{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T00:06:53Z","timestamp":1782518813309,"version":"3.54.5"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032297549","type":"print"},{"value":"9783032297556","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-29755-6_28","type":"book-chapter","created":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:50:09Z","timestamp":1782316209000},"page":"414-423","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Can Multimodal LLMs \u2018See\u2019 Science Instruction? Benchmarking Pedagogical Reasoning in\u00a0K\u201312 Classroom Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7653-0158","authenticated-orcid":false,"given":"Yixuan","family":"Shen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2877-0117","authenticated-orcid":false,"given":"Peng","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0897-5850","authenticated-orcid":false,"given":"Honglu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4471-5552","authenticated-orcid":false,"given":"Jinxuan","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8483-9659","authenticated-orcid":false,"given":"Yuyang","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5692-2042","authenticated-orcid":false,"given":"Tingting","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7774-8197","authenticated-orcid":false,"given":"Tianlong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4437-0671","authenticated-orcid":false,"given":"Kaidi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2103-4659","authenticated-orcid":false,"given":"Feng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"28_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"28_CR2","unstructured":"Agarwal, S., Ahmad, L., Ai, J., et\u00a0al.: gpt-oss-120b & gpt-oss-20b model card. arXiv preprint arXiv:2508.10925 (2025)"},{"key":"28_CR3","unstructured":"Anthropic: Claude Sonnet 4.5 Model Card (2025). https:\/\/assets.anthropic.com\/m\/12f214efcc2f457a\/original\/Claude-Sonnet-4-5-System-Card.pdf"},{"key":"28_CR4","unstructured":"Bai, S., et\u00a0al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"28_CR5","unstructured":"Brown, T., Mann, B., Ryder, N.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"28_CR6","unstructured":"Chakma, A., et al.: DrawSim-PD: simulating student science drawings to support NGSS-aligned teacher diagnostic reasoning. In: AIED (2026)"},{"key":"28_CR7","unstructured":"Comanici, G., Bieber, E., Schaekermann, M.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"28_CR8","volume-title":"A Framework for K-12 Science Education: Practices, Crosscutting Concepts, and Core Ideas","author":"NR Council","year":"2012","unstructured":"Council, N.R., et al.: A Framework for K-12 Science Education: Practices, Crosscutting Concepts, and Core Ideas. The National Academies Press, Washington (2012)"},{"issue":"1","key":"28_CR9","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1177\/0022487108328155","volume":"60","author":"M Gamoran Sherin","year":"2009","unstructured":"Gamoran Sherin, M., van Es, E.A.: Effects of video club participation on teachers\u2019 professional vision. J. Teach. Educ. 60(1), 20\u201337 (2009)","journal-title":"J. Teach. Educ."},{"key":"28_CR10","volume-title":"Video Research in the Learning Sciences","year":"2007","unstructured":"Goldman, R., Pea, R., Barron, B., Derry, S.J. (eds.): Video Research in the Learning Sciences. Lawrence Erlbaum Associates, Mahwah (2007)"},{"key":"28_CR11","unstructured":"Grattafiori, A., Dubey, A., Jauhri, A.: The Llama 3 Herd of Models. arXiv preprint arXiv:2407.21783 (2024)"},{"issue":"1","key":"28_CR12","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1186\/s43031-023-00088-z","volume":"5","author":"P He","year":"2023","unstructured":"He, P., Krajcik, J., Schneider, B.: Transforming standards into classrooms for knowledge-in-use: an effective and coherent project-based learning system. Disciplin. Interdisc. Sci. Educ. Res. 5(1), 22 (2023)","journal-title":"Disciplin. Interdisc. Sci. Educ. Res."},{"key":"28_CR13","unstructured":"Hou, R., Buhler, B., Futterer, T.: Multimodal assessment of classroom discourse quality: a text-centered attention-based multi-task learning approach. EDM (2025)"},{"key":"28_CR14","unstructured":"Hurst, A., Lerer, A., Goucher, A.P.: GPT-4o System Card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"28_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.tate.2022.103631","volume":"112","author":"J Jacobs","year":"2022","unstructured":"Jacobs, J., Scornavacco, K., Harty, C., et al.: Promoting rich discussions in mathematics classrooms: using personalized, automated feedback to support reflection and instructional change. Teach. Teach. Educ. 112, 103631 (2022)","journal-title":"Teach. Teach. Educ."},{"key":"28_CR16","unstructured":"Jiang, A.Q., Sablayrolles, A., Mensch, A.: Mistral 7b. arXiv preprintarXiv:2310.06825 (2023)"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., et\u00a0al.: Visual instruction tuning. In: NeurIPS (2023)","DOI":"10.52202\/075280-1516"},{"key":"28_CR18","unstructured":"NGSS Lead States: Next Generation Science Standards: For States, By States. The National Academies Press, Washington, DC (2013)"},{"key":"28_CR19","unstructured":"Radford, A., Kim, J.W., Xu, T.: Robust speech recognition via large-scale weak supervision. In: ICML (2023)"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Suresh, A., Jacobs, J., Harty, C.: The TalkMoves Dataset: K-12 mathematics lesson transcripts annotated for teacher and student discursive moves. In: LREC (2022)","DOI":"10.63317\/2azjpibjyj5e"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Suresh, A., Jacobs, J., Perkoff, M.: Fine-tuning transformers with additional context to classify discursive moves in mathematics classrooms. In: BEA Workshop (2022)","DOI":"10.18653\/v1\/2022.bea-1.11"},{"key":"28_CR22","unstructured":"Wang, D., Shan, D., Zheng, Y., Guo, K., Chen, G., Lu, Y.: Can chatgpt detect student talk moves in classroom discourse? a preliminary comparison with Bert. In: EDM (2023)"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Wei, J., Wang, X., Schuurmans, D.: Chain-of-thought prompting elicits reasoning in large language models. In: NeurIPS (2022)","DOI":"10.52202\/068431-1800"},{"issue":"5","key":"28_CR24","first-page":"878","volume":"96","author":"M Windschitl","year":"2012","unstructured":"Windschitl, M., Thompson, J., Braaten, M., et al.: Proposing a core set of instructional practices and tools for teachers of science. Sci. Educ. 96(5), 878\u2013903 (2012)","journal-title":"Sci. Educ."},{"key":"28_CR25","unstructured":"Worsley, M., Martinez-Maldonado, R.: Multimodal learning analytics\u2019 past, present, and potential futures. In: CrossMMLA@ LAK 2 (2018)"},{"key":"28_CR26","unstructured":"Zhu, J., Wang, W., Chen, Z.: InternVL3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-29755-6_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:50:42Z","timestamp":1782316242000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-29755-6_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"ISBN":["9783032297549","9783032297556"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-29755-6_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,25]]},"assertion":[{"value":"25 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIED","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Intelligence in Education","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Seoul","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aied2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.aied-conference.org\/2026","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}