025-02-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}