{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T20:30:26Z","timestamp":1773520226933,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":10,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,2,18]]},"DOI":"10.1145\/3770761.3777333","type":"proceedings-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T15:18:26Z","timestamp":1770995906000},"page":"1263-1264","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CSTutorBench: Benchmarking Large Language Models for Realistic Computer Science Tutoring"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4796-3385","authenticated-orcid":false,"given":"Zekai","family":"Cheng","sequence":"first","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5189-9444","authenticated-orcid":false,"given":"Yunfeng","family":"Wan","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8700-6642","authenticated-orcid":false,"given":"Daijiao","family":"Liu","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4382-0757","authenticated-orcid":false,"given":"Yuekang","family":"Li","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2031-4712","authenticated-orcid":false,"given":"Yuchao","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2668-9630","authenticated-orcid":false,"given":"Dong","family":"Gong","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,2,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (CIKM). 5333-5337","author":"Jiahao","unstructured":"Jiahao Chen et al. 2024. Multi-turn Classroom Dialogue Dataset: Assessing Student Performance from One-on-one Conversations. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (CIKM). 5333-5337."},{"key":"e_1_3_2_1_2_1","volume-title":"The 18th Workshop on Innovative Use of NLP for Building Educational Applications","author":"Demszky Dorottya","year":"2024","unstructured":"Dorottya Demszky and Heather Hill. 2024. The NCTE transcripts: A dataset of elementary math classroom transcripts. The 18th Workshop on Innovative Use of NLP for Building Educational Applications (2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS)","author":"Dan","year":"2021","unstructured":"Dan Hendrycks et al. 2021. Measuring mathematical problem solving with the math dataset. Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS) (2021)."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 2024 chi conference on human factors in computing systems. 1-20","author":"Majeed","unstructured":"Majeed Kazemitabaar et al. 2024. Codeaid: Evaluating a classroom deployment of an llm-based programming assistant that balances student and educator needs. In Proceedings of the 2024 chi conference on human factors in computing systems. 1-20."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Jakub Macina et al. 2023. Mathdial: A dialogue tutoring dataset with rich pedagogical properties grounded in math reasoning problems. Findings of the Association for Computational Linguistics: Empirical Methods in Natural Language Processing (EMNLP) (2023).","DOI":"10.18653\/v1\/2023.findings-emnlp.372"},{"key":"e_1_3_2_1_6_1","unstructured":"Jakub Macina et al. 2023. Opportunities and Challenges in Neural Dialog Tutoring. arXiv:2301.09919 [cs.CL] https:\/\/arxiv.org\/abs\/2301.09919"},{"key":"e_1_3_2_1_7_1","unstructured":"Kaushal Kumar Maurya et al. 2024. Unifying AI Tutor Evaluation: An Evaluation Taxonomy for Pedagogical Ability Assessment of LLM-Powered AI Tutors. arXiv preprint arXiv:2412.09416 (2024)."},{"key":"e_1_3_2_1_8_1","unstructured":"Ana\u00efs Tack and Chris Piech. 2022. The AITeacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialogues. arXiv:2205.07540 [cs.CL]. https:\/\/arxiv.org\/abs\/2205.07540"},{"key":"e_1_3_2_1_9_1","volume-title":"Gemini: A family of highly capable multimodal models. arXiv preprint arXiv:2312.11805","author":"Gemini Team","year":"2023","unstructured":"Gemini Team et al. 2023. Gemini: A family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Junling Wang et al. 2024. Book2dial: Generating teacher-student interactions from textbooks for cost-effective development of educational chatbots. arXiv preprint arXiv:2403.03307 (2024).","DOI":"10.18653\/v1\/2024.findings-acl.578"}],"event":{"name":"SIGCSE TS 2026:The 57th ACM Technical Symposium on Computer Science Education","location":"St. Louis MO USA","sponsor":["SIGCSE ACM Special Interest Group on Computer Science Education"]},"container-title":["Proceedings of the 57th ACM Technical Symposium on Computer Science Education V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770761.3777333","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T17:19:36Z","timestamp":1773508776000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770761.3777333"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,17]]},"references-count":10,"alternative-id":["10.1145\/3770761.3777333","10.1145\/3770761"],"URL":"https:\/\/doi.org\/10.1145\/3770761.3777333","relation":{},"subject":[],"published":{"date-parts":[[2026,2,17]]},"assertion":[{"value":"2026-02-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}